diff --git a/.github/workflows/create-release.yml b/.github/workflows/create-release.yml index 4834775e329..0ad84cd3ceb 100644 --- a/.github/workflows/create-release.yml +++ b/.github/workflows/create-release.yml @@ -122,10 +122,28 @@ jobs: makeLatest = (!latestVersion || isAtLeast(newVersion, latestVersion)) ? "true" : "false"; } + try { + await github.rest.git.createRef({ + owner: context.repo.owner, + repo: context.repo.repo, + ref: `refs/tags/${tag}`, + sha: commitHash, + }); + } catch (error) { + if (error.status !== 422) throw error; + const existing = await github.rest.git.getRef({ + owner: context.repo.owner, + repo: context.repo.repo, + ref: `tags/${tag}`, + }); + if (existing.data.object.sha !== commitHash) { + throw new Error(`Tag ${tag} already exists at ${existing.data.object.sha}, expected ${commitHash}`); + } + } + const response = await github.rest.repos.createRelease({ draft: true, generate_release_notes: true, - target_commitish: commitHash, name: tag, owner: context.repo.owner, prerelease: isPrerelease, @@ -138,11 +156,21 @@ jobs: owner: context.repo.owner, repo: context.repo.repo, release_id: response.data.id, + tag_name: tag, body: updatedBody, draft: false, - make_latest: makeLatest, }); + if (!isPrerelease) { + await github.rest.repos.updateRelease({ + owner: context.repo.owner, + repo: context.repo.repo, + release_id: response.data.id, + tag_name: tag, + make_latest: makeLatest, + }); + } + } catch (error) { core.setFailed(error.message); } diff --git a/.gitignore b/.gitignore index 59fa5803abe..62db5fe6182 100644 --- a/.gitignore +++ b/.gitignore @@ -130,3 +130,5 @@ crash.*.log # pytest coverage data .coverage + +ui/litellm-dashboard/out/ diff --git a/CLAUDE.md b/CLAUDE.md index 7d9a6367f18..84d2efaab6a 100644 --- a/CLAUDE.md +++ b/CLAUDE.md @@ -17,6 +17,8 @@ Same thing for bug fixes. The tests should make it so that this specific bug can `tests/test_litellm/` mirrors `litellm/` in a parallel path (see `tests/test_litellm/readme.md`). Name tests `test_.py`, but always match the existing test file in the directory you touch β€” many provider dirs use longer descriptive names (e.g. `test_anthropic_chat_transformation.py`) to avoid ambiguity across sibling folders. For bug fixes, extend the existing mapped test file rather than creating a new one. Only create a new test file for a new feature (provider, endpoint, or transformation module) that has no mapped test yet, following that directory's naming convention (or `test_.py` if you're the first test there). One focused regression test beats many shallow ones +End-to-end tests belong in `tests/e2e/` and must follow the harness conventions documented in that directory's `CLAUDE.md` + When creating PRs, don't set base to `main`. `litellm_internal_staging` serves that purpose Always use @.github/pull_request_template.md as a guide for your PR body diff --git a/Makefile b/Makefile index 2cc4ec3e45a..f8d10de2917 100644 --- a/Makefile +++ b/Makefile @@ -4,7 +4,7 @@ .PHONY: help test test-unit test-unit-llms test-unit-proxy-guardrails test-unit-proxy-core test-unit-proxy-misc \ test-unit-integrations test-unit-core-utils test-unit-other test-unit-root \ test-proxy-unit-a test-proxy-unit-b test-integration test-unit-helm \ - info lint lint-dev format \ + info lint lint-dev lint-checks format \ lint-basedpyright lint-basedpyright-budget-update lint-type-discipline lint-type-discipline-budget-update \ lint-ruff-budget lint-ruff-budget-update lint-budget-update lint-gate \ install-dev install-proxy-dev install-test-deps install-hooks \ @@ -53,6 +53,11 @@ help: UV := uv UV_RUN := $(UV) run --no-sync +LINT_DEP_INSTALL ?= install-dev +LINT_DEP_BASE ?= lint-fetch-base +LINT_JOBS := $(shell sysctl -n hw.ncpu 2>/dev/null || nproc 2>/dev/null || echo 4) +LINT_OUTPUT_SYNC := $(if $(filter output-sync,$(.FEATURES)),--output-sync=target,) + # Show info info: @echo "UV: $(UV)" @@ -107,12 +112,12 @@ lint-fetch-base: # running proxy need. lint-install: $(UV) sync --inexact --frozen --group proxy-dev - $(UV_RUN) prisma generate --schema litellm/proxy/schema.prisma + $(UV_RUN) python scripts/prisma_generate_if_needed.py # Diff-scoped format check, identical to test-linting.yml's "Check ruff format" step: # only the litellm Python files changed vs the base are checked, so a pre-existing # format issue elsewhere doesn't block an unrelated commit. -lint-format-check-changed: install-dev lint-fetch-base +lint-format-check-changed: $(LINT_DEP_INSTALL) $(LINT_DEP_BASE) @files=$$(git diff --name-only origin/litellm_internal_staging...HEAD -- 'litellm/**/*.py' | grep -v '^litellm/enterprise/' || true); \ if [ -z "$$files" ]; then \ echo "No changed litellm Python files to format-check."; \ @@ -121,7 +126,7 @@ lint-format-check-changed: install-dev lint-fetch-base fi # Linting targets -lint-ruff: install-dev +lint-ruff: $(LINT_DEP_INSTALL) cd litellm && $(UV_RUN) ruff check . && cd .. # faster linter for developing ... @@ -156,12 +161,12 @@ lint-ruff-FULL-dev: install-dev if [ -n "$$files" ]; then echo "$$files" | xargs $(UV_RUN) ruff check; \ else echo "No changed .py files to check."; fi -lint-basedpyright: install-dev lint-fetch-base +lint-basedpyright: $(LINT_DEP_INSTALL) $(LINT_DEP_BASE) ($(UV_RUN) basedpyright --outputjson || true) | $(UV_RUN) python scripts/type_check_gate.py --base origin/litellm_internal_staging # Type-discipline budget (mutable collections / casts / type guards / kwargs / # unexplained suppressions), the test-linting.yml step `make lint` used to omit. -lint-type-discipline: install-dev lint-fetch-base +lint-type-discipline: $(LINT_DEP_INSTALL) $(LINT_DEP_BASE) $(UV_RUN) python scripts/type_discipline_gate.py --base origin/litellm_internal_staging # --update lowers each limit by what this branch fixed since its branch point, so @@ -176,7 +181,7 @@ lint-ruff-budget: install-dev # Strict gate, invoked the same way CI does in test-linting.yml so a local pass # means the CI check will pass too. -lint-gate: install-dev lint-fetch-base +lint-gate: $(LINT_DEP_INSTALL) $(LINT_DEP_BASE) $(UV_RUN) python scripts/ruff_strict_gate.py --base origin/litellm_internal_staging lint-ruff-budget-update: install-dev lint-fetch-base @@ -188,10 +193,10 @@ lint-type-discipline-budget-update: install-dev lint-fetch-base # Ratchet all budgets in one shot (ruff strict + type-discipline + basedpyright) lint-budget-update: lint-ruff-budget-update lint-type-discipline-budget-update lint-basedpyright-budget-update -check-circular-imports: install-dev +check-circular-imports: $(LINT_DEP_INSTALL) cd litellm && $(UV_RUN) python ../tests/documentation_tests/test_circular_imports.py && cd .. -check-import-safety: install-dev +check-import-safety: $(LINT_DEP_INSTALL) @$(UV_RUN) python -c "from litellm import *; print('[from litellm import *] OK! no issues!');" || (echo '🚨 import failed, this means you introduced unprotected imports! 🚨'; exit 1) # Combined linting, isomorphic to test-linting.yml's lint job so a local pass means a @@ -199,9 +204,13 @@ check-import-safety: install-dev # runs the diff-scoped ruff format check, whole-tree ruff check, the strict-rule / # type-discipline / basedpyright budgets as a delta vs the base, then the circular-import # and import-safety checks. Steps that compare against the base resolve it the same way CI -# does (merge-base with origin/litellm_internal_staging). lint-install is first so the -# Prisma client exists before basedpyright runs. -lint: lint-install lint-format-check-changed lint-ruff lint-gate lint-type-discipline lint-basedpyright check-circular-imports check-import-safety +# does (merge-base with origin/litellm_internal_staging). Setup (env sync, Prisma client, +# base fetch) runs once up front; the checks themselves are independent, so a sub-make +# fans them out with -j and the fast ones finish under basedpyright's shadow. +lint: lint-install lint-fetch-base + $(MAKE) -j $(LINT_JOBS) $(LINT_OUTPUT_SYNC) LINT_DEP_INSTALL= LINT_DEP_BASE= lint-checks + +lint-checks: lint-format-check-changed lint-ruff lint-gate lint-type-discipline lint-basedpyright check-circular-imports check-import-safety # Faster linting for local development (only checks changed code) lint-dev: lint-format-changed check-circular-imports check-import-safety diff --git a/basedpyright-code-budget.json b/basedpyright-code-budget.json index 79e6af05978..b65cd01e1eb 100644 --- a/basedpyright-code-budget.json +++ b/basedpyright-code-budget.json @@ -141,6 +141,6 @@ "limit": 1005 }, "reportUnusedVariable": { - "limit": 1298 + "limit": 1297 } } diff --git a/docker/build_admin_ui.sh b/docker/build_admin_ui.sh index efb2bac3535..68acdd78e3e 100755 --- a/docker/build_admin_ui.sh +++ b/docker/build_admin_ui.sh @@ -57,8 +57,6 @@ source ~/.nvm/nvm.sh nvm install v18.17.0 nvm use v18.17.0 -# copy _enterprise.json from this directory to /ui/litellm-dashboard, and rename it to ui_colors.json -cp enterprise/enterprise_ui/enterprise_colors.json ui/litellm-dashboard/ui_colors.json # cd in to /ui/litellm-dashboard cd ui/litellm-dashboard diff --git a/enterprise/pyproject.toml b/enterprise/pyproject.toml index f2ad04510a8..c7f37600fd5 100644 --- a/enterprise/pyproject.toml +++ b/enterprise/pyproject.toml @@ -1,6 +1,6 @@ [project] name = "litellm-enterprise" -version = "0.1.45" +version = "0.1.46" description = "Package for LiteLLM Enterprise features" readme = "README.md" requires-python = ">=3.9" @@ -26,7 +26,7 @@ required-version = ">=0.10.9" module-root = "" [tool.commitizen] -version = "0.1.45" +version = "0.1.46" version_files = [ "pyproject.toml:^version", "../pyproject.toml:litellm-enterprise==", diff --git a/litellm-proxy-extras/litellm_proxy_extras/migrations/20260629000000_add_max_concurrent_requests_to_mcp_server_table/migration.sql b/litellm-proxy-extras/litellm_proxy_extras/migrations/20260629000000_add_max_concurrent_requests_to_mcp_server_table/migration.sql new file mode 100644 index 00000000000..eeeecce741d --- /dev/null +++ b/litellm-proxy-extras/litellm_proxy_extras/migrations/20260629000000_add_max_concurrent_requests_to_mcp_server_table/migration.sql @@ -0,0 +1,2 @@ +-- AlterTable +ALTER TABLE "LiteLLM_MCPServerTable" ADD COLUMN "max_concurrent_requests" INTEGER; diff --git a/litellm-proxy-extras/litellm_proxy_extras/schema.prisma b/litellm-proxy-extras/litellm_proxy_extras/schema.prisma index 5351e0a1470..5e8bb2f37f4 100644 --- a/litellm-proxy-extras/litellm_proxy_extras/schema.prisma +++ b/litellm-proxy-extras/litellm_proxy_extras/schema.prisma @@ -338,6 +338,7 @@ model LiteLLM_MCPServerTable { byok_api_key_help_url String? source_url String? timeout Float? + max_concurrent_requests Int? // BYOM submission lifecycle approval_status String? @default("active") submitted_by String? diff --git a/litellm-proxy-extras/pyproject.toml b/litellm-proxy-extras/pyproject.toml index e2a86205fc5..4d237622da2 100644 --- a/litellm-proxy-extras/pyproject.toml +++ b/litellm-proxy-extras/pyproject.toml @@ -1,6 +1,6 @@ [project] name = "litellm-proxy-extras" -version = "0.4.74" +version = "0.4.75" description = "Additional files for the LiteLLM Proxy. Reduces the size of the main litellm package." readme = "README.md" requires-python = ">=3.9" @@ -26,7 +26,7 @@ required-version = ">=0.10.9" module-root = "" [tool.commitizen] -version = "0.4.74" +version = "0.4.75" version_files = [ "pyproject.toml:^version", "../pyproject.toml:litellm-proxy-extras==", diff --git a/litellm/__init__.py b/litellm/__init__.py index 9327e121b1d..2ec0830d622 100644 --- a/litellm/__init__.py +++ b/litellm/__init__.py @@ -588,6 +588,7 @@ gemini_models: Set = set() xai_models: Set = set() zai_models: Set = set() deepseek_models: Set = set() +tencent_models: Set = set() runwayml_models: Set = set() azure_ai_models: Set = set() jina_ai_models: Set = set() @@ -801,6 +802,8 @@ def add_known_models(model_cost_map: Optional[Dict] = None): fal_ai_models.add(key) elif value.get("litellm_provider") == "deepseek": deepseek_models.add(key) + elif value.get("litellm_provider") == "tencent": + tencent_models.add(key) elif value.get("litellm_provider") == "runwayml": runwayml_models.add(key) elif value.get("litellm_provider") == "meta_llama": @@ -1093,6 +1096,7 @@ models_by_provider: dict = { "zai": zai_models, "fal_ai": fal_ai_models, "deepseek": deepseek_models, + "tencent": tencent_models, "runwayml": runwayml_models, "mistral": mistral_chat_models, "azure_ai": azure_ai_models, @@ -1804,6 +1808,9 @@ if TYPE_CHECKING: from .llms.deepseek.chat.transformation import ( DeepSeekChatConfig as _DeepSeekChatConfig, ) + from .llms.tencent.chat.transformation import ( + TencentChatConfig as _TencentChatConfig, + ) from .llms.sap.chat.transformation import ( GenAIHubOrchestrationConfig as _GenAIHubOrchestrationConfig, ) @@ -1846,6 +1853,7 @@ if TYPE_CHECKING: # Type stubs for lazy-loaded config classes (to help mypy understand types) VLLMConfig: Type[_VLLMConfig] DeepSeekChatConfig: Type[_DeepSeekChatConfig] + TencentChatConfig: Type[_TencentChatConfig] GenAIHubOrchestrationConfig: Type[_GenAIHubOrchestrationConfig] GenAIHubEmbeddingConfig: Type[_GenAIHubEmbeddingConfig] AzureOpenAIO1Config: Type[_AzureOpenAIO1Config] diff --git a/litellm/_lazy_imports_registry.py b/litellm/_lazy_imports_registry.py index 0f9d3a560d1..488331e3895 100644 --- a/litellm/_lazy_imports_registry.py +++ b/litellm/_lazy_imports_registry.py @@ -284,6 +284,7 @@ LLM_CONFIG_NAMES = ( "LiteLLMProxyChatConfig", "VLLMConfig", "DeepSeekChatConfig", + "TencentChatConfig", "LMStudioChatConfig", "LmStudioEmbeddingConfig", "NscaleConfig", @@ -1096,6 +1097,7 @@ _LLM_CONFIGS_IMPORT_MAP = { ), "VLLMConfig": (".llms.vllm.completion.transformation", "VLLMConfig"), "DeepSeekChatConfig": (".llms.deepseek.chat.transformation", "DeepSeekChatConfig"), + "TencentChatConfig": (".llms.tencent.chat.transformation", "TencentChatConfig"), "LMStudioChatConfig": (".llms.lm_studio.chat.transformation", "LMStudioChatConfig"), "LmStudioEmbeddingConfig": ( ".llms.lm_studio.embed.transformation", diff --git a/litellm/a2a_protocol/main.py b/litellm/a2a_protocol/main.py index 37bf7c34f02..4c23ecfed54 100644 --- a/litellm/a2a_protocol/main.py +++ b/litellm/a2a_protocol/main.py @@ -129,6 +129,33 @@ def _set_agent_id_on_logging_obj( litellm_logging_obj.model_call_details["agent_id"] = agent_id +_A2A_COST_PARAM_KEYS = ("cost_per_query", "input_cost_per_token", "output_cost_per_token") + + +def _set_litellm_params_on_logging_obj( + kwargs: dict[str, Any], + litellm_params: dict[str, Any], +) -> None: + """ + Merge the agent's pricing params into model_call_details["litellm_params"] + so A2ACostCalculator can read them. + + The non-streaming path reuses the proxy-built logging object, whose + litellm_params already carries metadata / proxy_server_request / user-key + context, so merge the pricing keys in rather than replacing the dict. + """ + logging_obj = kwargs.get("litellm_logging_obj") + if logging_obj is None: + return + + cost_params = {key: litellm_params[key] for key in _A2A_COST_PARAM_KEYS if litellm_params.get(key) is not None} + if not cost_params: + return + + existing = logging_obj.model_call_details.get("litellm_params") or {} + logging_obj.model_call_details["litellm_params"] = {**existing, **cost_params} + + def _get_a2a_model_info(a2a_client: Any, kwargs: Dict[str, Any]) -> str: """ Extract agent info and set model/custom_llm_provider for cost tracking. @@ -477,6 +504,9 @@ async def asend_message( completion_tokens=completion_tokens, ) + # Merge agent pricing params into the logging obj so cost is calculated + _set_litellm_params_on_logging_obj(kwargs=kwargs, litellm_params=litellm_params) + # Set agent_id on logging obj for SpendLogs tracking _set_agent_id_on_logging_obj(kwargs=kwargs, agent_id=agent_id) diff --git a/litellm/a2a_protocol/utils.py b/litellm/a2a_protocol/utils.py index 0dbd1eefc63..ce5a168c3ac 100644 --- a/litellm/a2a_protocol/utils.py +++ b/litellm/a2a_protocol/utils.py @@ -121,8 +121,13 @@ class A2ARequestUtils: Returns: Tuple of (prompt_tokens, completion_tokens, total_tokens) """ - # Count input tokens + # Count input tokens. Dump the message to a dict first so extraction hits + # the dict branch β€” request-side parts are a2a-sdk Part RootModels whose + # kind/text live on part.root, which the object branch cannot read. This + # mirrors how the response side already works (it operates on model_dump). input_message = A2ARequestUtils.get_input_message_from_request(request) + if input_message is not None and hasattr(input_message, "model_dump"): + input_message = input_message.model_dump(mode="json") input_text = A2ARequestUtils.extract_text_from_message(input_message) prompt_tokens = A2ARequestUtils.count_tokens(input_text) diff --git a/litellm/constants.py b/litellm/constants.py index 6eb2779dcae..1300668cc70 100644 --- a/litellm/constants.py +++ b/litellm/constants.py @@ -508,6 +508,7 @@ LITELLM_CHAT_PROVIDERS = [ "text-completion-codestral", "text-completion-inception", "deepseek", + "tencent", "sambanova", "maritalk", "cloudflare", @@ -729,6 +730,7 @@ openai_compatible_providers: List = [ "volcengine", "codestral", "deepseek", + "tencent", "deepinfra", "perplexity", "xinference", diff --git a/litellm/cost_calculator.py b/litellm/cost_calculator.py index e8535a570c8..8f4dd5badce 100644 --- a/litellm/cost_calculator.py +++ b/litellm/cost_calculator.py @@ -52,6 +52,9 @@ from litellm.llms.databricks.cost_calculator import ( from litellm.llms.deepseek.cost_calculator import ( cost_per_token as deepseek_cost_per_token, ) +from litellm.llms.tencent.cost_calculator import ( + cost_per_token as tencent_cost_per_token, +) from litellm.llms.fireworks_ai.cost_calculator import ( cost_per_token as fireworks_ai_cost_per_token, ) @@ -625,6 +628,8 @@ def cost_per_token( return gemini_cost_per_token(model=model, usage=usage_block, service_tier=service_tier) elif custom_llm_provider == "deepseek": return deepseek_cost_per_token(model=model, usage=usage_block) + elif custom_llm_provider == "tencent": + return tencent_cost_per_token(model=model, usage=usage_block) elif custom_llm_provider == "perplexity": return perplexity_cost_per_token(model=model, usage=usage_block) elif custom_llm_provider == "xai": diff --git a/litellm/exceptions.py b/litellm/exceptions.py index d97ba347b07..adf7b3ef05a 100644 --- a/litellm/exceptions.py +++ b/litellm/exceptions.py @@ -1165,12 +1165,18 @@ class ModifyResponseException(Exception): request_data: Dict[str, Any], guardrail_name: Optional[str] = None, detection_info: Optional[Dict[str, Any]] = None, + original_response: Optional[Any] = None, ): self.message = message self.model = model self.request_data = request_data self.guardrail_name = guardrail_name self.detection_info = detection_info or {} + # The LLM response that was blocked (post-call). Carries the real token + # usage the upstream call consumed, so the synthetic block response can + # report it instead of discarding it. None for pre-call blocks (the LLM + # was never invoked). + self.original_response = original_response super().__init__(message) diff --git a/litellm/integrations/prometheus.py b/litellm/integrations/prometheus.py index 4ebe312e301..0f89e21abda 100644 --- a/litellm/integrations/prometheus.py +++ b/litellm/integrations/prometheus.py @@ -4,6 +4,7 @@ from __future__ import annotations import asyncio +import math import os import sys from datetime import datetime, timedelta @@ -65,6 +66,26 @@ if TYPE_CHECKING: else: AsyncIOScheduler = Any +_DEFAULT_BUDGET_METRICS_PER_REQUEST_TIMEOUT = 5.0 + + +def _get_budget_metrics_per_request_timeout() -> float: + raw = os.getenv("PROMETHEUS_BUDGET_METRICS_PER_REQUEST_TIMEOUT") + if raw is None: + return _DEFAULT_BUDGET_METRICS_PER_REQUEST_TIMEOUT + try: + parsed = float(raw) + except ValueError: + parsed = None + if parsed is None or not math.isfinite(parsed) or parsed <= 0: + verbose_logger.debug( + "[Non-Blocking] Prometheus: invalid PROMETHEUS_BUDGET_METRICS_PER_REQUEST_TIMEOUT=%r; using default %ss.", + raw, + _DEFAULT_BUDGET_METRICS_PER_REQUEST_TIMEOUT, + ) + return _DEFAULT_BUDGET_METRICS_PER_REQUEST_TIMEOUT + return parsed + class PrometheusLogger(CustomLogger): # Class variables or attributes @@ -1607,7 +1628,15 @@ class PrometheusLogger(CustomLogger): _user_spend = _metadata.get("user_api_key_user_spend", None) _user_max_budget = _metadata.get("user_api_key_user_max_budget", None) - results = await asyncio.gather( + # Bound the per-request budget-metric emission so that slow Redis/DB + # lookups under load cannot consume the whole LoggingWorker watchdog + # (LOGGING_WORKER_MAX_TIME_PER_COROUTINE, default 20s) and get the entire + # success-logging event cancelled. Budget gauges are also refreshed by the + # periodic cron every PROMETHEUS_BUDGET_METRICS_REFRESH_INTERVAL_MINUTES, + # so dropping one slow per-request emission only loses sub-cron real-time + # detail, not correctness. + budget_metrics_timeout = _get_budget_metrics_per_request_timeout() + gather_coro = asyncio.gather( self._set_api_key_budget_metrics_after_api_request( user_api_key=user_api_key, user_api_key_alias=user_api_key_alias, @@ -1634,6 +1663,16 @@ class PrometheusLogger(CustomLogger): ), return_exceptions=True, ) + try: + results = await asyncio.wait_for(gather_coro, timeout=budget_metrics_timeout) + except asyncio.TimeoutError: + verbose_logger.debug( + "[Non-Blocking] Prometheus: per-request budget metric emission " + "exceeded %ss under load; skipping (values are refreshed by the " + "periodic budget-metrics cron job).", + budget_metrics_timeout, + ) + return for i, r in enumerate(results): if isinstance(r, Exception): verbose_logger.debug( diff --git a/litellm/integrations/s3_v2.py b/litellm/integrations/s3_v2.py index 939289f96ea..5b953035cfd 100644 --- a/litellm/integrations/s3_v2.py +++ b/litellm/integrations/s3_v2.py @@ -54,6 +54,7 @@ class S3Logger(CustomBatchLogger, BaseAWSLLM): s3_strip_base64_files: bool = False, s3_use_key_prefix: bool = False, s3_use_virtual_hosted_style: bool = False, + s3_server_side_encryption: Optional[str] = None, s3_callback_params_override: Optional[dict] = None, **kwargs, ): @@ -92,6 +93,7 @@ class S3Logger(CustomBatchLogger, BaseAWSLLM): s3_strip_base64_files=s3_strip_base64_files, s3_use_key_prefix=s3_use_key_prefix, s3_use_virtual_hosted_style=s3_use_virtual_hosted_style, + s3_server_side_encryption=s3_server_side_encryption, ) verbose_logger.debug(f"s3 logger using endpoint url {s3_endpoint_url}") @@ -145,6 +147,7 @@ class S3Logger(CustomBatchLogger, BaseAWSLLM): s3_strip_base64_files: bool = False, s3_use_key_prefix: bool = False, s3_use_virtual_hosted_style: bool = False, + s3_server_side_encryption: Optional[str] = None, params_source: Optional[dict] = None, ): """ @@ -194,6 +197,8 @@ class S3Logger(CustomBatchLogger, BaseAWSLLM): bool(params.get("s3_use_virtual_hosted_style", False)) or s3_use_virtual_hosted_style ) + self.s3_server_side_encryption = params.get("s3_server_side_encryption") or s3_server_side_encryption + return async def async_log_success_event(self, kwargs, response_obj, start_time, end_time): @@ -273,6 +278,7 @@ class S3Logger(CustomBatchLogger, BaseAWSLLM): async def async_upload_data_to_s3(self, batch_logging_element: s3BatchLoggingElement): try: + import base64 import hashlib import requests @@ -317,14 +323,23 @@ class S3Logger(CustomBatchLogger, BaseAWSLLM): # Calculate SHA256 hash of the content content_hash = hashlib.sha256(json_string.encode("utf-8")).hexdigest() + content_md5 = base64.b64encode( + hashlib.md5(json_string.encode("utf-8"), usedforsecurity=False).digest() + ).decode() # Prepare the request headers = { "Content-Type": "application/json", + "Content-MD5": content_md5, "x-amz-content-sha256": content_hash, "Content-Language": "en", "Content-Disposition": f'inline; filename="{batch_logging_element.s3_object_download_filename}"', "Cache-Control": "private, immutable, max-age=31536000, s-maxage=0", + **( + {"x-amz-server-side-encryption": self.s3_server_side_encryption} + if self.s3_server_side_encryption + else {} + ), } req = requests.Request("PUT", url, data=json_string, headers=headers) prepped = req.prepare() @@ -447,6 +462,7 @@ class S3Logger(CustomBatchLogger, BaseAWSLLM): def upload_data_to_s3(self, batch_logging_element: s3BatchLoggingElement): try: + import base64 import hashlib import requests @@ -482,14 +498,23 @@ class S3Logger(CustomBatchLogger, BaseAWSLLM): # Calculate SHA256 hash of the content content_hash = hashlib.sha256(json_string.encode("utf-8")).hexdigest() + content_md5 = base64.b64encode( + hashlib.md5(json_string.encode("utf-8"), usedforsecurity=False).digest() + ).decode() # Prepare the request headers = { "Content-Type": "application/json", + "Content-MD5": content_md5, "x-amz-content-sha256": content_hash, "Content-Language": "en", "Content-Disposition": f'inline; filename="{batch_logging_element.s3_object_download_filename}"', "Cache-Control": "private, immutable, max-age=31536000, s-maxage=0", + **( + {"x-amz-server-side-encryption": self.s3_server_side_encryption} + if self.s3_server_side_encryption + else {} + ), } req = requests.Request("PUT", url, data=json_string, headers=headers) prepped = req.prepare() diff --git a/litellm/litellm_core_utils/get_llm_provider_logic.py b/litellm/litellm_core_utils/get_llm_provider_logic.py index a7a576ff167..61a73201c43 100644 --- a/litellm/litellm_core_utils/get_llm_provider_logic.py +++ b/litellm/litellm_core_utils/get_llm_provider_logic.py @@ -652,6 +652,10 @@ def _get_openai_compatible_provider_info( api_base = api_base or get_secret("DEEPSEEK_API_BASE") or "https://api.deepseek.com/beta" # type: ignore dynamic_api_key = api_key or get_secret_str("DEEPSEEK_API_KEY") + elif custom_llm_provider == "tencent": + api_base = api_base or get_secret("TENCENT_API_BASE") or "https://tokenhub-intl.tencentcloudmaas.com/v1" + + dynamic_api_key = api_key or get_secret_str("TENCENT_API_KEY") elif custom_llm_provider == "fireworks_ai": # fireworks is openai compatible, we just need to set this to custom_openai and have the api_base be https://api.fireworks.ai/inference/v1 ( diff --git a/litellm/litellm_core_utils/get_supported_openai_params.py b/litellm/litellm_core_utils/get_supported_openai_params.py index c4ddb4b7ee0..19149da0316 100644 --- a/litellm/litellm_core_utils/get_supported_openai_params.py +++ b/litellm/litellm_core_utils/get_supported_openai_params.py @@ -106,6 +106,8 @@ def get_supported_openai_params( return litellm.VLLMConfig().get_supported_openai_params(model=model) elif custom_llm_provider == "deepseek": return litellm.DeepSeekChatConfig().get_supported_openai_params(model=model) + elif custom_llm_provider == "tencent": + return litellm.TencentChatConfig().get_supported_openai_params(model=model) elif custom_llm_provider == "cohere_chat" or custom_llm_provider == "cohere": return litellm.CohereChatConfig().get_supported_openai_params(model=model) elif custom_llm_provider == "maritalk": diff --git a/litellm/litellm_core_utils/initialize_dynamic_callback_params.py b/litellm/litellm_core_utils/initialize_dynamic_callback_params.py index d0a6ec30c9e..06a9e98c5ac 100644 --- a/litellm/litellm_core_utils/initialize_dynamic_callback_params.py +++ b/litellm/litellm_core_utils/initialize_dynamic_callback_params.py @@ -1,7 +1,23 @@ -from typing import Dict, Optional +from typing import Any, Dict, Iterator, Optional from litellm.types.utils import StandardCallbackDynamicParams +_CLIENT_CALLBACK_METADATA_SLOTS: tuple[str, ...] = ("litellm_metadata", "metadata") + + +def iter_client_callback_metadata_dicts( + kwargs: dict[str, Any], +) -> Iterator[tuple[str, dict[str, Any]]]: + litellm_params = kwargs.get("litellm_params") + if isinstance(litellm_params, dict): + nested = litellm_params.get("metadata") + if isinstance(nested, dict): + yield "litellm_params.metadata", nested + for key in _CLIENT_CALLBACK_METADATA_SLOTS: + candidate = kwargs.get(key) + if isinstance(candidate, dict): + yield key, candidate + def _is_env_reference(value: object) -> bool: return isinstance(value, str) and "os.environ/" in value @@ -55,6 +71,7 @@ _supported_callback_params = [ "dd_site", "dd_agent_host", "dd_agent_port", + "turn_off_message_logging", ] _request_blocked_callback_params = { @@ -87,19 +104,13 @@ def initialize_standard_callback_dynamic_params( validate_no_callback_env_reference(param, _param_value, source="request body") standard_callback_dynamic_params[param] = _param_value # type: ignore - # 2. Fallback: check "metadata" or "litellm_params" -> "metadata" - metadata = (kwargs.get("metadata") or {}).copy() - litellm_params = kwargs.get("litellm_params") or {} - if isinstance(litellm_params, dict): - metadata.update(litellm_params.get("metadata") or {}) - - if isinstance(metadata, dict): + for slot_label, metadata in iter_client_callback_metadata_dicts(kwargs): for param in _supported_callback_params: if param in _request_blocked_callback_params: continue if param not in standard_callback_dynamic_params and param in metadata: _param_value = metadata.get(param) - validate_no_callback_env_reference(param, _param_value, source="metadata") + validate_no_callback_env_reference(param, _param_value, source=slot_label) standard_callback_dynamic_params[param] = _param_value # type: ignore return standard_callback_dynamic_params diff --git a/litellm/llms/a2a/chat/transformation.py b/litellm/llms/a2a/chat/transformation.py index c9623a817bf..113c000f352 100644 --- a/litellm/llms/a2a/chat/transformation.py +++ b/litellm/llms/a2a/chat/transformation.py @@ -10,7 +10,7 @@ import httpx from litellm.llms.base_llm.base_model_iterator import BaseModelResponseIterator from litellm.llms.base_llm.chat.transformation import BaseConfig, BaseLLMException from litellm.types.llms.openai import AllMessageValues -from litellm.types.utils import Choices, Message, ModelResponse +from litellm.types.utils import Choices, Message, ModelResponse, Usage from ..common_utils import ( A2AError, @@ -312,6 +312,25 @@ class A2AConfig(BaseConfig): # Set ID from response model_response.id = response_json.get("id", str(uuid.uuid4())) + # A2A agents don't return token usage; estimate it so per-token pricing + # produces real cost and callers don't receive usage of 0/0/0. + try: + from litellm.utils import token_counter + + prompt_tokens = token_counter(model="gpt-3.5-turbo", messages=messages) + completion_tokens = token_counter(model="gpt-3.5-turbo", text=text, count_response_tokens=True) + setattr( + model_response, + "usage", + Usage( + prompt_tokens=prompt_tokens, + completion_tokens=completion_tokens, + total_tokens=prompt_tokens + completion_tokens, + ), + ) + except Exception: # noqa: BLE001 - best-effort estimate; a tokenizer hiccup must not break the response + pass + return model_response def get_model_response_iterator( diff --git a/litellm/llms/anthropic/chat/guardrail_translation/handler.py b/litellm/llms/anthropic/chat/guardrail_translation/handler.py index 4506c114208..7000c20d9c4 100644 --- a/litellm/llms/anthropic/chat/guardrail_translation/handler.py +++ b/litellm/llms/anthropic/chat/guardrail_translation/handler.py @@ -48,7 +48,10 @@ from litellm.types.utils import ( ) if TYPE_CHECKING: - from litellm.integrations.custom_guardrail import CustomGuardrail + from litellm.integrations.custom_guardrail import ( + CustomGuardrail, + ModifyResponseException, + ) from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj from litellm.types.llms.anthropic_messages.anthropic_response import ( AnthropicMessagesResponse, @@ -70,6 +73,170 @@ class AnthropicMessagesHandler(BaseTranslation): super().__init__() self.adapter = LiteLLMAnthropicMessagesAdapter() + @staticmethod + def _build_streaming_usage_response( + responses_so_far: list[Any], + request_data: Optional[dict], + ) -> Optional[ModelResponse]: + chunks = tuple(response for response in responses_so_far if isinstance(response, (str, bytes))) + if not chunks: + return None + try: + return AnthropicPassthroughLoggingHandler._build_usage_only_response_from_chunks( + all_chunks=chunks, + model=str((request_data or {}).get("model") or ""), + ) + except (AttributeError, TypeError, ValueError): + return None + + def build_block_sse_chunks( + self, + exc: "ModifyResponseException", + stream_started: bool = False, + responses_so_far: Optional[list[Any]] = None, + ) -> list[bytes]: + """ + Build an Anthropic SSE sequence delivering the guardrail block message + and terminating the stream cleanly. + + - ``stream_started`` False (buffered / pre-stream): nothing has been + sent, so emit a complete standalone message (message_start -> + content_block_* -> message_delta -> message_stop) via + FakeAnthropicMessagesStreamIterator, the same converter the + /v1/messages pre-stream block handler uses. + - ``stream_started`` True (sampling / detect-only end-of-stream): real + chunks were already sent, so *continue* the in-progress message -- + close the open content block, append the block message as a new text + block, then end the message. Emitting a second ``message_start`` here + would make Anthropic clients reject the stream. + """ + if stream_started: + return self._block_continuation_chunks(exc, responses_so_far or []) + return self._standalone_block_chunks(exc) + + def _standalone_block_chunks(self, exc: "ModifyResponseException") -> list[bytes]: + import uuid + + from litellm.llms.anthropic.experimental_pass_through.messages.fake_stream_iterator import ( + FakeAnthropicMessagesStreamIterator, + ) + from litellm.llms.base_llm.guardrail_translation.utils import ( + blocked_response_usage, + ) + from litellm.types.utils import AnthropicMessagesResponse + + block_response = AnthropicMessagesResponse( + id=f"msg_{uuid.uuid4()}", + type="message", + role="assistant", + content=[{"type": "text", "text": exc.message}], + model=exc.model, + stop_reason="end_turn", + usage=blocked_response_usage(getattr(exc, "original_response", None)), + ) + return list(FakeAnthropicMessagesStreamIterator(response=block_response)) + + def _block_continuation_chunks(self, exc: "ModifyResponseException", responses_so_far: list[Any]) -> list[bytes]: + """Continue an already-started message: close the open content block, + append the block message as a new text block, then end the message -- + without a second message_start.""" + + from litellm.llms.base_llm.guardrail_translation.utils import ( + blocked_response_usage, + ) + + def _sse(event_type: str, payload: dict) -> bytes: + return f"event: {event_type}\ndata: {json.dumps(payload)}\n\n".encode() + + output_tokens = blocked_response_usage(getattr(exc, "original_response", None))["output_tokens"] + open_index, max_index = self._content_block_state(responses_so_far) + new_index = (max_index + 1) if max_index is not None else 0 + chunks: list[bytes] = [] + if open_index is not None: + chunks.append(_sse("content_block_stop", {"type": "content_block_stop", "index": open_index})) + chunks += [ + _sse( + "content_block_start", + { + "type": "content_block_start", + "index": new_index, + "content_block": {"type": "text", "text": ""}, + }, + ), + _sse( + "content_block_delta", + { + "type": "content_block_delta", + "index": new_index, + "delta": {"type": "text_delta", "text": exc.message}, + }, + ), + _sse("content_block_stop", {"type": "content_block_stop", "index": new_index}), + _sse( + "message_delta", + { + "type": "message_delta", + "delta": {"stop_reason": "end_turn", "stop_sequence": None}, + "usage": {"output_tokens": output_tokens}, + }, + ), + _sse("message_stop", {"type": "message_stop"}), + ] + return chunks + + @staticmethod + def _content_block_state( + responses_so_far: list[Any], + ) -> tuple[Optional[int], Optional[int]]: + """From the SSE chunks already sent to the client, return (open + content-block index or None, highest content-block index seen or None). + + A single streamed item may bundle multiple SSE events (raw bytes) or be + an already-parsed event dict, so every event across every item is + considered -- matching how ``get_streaming_string_so_far`` reads the + same stream.""" + open_indices: set[int] = set() + max_index: Optional[int] = None + for item in responses_so_far: + for data in AnthropicMessagesHandler._iter_sse_events(item): + event_type = data.get("type") + index = data.get("index") + if not isinstance(index, int): + continue + if event_type == "content_block_start": + open_indices.add(index) + max_index = index if max_index is None else max(max_index, index) + elif event_type == "content_block_stop": + open_indices.discard(index) + open_index = max(open_indices) if open_indices else None + return open_index, max_index + + @staticmethod + def _iter_sse_events(item: Any) -> list[dict]: + """Yield the event-data dicts in one stream chunk. + + Handles both formats this stream can carry (see + ``get_streaming_string_so_far``): raw SSE ``bytes`` -- which may bundle + several events separated by a blank line -- and an already-parsed event + ``dict``.""" + if isinstance(item, dict): + return [item] + if not isinstance(item, (bytes, bytearray)): + return [] + events: list[dict] = [] + for block in item.decode("utf-8", errors="replace").split("\n\n"): + for line in block.split("\n"): + line = line.strip() + if not line.startswith("data:"): + continue + try: + parsed = json.loads(line[len("data:") :].strip()) + except json.JSONDecodeError: + continue + if isinstance(parsed, dict): + events.append(parsed) + return events + def _translate_to_openai(self, data: dict) -> ChatCompletionRequest: """Translate Anthropic request to OpenAI chat completion format.""" ( @@ -406,6 +573,8 @@ class AnthropicMessagesHandler(BaseTranslation): Get the string so far, check the apply guardrail to the string so far, and return the list of responses so far. """ + from litellm.integrations.custom_guardrail import ModifyResponseException + has_ended = self._check_streaming_has_ended(responses_so_far) if has_ended: # build the model response from the responses_so_far @@ -430,25 +599,35 @@ class AnthropicMessagesHandler(BaseTranslation): if tool_calls_list: guardrail_inputs["tool_calls"] = tool_calls_list - _guardrailed_inputs = ( - await guardrail_to_apply.apply_guardrail( # allow rejecting the response, if invalid + try: + _guardrailed_inputs = await guardrail_to_apply.apply_guardrail( inputs=guardrail_inputs, request_data=request_data if request_data is not None else {}, input_type="response", logging_obj=litellm_logging_obj, ) - ) + except ModifyResponseException as e: + if e.original_response is None: + e.original_response = built_response or self._build_streaming_usage_response( + responses_so_far, request_data + ) + raise else: verbose_proxy_logger.debug("Skipping output guardrail - model response has no choices") return responses_so_far string_so_far = self.get_streaming_string_so_far(responses_so_far) - _guardrailed_inputs = await guardrail_to_apply.apply_guardrail( # allow rejecting the response, if invalid - inputs={"texts": [string_so_far]}, - request_data=request_data if request_data is not None else {}, - input_type="response", - logging_obj=litellm_logging_obj, - ) + try: + _guardrailed_inputs = await guardrail_to_apply.apply_guardrail( + inputs={"texts": [string_so_far]}, + request_data=request_data if request_data is not None else {}, + input_type="response", + logging_obj=litellm_logging_obj, + ) + except ModifyResponseException as e: + if e.original_response is None: + e.original_response = self._build_streaming_usage_response(responses_so_far, request_data) + raise return responses_so_far def _prepare_request_data( diff --git a/litellm/llms/azure_ai/ocr/document_intelligence/transformation.py b/litellm/llms/azure_ai/ocr/document_intelligence/transformation.py index c67703f64d7..7d915892a28 100644 --- a/litellm/llms/azure_ai/ocr/document_intelligence/transformation.py +++ b/litellm/llms/azure_ai/ocr/document_intelligence/transformation.py @@ -15,6 +15,7 @@ from typing import Any, Dict from urllib.parse import quote import httpx +from pydantic import BaseModel from litellm._logging import verbose_logger from litellm.litellm_core_utils.url_utils import SSRFError, assert_same_origin @@ -38,6 +39,30 @@ from litellm.secret_managers.main import get_secret_str AZURE_DOCUMENT_INTELLIGENCE_API_KEY_ENV_VAR = "AZURE_DOCUMENT_INTELLIGENCE_API_KEY" +class AzureDocumentIntelligenceLine(BaseModel): + content: str | None = None + + +class AzureDocumentIntelligencePage(BaseModel): + pageNumber: int | None = None + width: float | None = None + height: float | None = None + unit: str | None = None + lines: tuple[AzureDocumentIntelligenceLine, ...] = () + + +class AzureDocumentIntelligenceAnalyzeResult(BaseModel): + content: str | None = None + pages: tuple[AzureDocumentIntelligencePage, ...] = () + tables: list[dict[str, object]] | None = None + keyValuePairs: list[dict[str, object]] | None = None + + +class AzureDocumentIntelligenceOperation(BaseModel): + status: str | None = None + analyzeResult: AzureDocumentIntelligenceAnalyzeResult | None = None + + class AzureDocumentIntelligenceOCRConfig(BaseOCRConfig): """ Azure Document Intelligence OCR transformation configuration. @@ -67,11 +92,14 @@ class AzureDocumentIntelligenceOCRConfig(BaseOCRConfig): (1-based, e.g. "1-3,5,7-9"). To keep the public request shape aligned with Mistral OCR, callers pass `pages` using Mistral semantics β€” a list of 0-based integers β€” or a pre-formatted - Azure-style string. Other Mistral-specific params (e.g. + Azure-style string. Azure DI also exposes a `features` query + parameter enabling add-on capabilities (e.g. "keyValuePairs", + "languages"), passed as a list of feature names or a + comma-separated string. Other Mistral-specific params (e.g. `include_image_base64`) are not supported by Azure DI and are ignored during transformation. """ - return ["pages"] + return ["pages", "features"] def map_ocr_params( self, @@ -85,16 +113,18 @@ class AzureDocumentIntelligenceOCRConfig(BaseOCRConfig): Translates Mistral-style `pages` (list[int], 0-based) into Azure's `pages` query string (1-based, e.g. "1,2,3" or "1-3,5"). A raw string that already matches Azure's format is passed through - unchanged. + unchanged. `features` (list[str] or comma-separated string) is + normalized into Azure's comma-joined `features` query string. """ pages = non_default_params.get("pages") - if pages is None: - return optional_params - - normalized = self._normalize_pages_param(pages) - if normalized: - optional_params["pages"] = normalized - return optional_params + features = non_default_params.get("features") + normalized_pages = self._normalize_pages_param(pages) if pages is not None else "" + normalized_features = self._normalize_features_param(features) if features is not None else "" + return { + **optional_params, + **({"pages": normalized_pages} if normalized_pages else {}), + **({"features": normalized_features} if normalized_features else {}), + } @staticmethod def _normalize_pages_param(pages: Any) -> str: @@ -140,6 +170,39 @@ class AzureDocumentIntelligenceOCRConfig(BaseOCRConfig): raise ValueError("`pages` must be a list[int] (0-based, Mistral-style) or a string like '1-3,5,7-9'.") + @staticmethod + def _normalize_features_param(features: object) -> str: + """ + Convert a caller-provided `features` value to Azure DI's query-string + form (comma-joined feature names, e.g. "keyValuePairs,languages"). + + Accepted inputs: + - list[str]: feature names like ["keyValuePairs", "languages"]. + - str: a single feature name or comma-separated names. + """ + invalid_features_error = ValueError( + f"Invalid `features` for Azure Document Intelligence: {features!r}. " + f"Expected a list of feature names or a comma-separated string like " + f"'keyValuePairs' or 'keyValuePairs,languages'." + ) + + if isinstance(features, str): + raw_tokens = features.split(",") + elif isinstance(features, list): + if len(features) == 0: + return "" + raw_tokens = [feature for feature in features if isinstance(feature, str)] + if len(raw_tokens) != len(features): + raise invalid_features_error + else: + raise invalid_features_error + + tokens = tuple(token.strip() for token in raw_tokens) + feature_pattern = re.compile(r"^[A-Za-z][A-Za-z0-9]*$") + if not all(feature_pattern.match(token) for token in tokens): + raise invalid_features_error + return ",".join(tokens) + def validate_environment( self, headers: Dict, @@ -228,13 +291,15 @@ class AzureDocumentIntelligenceOCRConfig(BaseOCRConfig): f"?api-version={AZURE_DOCUMENT_INTELLIGENCE_API_VERSION}" ) - # Azure DI accepts `pages` as a query param (1-based, e.g. "1-3,5"). + # Azure DI accepts `pages` (1-based, e.g. "1-3,5") and `features` + # (comma-joined names, e.g. "keyValuePairs") as query params. # `optional_params` has already been normalized in `map_ocr_params`. pages = optional_params.get("pages") if optional_params else None - if pages: - url += f"&pages={quote(str(pages), safe=',-')}" + features = optional_params.get("features") if optional_params else None + pages_query = f"&pages={quote(str(pages), safe=',-')}" if pages else "" + features_query = f"&features={quote(str(features), safe=',')}" if features else "" - return url + return f"{url}{pages_query}{features_query}" def _extract_base64_from_data_uri(self, data_uri: str) -> str: """ @@ -328,27 +393,15 @@ class AzureDocumentIntelligenceOCRConfig(BaseOCRConfig): return OCRRequestData(data=data, files=None) - def _extract_page_markdown(self, page_data: Dict[str, Any]) -> str: - """ - Extract text from Azure DI page and format as markdown. - - Azure DI provides text in 'lines' array. We concatenate them with newlines. - - Args: - page_data: Azure DI page object - - Returns: - Markdown-formatted text - """ - lines = page_data.get("lines", []) - if not lines: - return "" - - # Extract text content from each line - text_lines = [line.get("content", "") for line in lines] - - # Join with newlines to preserve structure - return "\n".join(text_lines) + def _transform_azure_page(self, azure_page: AzureDocumentIntelligencePage) -> OCRPage: + page_number = azure_page.pageNumber if azure_page.pageNumber is not None else 1 + markdown = "\n".join(line.content or "" for line in azure_page.lines) + dimensions = self._convert_dimensions( + width=azure_page.width if azure_page.width is not None else 8.5, + height=azure_page.height if azure_page.height is not None else 11, + unit=azure_page.unit if azure_page.unit is not None else "inch", + ) + return OCRPage(index=page_number - 1, markdown=markdown, dimensions=dimensions) def _convert_dimensions(self, width: float, height: float, unit: str) -> OCRPageDimensions: """ @@ -526,6 +579,52 @@ class AzureDocumentIntelligenceOCRConfig(BaseOCRConfig): retry_after = self._get_retry_after(response=response) await asyncio.sleep(retry_after) + def _get_polling_target(self, raw_response: httpx.Response) -> tuple[str, Dict[str, str]]: + operation_url = raw_response.headers.get("Operation-Location") + if not operation_url: + raise ValueError("Azure Document Intelligence returned 202 but no Operation-Location header found") + + # Reject cross-origin polling URLs β€” the auth headers + # below would otherwise leak to whatever URL the upstream + # (or an attacker-controlled upstream) returns. VERIA-51. + try: + assert_same_origin(operation_url, str(raw_response.request.url)) + except SSRFError as ssrf_err: + raise ValueError(f"Azure Document Intelligence: rejected polling URL ({ssrf_err})") + + poll_headers = {"Ocp-Apim-Subscription-Key": raw_response.request.headers.get("Ocp-Apim-Subscription-Key", "")} + return operation_url, poll_headers + + def _transform_completed_response(self, model: str, raw_response: httpx.Response) -> OCRResponse: + """ + Transform a completed Azure Document Intelligence analyze operation + into the Mistral OCR response shape, preserving Azure-native + `analyzeResult` fields (`content`, `tables`, `keyValuePairs`) as + top-level response fields. + """ + operation = AzureDocumentIntelligenceOperation.model_validate(raw_response.json()) + + verbose_logger.debug(f"Azure Document Intelligence response status: {operation.status}") + + if operation.status != "succeeded": + raise ValueError(f"Azure Document Intelligence analysis failed with status: {operation.status}") + + analyze_result = ( + operation.analyzeResult if operation.analyzeResult is not None else AzureDocumentIntelligenceAnalyzeResult() + ) + mistral_pages = [self._transform_azure_page(azure_page) for azure_page in analyze_result.pages] + usage_info = OCRUsageInfo(pages_processed=len(mistral_pages), doc_size_bytes=None) + + return OCRResponse( + pages=mistral_pages, + model=model, + usage_info=usage_info, + object="ocr", + content=analyze_result.content, + tables=analyze_result.tables, + keyValuePairs=analyze_result.keyValuePairs, + ) + def transform_ocr_response( self, model: str, @@ -552,11 +651,13 @@ class AzureDocumentIntelligenceOCRConfig(BaseOCRConfig): "unit": "inch", "lines": [{"content": "text", "boundingBox": [...]}] } - ] + ], + "tables": [...], + "keyValuePairs": [...] } } - Mistral OCR format: + Mistral OCR format (with Azure-native fields preserved): { "pages": [ { @@ -567,7 +668,10 @@ class AzureDocumentIntelligenceOCRConfig(BaseOCRConfig): ], "model": "azure_ai/doc-intelligence/prebuilt-layout", "usage_info": {"pages_processed": 1}, - "object": "ocr" + "object": "ocr", + "content": "Full document text...", + "tables": [...], + "keyValuePairs": [...] } Args: @@ -578,86 +682,17 @@ class AzureDocumentIntelligenceOCRConfig(BaseOCRConfig): Returns: OCRResponse in Mistral format """ - try: - # Check if we got 202 Accepted (async operation started) - if raw_response.status_code == 202: - verbose_logger.debug("Azure DI returned 202 Accepted, polling operation...") + if raw_response.status_code != 202: + return self._transform_completed_response(model=model, raw_response=raw_response) - # Get Operation-Location header - operation_url = raw_response.headers.get("Operation-Location") - if not operation_url: - raise ValueError("Azure Document Intelligence returned 202 but no Operation-Location header found") - - # Reject cross-origin polling URLs β€” the auth headers - # below would otherwise leak to whatever URL the upstream - # (or an attacker-controlled upstream) returns. VERIA-51. - try: - assert_same_origin(operation_url, str(raw_response.request.url)) - except SSRFError as ssrf_err: - raise ValueError(f"Azure Document Intelligence: rejected polling URL ({ssrf_err})") - - # Get headers for polling (need auth) - poll_headers = { - "Ocp-Apim-Subscription-Key": raw_response.request.headers.get("Ocp-Apim-Subscription-Key", "") - } - - # Get timeout from kwargs or use default - timeout_secs = AZURE_OPERATION_POLLING_TIMEOUT - - # Poll until operation completes - raw_response = self._poll_operation_sync( - operation_url=operation_url, - headers=poll_headers, - timeout_secs=timeout_secs, - ) - - # Now parse the completed response - response_json = raw_response.json() - - verbose_logger.debug(f"Azure Document Intelligence response status: {response_json.get('status')}") - - # Check if request succeeded - status = response_json.get("status") - if status != "succeeded": - raise ValueError(f"Azure Document Intelligence analysis failed with status: {status}") - - # Extract analyze result - analyze_result = response_json.get("analyzeResult", {}) - azure_pages = analyze_result.get("pages", []) - - # Transform pages to Mistral format - mistral_pages = [] - for azure_page in azure_pages: - page_number = azure_page.get("pageNumber", 1) - index = page_number - 1 # Convert to 0-based index - - # Extract markdown text - markdown = self._extract_page_markdown(azure_page) - - # Convert dimensions - width = azure_page.get("width", 8.5) - height = azure_page.get("height", 11) - unit = azure_page.get("unit", "inch") - dimensions = self._convert_dimensions(width=width, height=height, unit=unit) - - # Build OCR page - ocr_page = OCRPage(index=index, markdown=markdown, dimensions=dimensions) - mistral_pages.append(ocr_page) - - # Build usage info - usage_info = OCRUsageInfo(pages_processed=len(mistral_pages), doc_size_bytes=None) - - # Return Mistral OCR response - return OCRResponse( - pages=mistral_pages, - model=model, - usage_info=usage_info, - object="ocr", - ) - - except Exception as e: - verbose_logger.error(f"Error parsing Azure Document Intelligence response: {e}") - raise e + verbose_logger.debug("Azure DI returned 202 Accepted, polling operation...") + operation_url, poll_headers = self._get_polling_target(raw_response) + completed_response = self._poll_operation_sync( + operation_url=operation_url, + headers=poll_headers, + timeout_secs=AZURE_OPERATION_POLLING_TIMEOUT, + ) + return self._transform_completed_response(model=model, raw_response=completed_response) async def async_transform_ocr_response( self, @@ -680,81 +715,14 @@ class AzureDocumentIntelligenceOCRConfig(BaseOCRConfig): Returns: OCRResponse in Mistral format """ - try: - # Check if we got 202 Accepted (async operation started) - if raw_response.status_code == 202: - verbose_logger.debug("Azure DI returned 202 Accepted, polling operation (async)...") + if raw_response.status_code != 202: + return self._transform_completed_response(model=model, raw_response=raw_response) - # Get Operation-Location header - operation_url = raw_response.headers.get("Operation-Location") - if not operation_url: - raise ValueError("Azure Document Intelligence returned 202 but no Operation-Location header found") - - # Reject cross-origin polling URLs (see sync path). VERIA-51. - try: - assert_same_origin(operation_url, str(raw_response.request.url)) - except SSRFError as ssrf_err: - raise ValueError(f"Azure Document Intelligence: rejected polling URL ({ssrf_err})") - - # Get headers for polling (need auth) - poll_headers = { - "Ocp-Apim-Subscription-Key": raw_response.request.headers.get("Ocp-Apim-Subscription-Key", "") - } - - # Get timeout from kwargs or use default - timeout_secs = AZURE_OPERATION_POLLING_TIMEOUT - - # Poll until operation completes (async) - raw_response = await self._poll_operation_async( - operation_url=operation_url, - headers=poll_headers, - timeout_secs=timeout_secs, - ) - - # Now parse the completed response - response_json = raw_response.json() - - verbose_logger.debug(f"Azure Document Intelligence response status: {response_json.get('status')}") - - # Check if request succeeded - status = response_json.get("status") - if status != "succeeded": - raise ValueError(f"Azure Document Intelligence analysis failed with status: {status}") - - # Extract analyze result - analyze_result = response_json.get("analyzeResult", {}) - azure_pages = analyze_result.get("pages", []) - - # Transform pages to Mistral format - mistral_pages = [] - for azure_page in azure_pages: - page_number = azure_page.get("pageNumber", 1) - index = page_number - 1 # Convert to 0-based index - - # Extract markdown text - markdown = self._extract_page_markdown(azure_page) - - # Convert dimensions - width = azure_page.get("width", 8.5) - height = azure_page.get("height", 11) - unit = azure_page.get("unit", "inch") - dimensions = self._convert_dimensions(width=width, height=height, unit=unit) - - # Build OCR page - ocr_page = OCRPage(index=index, markdown=markdown, dimensions=dimensions) - mistral_pages.append(ocr_page) - - # Build usage info - usage_info = OCRUsageInfo(pages_processed=len(mistral_pages), doc_size_bytes=None) - - # Return Mistral OCR response - return OCRResponse( - pages=mistral_pages, - model=model, - usage_info=usage_info, - object="ocr", - ) - - except Exception as e: - verbose_logger.error(f"Error parsing Azure Document Intelligence response (async): {e}") - raise e + verbose_logger.debug("Azure DI returned 202 Accepted, polling operation (async)...") + operation_url, poll_headers = self._get_polling_target(raw_response) + completed_response = await self._poll_operation_async( + operation_url=operation_url, + headers=poll_headers, + timeout_secs=AZURE_OPERATION_POLLING_TIMEOUT, + ) + return self._transform_completed_response(model=model, raw_response=completed_response) diff --git a/litellm/llms/base_llm/guardrail_translation/base_translation.py b/litellm/llms/base_llm/guardrail_translation/base_translation.py index 68db36b529e..6c41b46cfa0 100644 --- a/litellm/llms/base_llm/guardrail_translation/base_translation.py +++ b/litellm/llms/base_llm/guardrail_translation/base_translation.py @@ -2,7 +2,10 @@ from abc import ABC, abstractmethod from typing import TYPE_CHECKING, Any, Dict, List, Optional if TYPE_CHECKING: - from litellm.integrations.custom_guardrail import CustomGuardrail + from litellm.integrations.custom_guardrail import ( + CustomGuardrail, + ModifyResponseException, + ) from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj from litellm.proxy._types import UserAPIKeyAuth from litellm.types.llms.openai import AllMessageValues @@ -98,6 +101,30 @@ class BaseTranslation(ABC): """ return responses_so_far + def build_block_sse_chunks( + self, + exc: "ModifyResponseException", + stream_started: bool = False, + responses_so_far: Optional[list[Any]] = None, + ) -> Optional[list[bytes]]: + """ + Build the streaming chunks that deliver a guardrail block message and + cleanly terminate the stream in this provider's wire format. + + ``stream_started`` is True when real chunks were already sent to the + client: the result must *continue* the in-progress message (e.g. close + the open content block and append the block message) rather than start + a new one, which clients reject. ``responses_so_far`` provides the prior + chunks needed to do so. When False, nothing has been sent and a + standalone block message is emitted. + + Returns None when the format has no safe terminator; the caller then + re-raises ``exc`` so the proxy can surface a clean error instead. + Override in provider subclasses that support synthesizing a block + stream. + """ + return None + def get_structured_messages(self, data: dict) -> Optional[List["AllMessageValues"]]: """ Convert request data to OpenAI-spec structured messages. diff --git a/litellm/llms/base_llm/guardrail_translation/utils.py b/litellm/llms/base_llm/guardrail_translation/utils.py index 97ece6b5eab..8a06dd4ea52 100644 --- a/litellm/llms/base_llm/guardrail_translation/utils.py +++ b/litellm/llms/base_llm/guardrail_translation/utils.py @@ -1,10 +1,100 @@ from __future__ import annotations -from typing import Any, List +import json +from typing import Any, List, Optional +from litellm.types.llms.anthropic_messages.anthropic_response import AnthropicUsage from litellm.types.llms.openai import AllMessageValues +def _anthropic_stream_chunk_events(item: Any) -> list[dict]: + if isinstance(item, dict): + return [item] + if isinstance(item, bytes): + chunk = item.decode("utf-8", errors="replace") + elif isinstance(item, str): + chunk = item + else: + return [] + + events: list[dict] = [] + for block in chunk.split("\n\n"): + for line in block.splitlines(): + stripped = line.strip() + if not stripped.startswith("data:"): + continue + payload = stripped[len("data:") :].strip() + if not payload or payload == "[DONE]": + continue + try: + parsed = json.loads(payload) + except json.JSONDecodeError: + continue + if isinstance(parsed, dict): + events.append(parsed) + return events + + +def _usage_from_anthropic_stream_chunks(original_response: list[Any]) -> Optional[AnthropicUsage]: + input_tokens = 0 + output_tokens = 0 + found_usage = False + + for item in original_response: + for event in _anthropic_stream_chunk_events(item): + event_type = event.get("type") + if event_type == "message_start": + message = event.get("message") or {} + usage_obj = message.get("usage") or {} + elif event_type == "message_delta": + usage_obj = event.get("usage") or {} + else: + usage_obj = {} + if not isinstance(usage_obj, dict): + continue + if usage_obj.get("input_tokens") is not None: + input_tokens = int(usage_obj.get("input_tokens") or 0) + found_usage = True + if usage_obj.get("output_tokens") is not None: + output_tokens = int(usage_obj.get("output_tokens") or 0) + found_usage = True + + if not found_usage: + return None + return AnthropicUsage(input_tokens=input_tokens, output_tokens=output_tokens) + + +def blocked_response_usage(original_response: Optional[Any]) -> AnthropicUsage: + """ + Token usage for a synthetic guardrail-blocked response. + + A post-call block replaces the LLM's response with the violation message, + but the upstream call already consumed tokens -- report that real usage + (carried on ``ModifyResponseException.original_response``) rather than + discarding it. Pre-call blocks never invoked the LLM (no original_response), + so usage is zero. + """ + usage_obj: Any = None + if isinstance(original_response, list): + stream_usage = _usage_from_anthropic_stream_chunks(original_response) + if stream_usage is not None: + return stream_usage + elif isinstance(original_response, dict): + usage_obj = original_response.get("usage") + elif original_response is not None: + usage_obj = getattr(original_response, "usage", None) + + def _tokens(key: str, fallback_key: str) -> int: + if isinstance(usage_obj, dict): + return int(usage_obj.get(key, usage_obj.get(fallback_key, 0)) or 0) + return int(getattr(usage_obj, key, getattr(usage_obj, fallback_key, 0)) or 0) + + return AnthropicUsage( + input_tokens=_tokens("input_tokens", "prompt_tokens"), + output_tokens=_tokens("output_tokens", "completion_tokens"), + ) + + def effective_skip_system_message_for_guardrail(guardrail_to_apply: Any) -> bool: per = getattr(guardrail_to_apply, "skip_system_message_in_guardrail", None) if per is not None: diff --git a/litellm/llms/base_llm/ocr/transformation.py b/litellm/llms/base_llm/ocr/transformation.py index a38e5bfdcd6..0d878bd308c 100644 --- a/litellm/llms/base_llm/ocr/transformation.py +++ b/litellm/llms/base_llm/ocr/transformation.py @@ -70,6 +70,9 @@ class OCRResponse(LiteLLMPydanticObjectBase): model: str document_annotation: Any | None = None usage_info: OCRUsageInfo | None = None + content: str | None = None + tables: list[dict[str, object]] | None = None + keyValuePairs: list[dict[str, object]] | None = None object: str = "ocr" model_config = {"extra": "allow"} diff --git a/litellm/llms/bedrock/chat/converse_transformation.py b/litellm/llms/bedrock/chat/converse_transformation.py index b135a116753..5a8ada45651 100644 --- a/litellm/llms/bedrock/chat/converse_transformation.py +++ b/litellm/llms/bedrock/chat/converse_transformation.py @@ -76,6 +76,7 @@ from litellm.utils import ( from ..common_utils import ( BedrockError, BedrockModelInfo, + bedrock_converse_supports_parallel_tool_use_config, get_anthropic_beta_from_headers, get_bedrock_tool_name, is_claude_4_5_on_bedrock, @@ -1106,18 +1107,28 @@ class AmazonConverseConfig(BaseConfig): if cache_control is None: return None - cache_point = CachePointBlock(type="default") - if isinstance(cache_control, dict) and "ttl" in cache_control: - ttl = cache_control["ttl"] - if ttl in ["5m", "1h"] and model is not None: - if is_claude_4_5_on_bedrock(model): - cache_point["ttl"] = ttl + cache_point = self._build_cache_point_block(cache_control, model) if block_type == "system": return SystemContentBlock(cachePoint=cache_point) else: return ContentBlock(cachePoint=cache_point) + @staticmethod + def _build_cache_point_block(control: Optional[dict], model: Optional[str] = None) -> CachePointBlock: + """Build a Bedrock ``cachePoint`` block from an OpenAI-style ``cache_control``/``control`` dict. + + ``type`` is always ``"default"`` (the only value Bedrock's Converse API + accepts). ``ttl`` is only honored for models that support extended TTL + caching (Claude 4.5 family on Bedrock). + """ + cache_point = CachePointBlock(type="default") + if isinstance(control, dict) and "ttl" in control: + ttl = control["ttl"] + if ttl in ["5m", "1h"] and model is not None and is_claude_4_5_on_bedrock(model): + cache_point["ttl"] = ttl + return cache_point + def _transform_system_message( self, messages: List[AllMessageValues], model: Optional[str] = None ) -> Tuple[List[AllMessageValues], List[SystemContentBlock]]: @@ -1241,7 +1252,7 @@ class AmazonConverseConfig(BaseConfig): # Handle parallel_tool_calls configuration parallel_tool_use_config = additional_request_params.pop("_parallel_tool_use_config", None) - if parallel_tool_use_config is not None and is_claude_4_5_on_bedrock(model): + if parallel_tool_use_config is not None and bedrock_converse_supports_parallel_tool_use_config(model): for key, value in parallel_tool_use_config.items(): if ( key in additional_request_params @@ -1526,7 +1537,8 @@ class AmazonConverseConfig(BaseConfig): if cache_injection_points and len(bedrock_tools) > 0: for point in cache_injection_points: if point.get("location") == "tool_config": - bedrock_tools.append({"cachePoint": {"type": "default"}}) + cache_point = self._build_cache_point_block(point.get("control"), model) + bedrock_tools.append(ToolBlock(cachePoint=cache_point)) break bedrock_tool_config: Optional[ToolConfigBlock] = None diff --git a/litellm/llms/bedrock/chat/invoke_transformations/base_invoke_transformation.py b/litellm/llms/bedrock/chat/invoke_transformations/base_invoke_transformation.py index bbe16e26713..dd7cf12604d 100644 --- a/litellm/llms/bedrock/chat/invoke_transformations/base_invoke_transformation.py +++ b/litellm/llms/bedrock/chat/invoke_transformations/base_invoke_transformation.py @@ -5,6 +5,7 @@ from functools import partial from typing import TYPE_CHECKING, Any, List, Optional, Tuple, Union, cast, get_args import httpx +from pydantic import TypeAdapter, ValidationError import litellm from litellm._logging import verbose_logger @@ -24,6 +25,7 @@ from litellm.llms.custom_httpx.http_handler import ( HTTPHandler, _get_httpx_client, ) +from litellm.types.llms.bedrock import GuardrailConfigBlock from litellm.types.llms.openai import AllMessageValues from litellm.types.utils import ModelResponse, Usage from litellm.utils import CustomStreamWrapper @@ -37,6 +39,38 @@ else: from litellm.llms.bedrock.base_aws_llm import BaseAWSLLM +_GUARDRAIL_CONFIG_VALIDATOR: "TypeAdapter[GuardrailConfigBlock]" = TypeAdapter(GuardrailConfigBlock) + +_GUARDRAIL_CONFIG_EXPECTED_FORMAT = ( + "{'guardrailIdentifier': str, 'guardrailVersion': str, 'trace': 'enabled'|'disabled'|'enabled_full'}" +) + + +def _bedrock_invoke_guardrail_headers(raw_guardrail_config: object) -> "dict[str, str]": + try: + guardrail_config = _GUARDRAIL_CONFIG_VALIDATOR.validate_python(raw_guardrail_config) + except ValidationError as e: + raise BedrockError( + status_code=400, + message="Invalid guardrailConfig={}. Expected format: {}. Error: {}".format( + raw_guardrail_config, _GUARDRAIL_CONFIG_EXPECTED_FORMAT, e + ), + ) + if "guardrailIdentifier" not in guardrail_config: + raise BedrockError( + status_code=400, + message="guardrailConfig={} is missing 'guardrailIdentifier'. Expected format: {}".format( + raw_guardrail_config, _GUARDRAIL_CONFIG_EXPECTED_FORMAT + ), + ) + trace = guardrail_config.get("trace") + candidate_headers = { + "X-Amzn-Bedrock-GuardrailIdentifier": guardrail_config.get("guardrailIdentifier"), + "X-Amzn-Bedrock-GuardrailVersion": guardrail_config.get("guardrailVersion"), + "X-Amzn-Bedrock-Trace": trace.upper() if trace is not None else None, + } + return {name: value for name, value in candidate_headers.items() if value is not None} + class AmazonInvokeConfig(BaseConfig, BaseAWSLLM): def __init__(self, **kwargs): @@ -390,7 +424,16 @@ class AmazonInvokeConfig(BaseConfig, BaseAWSLLM): api_key: Optional[str] = None, api_base: Optional[str] = None, ) -> dict: - return headers + raw_guardrail_config = optional_params.pop("guardrailConfig", None) + if raw_guardrail_config is None: + return headers + existing_header_names = frozenset(name.lower() for name in headers) + guardrail_headers = { + name: value + for name, value in _bedrock_invoke_guardrail_headers(raw_guardrail_config).items() + if name.lower() not in existing_header_names + } + return {**headers, **guardrail_headers} def get_error_class( self, error_message: str, status_code: int, headers: Union[dict, httpx.Headers] diff --git a/litellm/llms/bedrock/common_utils.py b/litellm/llms/bedrock/common_utils.py index df432a4d7e3..5114677ffc0 100644 --- a/litellm/llms/bedrock/common_utils.py +++ b/litellm/llms/bedrock/common_utils.py @@ -685,39 +685,27 @@ def get_bedrock_base_model(model: str) -> str: return model +def bedrock_converse_supports_parallel_tool_use_config(model: str) -> bool: + return any( + (litellm.model_cost.get(candidate) or {}).get("supports_parallel_tool_use_config") is True + for candidate in (model, get_bedrock_base_model(model)) + ) + + def is_claude_4_5_on_bedrock(model: str) -> bool: """ - Check if the model is a Claude 4.5 model on Bedrock. - Claude 4.5 models support prompt caching with '5m' and '1h' TTL on Bedrock. + Check if the model supports Bedrock prompt caching with an extended '1h' TTL + (in addition to the default 5m TTL). + + Backed by the ``cache_creation_input_token_cost_above_1hr`` field in + ``model_prices_and_context_window.json`` instead of a hardcoded list of + model-name patterns, so newly released models pick up support as soon as + their pricing entry ships, with no code change required here. """ - model_lower = model.lower() - claude_4_5_patterns = [ - "sonnet-4.5", - "sonnet_4.5", - "sonnet-4-5", - "sonnet_4_5", - "haiku-4.5", - "haiku_4.5", - "haiku-4-5", - "haiku_4_5", - "opus-4.5", - "opus_4.5", - "opus-4-5", - "opus_4_5", - "sonnet-4.6", - "sonnet_4.6", - "sonnet-4-6", - "sonnet_4_6", - "opus-4.6", - "opus_4.6", - "opus-4-6", - "opus_4_6", - "opus-4.7", - "opus_4.7", - "opus-4-7", - "opus_4_7", - ] - return any(pattern in model_lower for pattern in claude_4_5_patterns) + return any( + (litellm.model_cost.get(candidate) or {}).get("cache_creation_input_token_cost_above_1hr") is not None + for candidate in (model, get_bedrock_base_model(model)) + ) _BEDROCK_MODEL_VERSION_SUFFIX_RE = re.compile(r"-v\d+(?::\d+)?$") diff --git a/litellm/llms/openai/responses/guardrail_translation/handler.py b/litellm/llms/openai/responses/guardrail_translation/handler.py index 6ac33ffa44a..d1323b1a2bf 100644 --- a/litellm/llms/openai/responses/guardrail_translation/handler.py +++ b/litellm/llms/openai/responses/guardrail_translation/handler.py @@ -45,6 +45,7 @@ from litellm.types.llms.openai import ( AllMessageValues, ChatCompletionToolCallChunk, ChatCompletionToolParam, + ResponsesAPIStreamEvents, ) from litellm.types.responses.main import ( GenericResponseOutputItem, @@ -586,7 +587,14 @@ class OpenAIResponsesHandler(BaseTranslation): """ Check if the streaming has ended. """ - return all(response.choices[0].finish_reason is not None for response in responses_so_far) + if not responses_so_far: + return False + terminal_types = { + ResponsesAPIStreamEvents.RESPONSE_COMPLETED.value, + ResponsesAPIStreamEvents.RESPONSE_FAILED.value, + ResponsesAPIStreamEvents.RESPONSE_INCOMPLETE.value, + } + return responses_so_far[-1].get("type") in terminal_types def get_streaming_string_so_far(self, responses_so_far: List[Any]) -> str: """ diff --git a/litellm/llms/tencent/__init__.py b/litellm/llms/tencent/__init__.py new file mode 100644 index 00000000000..e69de29bb2d diff --git a/litellm/llms/tencent/chat/__init__.py b/litellm/llms/tencent/chat/__init__.py new file mode 100644 index 00000000000..e69de29bb2d diff --git a/litellm/llms/tencent/chat/transformation.py b/litellm/llms/tencent/chat/transformation.py new file mode 100644 index 00000000000..4dea0c4b8c7 --- /dev/null +++ b/litellm/llms/tencent/chat/transformation.py @@ -0,0 +1,68 @@ +""" +Translates from OpenAI's `/v1/chat/completions` to Tencent TokenHub's +OpenAI-compatible endpoint. +""" + +from typing import Optional + +from litellm.secret_managers.main import get_secret_str +from litellm.utils import supports_reasoning + +from ...openai.chat.gpt_transformation import OpenAIGPTConfig + + +class TencentChatConfig(OpenAIGPTConfig): + def get_supported_openai_params(self, model: str) -> list: + params = super().get_supported_openai_params(model) + if supports_reasoning(model, custom_llm_provider="tencent"): + params.extend(["thinking", "reasoning_effort"]) + return params + + def map_openai_params( + self, + non_default_params: dict, + optional_params: dict, + model: str, + drop_params: bool, + ) -> dict: + optional_params = super().map_openai_params(non_default_params, optional_params, model, drop_params) + + thinking_value = optional_params.pop("thinking", None) + reasoning_effort = optional_params.pop("reasoning_effort", None) + + if thinking_value is not None: + if isinstance(thinking_value, dict): + optional_params["thinking"] = thinking_value + elif reasoning_effort is not None and reasoning_effort != "none": + optional_params["thinking"] = {"type": "enabled"} + + return optional_params + + def _get_openai_compatible_provider_info( + self, api_base: Optional[str], api_key: Optional[str] + ) -> tuple[Optional[str], Optional[str]]: + api_base = api_base or get_secret_str("TENCENT_API_BASE") or "https://tokenhub-intl.tencentcloudmaas.com/v1" + dynamic_api_key = api_key or get_secret_str("TENCENT_API_KEY") + return api_base, dynamic_api_key + + def get_complete_url( + self, + api_base: Optional[str], + api_key: Optional[str], + model: str, + optional_params: dict, + litellm_params: dict, + stream: Optional[bool] = None, + ) -> str: + if not api_base: + api_base = "https://tokenhub-intl.tencentcloudmaas.com/v1" + + api_base = api_base.rstrip("/") + + if api_base.endswith("/chat/completions"): + return api_base + + if not api_base.endswith("/v1"): + api_base = f"{api_base}/v1" + + return f"{api_base}/chat/completions" diff --git a/litellm/llms/tencent/cost_calculator.py b/litellm/llms/tencent/cost_calculator.py new file mode 100644 index 00000000000..d9aebdc3284 --- /dev/null +++ b/litellm/llms/tencent/cost_calculator.py @@ -0,0 +1,6 @@ +from litellm.litellm_core_utils.llm_cost_calc.utils import generic_cost_per_token +from litellm.types.utils import Usage + + +def cost_per_token(model: str, usage: Usage) -> tuple[float, float]: + return generic_cost_per_token(model=model, usage=usage, custom_llm_provider="tencent") diff --git a/litellm/llms/tencent/messages/__init__.py b/litellm/llms/tencent/messages/__init__.py new file mode 100644 index 00000000000..e69de29bb2d diff --git a/litellm/llms/tencent/messages/transformation.py b/litellm/llms/tencent/messages/transformation.py new file mode 100644 index 00000000000..e0f13aa9ca4 --- /dev/null +++ b/litellm/llms/tencent/messages/transformation.py @@ -0,0 +1,85 @@ +""" +Tencent Anthropic-compatible messages transformation config. + +Tencent TokenHub exposes an Anthropic-compatible Messages API endpoint +alongside its standard OpenAI-compatible chat completions endpoint. +""" + +from typing import Any, Optional + +import litellm +from litellm.llms.anthropic.experimental_pass_through.messages.transformation import ( + AnthropicMessagesConfig, +) +from litellm.secret_managers.main import get_secret_str + + +class TencentAnthropicMessagesConfig(AnthropicMessagesConfig): + """ + Tencent TokenHub exposes an Anthropic-compatible Messages API. + + Unlike the chat completions endpoint (which uses /v1), the Anthropic + endpoint may use a different base URL. Configure via + TENCENT_ANTHROPIC_API_BASE or TENCENT_API_BASE. + """ + + @property + def custom_llm_provider(self) -> Optional[str]: + return "tencent" + + def should_strip_billing_metadata(self) -> bool: + return True + + @staticmethod + def get_api_key(api_key: Optional[str] = None) -> Optional[str]: + return api_key or get_secret_str("TENCENT_API_KEY") or litellm.api_key + + @staticmethod + def get_api_base(api_base: Optional[str] = None) -> str: + return ( + api_base + or get_secret_str("TENCENT_ANTHROPIC_API_BASE") + or get_secret_str("TENCENT_API_BASE") + or "https://tokenhub-intl.tencentcloudmaas.com" + ) + + def validate_anthropic_messages_environment( + self, + headers: dict, + model: str, + messages: list[Any], + optional_params: dict, + litellm_params: dict, + api_key: Optional[str] = None, + api_base: Optional[str] = None, + ) -> tuple[dict, Optional[str]]: + return super().validate_anthropic_messages_environment( + headers=headers, + model=model, + messages=messages, + optional_params=optional_params, + litellm_params=litellm_params, + api_key=self.get_api_key(api_key=api_key), + api_base=api_base, + ) + + def get_complete_url( + self, + api_base: Optional[str], + api_key: Optional[str], + model: str, + optional_params: dict, + litellm_params: dict, + stream: Optional[bool] = None, + ) -> str: + base_url = self.get_api_base(api_base=api_base).rstrip("/") + + if base_url.endswith("/v1/messages"): + return base_url + + if base_url.endswith("/v1/chat/completions"): + base_url = base_url[: -len("/v1/chat/completions")] + elif base_url.endswith("/v1"): + base_url = base_url[: -len("/v1")] + + return f"{base_url}/v1/messages" diff --git a/litellm/llms/vertex_ai/image_generation/vertex_gemini_transformation.py b/litellm/llms/vertex_ai/image_generation/vertex_gemini_transformation.py index 4bca3e8f71d..572725ac789 100644 --- a/litellm/llms/vertex_ai/image_generation/vertex_gemini_transformation.py +++ b/litellm/llms/vertex_ai/image_generation/vertex_gemini_transformation.py @@ -1,5 +1,5 @@ import os -from typing import TYPE_CHECKING, Any, Dict, List, Optional +from typing import TYPE_CHECKING, Any, Optional from litellm._logging import verbose_logger @@ -175,7 +175,7 @@ class VertexAIGeminiImageGenerationConfig(BaseImageGenerationConfig, VertexLLM): self, headers: dict, model: str, - messages: List[AllMessageValues], + messages: list[AllMessageValues], optional_params: dict, litellm_params: dict, api_key: Optional[str] = None, @@ -217,10 +217,10 @@ class VertexAIGeminiImageGenerationConfig(BaseImageGenerationConfig, VertexLLM): contents = [{"role": "user", "parts": [{"text": prompt}]}] # Prepare generation config - generation_config: Dict[str, Any] = {"responseModalities": ["IMAGE"]} + generation_config: dict[str, Any] = {"responseModalities": ["IMAGE"]} # Seed from user-supplied imageConfig dict; flat params are overlaid for backward compat. - image_config: Dict[str, Any] = dict(optional_params.get("imageConfig") or {}) + image_config: dict[str, Any] = dict(optional_params.get("imageConfig") or {}) if "aspectRatio" in optional_params: image_config["aspectRatio"] = optional_params["aspectRatio"] @@ -241,7 +241,7 @@ class VertexAIGeminiImageGenerationConfig(BaseImageGenerationConfig, VertexLLM): elif "n" in optional_params: generation_config["candidateCount"] = optional_params["n"] - request_body: Dict[str, Any] = { + request_body: dict[str, Any] = { "contents": contents, "generationConfig": generation_config, } diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index bf63ef73c22..26d54c05ffb 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -744,7 +744,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "anthropic.claude-haiku-4-5@20251001": { "cache_creation_input_token_cost": 1.25e-06, @@ -768,7 +769,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_native_streaming": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "anthropic.claude-3-5-sonnet-20240620-v1:0": { "input_cost_per_token": 3e-06, @@ -787,8 +789,6 @@ "output_cost_per_token_above_200k_tokens": 3e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, - "cache_creation_input_token_cost_above_1hr": 7.5e-06, - "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.5e-05, "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07 }, @@ -813,9 +813,7 @@ "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 3e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, - "cache_creation_input_token_cost_above_1hr": 7.5e-06, - "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.5e-05 + "cache_read_input_token_cost_above_200k_tokens": 6e-07 }, "anthropic.claude-3-7-sonnet-20240620-v1:0": { "cache_creation_input_token_cost": 4.5e-06, @@ -991,7 +989,8 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "high" + "bedrock_output_config_effort_ceiling": "high", + "supports_parallel_tool_use_config": true }, "anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, @@ -1010,7 +1009,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -1023,7 +1021,8 @@ "supports_native_structured_output": true, "supports_output_config": true, "supports_max_reasoning_effort": true, - "bedrock_output_config_effort_ceiling": "max" + "bedrock_output_config_effort_ceiling": "max", + "supports_parallel_tool_use_config": true }, "global.anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, @@ -1042,7 +1041,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -1055,7 +1053,8 @@ "supports_native_structured_output": true, "supports_output_config": true, "supports_max_reasoning_effort": true, - "bedrock_output_config_effort_ceiling": "max" + "bedrock_output_config_effort_ceiling": "max", + "supports_parallel_tool_use_config": true }, "us.anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, @@ -1074,7 +1073,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -1087,7 +1085,8 @@ "supports_native_structured_output": true, "supports_output_config": true, "supports_max_reasoning_effort": true, - "bedrock_output_config_effort_ceiling": "max" + "bedrock_output_config_effort_ceiling": "max", + "supports_parallel_tool_use_config": true }, "eu.anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, @@ -1106,7 +1105,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -1119,7 +1117,8 @@ "supports_native_structured_output": true, "supports_output_config": true, "supports_max_reasoning_effort": true, - "bedrock_output_config_effort_ceiling": "max" + "bedrock_output_config_effort_ceiling": "max", + "supports_parallel_tool_use_config": true }, "au.anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, @@ -1138,7 +1137,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -1151,7 +1149,8 @@ "supports_native_structured_output": true, "supports_output_config": true, "supports_max_reasoning_effort": true, - "bedrock_output_config_effort_ceiling": "max" + "bedrock_output_config_effort_ceiling": "max", + "supports_parallel_tool_use_config": true }, "anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -1171,7 +1170,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -1186,7 +1184,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "anthropic.claude-mythos-preview": { "input_cost_per_token": 0, @@ -1221,7 +1220,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -1236,7 +1234,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "us.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -1256,7 +1255,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -1271,7 +1269,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "eu.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -1291,7 +1290,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -1306,7 +1304,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "au.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -1326,7 +1325,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -1341,7 +1339,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "anthropic.claude-fable-5": { "cache_creation_input_token_cost": 1.25e-05, @@ -1374,7 +1373,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "global.anthropic.claude-fable-5": { "cache_creation_input_token_cost": 1.25e-05, @@ -1407,7 +1407,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "us.anthropic.claude-fable-5": { "cache_creation_input_token_cost": 1.375e-05, @@ -1440,7 +1441,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "eu.anthropic.claude-fable-5": { "cache_creation_input_token_cost": 1.375e-05, @@ -1473,7 +1475,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -1493,7 +1496,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -1508,7 +1510,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "global.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -1528,7 +1531,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -1543,7 +1545,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "us.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -1563,7 +1566,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -1578,7 +1580,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "eu.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -1598,7 +1601,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -1613,7 +1615,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "au.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -1633,7 +1636,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -1648,7 +1650,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "jp.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -1680,7 +1683,8 @@ "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "supports_parallel_tool_use_config": true }, "anthropic.claude-sonnet-5": { "cache_creation_input_token_cost": 2.5e-06, @@ -1713,7 +1717,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "global.anthropic.claude-sonnet-5": { "cache_creation_input_token_cost": 2.5e-06, @@ -1746,7 +1751,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "us.anthropic.claude-sonnet-5": { "cache_creation_input_token_cost": 2.75e-06, @@ -1779,7 +1785,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "eu.anthropic.claude-sonnet-5": { "cache_creation_input_token_cost": 2.75e-06, @@ -1812,7 +1819,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "au.anthropic.claude-sonnet-5": { "cache_creation_input_token_cost": 2.75e-06, @@ -1845,7 +1853,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "jp.anthropic.claude-sonnet-5": { "cache_creation_input_token_cost": 2.75e-06, @@ -1878,7 +1887,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -1897,7 +1907,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -1909,7 +1918,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, - "supports_output_config": true + "supports_output_config": true, + "supports_parallel_tool_use_config": true }, "global.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -1928,7 +1938,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -1940,7 +1949,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, - "supports_output_config": true + "supports_output_config": true, + "supports_parallel_tool_use_config": true }, "us.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -1959,7 +1969,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -1971,7 +1980,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, - "supports_output_config": true + "supports_output_config": true, + "supports_parallel_tool_use_config": true }, "eu.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -1990,7 +2000,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -2002,7 +2011,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, - "supports_output_config": true + "supports_output_config": true, + "supports_parallel_tool_use_config": true }, "au.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -2021,7 +2031,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -2033,7 +2042,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, - "supports_output_config": true + "supports_output_config": true, + "supports_parallel_tool_use_config": true }, "jp.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -2052,7 +2062,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -2064,7 +2073,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, - "supports_output_config": true + "supports_output_config": true, + "supports_parallel_tool_use_config": true }, "anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, @@ -2126,7 +2136,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "anthropic.claude-v1": { "input_cost_per_token": 8e-06, @@ -2376,7 +2387,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "apac.anthropic.claude-3-sonnet-20240229-v1:0": { "input_cost_per_token": 3e-06, @@ -2466,7 +2478,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "azure/ada": { "input_cost_per_token": 1e-07, @@ -2575,7 +2588,6 @@ "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_read_input_token_cost": 5e-07, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -2605,7 +2617,6 @@ "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_read_input_token_cost": 5e-07, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -2666,7 +2677,6 @@ "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_read_input_token_cost": 5e-07, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -2764,7 +2774,6 @@ "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, - "supports_adaptive_thinking": true, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -9373,17 +9382,16 @@ }, "bedrock/us-east-1/minimax.minimax-m2.5": { "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, - "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, - "output_cost_per_token": 1.2e-06 + "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/us-east-1/moonshotai.kimi-k2-thinking": { "input_cost_per_token": 6e-07, @@ -9612,7 +9620,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "bedrock/us-gov-east-1/claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.5e-06, @@ -9634,7 +9643,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "bedrock/us-gov-east-1/meta.llama3-70b-instruct-v1:0": { "input_cost_per_token": 2.65e-06, @@ -9787,7 +9797,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "bedrock/us-gov-west-1/claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.5e-06, @@ -9809,7 +9820,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "bedrock/us-gov-west-1/meta.llama3-70b-instruct-v1:0": { "input_cost_per_token": 2.65e-06, @@ -9995,17 +10007,16 @@ }, "bedrock/us-west-2/minimax.minimax-m2.5": { "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, - "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, - "output_cost_per_token": 1.2e-06 + "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/us-west-2/moonshotai.kimi-k2-thinking": { "input_cost_per_token": 6e-07, @@ -10573,7 +10584,8 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_parallel_tool_use_config": true }, "claude-opus-4-1": { "cache_creation_input_token_cost": 1.875e-05, @@ -14645,7 +14657,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "eu.anthropic.claude-3-5-sonnet-20240620-v1:0": { "input_cost_per_token": 3e-06, @@ -14859,7 +14872,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "eu.meta.llama3-2-1b-instruct-v1:0": { "input_cost_per_token": 1.3e-07, @@ -19222,7 +19236,6 @@ "supported_endpoints": [ "/v1/chat/completions" ], - "supports_adaptive_thinking": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true @@ -20059,7 +20072,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "global.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, @@ -20112,7 +20126,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "global.amazon.nova-2-lite-v1:0": { "cache_read_input_token_cost": 7.5e-08, @@ -21976,8 +21991,8 @@ "output_cost_per_token_flex": 1.5e-05, "output_cost_per_token_batches": 1.5e-05, "output_cost_per_token_priority": 6e-05, - "regional_processing_uplift_multiplier_eu": 1.10, - "regional_processing_uplift_multiplier_us": 1.10, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -22025,8 +22040,8 @@ "output_cost_per_token_flex": 1.5e-05, "output_cost_per_token_batches": 1.5e-05, "output_cost_per_token_priority": 6e-05, - "regional_processing_uplift_multiplier_eu": 1.10, - "regional_processing_uplift_multiplier_us": 1.10, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -22070,8 +22085,8 @@ "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 9e-05, "output_cost_per_token_batches": 9e-05, - "regional_processing_uplift_multiplier_eu": 1.10, - "regional_processing_uplift_multiplier_us": 1.10, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/responses", "/v1/batch" @@ -22115,8 +22130,8 @@ "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 9e-05, "output_cost_per_token_batches": 9e-05, - "regional_processing_uplift_multiplier_eu": 1.10, - "regional_processing_uplift_multiplier_us": 1.10, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/responses", "/v1/batch" @@ -22164,8 +22179,8 @@ "output_cost_per_token_flex": 7.5e-06, "output_cost_per_token_batches": 7.5e-06, "output_cost_per_token_priority": 3e-05, - "regional_processing_uplift_multiplier_eu": 1.10, - "regional_processing_uplift_multiplier_us": 1.10, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -22212,8 +22227,8 @@ "output_cost_per_token_flex": 7.5e-06, "output_cost_per_token_batches": 7.5e-06, "output_cost_per_token_priority": 3e-05, - "regional_processing_uplift_multiplier_eu": 1.10, - "regional_processing_uplift_multiplier_us": 1.10, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -22253,8 +22268,8 @@ "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 9e-05, "output_cost_per_token_batches": 9e-05, - "regional_processing_uplift_multiplier_eu": 1.10, - "regional_processing_uplift_multiplier_us": 1.10, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/responses", "/v1/batch" @@ -22297,8 +22312,8 @@ "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 9e-05, "output_cost_per_token_batches": 9e-05, - "regional_processing_uplift_multiplier_eu": 1.10, - "regional_processing_uplift_multiplier_us": 1.10, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/responses", "/v1/batch" @@ -22342,8 +22357,8 @@ "output_cost_per_token_flex": 2.25e-06, "output_cost_per_token_batches": 2.25e-06, "output_cost_per_token_priority": 9e-06, - "regional_processing_uplift_multiplier_eu": 1.10, - "regional_processing_uplift_multiplier_us": 1.10, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -22388,8 +22403,8 @@ "output_cost_per_token_flex": 2.25e-06, "output_cost_per_token_batches": 2.25e-06, "output_cost_per_token_priority": 9e-06, - "regional_processing_uplift_multiplier_eu": 1.10, - "regional_processing_uplift_multiplier_us": 1.10, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -22431,8 +22446,8 @@ "output_cost_per_token": 1.25e-06, "output_cost_per_token_flex": 6.25e-07, "output_cost_per_token_batches": 6.25e-07, - "regional_processing_uplift_multiplier_eu": 1.10, - "regional_processing_uplift_multiplier_us": 1.10, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -22474,8 +22489,8 @@ "output_cost_per_token": 1.25e-06, "output_cost_per_token_flex": 6.25e-07, "output_cost_per_token_batches": 6.25e-07, - "regional_processing_uplift_multiplier_eu": 1.10, - "regional_processing_uplift_multiplier_us": 1.10, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -24181,7 +24196,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "jp.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.375e-06, @@ -24204,7 +24220,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "crusoe/deepseek-ai/DeepSeek-R1-0528": { "input_cost_per_token": 3e-06, @@ -24992,14 +25009,13 @@ }, "minimax.minimax-m2.5": { "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1.2e-06, "supports_function_calling": true, - "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/" @@ -28455,7 +28471,6 @@ "output_cost_per_token": 1.5e-05, "output_cost_per_token_above_200k_tokens": 2.25e-05, "source": "https://openrouter.ai/anthropic/claude-sonnet-4.6", - "supports_adaptive_thinking": true, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -28495,7 +28510,6 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, - "supports_adaptive_thinking": true, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -28557,7 +28571,6 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -30480,7 +30493,6 @@ "supports_adaptive_thinking": true, "litellm_provider": "perplexity", "mode": "responses", - "supports_adaptive_thinking": true, "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true, @@ -30490,7 +30502,6 @@ "supports_adaptive_thinking": true, "litellm_provider": "perplexity", "mode": "responses", - "supports_adaptive_thinking": true, "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true, @@ -31406,7 +31417,7 @@ "supports_tool_choice": true }, "sambanova/Meta-Llama-3.2-1B-Instruct": { - "deprecation_date": "2025-06-25", + "deprecation_date": "2025-06-25", "input_cost_per_token": 4e-08, "litellm_provider": "sambanova", "max_input_tokens": 16384, @@ -31537,15 +31548,15 @@ "supports_vision": true, "source": "https://cloud.sambanova.ai/plans/pricing" }, - "snowflake/claude-3-5-sonnet": { + "snowflake/claude-3-5-sonnet": { "litellm_provider": "snowflake", "max_input_tokens": 200000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "input_cost_per_token": 0.000003, - "output_cost_per_token": 0.000015, - "cache_read_input_token_cost": 0.0000003, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "cache_read_input_token_cost": 3e-07, "supports_computer_use": true, "supports_function_calling": true, "supports_vision": true, @@ -31553,14 +31564,14 @@ "supports_system_messages": true, "supports_response_schema": true }, - "snowflake/deepseek-r1": { + "snowflake/deepseek-r1": { "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "input_cost_per_token": 0.00000135, - "output_cost_per_token": 0.0000054, + "input_cost_per_token": 1.35e-06, + "output_cost_per_token": 5.4e-06, "supports_reasoning": true, "supports_system_messages": true }, @@ -31619,8 +31630,8 @@ "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "input_cost_per_token": 0.0000012, - "output_cost_per_token": 0.0000012, + "input_cost_per_token": 1.2e-06, + "output_cost_per_token": 1.2e-06, "supports_function_calling": true, "supports_system_messages": true }, @@ -31630,8 +31641,8 @@ "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "input_cost_per_token": 0.00000072, - "output_cost_per_token": 0.00000072, + "input_cost_per_token": 7.2e-07, + "output_cost_per_token": 7.2e-07, "supports_function_calling": true, "supports_system_messages": true }, @@ -31641,8 +31652,8 @@ "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "input_cost_per_token": 0.00000024, - "output_cost_per_token": 0.00000024, + "input_cost_per_token": 2.4e-07, + "output_cost_per_token": 2.4e-07, "supports_system_messages": true }, "snowflake/llama3.2-1b": { @@ -31659,17 +31670,17 @@ "max_tokens": 8192, "mode": "chat" }, - "snowflake/llama3.3-70b": { + "snowflake/llama3.3-70b": { "max_tokens": 16384, "max_input_tokens": 128000, "max_output_tokens": 16384, - "input_cost_per_token": 0.00000072, - "output_cost_per_token": 0.00000072, + "input_cost_per_token": 7.2e-07, + "output_cost_per_token": 7.2e-07, "litellm_provider": "snowflake", "mode": "chat", "supports_function_calling": true, "supports_system_messages": true - }, + }, "snowflake/mistral-7b": { "litellm_provider": "snowflake", "max_input_tokens": 32000, @@ -31684,14 +31695,14 @@ "max_tokens": 8192, "mode": "chat" }, - "snowflake/mistral-large2": { + "snowflake/mistral-large2": { "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "input_cost_per_token": 0.000002, - "output_cost_per_token": 0.000006, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_response_schema": true @@ -31731,17 +31742,17 @@ "max_tokens": 8192, "mode": "chat" }, - "snowflake/snowflake-llama-3.3-70b": { + "snowflake/snowflake-llama-3.3-70b": { "max_tokens": 16384, "max_input_tokens": 128000, "max_output_tokens": 16384, - "input_cost_per_token": 0.00000072, - "output_cost_per_token": 0.00000072, + "input_cost_per_token": 7.2e-07, + "output_cost_per_token": 7.2e-07, "litellm_provider": "snowflake", "mode": "chat", "supports_function_calling": true, "supports_system_messages": true - }, + }, "stability/sd3": { "litellm_provider": "stability", "mode": "image_generation", @@ -32825,7 +32836,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "us.anthropic.claude-3-5-sonnet-20240620-v1:0": { "input_cost_per_token": 3e-06, @@ -32984,7 +32996,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.5e-06, @@ -32993,7 +33006,7 @@ "input_cost_per_token": 3.6e-06, "input_cost_per_token_above_200k_tokens": 7.2e-06, "output_cost_per_token_above_200k_tokens": 2.7e-05, - "cache_creation_input_token_cost_above_200k_tokens": 9.0e-06, + "cache_creation_input_token_cost_above_200k_tokens": 9e-06, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.44e-05, "cache_read_input_token_cost_above_200k_tokens": 7.2e-07, "litellm_provider": "bedrock_converse", @@ -33011,7 +33024,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "au.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.375e-06, @@ -33033,7 +33047,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "us.anthropic.claude-opus-4-20250514-v1:0": { "cache_creation_input_token_cost": 1.875e-05, @@ -33087,7 +33102,8 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "high" + "bedrock_output_config_effort_ceiling": "high", + "supports_parallel_tool_use_config": true }, "global.anthropic.claude-opus-4-5-20251101-v1:0": { "cache_creation_input_token_cost": 6.25e-06, @@ -33116,7 +33132,8 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "high" + "bedrock_output_config_effort_ceiling": "high", + "supports_parallel_tool_use_config": true }, "eu.anthropic.claude-opus-4-5-20251101-v1:0": { "cache_creation_input_token_cost": 6.25e-06, @@ -33144,7 +33161,8 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "high" + "bedrock_output_config_effort_ceiling": "high", + "supports_parallel_tool_use_config": true }, "us.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, @@ -33736,7 +33754,6 @@ "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, - "supports_adaptive_thinking": true, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -34971,7 +34988,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -35001,7 +35017,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -35031,7 +35046,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -35062,7 +35076,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -35153,7 +35166,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -35184,7 +35196,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -35267,7 +35278,6 @@ "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, - "supports_adaptive_thinking": true, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -37796,12 +37806,12 @@ }, "zai.glm-5": { "input_cost_per_token": 1e-06, + "output_cost_per_token": 3.2e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3.2e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -37822,20 +37832,6 @@ "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/" }, - "zai.glm-5": { - "input_cost_per_token": 1e-06, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 200000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 3.2e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "zai/glm-5": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 2e-07, @@ -42734,7 +42730,6 @@ "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, - "supports_adaptive_thinking": true, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -42768,7 +42763,10 @@ "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "supported_endpoints": ["/v1/chat/completions", "/v1/responses"], + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, @@ -42783,7 +42781,10 @@ "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "supported_endpoints": ["/v1/chat/completions", "/v1/responses"], + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, @@ -42798,7 +42799,9 @@ "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "supported_endpoints": ["/v1/chat/completions"], + "supported_endpoints": [ + "/v1/chat/completions" + ], "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -42812,7 +42815,9 @@ "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "supported_endpoints": ["/v1/chat/completions"], + "supported_endpoints": [ + "/v1/chat/completions" + ], "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -42828,9 +42833,16 @@ "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, - "supported_endpoints": ["/v1/responses"], - "supported_modalities": ["text", "image"], - "supported_output_modalities": ["text"], + "supported_endpoints": [ + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -42848,9 +42860,16 @@ "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, - "supported_endpoints": ["/v1/responses"], - "supported_modalities": ["text", "image"], - "supported_output_modalities": ["text"], + "supported_endpoints": [ + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -42867,7 +42886,10 @@ "max_tokens": 256000, "mode": "chat", "use_openai_responses_path": true, - "supported_endpoints": ["/v1/chat/completions", "/v1/responses"], + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_reasoning": true, @@ -42883,7 +42905,10 @@ "max_tokens": 256000, "mode": "chat", "use_openai_responses_path": true, - "supported_endpoints": ["/v1/chat/completions", "/v1/responses"], + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_reasoning": true, @@ -42899,7 +42924,10 @@ "max_tokens": 128000, "mode": "chat", "use_openai_responses_path": true, - "supported_endpoints": ["/v1/chat/completions", "/v1/responses"], + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_reasoning": true, @@ -43078,20 +43106,6 @@ } ] }, - "zai.glm-5": { - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3.2e-06, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 200000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" - }, "bedrock/us-east-1/zai.glm-5": { "input_cost_per_token": 1e-06, "output_cost_per_token": 3.2e-06, @@ -43120,45 +43134,6 @@ "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/" }, - "minimax.minimax-m2.5": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "supports_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" - }, - "bedrock/us-east-1/minimax.minimax-m2.5": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "supports_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" - }, - "bedrock/us-west-2/minimax.minimax-m2.5": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "supports_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" - }, "bedrock/us-gov-east-1/anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.5e-06, "cache_creation_input_token_cost_above_1hr": 2.4e-06, @@ -43180,7 +43155,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, - "supports_pdf_input": true + "supports_pdf_input": true, + "supports_parallel_tool_use_config": true }, "bedrock/us-gov-west-1/anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.5e-06, @@ -43203,364 +43179,368 @@ "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, - "supports_pdf_input": true + "supports_pdf_input": true, + "supports_parallel_tool_use_config": true + }, + "snowflake/claude-sonnet-4-5": { + "max_tokens": 16384, + "max_input_tokens": 200000, + "max_output_tokens": 16384, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "cache_read_input_token_cost": 3e-07, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_response_schema": true + }, + "snowflake/claude-sonnet-4-6": { + "max_tokens": 16384, + "max_input_tokens": 200000, + "max_output_tokens": 16384, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "cache_read_input_token_cost": 3e-07, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_response_schema": true + }, + "snowflake/claude-4-sonnet": { + "max_tokens": 16384, + "max_input_tokens": 200000, + "max_output_tokens": 16384, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "cache_read_input_token_cost": 3e-07, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_response_schema": true + }, + "snowflake/claude-4-opus": { + "max_tokens": 16384, + "max_input_tokens": 200000, + "max_output_tokens": 16384, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 2.5e-05, + "cache_read_input_token_cost": 5e-07, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_response_schema": true + }, + "snowflake/claude-haiku-4-5": { + "max_tokens": 16384, + "max_input_tokens": 200000, + "max_output_tokens": 16384, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 5e-06, + "cache_read_input_token_cost": 1e-07, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_response_schema": true + }, + "snowflake/claude-3-7-sonnet": { + "max_tokens": 16384, + "max_input_tokens": 200000, + "max_output_tokens": 16384, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "cache_read_input_token_cost": 3e-07, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_response_schema": true + }, + "snowflake/openai-gpt-4.1": { + "max_tokens": 16384, + "max_input_tokens": 300000, + "max_output_tokens": 16384, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 8e-06, + "cache_read_input_token_cost": 5e-07, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_response_schema": true + }, + "snowflake/openai-gpt-5": { + "max_tokens": 16384, + "max_input_tokens": 300000, + "max_output_tokens": 16384, + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1.25e-07, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_response_schema": true + }, + "snowflake/openai-gpt-5-mini": { + "max_tokens": 16384, + "max_input_tokens": 1000000, + "max_output_tokens": 16384, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_system_messages": true, + "supports_response_schema": true + }, + "snowflake/openai-gpt-5-nano": { + "max_tokens": 16384, + "max_input_tokens": 5000000, + "max_output_tokens": 16384, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_system_messages": true, + "supports_response_schema": true + }, + "snowflake/llama4-maverick": { + "max_tokens": 16384, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "input_cost_per_token": 2.4e-07, + "output_cost_per_token": 9.7e-07, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_system_messages": true + }, + "snowflake/snowflake-arctic-embed-l-v2.0": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "input_cost_per_token": 7e-08, + "output_cost_per_token": 0.0, + "litellm_provider": "snowflake", + "mode": "embedding" + }, + "snowflake/snowflake-arctic-embed-m-v2.0": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "input_cost_per_token": 7e-08, + "output_cost_per_token": 0.0, + "litellm_provider": "snowflake", + "mode": "embedding" + }, + "soniox/stt-async-v4": { + "litellm_provider": "soniox", + "max_output_tokens": 8000, + "max_tokens": 8000, + "input_cost_per_second": 0.0, + "output_cost_per_second": 2.77778e-05, + "mode": "audio_transcription", + "source": "https://soniox.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ], + "supports_audio_input": true + }, + "soniox/stt-async-v5": { + "litellm_provider": "soniox", + "max_output_tokens": 8000, + "max_tokens": 8000, + "input_cost_per_second": 0.0, + "output_cost_per_second": 2.77778e-05, + "mode": "audio_transcription", + "source": "https://soniox.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ], + "supports_audio_input": true + }, + "tensormesh/Qwen/Qwen3.5-397B-A17B-FP8": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 6e-07, + "output_cost_per_token": 3.6e-06, + "cache_read_input_token_cost": 0, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + }, + "tensormesh/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 4.5e-07, + "output_cost_per_token": 1.8e-06, + "cache_read_input_token_cost": 0, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + }, + "tensormesh/Qwen/Qwen3.6-27B-FP8": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 3.2e-07, + "output_cost_per_token": 3.2e-06, + "cache_read_input_token_cost": 0, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + }, + "tensormesh/lukealonso/GLM-5.1-NVFP4-MTP": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 1.4e-06, + "output_cost_per_token": 4.4e-06, + "cache_read_input_token_cost": 0, + "max_input_tokens": 202752, + "max_output_tokens": 202752, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + }, + "tensormesh/deepseek-ai/DeepSeek-V4-Flash": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 2.8e-07, + "cache_read_input_token_cost": 0, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + }, + "tensormesh/moonshotai/Kimi-K2.6": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 9.6e-07, + "output_cost_per_token": 4e-06, + "cache_read_input_token_cost": 0, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + }, + "tensormesh/MiniMaxAI/MiniMax-M2.5": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 0, + "max_input_tokens": 196608, + "max_output_tokens": 196608, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + }, + "tensormesh/google/gemma-4-31B-it": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 5.6e-07, + "cache_read_input_token_cost": 0, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + }, + "tensormesh/openai/gpt-oss-120b": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "cache_read_input_token_cost": 0, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + }, + "tensormesh/openai/gpt-oss-20b": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 7e-08, + "output_cost_per_token": 2.8e-07, + "cache_read_input_token_cost": 0, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" }, - "snowflake/claude-sonnet-4-5": { - "max_tokens": 16384, - "max_input_tokens": 200000, - "max_output_tokens": 16384, - "input_cost_per_token": 0.000003, - "output_cost_per_token": 0.000015, - "cache_read_input_token_cost": 0.0000003, - "litellm_provider": "snowflake", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_response_schema": true - }, - "snowflake/claude-sonnet-4-6": { - "max_tokens": 16384, - "max_input_tokens": 200000, - "max_output_tokens": 16384, - "input_cost_per_token": 0.000003, - "output_cost_per_token": 0.000015, - "cache_read_input_token_cost": 0.0000003, - "litellm_provider": "snowflake", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_response_schema": true - }, - "snowflake/claude-4-sonnet": { - "max_tokens": 16384, - "max_input_tokens": 200000, - "max_output_tokens": 16384, - "input_cost_per_token": 0.000003, - "output_cost_per_token": 0.000015, - "cache_read_input_token_cost": 0.0000003, - "litellm_provider": "snowflake", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_response_schema": true - }, - "snowflake/claude-4-opus": { - "max_tokens": 16384, - "max_input_tokens": 200000, - "max_output_tokens": 16384, - "input_cost_per_token": 0.000005, - "output_cost_per_token": 0.000025, - "cache_read_input_token_cost": 0.0000005, - "litellm_provider": "snowflake", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_reasoning": true, - "supports_response_schema": true - }, - "snowflake/claude-haiku-4-5": { - "max_tokens": 16384, - "max_input_tokens": 200000, - "max_output_tokens": 16384, - "input_cost_per_token": 0.000001, - "output_cost_per_token": 0.000005, - "cache_read_input_token_cost": 0.0000001, - "litellm_provider": "snowflake", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_response_schema": true - }, - "snowflake/claude-3-7-sonnet": { - "max_tokens": 16384, - "max_input_tokens": 200000, - "max_output_tokens": 16384, - "input_cost_per_token": 0.000003, - "output_cost_per_token": 0.000015, - "cache_read_input_token_cost": 0.0000003, - "litellm_provider": "snowflake", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_reasoning": true, - "supports_response_schema": true - }, - "snowflake/openai-gpt-4.1": { - "max_tokens": 16384, - "max_input_tokens": 300000, - "max_output_tokens": 16384, - "input_cost_per_token": 0.000002, - "output_cost_per_token": 0.000008, - "cache_read_input_token_cost": 0.0000005, - "litellm_provider": "snowflake", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_response_schema": true - }, - "snowflake/openai-gpt-5": { - "max_tokens": 16384, - "max_input_tokens": 300000, - "max_output_tokens": 16384, - "input_cost_per_token": 0.00000125, - "output_cost_per_token": 0.00001, - "cache_read_input_token_cost": 0.000000125, - "litellm_provider": "snowflake", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_reasoning": true, - "supports_response_schema": true - }, - "snowflake/openai-gpt-5-mini": { - "max_tokens": 16384, - "max_input_tokens": 1000000, - "max_output_tokens": 16384, - "input_cost_per_token": 0.0000003, - "output_cost_per_token": 0.0000012, - "litellm_provider": "snowflake", - "mode": "chat", - "supports_function_calling": true, - "supports_system_messages": true, - "supports_response_schema": true - }, - "snowflake/openai-gpt-5-nano": { - "max_tokens": 16384, - "max_input_tokens": 5000000, - "max_output_tokens": 16384, - "input_cost_per_token": 0.00000015, - "output_cost_per_token": 0.0000006, - "litellm_provider": "snowflake", - "mode": "chat", - "supports_function_calling": true, - "supports_system_messages": true, - "supports_response_schema": true - }, - "snowflake/llama4-maverick": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 0.00000024, - "output_cost_per_token": 0.00000097, - "litellm_provider": "snowflake", - "mode": "chat", - "supports_function_calling": true, - "supports_system_messages": true - }, - "snowflake/snowflake-arctic-embed-l-v2.0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "input_cost_per_token": 0.00000007, - "output_cost_per_token": 0.0, - "litellm_provider": "snowflake", - "mode": "embedding" - }, - "snowflake/snowflake-arctic-embed-m-v2.0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "input_cost_per_token": 0.00000007, - "output_cost_per_token": 0.0, - "litellm_provider": "snowflake", - "mode": "embedding" - }, - "soniox/stt-async-v4": { - "litellm_provider": "soniox", - "max_output_tokens": 8000, - "max_tokens": 8000, - "input_cost_per_second": 0.0, - "output_cost_per_second": 0.0000277778, - "mode": "audio_transcription", - "source": "https://soniox.com/pricing", - "supported_endpoints": ["/v1/audio/transcriptions"], - "supports_audio_input": true - }, - "soniox/stt-async-v5": { - "litellm_provider": "soniox", - "max_output_tokens": 8000, - "max_tokens": 8000, - "input_cost_per_second": 0.0, - "output_cost_per_second": 0.0000277778, - "mode": "audio_transcription", - "source": "https://soniox.com/pricing", - "supported_endpoints": ["/v1/audio/transcriptions"], - "supports_audio_input": true - }, - "tensormesh/Qwen/Qwen3.5-397B-A17B-FP8": { - "litellm_provider": "tensormesh", - "mode": "chat", - "input_cost_per_token": 6e-07, - "output_cost_per_token": 3.6e-06, - "cache_read_input_token_cost": 0, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_reasoning": true, - "source": "https://serverless.tensormesh.ai/v1/models/openrouter" - }, - "tensormesh/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { - "litellm_provider": "tensormesh", - "mode": "chat", - "input_cost_per_token": 4.5e-07, - "output_cost_per_token": 1.8e-06, - "cache_read_input_token_cost": 0, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "source": "https://serverless.tensormesh.ai/v1/models/openrouter" - }, - "tensormesh/Qwen/Qwen3.6-27B-FP8": { - "litellm_provider": "tensormesh", - "mode": "chat", - "input_cost_per_token": 3.2e-07, - "output_cost_per_token": 3.2e-06, - "cache_read_input_token_cost": 0, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_reasoning": true, - "source": "https://serverless.tensormesh.ai/v1/models/openrouter" - }, - "tensormesh/lukealonso/GLM-5.1-NVFP4-MTP": { - "litellm_provider": "tensormesh", - "mode": "chat", - "input_cost_per_token": 1.4e-06, - "output_cost_per_token": 4.4e-06, - "cache_read_input_token_cost": 0, - "max_input_tokens": 202752, - "max_output_tokens": 202752, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_reasoning": true, - "source": "https://serverless.tensormesh.ai/v1/models/openrouter" - }, - "tensormesh/deepseek-ai/DeepSeek-V4-Flash": { - "litellm_provider": "tensormesh", - "mode": "chat", - "input_cost_per_token": 1.4e-07, - "output_cost_per_token": 2.8e-07, - "cache_read_input_token_cost": 0, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_reasoning": true, - "source": "https://serverless.tensormesh.ai/v1/models/openrouter" - }, - "tensormesh/moonshotai/Kimi-K2.6": { - "litellm_provider": "tensormesh", - "mode": "chat", - "input_cost_per_token": 9.6e-07, - "output_cost_per_token": 4e-06, - "cache_read_input_token_cost": 0, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_reasoning": true, - "source": "https://serverless.tensormesh.ai/v1/models/openrouter" - }, - "tensormesh/MiniMaxAI/MiniMax-M2.5": { - "litellm_provider": "tensormesh", - "mode": "chat", - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "cache_read_input_token_cost": 0, - "max_input_tokens": 196608, - "max_output_tokens": 196608, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_reasoning": true, - "source": "https://serverless.tensormesh.ai/v1/models/openrouter" - }, - "tensormesh/google/gemma-4-31B-it": { - "litellm_provider": "tensormesh", - "mode": "chat", - "input_cost_per_token": 1.4e-07, - "output_cost_per_token": 5.6e-07, - "cache_read_input_token_cost": 0, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_reasoning": true, - "source": "https://serverless.tensormesh.ai/v1/models/openrouter" - }, - "tensormesh/openai/gpt-oss-120b": { - "litellm_provider": "tensormesh", - "mode": "chat", - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "cache_read_input_token_cost": 0, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_reasoning": true, - "source": "https://serverless.tensormesh.ai/v1/models/openrouter" - }, - "tensormesh/openai/gpt-oss-20b": { - "litellm_provider": "tensormesh", - "mode": "chat", - "input_cost_per_token": 7e-08, - "output_cost_per_token": 2.8e-07, - "cache_read_input_token_cost": 0, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_reasoning": true, - "source": "https://serverless.tensormesh.ai/v1/models/openrouter" - } - , "deepseek-v4-flash": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 2.8e-09, @@ -43695,12 +43675,64 @@ "supports_tool_choice": true, "supports_vision": false }, + "tencent/deepseek-v4-pro": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 3.625e-09, + "input_cost_per_token": 4.35e-07, + "input_cost_per_token_cache_hit": 3.625e-09, + "litellm_provider": "tencent", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 8.7e-07, + "source": "https://www.tencentcloud.com/products/tokenhub", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false + }, + "tencent/deepseek-v4-flash": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 2.8e-09, + "input_cost_per_token": 1.4e-07, + "input_cost_per_token_cache_hit": 2.8e-09, + "litellm_provider": "tencent", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "source": "https://www.tencentcloud.com/products/tokenhub", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false + }, "pinstripes/ps/glm-4.5-air": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, - "input_cost_per_token": 0.000000125, - "output_cost_per_token": 0.00000045, + "input_cost_per_token": 1.25e-07, + "output_cost_per_token": 4.5e-07, "litellm_provider": "pinstripes", "mode": "chat", "supports_function_calling": true, @@ -43712,8 +43744,8 @@ "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 0.00000014, - "output_cost_per_token": 0.00000045, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 4.5e-07, "litellm_provider": "pinstripes", "mode": "chat", "supports_function_calling": true, @@ -43725,8 +43757,8 @@ "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 0.00000009, - "output_cost_per_token": 0.0000002, + "input_cost_per_token": 9e-08, + "output_cost_per_token": 2e-07, "litellm_provider": "pinstripes", "mode": "chat", "supports_function_calling": true, @@ -43738,8 +43770,8 @@ "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 0.0000003, - "output_cost_per_token": 0.0000006, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 6e-07, "litellm_provider": "pinstripes", "mode": "chat", "supports_function_calling": true, @@ -43751,8 +43783,8 @@ "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, - "input_cost_per_token": 0.0000001, - "output_cost_per_token": 0.0000002, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 2e-07, "litellm_provider": "pinstripes", "mode": "chat", "supports_function_calling": true, @@ -43764,8 +43796,8 @@ "max_tokens": 1000192, "max_input_tokens": 1000192, "max_output_tokens": 1000192, - "input_cost_per_token": 0.000000255, - "output_cost_per_token": 0.00000055, + "input_cost_per_token": 2.55e-07, + "output_cost_per_token": 5.5e-07, "litellm_provider": "pinstripes", "mode": "chat", "supports_function_calling": true, @@ -43773,39 +43805,39 @@ "supports_reasoning": false, "source": "https://pinstripes.io/pricing" }, - "fallback_generalizations": { - "rules": [ - { - "name": "anthropic-claude-adaptive-thinking", - "pattern": "(?:opus|sonnet|haiku)[-._](?:4[-._](?:[6-9]|[1-9]\\d)(?!\\d)|(?:[5-9]|[1-9]\\d{1,})[-._]\\d{1,2}(?!\\d))", - "description": "Claude opus/sonnet/haiku at version 4.6 or higher: 4.6 through 4.99, then any 5.x, 6.x or later major. The minor is capped at two digits so an 8-digit date suffix such as claude-opus-4-20250514 is never read as a >= 4.6 minor. Turns on adaptive thinking for new families with no code change.", - "extends": "anthropic-claude", - "model_info": { - "supports_adaptive_thinking": true - } - }, - { - "name": "anthropic-claude", - "pattern": "^claude-[a-z]+-\\d+[-.]\\d+(?:-\\d{8})?$", - "description": "Any Claude family-major-minor id, optionally with an 8-digit date suffix, anchored to the whole name. Version-neutral fallback that gives an unmapped Claude provider routing and baseline capabilities; it carries no pricing, so cost stays on the standard unpriced behavior rather than a guessed number.", - "model_info": { - "litellm_provider": "anthropic", - "mode": "chat", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true, - "supports_assistant_prefill": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_pdf_input": true, - "supports_system_messages": true - } - } - ] - } + "fallback_generalizations": { + "rules": [ + { + "name": "anthropic-claude-adaptive-thinking", + "pattern": "(?:opus|sonnet|haiku)[-._](?:4[-._](?:[6-9]|[1-9]\\d)(?!\\d)|(?:[5-9]|[1-9]\\d{1,})[-._]\\d{1,2}(?!\\d))", + "description": "Claude opus/sonnet/haiku at version 4.6 or higher: 4.6 through 4.99, then any 5.x, 6.x or later major. The minor is capped at two digits so an 8-digit date suffix such as claude-opus-4-20250514 is never read as a >= 4.6 minor. Turns on adaptive thinking for new families with no code change.", + "extends": "anthropic-claude", + "model_info": { + "supports_adaptive_thinking": true + } + }, + { + "name": "anthropic-claude", + "pattern": "^claude-[a-z]+-\\d+[-.]\\d+(?:-\\d{8})?$", + "description": "Any Claude family-major-minor id, optionally with an 8-digit date suffix, anchored to the whole name. Version-neutral fallback that gives an unmapped Claude provider routing and baseline capabilities; it carries no pricing, so cost stays on the standard unpriced behavior rather than a guessed number.", + "model_info": { + "litellm_provider": "anthropic", + "mode": "chat", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_vision": true, + "supports_tool_choice": true, + "supports_assistant_prefill": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_pdf_input": true, + "supports_system_messages": true + } + } + ] + } } diff --git a/litellm/models/mcp_server.py b/litellm/models/mcp_server.py index 3d03eff6df8..5d3bc176134 100644 --- a/litellm/models/mcp_server.py +++ b/litellm/models/mcp_server.py @@ -93,6 +93,7 @@ class LiteLLM_MCPServerTable(LiteLLMPydanticObjectBase): has_user_credential: Optional[bool] = None source_url: Optional[str] = None timeout: Optional[float] = None + max_concurrent_requests: Optional[int] = None approval_status: Optional[str] = Field( default="active", description="Approval status: 'pending_review', 'active', 'rejected'", diff --git a/litellm/proxy/_experimental/mcp_server/mcp_server_manager.py b/litellm/proxy/_experimental/mcp_server/mcp_server_manager.py index 95d00554034..baa4a5a9e0c 100644 --- a/litellm/proxy/_experimental/mcp_server/mcp_server_manager.py +++ b/litellm/proxy/_experimental/mcp_server/mcp_server_manager.py @@ -13,7 +13,8 @@ import json import os import re import time -from typing import Any, Callable, Dict, List, Literal, Optional, Set, Tuple, Union, cast +from contextlib import asynccontextmanager +from typing import Any, AsyncIterator, Callable, Literal, Optional, Union, cast from urllib.parse import urlparse import anyio @@ -155,7 +156,7 @@ _AZURE_ENTRA_HOSTS = { # BYOK credential cache. Keyed by (user_id, server_id); value is # (values_dict, monotonic_timestamp). Keeps the tool-call and tool-listing # paths off the DB on every request within the TTL window. -_user_env_vars_cache: Dict[Tuple[str, str], Tuple[Dict[str, str], float]] = {} +_user_env_vars_cache: dict[tuple[str, str], tuple[dict[str, str], float]] = {} _USER_ENV_VARS_CACHE_TTL = 60 # seconds _USER_ENV_VARS_CACHE_MAX_SIZE = 4096 # cap to prevent unbounded growth @@ -166,7 +167,7 @@ def invalidate_user_env_vars_cache(user_id: str, server_id: str) -> None: _user_env_vars_cache.pop((user_id, server_id), None) -def _write_user_env_vars_cache(user_id: str, server_id: str, values: Dict[str, str]) -> None: +def _write_user_env_vars_cache(user_id: str, server_id: str, values: dict[str, str]) -> None: cache_key = (user_id, server_id) # Re-insert at the tail so eviction drops the oldest-written entry, not a # freshly refreshed one, and only sheds a single entry instead of wiping the @@ -179,7 +180,7 @@ def _write_user_env_vars_cache(user_id: str, server_id: str, values: Dict[str, s def _should_strip_caller_authorization( mcp_server: MCPServer, - raw_headers: Optional[Dict[str, str]], + raw_headers: Optional[dict[str, str]], user_api_key_auth: Optional[UserAPIKeyAuth], ) -> bool: """Decide whether the caller's ``Authorization`` header must NOT be @@ -243,7 +244,7 @@ def _without_authorization( def _extract_upstream_auth_failure( exc: BaseException, -) -> Optional[Tuple[int, Optional[str]]]: +) -> Optional[tuple[int, Optional[str]]]: """Walk the exception tree looking for an HTTP 401/403 response from the upstream MCP server. @@ -255,8 +256,8 @@ def _extract_upstream_auth_failure( Returns ``(status_code, www_authenticate)`` on match, else ``None``. """ - seen: Set[int] = set() - stack: List[BaseException] = [exc] + seen: set[int] = set() + stack: list[BaseException] = [exc] while stack: current = stack.pop() if id(current) in seen: @@ -337,7 +338,7 @@ def _warn_internal_delegate_pkce_if_applicable(server: MCPServer, *, source: str ) -def _deserialize_json_dict(data: Any) -> Optional[Dict[str, str]]: +def _deserialize_json_dict(data: Any) -> Optional[dict[str, str]]: """ Deserialize optional JSON mappings stored in the database. @@ -358,7 +359,7 @@ def _deserialize_json_dict(data: Any) -> Optional[Dict[str, str]]: return data -def _deserialize_json_list(data: Any) -> Optional[List[Dict[str, Any]]]: +def _deserialize_json_list(data: Any) -> Optional[list[dict[str, Any]]]: """Deserialize a JSON array stored in the DB (``env_vars`` and friends). Returns ``None`` for empty / null / unparseable input. Accepts strings @@ -532,8 +533,8 @@ class MCPServerManager: self._cred_provider = cred_provider or UpstreamCredentialProvider( oauth_token_store=LazyPerUserOAuthTokenStore(self.get_mcp_server_by_id) ) - self.registry: Dict[str, MCPServer] = {} - self.config_mcp_servers: Dict[str, MCPServer] = {} + self.registry: dict[str, MCPServer] = {} + self.config_mcp_servers: dict[str, MCPServer] = {} """ eg. [ @@ -550,17 +551,22 @@ class MCPServerManager: ] """ - self.tool_name_to_mcp_server_name_mapping: Dict[str, str] = {} + # Per-server outbound tool-call concurrency limiters, lazily created from + # each server's max_concurrent_requests. Keyed by server_id so the cap + # survives the registry atomic-swap on config reload; a missing key means + # the server has no configured limit. + self._server_call_semaphores: dict[str, asyncio.Semaphore] = {} + self.tool_name_to_mcp_server_name_mapping: dict[str, str] = {} """ { "gmail_send_email": "zapier_mcp_server", } """ - self._upstream_initialize_instructions_by_server_id: Dict[str, str] = {} + self._upstream_initialize_instructions_by_server_id: dict[str, str] = {} # Per-server monotonic timestamp of last upstream prefetch attempt (success, # empty result, or failure). Used to throttle re-probes for servers that do # not return instructions, and to apply a short cooldown after failures. - self._upstream_initialize_instructions_probed_at: Dict[str, float] = {} + self._upstream_initialize_instructions_probed_at: dict[str, float] = {} def _remember_upstream_initialize_instructions(self, server: MCPServer, client: MCPClient) -> None: raw = getattr(client, "_last_initialize_instructions", None) @@ -616,7 +622,7 @@ class MCPServerManager: user_api_key_auth=None, raise_on_missing=False, ) - extra_headers: Optional[Dict[str, str]] = dict(resolved_static_headers) if resolved_static_headers else None + extra_headers: Optional[dict[str, str]] = dict(resolved_static_headers) if resolved_static_headers else None client = await self._create_mcp_client( server=server, mcp_auth_header=None, @@ -636,7 +642,7 @@ class MCPServerManager: e, ) - def get_registry(self) -> Dict[str, MCPServer]: + def get_registry(self) -> dict[str, MCPServer]: """ Get the registered MCP Servers from the registry and union with the config MCP Servers """ @@ -644,8 +650,8 @@ class MCPServerManager: async def load_servers_from_config( self, - mcp_servers_config: Dict[str, Any], - mcp_aliases: Optional[Dict[str, str]] = None, + mcp_servers_config: dict[str, Any], + mcp_aliases: Optional[dict[str, str]] = None, ): """ Load the MCP Servers from the config @@ -663,7 +669,7 @@ class MCPServerManager: for server_name, server_config in mcp_servers_config.items(): validate_mcp_server_name(server_name) - _mcp_info: Dict[str, Any] = server_config.get("mcp_info", None) or {} + _mcp_info: dict[str, Any] = server_config.get("mcp_info", None) or {} # Preserve all custom fields from config while setting defaults for core fields mcp_info: MCPInfo = _mcp_info.copy() # Set default values for core fields if not present @@ -790,6 +796,7 @@ class MCPServerManager: allow_sampling=bool(server_config.get("allow_sampling", False)), allow_elicitation=bool(server_config.get("allow_elicitation", False)), timeout=server_config.get("timeout", None), + max_concurrent_requests=server_config.get("max_concurrent_requests", None), ) self._assign_unique_short_prefix(new_server) _warn_internal_delegate_pkce_if_applicable(new_server, source="config") @@ -851,7 +858,7 @@ class MCPServerManager: server_prefix = get_server_prefix(server) # Build headers from server configuration - headers: Dict[str, str] = {} + headers: dict[str, str] = {} # Add authentication headers if configured if server.authentication_token: @@ -961,7 +968,7 @@ class MCPServerManager: openapi_key_prefix = prefix_root + MCP_TOOL_PREFIX_SEPARATOR global_mcp_tool_registry.unregister_tools_with_prefix(openapi_key_prefix) - owned_raw: Set[str] = set() + owned_raw: set[str] = set() for p in iter_known_server_prefixes(server): if p: owned_raw.add(p) @@ -970,7 +977,7 @@ class MCPServerManager: owned_normalized = {normalize_server_name(x) for x in owned_raw} - stale_mapping_keys: List[str] = [] + stale_mapping_keys: list[str] = [] for tool_name, mapped_server in list(self.tool_name_to_mcp_server_name_mapping.items()): if mapped_server in owned_raw: stale_mapping_keys.append(tool_name) @@ -998,7 +1005,7 @@ class MCPServerManager: mcp_server: LiteLLM_MCPServerTable, *, env_vars_are_encrypted: bool, - ) -> Optional[List[Dict[str, Any]]]: + ) -> Optional[list[dict[str, Any]]]: env_vars_list = _deserialize_json_list(getattr(mcp_server, "env_vars", None)) if env_vars_are_encrypted: from litellm.proxy._experimental.mcp_server.db import ( # noqa: PLC0415 @@ -1073,7 +1080,7 @@ class MCPServerManager: # AWS SigV4 credential fields aws_creds = self._extract_aws_credentials(credentials_dict, credentials_are_encrypted) - scopes: Optional[List[str]] = None + scopes: Optional[list[str]] = None if credentials_dict: scopes_value = credentials_dict.get("scopes") if scopes_value is not None: @@ -1164,6 +1171,7 @@ class MCPServerManager: subject_token_type=(credentials_dict.get("subject_token_type") if credentials_dict else None) or "urn:ietf:params:oauth:token-type:access_token", timeout=getattr(mcp_server, "timeout", None), + max_concurrent_requests=getattr(mcp_server, "max_concurrent_requests", None), ) _warn_internal_delegate_pkce_if_applicable(new_server, source="database") return new_server @@ -1235,14 +1243,14 @@ class MCPServerManager: verbose_logger.debug(f"Failed to udpate MCP server: {str(e)}") raise e - def get_all_mcp_server_ids(self) -> Set[str]: + def get_all_mcp_server_ids(self) -> set[str]: """ Get all MCP server IDs """ all_servers = list(self.get_registry().values()) return {server.server_id for server in all_servers} - def get_allow_all_keys_server_ids(self) -> List[str]: + def get_allow_all_keys_server_ids(self) -> list[str]: """Return server IDs that bypass per-key restrictions.""" return [server.server_id for server in self.get_registry().values() if server.allow_all_keys is True] @@ -1307,7 +1315,7 @@ class MCPServerManager: return [server_id for server_id in submitted_server_ids if self.get_mcp_server_by_id(server_id) is not None] - async def get_allowed_mcp_servers(self, user_api_key_auth: Optional[UserAPIKeyAuth] = None) -> List[str]: + async def get_allowed_mcp_servers(self, user_api_key_auth: Optional[UserAPIKeyAuth] = None) -> list[str]: """ Get the allowed MCP Servers for the user. @@ -1404,8 +1412,8 @@ class MCPServerManager: async def resolve_toolset_tool_permissions( self, - toolset_ids: List[str], - ) -> Dict[str, List[str]]: + toolset_ids: list[str], + ) -> dict[str, list[str]]: """ Resolve a list of toolset IDs into a mcp_tool_permissions dict. @@ -1427,7 +1435,7 @@ class MCPServerManager: try: toolsets = await list_mcp_toolsets(prisma_client, toolset_ids=toolset_ids) - tool_permissions: Dict[str, List[str]] = {} + tool_permissions: dict[str, list[str]] = {} for toolset in toolsets: for tool in toolset.tools: raw_name = tool["tool_name"] @@ -1520,7 +1528,7 @@ class MCPServerManager: ) return toolset - def filter_server_ids_by_ip(self, server_ids: List[str], client_ip: Optional[str]) -> List[str]: + def filter_server_ids_by_ip(self, server_ids: list[str], client_ip: Optional[str]) -> list[str]: """ Filter server IDs by client IP β€” external callers only see public servers. @@ -1530,8 +1538,8 @@ class MCPServerManager: return filtered def filter_server_ids_by_ip_with_info( - self, server_ids: List[str], client_ip: Optional[str] - ) -> Tuple[List[str], int]: + self, server_ids: list[str], client_ip: Optional[str] + ) -> tuple[list[str], int]: """ Filter server IDs by client IP β€” external callers only see public servers. @@ -1551,7 +1559,7 @@ class MCPServerManager: blocked += 1 return allowed, blocked - async def get_tools_for_server(self, server_id: str) -> List[MCPTool]: + async def get_tools_for_server(self, server_id: str) -> list[MCPTool]: """ Get the tools for a given server """ @@ -1569,8 +1577,8 @@ class MCPServerManager: self, user_api_key_auth: Optional[UserAPIKeyAuth] = None, mcp_auth_header: Optional[str] = None, - mcp_server_auth_headers: Optional[Dict[str, Union[str, Dict[str, str]]]] = None, - ) -> List[MCPTool]: + mcp_server_auth_headers: Optional[dict[str, Union[str, dict[str, str]]]] = None, + ) -> list[MCPTool]: """ List all tools available across all MCP Servers. @@ -1587,7 +1595,7 @@ class MCPServerManager: verbose_logger.debug("SERVER MANAGER LISTING TOOLS") - async def _fetch_server_tools(server_id: str) -> List[MCPTool]: + async def _fetch_server_tools(server_id: str) -> list[MCPTool]: """Fetch tools from a single server with error handling.""" server = self.get_mcp_server_by_id(server_id) if server is None: @@ -1595,7 +1603,7 @@ class MCPServerManager: return [] # Get server-specific auth header if available - server_auth_header: Optional[Union[str, Dict[str, str]]] = None + server_auth_header: Optional[Union[str, dict[str, str]]] = None if mcp_server_auth_headers: from litellm.proxy._experimental.mcp_server.utils import ( lookup_mcp_server_auth_in_headers, @@ -1629,7 +1637,7 @@ class MCPServerManager: results = await asyncio.gather(*tasks) # Flatten results into single list - list_tools_result: List[MCPTool] = [tool for tools in results for tool in tools] + list_tools_result: list[MCPTool] = [tool for tools in results for tool in tools] verbose_logger.info(f"Successfully fetched {len(list_tools_result)} tools total from all servers") return list_tools_result @@ -1639,8 +1647,8 @@ class MCPServerManager: ######################################################### @staticmethod def _extract_bearer_token( - oauth2_headers: Optional[Dict[str, str]], - raw_headers: Optional[Dict[str, str]], + oauth2_headers: Optional[dict[str, str]], + raw_headers: Optional[dict[str, str]], ) -> Optional[str]: """Extract the bare Bearer token from oauth2_headers or raw_headers. @@ -1663,14 +1671,14 @@ class MCPServerManager: def _build_stdio_env( self, server: MCPServer, - raw_headers: Optional[Dict[str, str]] = None, - ) -> Optional[Dict[str, str]]: + raw_headers: Optional[dict[str, str]] = None, + ) -> Optional[dict[str, str]]: """Resolve stdio env values, supporting header-driven placeholders.""" if server.transport != MCPTransport.stdio or not server.env: return None - resolved_env: Dict[str, str] = {} + resolved_env: dict[str, str] = {} normalized_headers = {k.lower(): v for k, v in (raw_headers or {}).items()} for env_key, env_value in server.env.items(): @@ -1712,7 +1720,7 @@ class MCPServerManager: user_api_key_auth: Optional[UserAPIKeyAuth], *, raise_on_missing: bool = True, - ) -> Optional[Dict[str, str]]: + ) -> Optional[dict[str, str]]: """Return server.static_headers with ``${NAME}`` interpolated. Globals come from ``server.env_vars`` entries with ``scope=="global"``. @@ -1755,7 +1763,7 @@ class MCPServerManager: referenced_user_vars = referenced & user_var_names required_user_vars = {name for name in referenced_user_vars if name not in global_values} - user_values: Dict[str, str] = {} + user_values: dict[str, str] = {} if required_user_vars: try: user_values = await self._load_user_env_vars(server, user_api_key_auth) @@ -1794,7 +1802,7 @@ class MCPServerManager: # admin globals win, so a stale row from when a var was user-scoped can # never override the global value the admin set after switching it. scoped_user_values = {name: value for name, value in user_values.items() if name in user_var_names} - merged_vars: Dict[str, str] = {**scoped_user_values, **global_values} + merged_vars: dict[str, str] = {**scoped_user_values, **global_values} if not static_headers: return static_headers return interpolate_headers(static_headers, merged_vars) @@ -1805,7 +1813,7 @@ class MCPServerManager: user_api_key_auth: Optional[UserAPIKeyAuth], *, force_refresh: bool = False, - ) -> Dict[str, str]: + ) -> dict[str, str]: """Look up the calling user's env var values for ``server``. Returns an empty dict when no user is available. Results are cached in a @@ -1853,9 +1861,9 @@ class MCPServerManager: async def _create_mcp_client( self, server: MCPServer, - mcp_auth_header: Optional[Union[str, Dict[str, str]]] = None, - extra_headers: Optional[Dict[str, str]] = None, - stdio_env: Optional[Dict[str, str]] = None, + mcp_auth_header: Optional[Union[str, dict[str, str]]] = None, + extra_headers: Optional[dict[str, str]] = None, + stdio_env: Optional[dict[str, str]] = None, subject_token: Optional[str] = None, user_api_key_auth: Optional[UserAPIKeyAuth] = None, cred_provider: Optional[UpstreamCredentialProvider] = None, @@ -2013,12 +2021,12 @@ class MCPServerManager: async def _get_tools_from_server( self, server: MCPServer, - mcp_auth_header: Optional[Union[str, Dict[str, str]]] = None, - extra_headers: Optional[Dict[str, str]] = None, + mcp_auth_header: Optional[Union[str, dict[str, str]]] = None, + extra_headers: Optional[dict[str, str]] = None, add_prefix: bool = True, - raw_headers: Optional[Dict[str, str]] = None, + raw_headers: Optional[dict[str, str]] = None, user_api_key_auth: Optional[UserAPIKeyAuth] = None, - ) -> List[MCPTool]: + ) -> list[MCPTool]: """ Helper method to get tools from a single MCP server with prefixed names. @@ -2122,7 +2130,7 @@ class MCPServerManager: ] return tools else: - tools = await self._fetch_tools_with_timeout(client, server.name, server=server) + tools = await self._fetch_tools_with_timeout(client, server.name) self._remember_upstream_initialize_instructions(server, client) prefixed_or_original_tools = self._create_prefixed_tools(tools, server, add_prefix=add_prefix) @@ -2134,6 +2142,17 @@ class MCPServerManager: # client triggers the upstream OAuth flow. The multi-server # aggregator catches this explicitly to keep absorbing. raise + except HTTPException as e: + headers = e.headers or {} + www_authenticate = headers.get("WWW-Authenticate") or headers.get("www-authenticate") + if e.status_code == 401 and www_authenticate is not None: + raise MCPUpstreamAuthError( + status_code=401, + www_authenticate=www_authenticate, + server_name=server.name, + ) from e + verbose_logger.warning(f"Failed to get tools from server {server.name}: {str(e)}") + return [] except Exception as e: verbose_logger.warning(f"Failed to get tools from server {server.name}: {str(e)}") return [] @@ -2141,11 +2160,11 @@ class MCPServerManager: async def get_prompts_from_server( self, server: MCPServer, - mcp_auth_header: Optional[Union[str, Dict[str, str]]] = None, - extra_headers: Optional[Dict[str, str]] = None, + mcp_auth_header: Optional[Union[str, dict[str, str]]] = None, + extra_headers: Optional[dict[str, str]] = None, add_prefix: bool = True, - raw_headers: Optional[Dict[str, str]] = None, - ) -> List[Prompt]: + raw_headers: Optional[dict[str, str]] = None, + ) -> list[Prompt]: """ Helper method to get prompts from a single MCP server with prefixed names. @@ -2190,11 +2209,11 @@ class MCPServerManager: async def get_resources_from_server( self, server: MCPServer, - mcp_auth_header: Optional[Union[str, Dict[str, str]]] = None, - extra_headers: Optional[Dict[str, str]] = None, + mcp_auth_header: Optional[Union[str, dict[str, str]]] = None, + extra_headers: Optional[dict[str, str]] = None, add_prefix: bool = True, - raw_headers: Optional[Dict[str, str]] = None, - ) -> List[Resource]: + raw_headers: Optional[dict[str, str]] = None, + ) -> list[Resource]: """Fetch available resources from a single MCP server.""" verbose_logger.debug(f"Connecting to url: {server.url}") @@ -2230,11 +2249,11 @@ class MCPServerManager: async def get_resource_templates_from_server( self, server: MCPServer, - mcp_auth_header: Optional[Union[str, Dict[str, str]]] = None, - extra_headers: Optional[Dict[str, str]] = None, + mcp_auth_header: Optional[Union[str, dict[str, str]]] = None, + extra_headers: Optional[dict[str, str]] = None, add_prefix: bool = True, - raw_headers: Optional[Dict[str, str]] = None, - ) -> List[ResourceTemplate]: + raw_headers: Optional[dict[str, str]] = None, + ) -> list[ResourceTemplate]: """Fetch available resource templates from a single MCP server.""" verbose_logger.debug(f"Connecting to url: {server.url}") @@ -2273,9 +2292,9 @@ class MCPServerManager: self, server: MCPServer, url: AnyUrl, - mcp_auth_header: Optional[Union[str, Dict[str, str]]] = None, - extra_headers: Optional[Dict[str, str]] = None, - raw_headers: Optional[Dict[str, str]] = None, + mcp_auth_header: Optional[Union[str, dict[str, str]]] = None, + extra_headers: Optional[dict[str, str]] = None, + raw_headers: Optional[dict[str, str]] = None, ) -> ReadResourceResult: """Read resource contents from a specific MCP server.""" @@ -2302,10 +2321,10 @@ class MCPServerManager: self, server: MCPServer, prompt_name: str, - arguments: Optional[Dict[str, Any]] = None, - mcp_auth_header: Optional[Union[str, Dict[str, str]]] = None, - extra_headers: Optional[Dict[str, str]] = None, - raw_headers: Optional[Dict[str, str]] = None, + arguments: Optional[dict[str, Any]] = None, + mcp_auth_header: Optional[Union[str, dict[str, str]]] = None, + extra_headers: Optional[dict[str, str]] = None, + raw_headers: Optional[dict[str, str]] = None, ) -> GetPromptResult: """Fetch a specific prompt definition from a single MCP server.""" @@ -2449,7 +2468,7 @@ class MCPServerManager: verbose_logger.debug("MCP OAuth discovery failed for %s: %s", server_url, exc) return None - def _parse_www_authenticate_header(self, header_value: Optional[str]) -> Tuple[Optional[str], Optional[List[str]]]: + def _parse_www_authenticate_header(self, header_value: Optional[str]) -> tuple[Optional[str], Optional[list[str]]]: if not header_value: return None, None @@ -2457,7 +2476,7 @@ class MCPServerManager: params_section = params_section or header_value param_pattern = re.compile(r"([a-zA-Z0-9_]+)\s*=\s*\"?([^\",]+)\"?") - params: Dict[str, str] = { + params: dict[str, str] = { match.group(1).lower(): match.group(2).strip() for match in param_pattern.finditer(params_section) } @@ -2471,7 +2490,7 @@ class MCPServerManager: async def _fetch_oauth_metadata_from_resource( self, resource_metadata_url: str, server_url: str - ) -> Tuple[List[str], Optional[List[str]]]: + ) -> tuple[list[str], Optional[list[str]]]: if not resource_metadata_url: return [], None @@ -2506,7 +2525,7 @@ class MCPServerManager: return authorization_servers, scopes - async def _attempt_well_known_discovery(self, server_url: str) -> Tuple[List[str], Optional[List[str]]]: + async def _attempt_well_known_discovery(self, server_url: str) -> tuple[list[str], Optional[list[str]]]: try: parsed = urlparse(server_url) except Exception: @@ -2519,7 +2538,7 @@ class MCPServerManager: path = parsed.path or "" path = path.strip("/") - candidate_urls: List[str] = [] + candidate_urls: list[str] = [] if path: candidate_urls.append(f"{base}/.well-known/oauth-protected-resource/{path}") candidate_urls.append(f"{base}/.well-known/oauth-protected-resource") @@ -2535,7 +2554,7 @@ class MCPServerManager: return [], None async def _fetch_authorization_server_metadata( - self, authorization_servers: List[str], server_url: str + self, authorization_servers: list[str], server_url: str ) -> Optional[MCPOAuthMetadata]: for issuer in authorization_servers: metadata = await self._fetch_single_authorization_server_metadata(issuer, server_url) @@ -2557,7 +2576,7 @@ class MCPServerManager: base = f"{parsed.scheme}://{parsed.netloc}" path = (parsed.path or "").strip("/") - candidate_urls: List[str] = [] + candidate_urls: list[str] = [] if path: candidate_urls.append(f"{base}/.well-known/oauth-authorization-server/{path}") candidate_urls.append(f"{base}/.well-known/openid-configuration/{path}") @@ -2643,9 +2662,9 @@ class MCPServerManager: def _extract_aws_credentials( self, - credentials_dict: Optional[Dict[str, str]], + credentials_dict: Optional[dict[str, str]], credentials_are_encrypted: bool, - ) -> Dict[str, Optional[str]]: + ) -> dict[str, Optional[str]]: """Extract and decrypt AWS SigV4 credential fields from credentials dict.""" if not credentials_dict: return {} @@ -2671,7 +2690,7 @@ class MCPServerManager: "aws_session_name": credentials_dict.get("aws_session_name"), } - def _extract_scopes(self, scopes_value: Any) -> Optional[List[str]]: + def _extract_scopes(self, scopes_value: Any) -> Optional[list[str]]: if isinstance(scopes_value, str): scopes = [s.strip() for s in scopes_value.split() if s.strip()] return scopes or None @@ -2684,46 +2703,34 @@ class MCPServerManager: self, client: MCPClient, server_name: str, - server: Optional[MCPServer] = None, - ) -> List[MCPTool]: + ) -> list[MCPTool]: """ Fetch tools from MCP client with timeout and error handling. Uses anyio.fail_after() instead of asyncio.wait_for() to avoid conflicts with the MCP SDK's anyio TaskGroup. See GitHub issue #20715 for details. - For OAuth pass-through and upstream-delegated OAuth2 MCP servers, an - upstream HTTP 401 is converted into :class:`MCPUpstreamAuthError` - instead of being swallowed to an empty tool list. That lets the - single-server HTTP routes surface a proper 401 + ``WWW-Authenticate`` - challenge so standards-compliant MCP clients trigger the upstream - OAuth flow. Other servers keep today's swallow-and-log behaviour so - the multi-server ``/mcp`` aggregator doesn't get tainted by a single - bad server. + An upstream HTTP 401 is converted into :class:`MCPUpstreamAuthError` + instead of being swallowed to an empty tool list, regardless of the + server's auth_type. Callers route it by surface: the single-server HTTP + routes turn it into a 401 + ``WWW-Authenticate`` challenge so standards- + compliant MCP clients trigger the upstream OAuth flow, while the + multi-server ``/mcp`` aggregator absorbs it to an empty list so one + unauthenticated server doesn't fail the whole listing. Only a 401 + (missing/invalid credential) drives the re-auth challenge; a 403 + (authenticated but forbidden, e.g. insufficient scope) is not a re-auth + signal and, like other non-auth errors, returns an empty list. Args: client: MCP client instance server_name: Name of the server for logging - server: Optional MCPServer; when upstream auth is delegated, auth - errors are re-raised as :class:`MCPUpstreamAuthError`. Returns: List of tools from the server """ - should_surface_upstream_auth = bool( - server is not None - and ( - server.is_oauth_passthrough - or ( - server.auth_type == MCPAuth.oauth2 - and getattr(server, "delegate_auth_to_upstream", False) is True - and not server.has_client_credentials - ) - ) - ) try: with anyio.fail_after(MCP_TOOL_LISTING_TIMEOUT): - tools = await client.list_tools(raise_on_error=should_surface_upstream_auth) + tools = await client.list_tools(raise_on_error=True) verbose_logger.debug(f"Tools from {server_name}: {tools}") return tools except TimeoutError: @@ -2736,16 +2743,15 @@ class MCPServerManager: verbose_logger.warning(f"Connection error while listing tools from {server_name}: {str(e)}") return [] except Exception as e: - if should_surface_upstream_auth: - auth_info = _extract_upstream_auth_failure(e) - if auth_info is not None: - status_code, www_authenticate = auth_info - verbose_logger.info(f"Upstream auth failure from MCP server {server_name}: HTTP {status_code}") - raise MCPUpstreamAuthError( - status_code=status_code, - www_authenticate=www_authenticate, - server_name=server_name, - ) from e + auth_info = _extract_upstream_auth_failure(e) + if auth_info is not None and auth_info[0] == 401: + _, www_authenticate = auth_info + verbose_logger.info(f"Upstream auth failure from MCP server {server_name}: HTTP 401") + raise MCPUpstreamAuthError( + status_code=401, + www_authenticate=www_authenticate, + server_name=server_name, + ) from e verbose_logger.warning(f"Error listing tools from {server_name}: {str(e)}") return [] @@ -2754,7 +2760,7 @@ class MCPServerManager: def _assign_unique_short_prefix( self, server: MCPServer, - registry: Optional[Dict[str, MCPServer]] = None, + registry: Optional[dict[str, MCPServer]] = None, ) -> None: """Resolve and cache a collision-free short tool prefix on ``server``. @@ -2778,7 +2784,7 @@ class MCPServerManager: if not server.server_id: return - used: Dict[str, str] = {} + used: dict[str, str] = {} registry_for_collision_check = registry or self.get_registry() for other in registry_for_collision_check.values(): if other.server_id == server.server_id: @@ -2811,7 +2817,7 @@ class MCPServerManager: "attempts; the 3-character prefix space is too crowded." ) - def _create_prefixed_tools(self, tools: List[MCPTool], server: MCPServer, add_prefix: bool = True) -> List[MCPTool]: + def _create_prefixed_tools(self, tools: list[MCPTool], server: MCPServer, add_prefix: bool = True) -> list[MCPTool]: """ Create prefixed tools and update tool mapping. @@ -2849,8 +2855,8 @@ class MCPServerManager: return prefixed_tools def _create_prefixed_prompts( - self, prompts: List[Prompt], server: MCPServer, add_prefix: bool = True - ) -> List[Prompt]: + self, prompts: list[Prompt], server: MCPServer, add_prefix: bool = True + ) -> list[Prompt]: """ Create prefixed prompts and update prompt mapping. @@ -2876,11 +2882,11 @@ class MCPServerManager: return prefixed_prompts def _create_prefixed_resources( - self, resources: List[Resource], server: MCPServer, add_prefix: bool = True - ) -> List[Resource]: + self, resources: list[Resource], server: MCPServer, add_prefix: bool = True + ) -> list[Resource]: """Prefix resource names and track origin server for read requests.""" - prefixed_resources: List[Resource] = [] + prefixed_resources: list[Resource] = [] prefix = get_server_prefix(server) for resource in resources: @@ -2893,13 +2899,13 @@ class MCPServerManager: def _create_prefixed_resource_templates( self, - resource_templates: List[ResourceTemplate], + resource_templates: list[ResourceTemplate], server: MCPServer, add_prefix: bool = True, - ) -> List[ResourceTemplate]: + ) -> list[ResourceTemplate]: """Prefix resource template names for multi-server scenarios.""" - prefixed_templates: List[ResourceTemplate] = [] + prefixed_templates: list[ResourceTemplate] = [] prefix = get_server_prefix(server) for resource_template in resource_templates: @@ -2932,7 +2938,7 @@ class MCPServerManager: ) return True - def validate_allowed_params(self, tool_name: str, arguments: Dict[str, Any], server: MCPServer) -> None: + def validate_allowed_params(self, tool_name: str, arguments: dict[str, Any], server: MCPServer) -> None: """ Filter arguments to only include allowed parameters for the given tool. @@ -3023,7 +3029,7 @@ class MCPServerManager: self, server: MCPServer, tool_name: str, - arguments: Dict[str, Any], + arguments: dict[str, Any], ) -> CallToolResult: """ Call an OpenAPI tool handler directly. @@ -3080,13 +3086,13 @@ class MCPServerManager: async def pre_call_tool_check( self, name: str, - arguments: Dict[str, Any], + arguments: dict[str, Any], server_name: str, user_api_key_auth: Optional[UserAPIKeyAuth], proxy_logging_obj: ProxyLogging, server: MCPServer, - raw_headers: Optional[Dict[str, str]] = None, - ) -> Dict[str, Any]: + raw_headers: Optional[dict[str, str]] = None, + ) -> dict[str, Any]: """ Run pre-call checks and guardrail hooks for an MCP tool call. @@ -3146,7 +3152,7 @@ class MCPServerManager: # Convert to LLM format for existing guardrail compatibility synthetic_llm_data = proxy_logging_obj._convert_mcp_to_llm_format(mcp_request_obj, pre_hook_kwargs) - hook_result: Dict[str, Any] = {} + hook_result: dict[str, Any] = {} try: # Use standard pre_call_hook modified_data = await proxy_logging_obj.pre_call_hook( @@ -3176,7 +3182,7 @@ class MCPServerManager: def _create_during_hook_task( self, name: str, - arguments: Dict[str, Any], + arguments: dict[str, Any], server_name_from_prefix: Optional[str], user_api_key_auth: Optional[UserAPIKeyAuth], proxy_logging_obj: ProxyLogging, @@ -3211,19 +3217,38 @@ class MCPServerManager: ) ) + def _get_call_semaphore(self, mcp_server: MCPServer) -> Optional[asyncio.Semaphore]: + limit = mcp_server.max_concurrent_requests + if limit is None or limit <= 0: + return None + semaphore = self._server_call_semaphores.get(mcp_server.server_id) + if semaphore is None: + semaphore = asyncio.Semaphore(limit) + self._server_call_semaphores[mcp_server.server_id] = semaphore + return semaphore + + @asynccontextmanager + async def _limit_outbound_concurrency(self, mcp_server: MCPServer) -> AsyncIterator[None]: + semaphore = self._get_call_semaphore(mcp_server) + if semaphore is None: + yield + return + async with semaphore: + yield + async def _call_regular_mcp_tool( self, mcp_server: MCPServer, original_tool_name: str, - arguments: Dict[str, Any], - tasks: List, + arguments: dict[str, Any], + tasks: list, mcp_auth_header: Optional[str], - mcp_server_auth_headers: Optional[Dict[str, Dict[str, str]]], - oauth2_headers: Optional[Dict[str, str]], - raw_headers: Optional[Dict[str, str]], + mcp_server_auth_headers: Optional[dict[str, dict[str, str]]], + oauth2_headers: Optional[dict[str, str]], + raw_headers: Optional[dict[str, str]], proxy_logging_obj: Optional[ProxyLogging], host_progress_callback: Optional[Callable] = None, - hook_extra_headers: Optional[Dict[str, str]] = None, + hook_extra_headers: Optional[dict[str, str]] = None, user_api_key_auth: Optional[UserAPIKeyAuth] = None, ) -> CallToolResult: """ @@ -3254,7 +3279,7 @@ class MCPServerManager: # Get server-specific auth header if available (case-insensitive) # FIX: Added case-insensitive matching to handle auth header keys that may not match # the exact case of server alias/name (e.g., '1litellmagcgateway' vs '1LiteLLMAGCGateway') - server_auth_header: Optional[Union[Dict[str, str], str]] = None + server_auth_header: Optional[Union[dict[str, str], str]] = None if mcp_server_auth_headers: # Normalize keys for case-insensitive lookup from litellm.proxy._experimental.mcp_server.utils import ( @@ -3273,7 +3298,7 @@ class MCPServerManager: # Extract subject token for OAuth2 Token Exchange (OBO) flow subject_token: Optional[str] = None - extra_headers: Optional[Dict[str, str]] = None + extra_headers: Optional[dict[str, str]] = None if mcp_server.auth_type == MCPAuth.oauth2_token_exchange: subject_token = self._extract_bearer_token(oauth2_headers, raw_headers) elif mcp_server.auth_type == MCPAuth.oauth2: @@ -3370,7 +3395,8 @@ class MCPServerManager: ) async def _call_tool_via_client(client, params): - return await client.call_tool(params, host_progress_callback=host_progress_callback) + async with self._limit_outbound_concurrency(mcp_server): + return await client.call_tool(params, host_progress_callback=host_progress_callback) tasks.append(asyncio.create_task(_call_tool_via_client(client, call_tool_params))) @@ -3460,9 +3486,9 @@ class MCPServerManager: async def _resolve_oauth2_headers_for_tool_call( self, mcp_server: MCPServer, - oauth2_headers: Optional[Dict[str, str]], + oauth2_headers: Optional[dict[str, str]], user_api_key_auth: Optional[UserAPIKeyAuth], - ) -> Optional[Dict[str, str]]: + ) -> Optional[dict[str, str]]: """Look up per-user OAuth headers when the client did not supply a token.""" if not mcp_server.needs_user_oauth_token or oauth2_headers or user_api_key_auth is None: return oauth2_headers @@ -3499,7 +3525,7 @@ class MCPServerManager: async def _gather_openapi_tool_tasks( self, - tasks: List[Any], + tasks: list[Any], proxy_logging_obj: Optional[ProxyLogging], ) -> CallToolResult: """Await OpenAPI tool tasks and return the tool call result.""" @@ -3519,13 +3545,13 @@ class MCPServerManager: self, server_name: str, name: str, - arguments: Dict[str, Any], + arguments: dict[str, Any], user_api_key_auth: Optional[UserAPIKeyAuth] = None, mcp_auth_header: Optional[str] = None, - mcp_server_auth_headers: Optional[Dict[str, Dict[str, str]]] = None, + mcp_server_auth_headers: Optional[dict[str, dict[str, str]]] = None, proxy_logging_obj: Optional[ProxyLogging] = None, - oauth2_headers: Optional[Dict[str, str]] = None, - raw_headers: Optional[Dict[str, str]] = None, + oauth2_headers: Optional[dict[str, str]] = None, + raw_headers: Optional[dict[str, str]] = None, host_progress_callback: Optional[Callable] = None, ) -> CallToolResult: """ @@ -3552,7 +3578,7 @@ class MCPServerManager: # Allow validation and modification of tool calls before execution # Using standard pre_call_hook ######################################################### - hook_result: Dict[str, Any] = {} + hook_result: dict[str, Any] = {} if proxy_logging_obj: hook_result = await self.pre_call_tool_check( name=name, @@ -3592,7 +3618,12 @@ class MCPServerManager: "transport to enable hook header injection.", server_name, ) - tasks.append(asyncio.create_task(self._call_openapi_tool_handler(mcp_server, name, arguments))) + + async def _call_openapi_via_handler(): + async with self._limit_outbound_concurrency(mcp_server): + return await self._call_openapi_tool_handler(mcp_server, name, arguments) + + tasks.append(asyncio.create_task(_call_openapi_via_handler())) else: return await self._call_regular_mcp_tool( mcp_server=mcp_server, @@ -3673,7 +3704,7 @@ class MCPServerManager: # Build prefix β†’ server lookup covering every known form a tool name # may take (alias / server_name / server_id / short ID). This is what # makes the short-prefix mode work without breaking historical names. - prefix_to_server: Dict[str, MCPServer] = {} + prefix_to_server: dict[str, MCPServer] = {} for server in registry_servers: for known_prefix in iter_known_server_prefixes(server): normalised = normalize_server_name(known_prefix) @@ -3734,7 +3765,7 @@ class MCPServerManager: verbose_logger.info(f"Found {len(db_mcp_servers)} MCP servers in database") previous_registry = self.registry - new_registry: Dict[str, MCPServer] = {} + new_registry: dict[str, MCPServer] = {} # Stage one: build every server. Stage two assigns short prefixes # against the *full* set so dedup is deterministic regardless of @@ -3780,7 +3811,7 @@ class MCPServerManager: # Assign short prefixes against the full candidate set without # publishing the staged registry to concurrent callers. - registered_registry: Dict[str, MCPServer] = {} + registered_registry: dict[str, MCPServer] = {} registered_openapi_tools = False for server_id, new_server in new_registry.items(): try: @@ -3806,7 +3837,7 @@ class MCPServerManager: verbose_logger.debug("MCP registry refreshed (%s servers in registry)", len(registered_registry)) - def get_mcp_servers_from_ids(self, server_ids: List[str]) -> List[MCPServer]: + def get_mcp_servers_from_ids(self, server_ids: list[str]) -> list[MCPServer]: servers = [] registry = self.get_registry() for server in registry.values(): @@ -3814,7 +3845,7 @@ class MCPServerManager: servers.append(server) return servers - def _get_general_settings(self) -> Dict[str, Any]: + def _get_general_settings(self) -> dict[str, Any]: """Get general_settings, importing lazily to avoid circular imports.""" try: from litellm.proxy.proxy_server import ( @@ -3857,7 +3888,7 @@ class MCPServerManager: return server return None - def get_public_mcp_servers(self) -> List[MCPServer]: + def get_public_mcp_servers(self) -> list[MCPServer]: """ Return the MCP servers published to the AI Hub via /v1/mcp/make_public. @@ -3887,7 +3918,7 @@ class MCPServerManager: if server.available_on_public_internet or server.server_id in public_ids ] - def expand_permission_list(self, identifiers: List[str]) -> List[str]: + def expand_permission_list(self, identifiers: list[str]) -> list[str]: """ Expand a permission list of server_ids/names/aliases into concrete server_ids against the current region's config + DB registry union. @@ -3903,12 +3934,12 @@ class MCPServerManager: if not identifiers: return [] registry = self.get_registry() - expanded: Set[str] = set() + expanded: set[str] = set() for identifier in identifiers: if identifier in registry: expanded.add(identifier) continue - matches: List[str] = [ + matches: list[str] = [ server_id for server_id, server in registry.items() if server.alias == identifier or server.server_name == identifier or server.name == identifier @@ -3929,8 +3960,8 @@ class MCPServerManager: def expand_tool_permissions( self, - tool_permissions: Optional[Dict[str, List[str]]], - ) -> Dict[str, List[str]]: + tool_permissions: Optional[dict[str, list[str]]], + ) -> dict[str, list[str]]: """ Rewrite an ``mcp_tool_permissions`` dict keyed by id/name/alias so every key is a concrete server_id where possible. Tool lists from @@ -3945,7 +3976,7 @@ class MCPServerManager: """ if not tool_permissions: return {} - result: Dict[str, List[str]] = {} + result: dict[str, list[str]] = {} for key, tools in tool_permissions.items(): for server_id in self.expand_permission_list([key]): result.setdefault(server_id, []).extend(tools or []) @@ -3986,7 +4017,7 @@ class MCPServerManager: return server return None - def get_filtered_registry(self, client_ip: Optional[str] = None) -> Dict[str, MCPServer]: + def get_filtered_registry(self, client_ip: Optional[str] = None) -> dict[str, MCPServer]: """ Get registry filtered by client IP access control. @@ -4149,13 +4180,14 @@ class MCPServerManager: allow_all_keys=server.allow_all_keys, instructions=server.instructions, timeout=server.timeout, + max_concurrent_requests=server.max_concurrent_requests, ) async def get_all_mcp_servers_with_health_and_teams( self, user_api_key_auth: Optional[UserAPIKeyAuth] = None, - server_ids: Optional[List[str]] = None, - ) -> List[LiteLLM_MCPServerTable]: + server_ids: Optional[list[str]] = None, + ) -> list[LiteLLM_MCPServerTable]: """ Get all MCP servers that the user has access to, with health status and team information. @@ -4184,7 +4216,7 @@ class MCPServerManager: async def get_all_allowed_mcp_servers( self, user_api_key_auth: Optional[UserAPIKeyAuth] = None, - ) -> List[LiteLLM_MCPServerTable]: + ) -> list[LiteLLM_MCPServerTable]: """ Get all MCP servers that the user has access to. @@ -4197,7 +4229,7 @@ class MCPServerManager: # Get allowed server IDs allowed_server_ids = await self.get_allowed_mcp_servers(user_api_key_auth) - list_mcp_servers: List[LiteLLM_MCPServerTable] = [] + list_mcp_servers: list[LiteLLM_MCPServerTable] = [] for server_id in allowed_server_ids: server = self.get_mcp_server_by_id(server_id) @@ -4212,8 +4244,8 @@ class MCPServerManager: @staticmethod def _env_vars_to_models( - env_vars: Optional[List[Dict[str, Any]]], - ) -> Optional[List[MCPEnvVar]]: + env_vars: Optional[list[dict[str, Any]]], + ) -> Optional[list[MCPEnvVar]]: if env_vars is None: return None return [MCPEnvVar.model_validate(env_var) for env_var in env_vars] @@ -4256,23 +4288,24 @@ class MCPServerManager: source_url=server.source_url, instructions=server.instructions, timeout=server.timeout, + max_concurrent_requests=server.max_concurrent_requests, ) - async def get_all_mcp_servers_unfiltered(self) -> List[LiteLLM_MCPServerTable]: + async def get_all_mcp_servers_unfiltered(self) -> list[LiteLLM_MCPServerTable]: """Return all MCP servers from registry without applying access controls.""" registry = self.get_registry() if not registry: return [] - servers: List[LiteLLM_MCPServerTable] = [] + servers: list[LiteLLM_MCPServerTable] = [] for server in registry.values(): servers.append(self._build_mcp_server_table(server)) return servers async def get_all_mcp_servers_with_health_unfiltered( - self, server_ids: Optional[List[str]] = None - ) -> List[LiteLLM_MCPServerTable]: + self, server_ids: Optional[list[str]] = None + ) -> list[LiteLLM_MCPServerTable]: """Return health info for all servers in registry regardless of user access.""" registry = self.get_registry() @@ -4289,7 +4322,7 @@ class MCPServerManager: return await self._run_health_checks(target_server_ids) - async def _run_health_checks(self, target_server_ids: List[str]) -> List[LiteLLM_MCPServerTable]: + async def _run_health_checks(self, target_server_ids: list[str]) -> list[LiteLLM_MCPServerTable]: if not target_server_ids: return [] diff --git a/litellm/proxy/_types.py b/litellm/proxy/_types.py index 12466b525d6..78bcdc490dc 100644 --- a/litellm/proxy/_types.py +++ b/litellm/proxy/_types.py @@ -1261,6 +1261,7 @@ class NewMCPServerRequest(LiteLLMPydanticObjectBase): byok_api_key_help_url: Optional[str] = None source_url: Optional[str] = None timeout: Optional[float] = None + max_concurrent_requests: Optional[int] = None # BYOM submission fields β€” set by the endpoint, not by the caller. # Any caller-provided values are silently overridden before persistence. approval_status: Optional[str] = Field( @@ -1346,6 +1347,7 @@ class UpdateMCPServerRequest(LiteLLMPydanticObjectBase): byok_api_key_help_url: Optional[str] = None source_url: Optional[str] = None timeout: Optional[float] = None + max_concurrent_requests: Optional[int] = None @model_validator(mode="before") @classmethod diff --git a/litellm/proxy/anthropic_endpoints/endpoints.py b/litellm/proxy/anthropic_endpoints/endpoints.py index 71acc1f3106..92279a9e685 100644 --- a/litellm/proxy/anthropic_endpoints/endpoints.py +++ b/litellm/proxy/anthropic_endpoints/endpoints.py @@ -12,6 +12,9 @@ from litellm.integrations.custom_guardrail import ModifyResponseException from litellm.llms.anthropic.experimental_pass_through.context_management import ( AnthropicContextManagementError, ) +from litellm.llms.base_llm.guardrail_translation.utils import ( + blocked_response_usage as _blocked_response_usage, +) from litellm.proxy._types import * from litellm.proxy.auth.user_api_key_auth import user_api_key_auth from litellm.proxy.common_request_processing import ( @@ -134,6 +137,10 @@ async def anthropic_response( from litellm.types.utils import AnthropicMessagesResponse + # Report the blocked LLM response's real token usage (carried on the + # exception) instead of discarding it; zero for pre-call blocks. + _usage = _blocked_response_usage(e.original_response) + _anthropic_response = AnthropicMessagesResponse( id=f"msg_{str(uuid.uuid4())}", type="message", @@ -141,7 +148,7 @@ async def anthropic_response( content=[{"type": "text", "text": e.message}], model=e.model, stop_reason="end_turn", - usage={"input_tokens": 0, "output_tokens": 0}, + usage=_usage, ) if data.get("stream", None) is not None and data["stream"] is True: diff --git a/litellm/proxy/auth/auth_checks.py b/litellm/proxy/auth/auth_checks.py index ced2cf125ce..41468a9ec05 100644 --- a/litellm/proxy/auth/auth_checks.py +++ b/litellm/proxy/auth/auth_checks.py @@ -3017,7 +3017,9 @@ async def can_key_call_resolved_model( ) skip_key_model_check = valid_token.config or ( - isinstance(valid_token.models, list) and SpecialModelNames.all_team_models.value in valid_token.models + isinstance(valid_token.models, list) + and SpecialModelNames.all_team_models.value in valid_token.models + and valid_token.team_id is not None ) if not skip_key_model_check: await can_key_call_model( diff --git a/litellm/proxy/auth/auth_utils.py b/litellm/proxy/auth/auth_utils.py index 2bf0acc7232..3c508df0cc9 100644 --- a/litellm/proxy/auth/auth_utils.py +++ b/litellm/proxy/auth/auth_utils.py @@ -375,6 +375,16 @@ def is_request_body_safe(request_body: dict, general_settings: dict, llm_router: metadata = _coerce_metadata_to_dict(request_body.get(metadata_key)) if metadata is not None: _check_banned_params(metadata, general_settings, llm_router, model) + litellm_params = _coerce_metadata_to_dict(request_body.get("litellm_params")) + if litellm_params is not None: + litellm_params_metadata = _coerce_metadata_to_dict(litellm_params.get("metadata")) + if litellm_params_metadata is not None: + _check_banned_params( + litellm_params_metadata, + general_settings, + llm_router, + model, + ) return True diff --git a/litellm/proxy/auth/user_api_key_auth.py b/litellm/proxy/auth/user_api_key_auth.py index 73f9def822b..a28c8be9408 100644 --- a/litellm/proxy/auth/user_api_key_auth.py +++ b/litellm/proxy/auth/user_api_key_auth.py @@ -2676,7 +2676,11 @@ async def _enforce_key_and_fallback_model_access( model_list = config.get("model_list", []) new_model_list = model_list verbose_proxy_logger.debug(f"\n new llm router model list {new_model_list}") - elif isinstance(valid_token.models, list) and "all-team-models" in valid_token.models: + elif ( + isinstance(valid_token.models, list) + and "all-team-models" in valid_token.models + and valid_token.team_id is not None + ): pass else: model = _get_model_from_request_context( diff --git a/litellm/proxy/guardrails/guardrail_hooks/unified_guardrail/unified_guardrail.py b/litellm/proxy/guardrails/guardrail_hooks/unified_guardrail/unified_guardrail.py index 79c29670d93..e0b387e92c0 100644 --- a/litellm/proxy/guardrails/guardrail_hooks/unified_guardrail/unified_guardrail.py +++ b/litellm/proxy/guardrails/guardrail_hooks/unified_guardrail/unified_guardrail.py @@ -8,7 +8,7 @@ Unified Guardrail, leveraging LiteLLM's /applyGuardrail endpoint import copy import json -from typing import Any, AsyncGenerator, List, Optional, Union +from typing import TYPE_CHECKING, Any, AsyncGenerator, List, Optional, Union from fastapi import HTTPException @@ -23,6 +23,11 @@ from litellm.proxy._types import UserAPIKeyAuth from litellm.types.guardrails import GuardrailEventHooks from litellm.types.utils import CallTypes, CallTypesLiteral +if TYPE_CHECKING: + # Imported lazily at runtime (inside the streaming hook) to avoid a + # module-level cyclic import with litellm.integrations.custom_guardrail. + from litellm.integrations.custom_guardrail import ModifyResponseException + # Call types that use NDJSON streaming (A2A); guardrail HTTPException is emitted as in-stream error A2A_CALL_TYPES = (CallTypes.asend_message, CallTypes.send_message) @@ -197,6 +202,10 @@ class UnifiedLLMGuardrails(CustomLogger): ) from litellm.types.guardrails import GuardrailEventHooks + # Local import avoids a module-level cyclic import with + # litellm.integrations.custom_guardrail. + from litellm.integrations.custom_guardrail import ModifyResponseException + guardrail_to_apply: CustomGuardrail = data.pop("guardrail_to_apply", None) if guardrail_to_apply is None: @@ -238,18 +247,51 @@ class UnifiedLLMGuardrails(CustomLogger): endpoint_translation = endpoint_guardrail_translation_mappings[CallTypes(call_type)]() - response = await endpoint_translation.process_output_response( - response=response, # type: ignore - guardrail_to_apply=guardrail_to_apply, - litellm_logging_obj=data.get("litellm_logging_obj"), - user_api_key_dict=user_api_key_dict, - request_data=data, - ) + try: + response = await endpoint_translation.process_output_response( + response=response, # type: ignore + guardrail_to_apply=guardrail_to_apply, + litellm_logging_obj=data.get("litellm_logging_obj"), + user_api_key_dict=user_api_key_dict, + request_data=data, + ) + except ModifyResponseException as e: + # The guardrail blocked the response. Attach the original LLM + # response so the endpoint handler can report its real token usage + # instead of discarding it (the block replaces the content, but the + # upstream call already consumed those tokens). + if e.original_response is None: + e.original_response = response + raise # Add guardrail to applied guardrails header add_guardrail_to_applied_guardrails_header(request_data=data, guardrail_name=guardrail_to_apply.guardrail_name) return response + async def _handle_streaming_block( + self, + exc: "ModifyResponseException", + endpoint_translation: Any, + stream_started: bool, + responses_so_far: list[Any], + ) -> AsyncGenerator[Any, None]: + """ + Terminate a streamed response cleanly when a guardrail blocks it. + + Format-agnostic routing: delegates to the provider translation handler's + ``build_block_sse_chunks`` (see ``BaseTranslation.build_block_sse_chunks`` + for the ``stream_started`` / ``responses_so_far`` contract). When the + format has no safe terminator the handler returns None and we re-raise + ``exc`` so the proxy can surface a clean error. + """ + block_chunks = endpoint_translation.build_block_sse_chunks( + exc, stream_started=stream_started, responses_so_far=responses_so_far + ) + if block_chunks is None: + raise exc + for chunk in block_chunks: + yield chunk + async def async_post_call_streaming_iterator_hook( self, user_api_key_dict: UserAPIKeyAuth, @@ -271,26 +313,53 @@ class UnifiedLLMGuardrails(CustomLogger): global endpoint_guardrail_translation_mappings + # Local import avoids a module-level cyclic import with + # litellm.integrations.custom_guardrail. + from litellm.integrations.custom_guardrail import ModifyResponseException + guardrail_to_apply: CustomGuardrail = request_data.pop("guardrail_to_apply", None) - # Get streaming configuration from guardrail or optional_params - sampling_rate = 5 - end_of_stream_only = False # If True, only apply guardrail at end of stream + # Get streaming configuration. Resolution order (later wins): default + # < guardrail attribute < guardrail_config dict < this callback's + # optional_params. + def _streaming_flag(name: str, default: Any) -> Any: + value = default + if guardrail_to_apply is not None: + value = getattr(guardrail_to_apply, name, value) + config = getattr(guardrail_to_apply, "guardrail_config", {}) + if isinstance(config, dict): + value = config.get(name, value) + return self.optional_params.get(name, value) - if guardrail_to_apply is not None: - # Check direct attributes on guardrail first - sampling_rate = getattr(guardrail_to_apply, "streaming_sampling_rate", sampling_rate) - end_of_stream_only = getattr(guardrail_to_apply, "streaming_end_of_stream_only", end_of_stream_only) + sampling_rate = _streaming_flag("streaming_sampling_rate", 5) + # Only apply the guardrail at end of stream (not per chunk). + end_of_stream_only = _streaming_flag("streaming_end_of_stream_only", False) + # Withhold every chunk until end-of-stream moderation passes, then + # release the original chunks (clean) or only the block message + # (blocked) -- moderating the whole response *before* any content + # reaches the client. Only safe for allow/block guardrails: on + # release the original chunks are replayed as-is, so a + # content-rewriting guardrail (e.g. PII masking) would leak + # unredacted content. Guarded below via mask_response_content. + buffer_until_moderated = _streaming_flag("streaming_buffer_until_moderated", False) - # Also check guardrail_config dict if present - guardrail_config = getattr(guardrail_to_apply, "guardrail_config", {}) - if isinstance(guardrail_config, dict): - sampling_rate = guardrail_config.get("streaming_sampling_rate", sampling_rate) - end_of_stream_only = guardrail_config.get("streaming_end_of_stream_only", end_of_stream_only) + if ( + buffer_until_moderated + and guardrail_to_apply is not None + and getattr(guardrail_to_apply, "mask_response_content", False) + ): + verbose_proxy_logger.warning( + "UnifiedLLMGuardrails: streaming_buffer_until_moderated is disabled for %s " + "because mask_response_content=True -- buffered replay would release " + "unredacted original chunks instead of the moderated output.", + guardrail_to_apply.guardrail_name, + ) + buffer_until_moderated = False - # Also check optional_params as fallback - sampling_rate = self.optional_params.get("streaming_sampling_rate", sampling_rate) - end_of_stream_only = self.optional_params.get("streaming_end_of_stream_only", end_of_stream_only) + # Buffering can only moderate the assembled response, so it always + # defers to end-of-stream. + if buffer_until_moderated: + end_of_stream_only = True if guardrail_to_apply is None: async for item in response: @@ -315,6 +384,12 @@ class UnifiedLLMGuardrails(CustomLogger): call_type = None chunk_counter = 0 responses_so_far: List[Any] = [] + responses_yielded: list[Any] = [] + pending_end_of_stream_items: list[Any] = [] + # Whether any real response chunk has been forwarded to the client. + # Drives how a block terminates the stream: continue the in-progress + # message (True) vs emit a standalone block message (False, buffered). + chunks_yielded = False async for item in response: chunk_counter += 1 @@ -336,9 +411,22 @@ class UnifiedLLMGuardrails(CustomLogger): yield remaining_item return - # If end_of_stream_only mode, yield chunks without processing + # If end_of_stream_only mode, yield chunks without processing. + # When buffering, withhold them instead -- they are released (or + # replaced by the block message) only after end-of-stream + # moderation runs below. if end_of_stream_only: - yield item + if not buffer_until_moderated: + endpoint_translation = endpoint_guardrail_translation_mappings[CallTypes(call_type)]() + stream_has_ended = hasattr( + endpoint_translation, "_check_streaming_has_ended" + ) and endpoint_translation._check_streaming_has_ended(responses_so_far) + if pending_end_of_stream_items or stream_has_ended: + pending_end_of_stream_items.append(item) + else: + chunks_yielded = True + responses_yielded.append(item) + yield item continue # Process chunk based on sampling rate @@ -368,6 +456,26 @@ class UnifiedLLMGuardrails(CustomLogger): user_api_key_dict=user_api_key_dict, request_data=request_data, ) + except ModifyResponseException as e: + if e.original_response is None: + e.original_response = responses_so_far + # Guardrail blocked the response mid-stream. Emit a clean + # terminating SSE sequence delivering the block message + # instead of letting the exception propagate into a bare + # `data: {"error": ...}` blob (which truncates the stream). + # Chunks have already been forwarded here, so the block + # continues the in-progress message (stream_started=True). + # The current chunk was appended to responses_so_far but not + # yet yielded, so exclude it: the continuation must reflect + # only what the client has actually received. + async for block_chunk in self._handle_streaming_block( + e, + endpoint_translation, + stream_started=chunks_yielded, + responses_so_far=responses_yielded, + ): + yield block_chunk + return except HTTPException as e: # Response already started (we already yielded chunks); cannot send 400. # For A2A (NDJSON), yield an in-stream JSON-RPC error so the client sees it. @@ -394,8 +502,12 @@ class UnifiedLLMGuardrails(CustomLogger): yield error_chunk return raise + chunks_yielded = True + responses_yielded.append(original_item) yield original_item else: + chunks_yielded = True + responses_yielded.append(item) yield item # Stream has ended - do final processing with all collected chunks @@ -408,6 +520,15 @@ class UnifiedLLMGuardrails(CustomLogger): endpoint_translation = endpoint_guardrail_translation_mappings[CallTypes(call_type)]() + # When buffering, snapshot the original chunks before moderation. + # A shallow copy suffices: end-of-stream + # process_output_streaming_response builds a separate assembled + # response (it does not mutate the individual chunks in place), and + # the chunks themselves are replayed verbatim -- so we only need to + # preserve the list, not clone every chunk (deepcopy would double + # peak memory for large responses). + buffered_items = list(responses_so_far) if buffer_until_moderated else None + try: await endpoint_translation.process_output_streaming_response( responses_so_far=responses_so_far, @@ -416,6 +537,28 @@ class UnifiedLLMGuardrails(CustomLogger): user_api_key_dict=user_api_key_dict, request_data=request_data, ) + # Moderation passed: release the withheld original chunks. + if buffered_items is not None: + for buffered_item in buffered_items: + yield buffered_item + for pending_item in pending_end_of_stream_items: + responses_yielded.append(pending_item) + yield pending_item + except ModifyResponseException as e: + if e.original_response is None: + e.original_response = responses_so_far + # Block detected during end-of-stream processing. Emit a clean + # terminating SSE sequence with the block message rather than + # propagating into a bare error blob that truncates the stream. + # The withheld original chunks are never released. + async for block_chunk in self._handle_streaming_block( + e, + endpoint_translation, + stream_started=bool(responses_yielded), + responses_so_far=responses_yielded, + ): + yield block_chunk + return except HTTPException as e: if call_type is not None and CallTypes(call_type) in A2A_CALL_TYPES: request_id = _get_a2a_request_id(responses_so_far, request_data) diff --git a/litellm/proxy/litellm_pre_call_utils.py b/litellm/proxy/litellm_pre_call_utils.py index 6f5c82530e3..afd8a437cc1 100644 --- a/litellm/proxy/litellm_pre_call_utils.py +++ b/litellm/proxy/litellm_pre_call_utils.py @@ -15,6 +15,9 @@ from litellm._logging import verbose_logger, verbose_proxy_logger from litellm._service_logger import ServiceLogging from litellm.constants import PRE_CALL_EXECUTED_GUARDRAILS_KEY from litellm.litellm_core_utils.credential_accessor import CredentialAccessor +from litellm.litellm_core_utils.initialize_dynamic_callback_params import ( + iter_client_callback_metadata_dicts, +) from litellm.litellm_core_utils.safe_json_loads import safe_json_loads from litellm.litellm_core_utils.url_utils import is_url_destination_allowed_by_host from litellm.proxy._types import ( @@ -302,6 +305,24 @@ def _key_or_team_allows_client_pricing_override( ) +def _strip_client_message_redaction_opt_out(data: dict[str, Any]) -> None: + stripped: list[str] = [] + if "turn_off_message_logging" in data and _is_false_like(data["turn_off_message_logging"]): + stripped.append("turn_off_message_logging") + data.pop("turn_off_message_logging", None) + for slot_label, metadata in iter_client_callback_metadata_dicts(data): + if "turn_off_message_logging" in metadata and _is_false_like(metadata["turn_off_message_logging"]): + stripped.append(f"{slot_label}.turn_off_message_logging") + metadata.pop("turn_off_message_logging", None) + if stripped: + verbose_proxy_logger.debug( + "Stripped client-supplied message-redaction opt-out fields from request body: %s. " + "Set `allow_client_message_redaction_opt_out: true` on the key or team metadata " + "to keep these values.", + ", ".join(stripped), + ) + + def _strip_client_pricing_overrides(data: Dict[str, Any]) -> None: """Drop pricing overrides from the request body and any metadata variant. @@ -1308,13 +1329,6 @@ async def add_litellm_data_to_request( _headers, allow_client_message_redaction_opt_out=_allow_client_message_redaction_opt_out, ) - if ( - not _allow_client_message_redaction_opt_out - and litellm.turn_off_message_logging is True - and "turn_off_message_logging" in data - and _is_false_like(data["turn_off_message_logging"]) - ): - data.pop("turn_off_message_logging", None) verbose_proxy_logger.debug(f"Request Headers: {_headers}") verbose_proxy_logger.debug(f"Raw Headers: {_raw_headers}") @@ -1466,6 +1480,9 @@ async def add_litellm_data_to_request( if not _key_or_team_allows_client_pricing_override(user_api_key_dict): _strip_client_pricing_overrides(data) + if not _allow_client_message_redaction_opt_out and litellm.turn_off_message_logging is True: + _strip_client_message_redaction_opt_out(data) + # Fill in the proxy_server_request body snapshot now that metadata has # been parsed. Consumers (standard_logging_payload, lago, # spend_tracking_utils, streaming_iterator) read `body` to audit the @@ -1649,6 +1666,16 @@ async def add_litellm_data_to_request( tags_to_add=tags, ) + if _metadata_variable_name != "metadata": + _user_metadata = data.get("metadata") + if isinstance(_user_metadata, dict): + _user_tags = _user_metadata.get("tags") + if isinstance(_user_tags, list) and _user_tags: + data[_metadata_variable_name]["tags"] = LiteLLMProxyRequestSetup._merge_tags( + request_tags=data[_metadata_variable_name].get("tags"), + tags_to_add=_user_tags, + ) + # Team Callbacks controls callback_settings_obj = _get_dynamic_logging_metadata( user_api_key_dict=user_api_key_dict, proxy_config=proxy_config diff --git a/litellm/proxy/management_endpoints/internal_user_endpoints.py b/litellm/proxy/management_endpoints/internal_user_endpoints.py index 9374aa3180b..d98dcf984b2 100644 --- a/litellm/proxy/management_endpoints/internal_user_endpoints.py +++ b/litellm/proxy/management_endpoints/internal_user_endpoints.py @@ -39,6 +39,7 @@ from litellm.proxy.management_endpoints.common_utils import ( validate_finite_spend, ) from litellm.proxy.management_endpoints.key_management_endpoints import ( + _check_permissions_caller_permission, generate_key_helper_fn, prepare_metadata_fields, ) @@ -440,6 +441,11 @@ async def new_user( detail=f"Only proxy admins can create administrative users (proxy_admin, proxy_admin_viewer). Attempted to create user with role: {data.user_role}. Your role: {user_api_key_dict.user_role}", ) + _check_permissions_caller_permission( + data=data, + user_api_key_dict=user_api_key_dict, + ) + data_json = data.json() # type: ignore data_json = _update_internal_new_user_params(data_json, data) _hash_password_in_dict(data_json) @@ -1198,6 +1204,11 @@ async def _update_single_user_helper( if not user_request.user_id and not user_request.user_email: raise ValueError("Either user_id or user_email must be provided") + _check_permissions_caller_permission( + data=user_request, + user_api_key_dict=user_api_key_dict, + ) + data_json: dict = user_request.model_dump(exclude_unset=True) non_default_values = _update_internal_user_params(data_json=data_json, data=user_request) _hash_password_in_dict(non_default_values) diff --git a/litellm/proxy/management_endpoints/key_management_endpoints.py b/litellm/proxy/management_endpoints/key_management_endpoints.py index f0473edded5..ade865a5378 100644 --- a/litellm/proxy/management_endpoints/key_management_endpoints.py +++ b/litellm/proxy/management_endpoints/key_management_endpoints.py @@ -530,26 +530,33 @@ def _check_allowed_routes_caller_permission( allowed_routes: Optional[list], user_api_key_dict: UserAPIKeyAuth, *, + allowed_routes_was_provided: bool = False, allow_safe_presets: bool = False, ) -> None: """ - Only proxy admins may set `allowed_routes` on a key. + Require PROXY_ADMIN when `allowed_routes` is present in the request body, + unless the caller went through the `key_type` preset flow. - `allowed_routes` overrides the standard role-based route gate in - RouteChecks.non_proxy_admin_allowed_routes_check, so the field is - restricted to admins. Non-admins must instead use `key_type` to pick a - preset bucket β€” that path goes through `handle_key_type` and re-enters - this function with `allow_safe_presets=True`, which lets the derived - `llm_api_routes` / `info_routes` values through. Raw-body call sites - leave `allow_safe_presets=False` so non-admins can't write those values - directly. + Raw-body call sites pass + `allowed_routes_was_provided="allowed_routes" in data.model_fields_set` so a + caller that omits the field (model default flows through) is distinct from + one that sends any explicit value. + + Post-`handle_key_type` call sites pass `allow_safe_presets=True` with the + values derived by `handle_key_type`; those values are not from the request + body, so `allowed_routes_was_provided` stays False and the safe-preset + carve-out below accepts any list of tokens in + `_NON_ADMIN_SAFE_ALLOWED_ROUTES_PRESETS`. """ - # Empty list is the default on GenerateKeyRequest β€” treat as "not set". - if not allowed_routes: + if not allowed_routes_was_provided and not allowed_routes: return if user_api_key_dict.user_role == LitellmUserRoles.PROXY_ADMIN.value: return - if allow_safe_presets and all(r in _NON_ADMIN_SAFE_ALLOWED_ROUTES_PRESETS for r in allowed_routes): + if ( + allow_safe_presets + and allowed_routes + and all(r in _NON_ADMIN_SAFE_ALLOWED_ROUTES_PRESETS for r in allowed_routes) + ): return raise HTTPException( status_code=403, @@ -580,7 +587,7 @@ def _check_permissions_caller_permission( return raise HTTPException( status_code=403, - detail={"error": "Only proxy admins can set `permissions` on a key."}, + detail={"error": "Only proxy admins can set `permissions`."}, ) @@ -1566,6 +1573,7 @@ async def generate_key_fn( _check_allowed_routes_caller_permission( allowed_routes=data.allowed_routes, user_api_key_dict=user_api_key_dict, + allowed_routes_was_provided="allowed_routes" in data.model_fields_set, ) _check_passthrough_routes_caller_permission( data=data, @@ -1736,6 +1744,7 @@ async def generate_service_account_key_fn( _check_allowed_routes_caller_permission( allowed_routes=data.allowed_routes, user_api_key_dict=user_api_key_dict, + allowed_routes_was_provided="allowed_routes" in data.model_fields_set, ) _check_passthrough_routes_caller_permission( data=data, @@ -2060,6 +2069,11 @@ async def _process_single_key_update( # Validate max_budget _validate_max_budget(update_key_request.max_budget) + _check_permissions_caller_permission( + data=update_key_request, + user_api_key_dict=user_api_key_dict, + ) + # Get and validate existing key if existing_key_row is None: existing_key_row = await _get_and_validate_existing_key( @@ -2231,6 +2245,7 @@ async def _validate_update_key_data( _check_allowed_routes_caller_permission( allowed_routes=data.allowed_routes, user_api_key_dict=user_api_key_dict, + allowed_routes_was_provided="allowed_routes" in data.model_fields_set, ) _check_passthrough_routes_caller_permission( data=data, @@ -4551,6 +4566,7 @@ async def regenerate_key_fn( _check_allowed_routes_caller_permission( allowed_routes=data.allowed_routes, user_api_key_dict=user_api_key_dict, + allowed_routes_was_provided="allowed_routes" in data.model_fields_set, ) _check_passthrough_routes_caller_permission( data=data, diff --git a/litellm/proxy/management_endpoints/mcp_management_endpoints.py b/litellm/proxy/management_endpoints/mcp_management_endpoints.py index 9dab3498bc1..cb3daa84a0b 100644 --- a/litellm/proxy/management_endpoints/mcp_management_endpoints.py +++ b/litellm/proxy/management_endpoints/mcp_management_endpoints.py @@ -654,6 +654,7 @@ if MCP_AVAILABLE: allow_all_keys=payload.allow_all_keys, available_on_public_internet=payload.available_on_public_internet, timeout=payload.timeout, + max_concurrent_requests=payload.max_concurrent_requests, ) def get_prisma_client_or_throw(message: str): diff --git a/litellm/proxy/proxy_server.py b/litellm/proxy/proxy_server.py index a29acf3b06f..bb925799bb8 100644 --- a/litellm/proxy/proxy_server.py +++ b/litellm/proxy/proxy_server.py @@ -8361,6 +8361,22 @@ async def model_info( ) +def _blocked_response_usage(original_response: Optional[Any]) -> "litellm.Usage": + """ + Token usage for a synthetic guardrail-blocked response. + + A post-call block replaces the LLM's response with the violation message, + but the upstream call already consumed tokens -- report that real usage + (carried on ``ModifyResponseException.original_response``) rather than + discarding it. Pre-call blocks never invoked the LLM (no original_response), + so usage is zero. + """ + usage = getattr(original_response, "usage", None) if original_response is not None else None + if isinstance(usage, litellm.Usage): + return usage + return litellm.Usage(prompt_tokens=0, completion_tokens=0, total_tokens=0) + + @router.post( "/v1/chat/completions", dependencies=[Depends(user_api_key_auth)], @@ -8467,6 +8483,9 @@ async def chat_completion( _chat_response.model = e.model # type: ignore _chat_response.choices[0].message.content = e.message # type: ignore _chat_response.choices[0].finish_reason = "content_filter" # type: ignore + # Report the blocked LLM response's real usage (set before the stream + # branch so both paths carry it); zero for pre-call blocks. + _chat_response.usage = _blocked_response_usage(e.original_response) # type: ignore if data.get("stream", None) is not None and data["stream"] is True: _iterator = litellm.utils.ModelResponseIterator(model_response=_chat_response, convert_to_delta=True) @@ -8488,8 +8507,6 @@ async def chat_completion( media_type="text/event-stream", status_code=200, # Return 200 for passthrough mode ) - _usage = litellm.Usage(prompt_tokens=0, completion_tokens=0, total_tokens=0) - _chat_response.usage = _usage # type: ignore return _chat_response except RejectedRequestError as e: _data = e.request_data @@ -8618,11 +8635,7 @@ async def completion( # Set text attribute dynamically for text completion format setattr(_text_response.choices[0], "text", e.message) _text_response.model = e.model # type: ignore[assignment] - _usage = litellm.Usage( - prompt_tokens=0, - completion_tokens=0, - total_tokens=0, - ) + _usage = _blocked_response_usage(e.original_response) # Set usage attribute dynamically (ModelResponse accepts usage in __init__ but it's not in type definition) setattr(_text_response, "usage", _usage) _iterator = litellm.utils.ModelResponseIterator(model_response=_text_response, convert_to_delta=True) @@ -8647,11 +8660,7 @@ async def completion( _response = litellm.TextCompletionResponse() _response.choices[0].text = e.message _response.model = e.model # type: ignore - _usage = litellm.Usage( - prompt_tokens=0, - completion_tokens=0, - total_tokens=0, - ) + _usage = _blocked_response_usage(e.original_response) _response.usage = _usage # type: ignore return _response except RejectedRequestError as e: diff --git a/litellm/proxy/schema.prisma b/litellm/proxy/schema.prisma index 5351e0a1470..5e8bb2f37f4 100644 --- a/litellm/proxy/schema.prisma +++ b/litellm/proxy/schema.prisma @@ -338,6 +338,7 @@ model LiteLLM_MCPServerTable { byok_api_key_help_url String? source_url String? timeout Float? + max_concurrent_requests Int? // BYOM submission lifecycle approval_status String? @default("active") submitted_by String? diff --git a/litellm/types/integrations/anthropic_cache_control_hook.py b/litellm/types/integrations/anthropic_cache_control_hook.py index 3e2d0d688ac..601978bb04f 100644 --- a/litellm/types/integrations/anthropic_cache_control_hook.py +++ b/litellm/types/integrations/anthropic_cache_control_hook.py @@ -18,6 +18,7 @@ class CacheControlToolConfigInjectionPoint(TypedDict): """Type for tool_config-level injection points (Bedrock).""" location: Literal["tool_config"] + control: Optional[ChatCompletionCachedContent] CacheControlInjectionPoint = Union[ diff --git a/litellm/types/llms/bedrock.py b/litellm/types/llms/bedrock.py index a1dc08e5f29..bdf6b8fefed 100644 --- a/litellm/types/llms/bedrock.py +++ b/litellm/types/llms/bedrock.py @@ -325,7 +325,7 @@ class ToolConfigBlock(TypedDict, total=False): class GuardrailConfigBlock(TypedDict, total=False): guardrailIdentifier: str guardrailVersion: str - trace: Literal["enabled", "disabled"] + trace: Literal["enabled", "disabled", "enabled_full"] class InferenceConfig(TypedDict, total=False): diff --git a/litellm/types/mcp_server/mcp_server_manager.py b/litellm/types/mcp_server/mcp_server_manager.py index d7c04c09585..c4e37b236ae 100644 --- a/litellm/types/mcp_server/mcp_server_manager.py +++ b/litellm/types/mcp_server/mcp_server_manager.py @@ -118,6 +118,9 @@ class MCPServer(BaseModel): # MCP_PER_USER_TOKEN_DEFAULT_TTL when expires_in is absent. token_storage_ttl_seconds: Optional[int] = None timeout: Optional[float] = None + # Max concurrent outbound tool calls to this server; excess calls queue. + # None or a value <= 0 means unlimited. + max_concurrent_requests: Optional[int] = None # Resolved short-ID tool prefix when LITELLM_USE_SHORT_MCP_TOOL_PREFIX is # enabled. Set by ``MCPServerManager._assign_unique_short_prefix`` at # registration time so that natural-hash collisions between two diff --git a/litellm/types/utils.py b/litellm/types/utils.py index 997498803ac..2e0eceaddd9 100644 --- a/litellm/types/utils.py +++ b/litellm/types/utils.py @@ -3311,6 +3311,7 @@ class LlmProviders(str, Enum): CUSTOM = "custom" LITELLM_PROXY = "litellm_proxy" HOSTED_VLLM = "hosted_vllm" + TENCENT = "tencent" LLAMAFILE = "llamafile" LM_STUDIO = "lm_studio" GALADRIEL = "galadriel" diff --git a/litellm/utils.py b/litellm/utils.py index b5f77d75b93..83d129339a4 100644 --- a/litellm/utils.py +++ b/litellm/utils.py @@ -4204,6 +4204,13 @@ def get_optional_params( model=model, drop_params=(drop_params if drop_params is not None and isinstance(drop_params, bool) else False), ) + elif custom_llm_provider == "tencent": + optional_params = litellm.TencentChatConfig().map_openai_params( + non_default_params=non_default_params, + optional_params=optional_params, + model=model, + drop_params=(drop_params if drop_params is not None and isinstance(drop_params, bool) else False), + ) elif custom_llm_provider == "openrouter": optional_params = litellm.OpenrouterConfig().map_openai_params( non_default_params=non_default_params, @@ -6017,6 +6024,11 @@ def validate_environment( keys_in_environment = True else: missing_keys.append("DEEPSEEK_API_KEY") + elif custom_llm_provider == "tencent": + if "TENCENT_API_KEY" in os.environ: + keys_in_environment = True + else: + missing_keys.append("TENCENT_API_KEY") elif custom_llm_provider == "mistral": if "MISTRAL_API_KEY" in os.environ: keys_in_environment = True @@ -7558,6 +7570,7 @@ class ProviderConfigManager: ), # Simple provider mappings (no model parameter needed) LlmProviders.DEEPSEEK: (lambda: litellm.DeepSeekChatConfig(), False), + LlmProviders.TENCENT: (lambda: litellm.TencentChatConfig(), False), LlmProviders.GROQ: (lambda: litellm.GroqChatConfig(), False), LlmProviders.BEDROCK_MANTLE: ( lambda: litellm.BedrockMantleChatConfig(), @@ -7996,6 +8009,12 @@ class ProviderConfigManager: ) return DeepSeekAnthropicMessagesConfig() + elif litellm.LlmProviders.TENCENT == provider: + from litellm.llms.tencent.messages.transformation import ( + TencentAnthropicMessagesConfig, + ) + + return TencentAnthropicMessagesConfig() elif litellm.LlmProviders.GITHUB_COPILOT == provider: if "claude" in model_lower: from litellm.llms.github_copilot.messages.transformation import ( diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 851f41dd98e..a3dcdaed3f7 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -744,7 +744,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "anthropic.claude-haiku-4-5@20251001": { "cache_creation_input_token_cost": 1.25e-06, @@ -768,7 +769,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_native_streaming": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "anthropic.claude-3-5-sonnet-20240620-v1:0": { "input_cost_per_token": 3e-06, @@ -787,8 +789,6 @@ "output_cost_per_token_above_200k_tokens": 3e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, - "cache_creation_input_token_cost_above_1hr": 7.5e-06, - "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.5e-05, "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07 }, @@ -813,9 +813,7 @@ "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 3e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, - "cache_creation_input_token_cost_above_1hr": 7.5e-06, - "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.5e-05 + "cache_read_input_token_cost_above_200k_tokens": 6e-07 }, "anthropic.claude-3-7-sonnet-20240620-v1:0": { "cache_creation_input_token_cost": 4.5e-06, @@ -991,7 +989,8 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "high" + "bedrock_output_config_effort_ceiling": "high", + "supports_parallel_tool_use_config": true }, "anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, @@ -1010,7 +1009,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -1023,7 +1021,8 @@ "supports_native_structured_output": true, "supports_output_config": true, "supports_max_reasoning_effort": true, - "bedrock_output_config_effort_ceiling": "max" + "bedrock_output_config_effort_ceiling": "max", + "supports_parallel_tool_use_config": true }, "global.anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, @@ -1042,7 +1041,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -1055,7 +1053,8 @@ "supports_native_structured_output": true, "supports_output_config": true, "supports_max_reasoning_effort": true, - "bedrock_output_config_effort_ceiling": "max" + "bedrock_output_config_effort_ceiling": "max", + "supports_parallel_tool_use_config": true }, "us.anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, @@ -1074,7 +1073,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -1087,7 +1085,8 @@ "supports_native_structured_output": true, "supports_output_config": true, "supports_max_reasoning_effort": true, - "bedrock_output_config_effort_ceiling": "max" + "bedrock_output_config_effort_ceiling": "max", + "supports_parallel_tool_use_config": true }, "eu.anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, @@ -1106,7 +1105,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -1119,7 +1117,8 @@ "supports_native_structured_output": true, "supports_output_config": true, "supports_max_reasoning_effort": true, - "bedrock_output_config_effort_ceiling": "max" + "bedrock_output_config_effort_ceiling": "max", + "supports_parallel_tool_use_config": true }, "au.anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, @@ -1138,7 +1137,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -1151,7 +1149,8 @@ "supports_native_structured_output": true, "supports_output_config": true, "supports_max_reasoning_effort": true, - "bedrock_output_config_effort_ceiling": "max" + "bedrock_output_config_effort_ceiling": "max", + "supports_parallel_tool_use_config": true }, "anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -1171,7 +1170,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -1186,7 +1184,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "anthropic.claude-mythos-preview": { "input_cost_per_token": 0, @@ -1221,7 +1220,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -1236,7 +1234,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "us.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -1256,7 +1255,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -1271,7 +1269,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "eu.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -1291,7 +1290,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -1306,7 +1304,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "au.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -1326,7 +1325,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -1341,7 +1339,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "anthropic.claude-fable-5": { "cache_creation_input_token_cost": 1.25e-05, @@ -1374,7 +1373,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "global.anthropic.claude-fable-5": { "cache_creation_input_token_cost": 1.25e-05, @@ -1407,7 +1407,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "us.anthropic.claude-fable-5": { "cache_creation_input_token_cost": 1.375e-05, @@ -1440,7 +1441,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "eu.anthropic.claude-fable-5": { "cache_creation_input_token_cost": 1.375e-05, @@ -1473,7 +1475,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -1493,7 +1496,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -1508,7 +1510,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "global.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -1528,7 +1531,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -1543,7 +1545,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "us.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -1563,7 +1566,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -1578,7 +1580,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "eu.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -1598,7 +1601,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -1613,7 +1615,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "au.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -1633,7 +1636,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -1648,7 +1650,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "jp.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -1680,7 +1683,8 @@ "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "supports_parallel_tool_use_config": true }, "anthropic.claude-sonnet-5": { "cache_creation_input_token_cost": 2.5e-06, @@ -1713,7 +1717,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "global.anthropic.claude-sonnet-5": { "cache_creation_input_token_cost": 2.5e-06, @@ -1746,7 +1751,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "us.anthropic.claude-sonnet-5": { "cache_creation_input_token_cost": 2.75e-06, @@ -1779,7 +1785,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "eu.anthropic.claude-sonnet-5": { "cache_creation_input_token_cost": 2.75e-06, @@ -1812,7 +1819,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "au.anthropic.claude-sonnet-5": { "cache_creation_input_token_cost": 2.75e-06, @@ -1845,7 +1853,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "jp.anthropic.claude-sonnet-5": { "cache_creation_input_token_cost": 2.75e-06, @@ -1878,7 +1887,8 @@ "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh" + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true }, "anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -1897,7 +1907,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -1909,7 +1918,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, - "supports_output_config": true + "supports_output_config": true, + "supports_parallel_tool_use_config": true }, "global.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -1928,7 +1938,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -1940,7 +1949,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, - "supports_output_config": true + "supports_output_config": true, + "supports_parallel_tool_use_config": true }, "us.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -1959,7 +1969,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -1971,7 +1980,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, - "supports_output_config": true + "supports_output_config": true, + "supports_parallel_tool_use_config": true }, "eu.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -1990,7 +2000,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -2002,7 +2011,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, - "supports_output_config": true + "supports_output_config": true, + "supports_parallel_tool_use_config": true }, "au.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -2021,7 +2031,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -2033,7 +2042,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, - "supports_output_config": true + "supports_output_config": true, + "supports_parallel_tool_use_config": true }, "jp.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -2052,7 +2062,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -2064,7 +2073,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, - "supports_output_config": true + "supports_output_config": true, + "supports_parallel_tool_use_config": true }, "anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, @@ -2126,7 +2136,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "anthropic.claude-v1": { "input_cost_per_token": 8e-06, @@ -2376,7 +2387,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "apac.anthropic.claude-3-sonnet-20240229-v1:0": { "input_cost_per_token": 3e-06, @@ -2466,7 +2478,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "azure/ada": { "input_cost_per_token": 1e-07, @@ -2575,7 +2588,6 @@ "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_read_input_token_cost": 5e-07, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -2605,7 +2617,6 @@ "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_read_input_token_cost": 5e-07, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -2666,7 +2677,6 @@ "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_read_input_token_cost": 5e-07, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -2764,7 +2774,6 @@ "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, - "supports_adaptive_thinking": true, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -9373,17 +9382,16 @@ }, "bedrock/us-east-1/minimax.minimax-m2.5": { "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, - "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, - "output_cost_per_token": 1.2e-06 + "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/us-east-1/moonshotai.kimi-k2-thinking": { "input_cost_per_token": 6e-07, @@ -9612,7 +9620,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "bedrock/us-gov-east-1/claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.5e-06, @@ -9634,7 +9643,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "bedrock/us-gov-east-1/meta.llama3-70b-instruct-v1:0": { "input_cost_per_token": 2.65e-06, @@ -9787,7 +9797,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "bedrock/us-gov-west-1/claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.5e-06, @@ -9809,7 +9820,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "bedrock/us-gov-west-1/meta.llama3-70b-instruct-v1:0": { "input_cost_per_token": 2.65e-06, @@ -9995,17 +10007,16 @@ }, "bedrock/us-west-2/minimax.minimax-m2.5": { "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, - "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, - "output_cost_per_token": 1.2e-06 + "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/us-west-2/moonshotai.kimi-k2-thinking": { "input_cost_per_token": 6e-07, @@ -10573,7 +10584,8 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_parallel_tool_use_config": true }, "claude-opus-4-1": { "cache_creation_input_token_cost": 1.875e-05, @@ -14645,7 +14657,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "eu.anthropic.claude-3-5-sonnet-20240620-v1:0": { "input_cost_per_token": 3e-06, @@ -14859,7 +14872,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "eu.meta.llama3-2-1b-instruct-v1:0": { "input_cost_per_token": 1.3e-07, @@ -19381,7 +19395,6 @@ "supported_endpoints": [ "/v1/chat/completions" ], - "supports_adaptive_thinking": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true @@ -20217,7 +20230,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "global.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, @@ -20270,7 +20284,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "global.amazon.nova-2-lite-v1:0": { "cache_read_input_token_cost": 7.5e-08, @@ -22134,8 +22149,8 @@ "output_cost_per_token_flex": 1.5e-05, "output_cost_per_token_batches": 1.5e-05, "output_cost_per_token_priority": 6e-05, - "regional_processing_uplift_multiplier_eu": 1.10, - "regional_processing_uplift_multiplier_us": 1.10, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -22183,8 +22198,8 @@ "output_cost_per_token_flex": 1.5e-05, "output_cost_per_token_batches": 1.5e-05, "output_cost_per_token_priority": 6e-05, - "regional_processing_uplift_multiplier_eu": 1.10, - "regional_processing_uplift_multiplier_us": 1.10, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -22228,8 +22243,8 @@ "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 9e-05, "output_cost_per_token_batches": 9e-05, - "regional_processing_uplift_multiplier_eu": 1.10, - "regional_processing_uplift_multiplier_us": 1.10, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/responses", "/v1/batch" @@ -22273,8 +22288,8 @@ "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 9e-05, "output_cost_per_token_batches": 9e-05, - "regional_processing_uplift_multiplier_eu": 1.10, - "regional_processing_uplift_multiplier_us": 1.10, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/responses", "/v1/batch" @@ -22322,8 +22337,8 @@ "output_cost_per_token_flex": 7.5e-06, "output_cost_per_token_batches": 7.5e-06, "output_cost_per_token_priority": 3e-05, - "regional_processing_uplift_multiplier_eu": 1.10, - "regional_processing_uplift_multiplier_us": 1.10, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -22370,8 +22385,8 @@ "output_cost_per_token_flex": 7.5e-06, "output_cost_per_token_batches": 7.5e-06, "output_cost_per_token_priority": 3e-05, - "regional_processing_uplift_multiplier_eu": 1.10, - "regional_processing_uplift_multiplier_us": 1.10, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -22411,8 +22426,8 @@ "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 9e-05, "output_cost_per_token_batches": 9e-05, - "regional_processing_uplift_multiplier_eu": 1.10, - "regional_processing_uplift_multiplier_us": 1.10, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/responses", "/v1/batch" @@ -22455,8 +22470,8 @@ "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 9e-05, "output_cost_per_token_batches": 9e-05, - "regional_processing_uplift_multiplier_eu": 1.10, - "regional_processing_uplift_multiplier_us": 1.10, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/responses", "/v1/batch" @@ -22500,8 +22515,8 @@ "output_cost_per_token_flex": 2.25e-06, "output_cost_per_token_batches": 2.25e-06, "output_cost_per_token_priority": 9e-06, - "regional_processing_uplift_multiplier_eu": 1.10, - "regional_processing_uplift_multiplier_us": 1.10, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -22546,8 +22561,8 @@ "output_cost_per_token_flex": 2.25e-06, "output_cost_per_token_batches": 2.25e-06, "output_cost_per_token_priority": 9e-06, - "regional_processing_uplift_multiplier_eu": 1.10, - "regional_processing_uplift_multiplier_us": 1.10, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -22589,8 +22604,8 @@ "output_cost_per_token": 1.25e-06, "output_cost_per_token_flex": 6.25e-07, "output_cost_per_token_batches": 6.25e-07, - "regional_processing_uplift_multiplier_eu": 1.10, - "regional_processing_uplift_multiplier_us": 1.10, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -22632,8 +22647,8 @@ "output_cost_per_token": 1.25e-06, "output_cost_per_token_flex": 6.25e-07, "output_cost_per_token_batches": 6.25e-07, - "regional_processing_uplift_multiplier_eu": 1.10, - "regional_processing_uplift_multiplier_us": 1.10, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -24339,7 +24354,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "jp.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.375e-06, @@ -24362,7 +24378,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "crusoe/deepseek-ai/DeepSeek-R1-0528": { "input_cost_per_token": 3e-06, @@ -25150,14 +25167,13 @@ }, "minimax.minimax-m2.5": { "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1.2e-06, "supports_function_calling": true, - "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/" @@ -28613,7 +28629,6 @@ "output_cost_per_token": 1.5e-05, "output_cost_per_token_above_200k_tokens": 2.25e-05, "source": "https://openrouter.ai/anthropic/claude-sonnet-4.6", - "supports_adaptive_thinking": true, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -28653,7 +28668,6 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, - "supports_adaptive_thinking": true, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -28715,7 +28729,6 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -30654,7 +30667,6 @@ "supports_adaptive_thinking": true, "litellm_provider": "perplexity", "mode": "responses", - "supports_adaptive_thinking": true, "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true, @@ -30664,7 +30676,6 @@ "supports_adaptive_thinking": true, "litellm_provider": "perplexity", "mode": "responses", - "supports_adaptive_thinking": true, "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true, @@ -31711,15 +31722,15 @@ "supports_vision": true, "source": "https://cloud.sambanova.ai/plans/pricing" }, - "snowflake/claude-3-5-sonnet": { + "snowflake/claude-3-5-sonnet": { "litellm_provider": "snowflake", "max_input_tokens": 200000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "input_cost_per_token": 0.000003, - "output_cost_per_token": 0.000015, - "cache_read_input_token_cost": 0.0000003, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "cache_read_input_token_cost": 3e-07, "supports_computer_use": true, "supports_function_calling": true, "supports_vision": true, @@ -31727,14 +31738,14 @@ "supports_system_messages": true, "supports_response_schema": true }, - "snowflake/deepseek-r1": { + "snowflake/deepseek-r1": { "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "input_cost_per_token": 0.00000135, - "output_cost_per_token": 0.0000054, + "input_cost_per_token": 1.35e-06, + "output_cost_per_token": 5.4e-06, "supports_reasoning": true, "supports_system_messages": true }, @@ -31793,8 +31804,8 @@ "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "input_cost_per_token": 0.0000012, - "output_cost_per_token": 0.0000012, + "input_cost_per_token": 1.2e-06, + "output_cost_per_token": 1.2e-06, "supports_function_calling": true, "supports_system_messages": true }, @@ -31804,8 +31815,8 @@ "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "input_cost_per_token": 0.00000072, - "output_cost_per_token": 0.00000072, + "input_cost_per_token": 7.2e-07, + "output_cost_per_token": 7.2e-07, "supports_function_calling": true, "supports_system_messages": true }, @@ -31815,8 +31826,8 @@ "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "input_cost_per_token": 0.00000024, - "output_cost_per_token": 0.00000024, + "input_cost_per_token": 2.4e-07, + "output_cost_per_token": 2.4e-07, "supports_system_messages": true }, "snowflake/llama3.2-1b": { @@ -31833,17 +31844,17 @@ "max_tokens": 8192, "mode": "chat" }, - "snowflake/llama3.3-70b": { + "snowflake/llama3.3-70b": { "max_tokens": 16384, "max_input_tokens": 128000, "max_output_tokens": 16384, - "input_cost_per_token": 0.00000072, - "output_cost_per_token": 0.00000072, + "input_cost_per_token": 7.2e-07, + "output_cost_per_token": 7.2e-07, "litellm_provider": "snowflake", "mode": "chat", "supports_function_calling": true, "supports_system_messages": true - }, + }, "snowflake/mistral-7b": { "litellm_provider": "snowflake", "max_input_tokens": 32000, @@ -31858,14 +31869,14 @@ "max_tokens": 8192, "mode": "chat" }, - "snowflake/mistral-large2": { + "snowflake/mistral-large2": { "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "input_cost_per_token": 0.000002, - "output_cost_per_token": 0.000006, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_response_schema": true @@ -31905,17 +31916,17 @@ "max_tokens": 8192, "mode": "chat" }, - "snowflake/snowflake-llama-3.3-70b": { + "snowflake/snowflake-llama-3.3-70b": { "max_tokens": 16384, "max_input_tokens": 128000, "max_output_tokens": 16384, - "input_cost_per_token": 0.00000072, - "output_cost_per_token": 0.00000072, + "input_cost_per_token": 7.2e-07, + "output_cost_per_token": 7.2e-07, "litellm_provider": "snowflake", "mode": "chat", "supports_function_calling": true, "supports_system_messages": true - }, + }, "stability/sd3": { "litellm_provider": "stability", "mode": "image_generation", @@ -32999,7 +33010,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "us.anthropic.claude-3-5-sonnet-20240620-v1:0": { "input_cost_per_token": 3e-06, @@ -33158,7 +33170,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.5e-06, @@ -33167,7 +33180,7 @@ "input_cost_per_token": 3.6e-06, "input_cost_per_token_above_200k_tokens": 7.2e-06, "output_cost_per_token_above_200k_tokens": 2.7e-05, - "cache_creation_input_token_cost_above_200k_tokens": 9.0e-06, + "cache_creation_input_token_cost_above_200k_tokens": 9e-06, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.44e-05, "cache_read_input_token_cost_above_200k_tokens": 7.2e-07, "litellm_provider": "bedrock_converse", @@ -33185,7 +33198,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "au.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.375e-06, @@ -33207,7 +33221,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true }, "us.anthropic.claude-opus-4-20250514-v1:0": { "cache_creation_input_token_cost": 1.875e-05, @@ -33261,7 +33276,8 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "high" + "bedrock_output_config_effort_ceiling": "high", + "supports_parallel_tool_use_config": true }, "global.anthropic.claude-opus-4-5-20251101-v1:0": { "cache_creation_input_token_cost": 6.25e-06, @@ -33290,7 +33306,8 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "high" + "bedrock_output_config_effort_ceiling": "high", + "supports_parallel_tool_use_config": true }, "eu.anthropic.claude-opus-4-5-20251101-v1:0": { "cache_creation_input_token_cost": 6.25e-06, @@ -33318,7 +33335,8 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "high" + "bedrock_output_config_effort_ceiling": "high", + "supports_parallel_tool_use_config": true }, "us.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, @@ -33910,7 +33928,6 @@ "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, - "supports_adaptive_thinking": true, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -35145,7 +35162,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -35175,7 +35191,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -35205,7 +35220,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -35236,7 +35250,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -35327,7 +35340,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -35358,7 +35370,6 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -35441,7 +35452,6 @@ "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, - "supports_adaptive_thinking": true, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -37998,12 +38008,12 @@ }, "zai.glm-5": { "input_cost_per_token": 1e-06, + "output_cost_per_token": 3.2e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3.2e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -38024,20 +38034,6 @@ "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/" }, - "zai.glm-5": { - "input_cost_per_token": 1e-06, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 200000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 3.2e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "zai/glm-5": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 2e-07, @@ -42966,7 +42962,6 @@ "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, - "supports_adaptive_thinking": true, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -43000,7 +42995,10 @@ "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "supported_endpoints": ["/v1/chat/completions", "/v1/responses"], + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, @@ -43015,7 +43013,10 @@ "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "supported_endpoints": ["/v1/chat/completions", "/v1/responses"], + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, @@ -43030,7 +43031,9 @@ "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "supported_endpoints": ["/v1/chat/completions"], + "supported_endpoints": [ + "/v1/chat/completions" + ], "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -43044,7 +43047,9 @@ "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "supported_endpoints": ["/v1/chat/completions"], + "supported_endpoints": [ + "/v1/chat/completions" + ], "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -43060,9 +43065,16 @@ "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, - "supported_endpoints": ["/v1/responses"], - "supported_modalities": ["text", "image"], - "supported_output_modalities": ["text"], + "supported_endpoints": [ + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -43080,9 +43092,16 @@ "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, - "supported_endpoints": ["/v1/responses"], - "supported_modalities": ["text", "image"], - "supported_output_modalities": ["text"], + "supported_endpoints": [ + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -43099,7 +43118,10 @@ "max_tokens": 256000, "mode": "chat", "use_openai_responses_path": true, - "supported_endpoints": ["/v1/chat/completions", "/v1/responses"], + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_reasoning": true, @@ -43115,7 +43137,10 @@ "max_tokens": 256000, "mode": "chat", "use_openai_responses_path": true, - "supported_endpoints": ["/v1/chat/completions", "/v1/responses"], + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_reasoning": true, @@ -43131,7 +43156,10 @@ "max_tokens": 128000, "mode": "chat", "use_openai_responses_path": true, - "supported_endpoints": ["/v1/chat/completions", "/v1/responses"], + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_reasoning": true, @@ -43310,20 +43338,6 @@ } ] }, - "zai.glm-5": { - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3.2e-06, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 200000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" - }, "bedrock/us-east-1/zai.glm-5": { "input_cost_per_token": 1e-06, "output_cost_per_token": 3.2e-06, @@ -43352,45 +43366,6 @@ "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/" }, - "minimax.minimax-m2.5": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "supports_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" - }, - "bedrock/us-east-1/minimax.minimax-m2.5": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "supports_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" - }, - "bedrock/us-west-2/minimax.minimax-m2.5": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "supports_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" - }, "bedrock/us-gov-east-1/anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.5e-06, "cache_creation_input_token_cost_above_1hr": 2.4e-06, @@ -43412,7 +43387,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, - "supports_pdf_input": true + "supports_pdf_input": true, + "supports_parallel_tool_use_config": true }, "bedrock/us-gov-west-1/anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.5e-06, @@ -43435,365 +43411,369 @@ "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, - "supports_pdf_input": true + "supports_pdf_input": true, + "supports_parallel_tool_use_config": true + }, + "snowflake/claude-sonnet-4-5": { + "max_tokens": 16384, + "max_input_tokens": 200000, + "max_output_tokens": 16384, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "cache_read_input_token_cost": 3e-07, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_response_schema": true + }, + "snowflake/claude-sonnet-4-6": { + "supports_adaptive_thinking": true, + "max_tokens": 16384, + "max_input_tokens": 200000, + "max_output_tokens": 16384, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "cache_read_input_token_cost": 3e-07, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_response_schema": true + }, + "snowflake/claude-4-sonnet": { + "max_tokens": 16384, + "max_input_tokens": 200000, + "max_output_tokens": 16384, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "cache_read_input_token_cost": 3e-07, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_response_schema": true + }, + "snowflake/claude-4-opus": { + "max_tokens": 16384, + "max_input_tokens": 200000, + "max_output_tokens": 16384, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 2.5e-05, + "cache_read_input_token_cost": 5e-07, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_response_schema": true + }, + "snowflake/claude-haiku-4-5": { + "max_tokens": 16384, + "max_input_tokens": 200000, + "max_output_tokens": 16384, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 5e-06, + "cache_read_input_token_cost": 1e-07, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_response_schema": true + }, + "snowflake/claude-3-7-sonnet": { + "max_tokens": 16384, + "max_input_tokens": 200000, + "max_output_tokens": 16384, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "cache_read_input_token_cost": 3e-07, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_response_schema": true + }, + "snowflake/openai-gpt-4.1": { + "max_tokens": 16384, + "max_input_tokens": 300000, + "max_output_tokens": 16384, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 8e-06, + "cache_read_input_token_cost": 5e-07, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_response_schema": true + }, + "snowflake/openai-gpt-5": { + "max_tokens": 16384, + "max_input_tokens": 300000, + "max_output_tokens": 16384, + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1.25e-07, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_response_schema": true + }, + "snowflake/openai-gpt-5-mini": { + "max_tokens": 16384, + "max_input_tokens": 1000000, + "max_output_tokens": 16384, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_system_messages": true, + "supports_response_schema": true + }, + "snowflake/openai-gpt-5-nano": { + "max_tokens": 16384, + "max_input_tokens": 5000000, + "max_output_tokens": 16384, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_system_messages": true, + "supports_response_schema": true + }, + "snowflake/llama4-maverick": { + "max_tokens": 16384, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "input_cost_per_token": 2.4e-07, + "output_cost_per_token": 9.7e-07, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_system_messages": true + }, + "snowflake/snowflake-arctic-embed-l-v2.0": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "input_cost_per_token": 7e-08, + "output_cost_per_token": 0.0, + "litellm_provider": "snowflake", + "mode": "embedding" + }, + "snowflake/snowflake-arctic-embed-m-v2.0": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "input_cost_per_token": 7e-08, + "output_cost_per_token": 0.0, + "litellm_provider": "snowflake", + "mode": "embedding" + }, + "soniox/stt-async-v4": { + "litellm_provider": "soniox", + "max_output_tokens": 8000, + "max_tokens": 8000, + "input_cost_per_second": 0.0, + "output_cost_per_second": 2.77778e-05, + "mode": "audio_transcription", + "source": "https://soniox.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ], + "supports_audio_input": true + }, + "soniox/stt-async-v5": { + "litellm_provider": "soniox", + "max_output_tokens": 8000, + "max_tokens": 8000, + "input_cost_per_second": 0.0, + "output_cost_per_second": 2.77778e-05, + "mode": "audio_transcription", + "source": "https://soniox.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ], + "supports_audio_input": true + }, + "tensormesh/Qwen/Qwen3.5-397B-A17B-FP8": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 6e-07, + "output_cost_per_token": 3.6e-06, + "cache_read_input_token_cost": 0, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + }, + "tensormesh/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 4.5e-07, + "output_cost_per_token": 1.8e-06, + "cache_read_input_token_cost": 0, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + }, + "tensormesh/Qwen/Qwen3.6-27B-FP8": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 3.2e-07, + "output_cost_per_token": 3.2e-06, + "cache_read_input_token_cost": 0, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + }, + "tensormesh/lukealonso/GLM-5.1-NVFP4-MTP": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 1.4e-06, + "output_cost_per_token": 4.4e-06, + "cache_read_input_token_cost": 0, + "max_input_tokens": 202752, + "max_output_tokens": 202752, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + }, + "tensormesh/deepseek-ai/DeepSeek-V4-Flash": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 2.8e-07, + "cache_read_input_token_cost": 0, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + }, + "tensormesh/moonshotai/Kimi-K2.6": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 9.6e-07, + "output_cost_per_token": 4e-06, + "cache_read_input_token_cost": 0, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + }, + "tensormesh/MiniMaxAI/MiniMax-M2.5": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 0, + "max_input_tokens": 196608, + "max_output_tokens": 196608, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + }, + "tensormesh/google/gemma-4-31B-it": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 5.6e-07, + "cache_read_input_token_cost": 0, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + }, + "tensormesh/openai/gpt-oss-120b": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "cache_read_input_token_cost": 0, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + }, + "tensormesh/openai/gpt-oss-20b": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 7e-08, + "output_cost_per_token": 2.8e-07, + "cache_read_input_token_cost": 0, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" }, - "snowflake/claude-sonnet-4-5": { - "max_tokens": 16384, - "max_input_tokens": 200000, - "max_output_tokens": 16384, - "input_cost_per_token": 0.000003, - "output_cost_per_token": 0.000015, - "cache_read_input_token_cost": 0.0000003, - "litellm_provider": "snowflake", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_response_schema": true - }, - "snowflake/claude-sonnet-4-6": { - "supports_adaptive_thinking": true, - "max_tokens": 16384, - "max_input_tokens": 200000, - "max_output_tokens": 16384, - "input_cost_per_token": 0.000003, - "output_cost_per_token": 0.000015, - "cache_read_input_token_cost": 0.0000003, - "litellm_provider": "snowflake", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_response_schema": true - }, - "snowflake/claude-4-sonnet": { - "max_tokens": 16384, - "max_input_tokens": 200000, - "max_output_tokens": 16384, - "input_cost_per_token": 0.000003, - "output_cost_per_token": 0.000015, - "cache_read_input_token_cost": 0.0000003, - "litellm_provider": "snowflake", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_response_schema": true - }, - "snowflake/claude-4-opus": { - "max_tokens": 16384, - "max_input_tokens": 200000, - "max_output_tokens": 16384, - "input_cost_per_token": 0.000005, - "output_cost_per_token": 0.000025, - "cache_read_input_token_cost": 0.0000005, - "litellm_provider": "snowflake", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_reasoning": true, - "supports_response_schema": true - }, - "snowflake/claude-haiku-4-5": { - "max_tokens": 16384, - "max_input_tokens": 200000, - "max_output_tokens": 16384, - "input_cost_per_token": 0.000001, - "output_cost_per_token": 0.000005, - "cache_read_input_token_cost": 0.0000001, - "litellm_provider": "snowflake", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_response_schema": true - }, - "snowflake/claude-3-7-sonnet": { - "max_tokens": 16384, - "max_input_tokens": 200000, - "max_output_tokens": 16384, - "input_cost_per_token": 0.000003, - "output_cost_per_token": 0.000015, - "cache_read_input_token_cost": 0.0000003, - "litellm_provider": "snowflake", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_reasoning": true, - "supports_response_schema": true - }, - "snowflake/openai-gpt-4.1": { - "max_tokens": 16384, - "max_input_tokens": 300000, - "max_output_tokens": 16384, - "input_cost_per_token": 0.000002, - "output_cost_per_token": 0.000008, - "cache_read_input_token_cost": 0.0000005, - "litellm_provider": "snowflake", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_response_schema": true - }, - "snowflake/openai-gpt-5": { - "max_tokens": 16384, - "max_input_tokens": 300000, - "max_output_tokens": 16384, - "input_cost_per_token": 0.00000125, - "output_cost_per_token": 0.00001, - "cache_read_input_token_cost": 0.000000125, - "litellm_provider": "snowflake", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_reasoning": true, - "supports_response_schema": true - }, - "snowflake/openai-gpt-5-mini": { - "max_tokens": 16384, - "max_input_tokens": 1000000, - "max_output_tokens": 16384, - "input_cost_per_token": 0.0000003, - "output_cost_per_token": 0.0000012, - "litellm_provider": "snowflake", - "mode": "chat", - "supports_function_calling": true, - "supports_system_messages": true, - "supports_response_schema": true - }, - "snowflake/openai-gpt-5-nano": { - "max_tokens": 16384, - "max_input_tokens": 5000000, - "max_output_tokens": 16384, - "input_cost_per_token": 0.00000015, - "output_cost_per_token": 0.0000006, - "litellm_provider": "snowflake", - "mode": "chat", - "supports_function_calling": true, - "supports_system_messages": true, - "supports_response_schema": true - }, - "snowflake/llama4-maverick": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 0.00000024, - "output_cost_per_token": 0.00000097, - "litellm_provider": "snowflake", - "mode": "chat", - "supports_function_calling": true, - "supports_system_messages": true - }, - "snowflake/snowflake-arctic-embed-l-v2.0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "input_cost_per_token": 0.00000007, - "output_cost_per_token": 0.0, - "litellm_provider": "snowflake", - "mode": "embedding" - }, - "snowflake/snowflake-arctic-embed-m-v2.0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "input_cost_per_token": 0.00000007, - "output_cost_per_token": 0.0, - "litellm_provider": "snowflake", - "mode": "embedding" - }, - "soniox/stt-async-v4": { - "litellm_provider": "soniox", - "max_output_tokens": 8000, - "max_tokens": 8000, - "input_cost_per_second": 0.0, - "output_cost_per_second": 0.0000277778, - "mode": "audio_transcription", - "source": "https://soniox.com/pricing", - "supported_endpoints": ["/v1/audio/transcriptions"], - "supports_audio_input": true - }, - "soniox/stt-async-v5": { - "litellm_provider": "soniox", - "max_output_tokens": 8000, - "max_tokens": 8000, - "input_cost_per_second": 0.0, - "output_cost_per_second": 0.0000277778, - "mode": "audio_transcription", - "source": "https://soniox.com/pricing", - "supported_endpoints": ["/v1/audio/transcriptions"], - "supports_audio_input": true - }, - "tensormesh/Qwen/Qwen3.5-397B-A17B-FP8": { - "litellm_provider": "tensormesh", - "mode": "chat", - "input_cost_per_token": 6e-07, - "output_cost_per_token": 3.6e-06, - "cache_read_input_token_cost": 0, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_reasoning": true, - "source": "https://serverless.tensormesh.ai/v1/models/openrouter" - }, - "tensormesh/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { - "litellm_provider": "tensormesh", - "mode": "chat", - "input_cost_per_token": 4.5e-07, - "output_cost_per_token": 1.8e-06, - "cache_read_input_token_cost": 0, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "source": "https://serverless.tensormesh.ai/v1/models/openrouter" - }, - "tensormesh/Qwen/Qwen3.6-27B-FP8": { - "litellm_provider": "tensormesh", - "mode": "chat", - "input_cost_per_token": 3.2e-07, - "output_cost_per_token": 3.2e-06, - "cache_read_input_token_cost": 0, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_reasoning": true, - "source": "https://serverless.tensormesh.ai/v1/models/openrouter" - }, - "tensormesh/lukealonso/GLM-5.1-NVFP4-MTP": { - "litellm_provider": "tensormesh", - "mode": "chat", - "input_cost_per_token": 1.4e-06, - "output_cost_per_token": 4.4e-06, - "cache_read_input_token_cost": 0, - "max_input_tokens": 202752, - "max_output_tokens": 202752, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_reasoning": true, - "source": "https://serverless.tensormesh.ai/v1/models/openrouter" - }, - "tensormesh/deepseek-ai/DeepSeek-V4-Flash": { - "litellm_provider": "tensormesh", - "mode": "chat", - "input_cost_per_token": 1.4e-07, - "output_cost_per_token": 2.8e-07, - "cache_read_input_token_cost": 0, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_reasoning": true, - "source": "https://serverless.tensormesh.ai/v1/models/openrouter" - }, - "tensormesh/moonshotai/Kimi-K2.6": { - "litellm_provider": "tensormesh", - "mode": "chat", - "input_cost_per_token": 9.6e-07, - "output_cost_per_token": 4e-06, - "cache_read_input_token_cost": 0, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_reasoning": true, - "source": "https://serverless.tensormesh.ai/v1/models/openrouter" - }, - "tensormesh/MiniMaxAI/MiniMax-M2.5": { - "litellm_provider": "tensormesh", - "mode": "chat", - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "cache_read_input_token_cost": 0, - "max_input_tokens": 196608, - "max_output_tokens": 196608, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_reasoning": true, - "source": "https://serverless.tensormesh.ai/v1/models/openrouter" - }, - "tensormesh/google/gemma-4-31B-it": { - "litellm_provider": "tensormesh", - "mode": "chat", - "input_cost_per_token": 1.4e-07, - "output_cost_per_token": 5.6e-07, - "cache_read_input_token_cost": 0, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_reasoning": true, - "source": "https://serverless.tensormesh.ai/v1/models/openrouter" - }, - "tensormesh/openai/gpt-oss-120b": { - "litellm_provider": "tensormesh", - "mode": "chat", - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "cache_read_input_token_cost": 0, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_reasoning": true, - "source": "https://serverless.tensormesh.ai/v1/models/openrouter" - }, - "tensormesh/openai/gpt-oss-20b": { - "litellm_provider": "tensormesh", - "mode": "chat", - "input_cost_per_token": 7e-08, - "output_cost_per_token": 2.8e-07, - "cache_read_input_token_cost": 0, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_reasoning": true, - "source": "https://serverless.tensormesh.ai/v1/models/openrouter" - } - , "deepseek-v4-flash": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 2.8e-09, @@ -43894,12 +43874,64 @@ "supports_tool_choice": true, "supports_vision": false }, + "tencent/deepseek-v4-pro": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 3.625e-09, + "input_cost_per_token": 4.35e-07, + "input_cost_per_token_cache_hit": 3.625e-09, + "litellm_provider": "tencent", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 8.7e-07, + "source": "https://www.tencentcloud.com/products/tokenhub", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false + }, + "tencent/deepseek-v4-flash": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 2.8e-09, + "input_cost_per_token": 1.4e-07, + "input_cost_per_token_cache_hit": 2.8e-09, + "litellm_provider": "tencent", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "source": "https://www.tencentcloud.com/products/tokenhub", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false + }, "pinstripes/ps/glm-4.5-air": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, - "input_cost_per_token": 0.000000125, - "output_cost_per_token": 0.00000045, + "input_cost_per_token": 1.25e-07, + "output_cost_per_token": 4.5e-07, "litellm_provider": "pinstripes", "mode": "chat", "supports_function_calling": true, @@ -43911,8 +43943,8 @@ "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 0.00000014, - "output_cost_per_token": 0.00000045, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 4.5e-07, "litellm_provider": "pinstripes", "mode": "chat", "supports_function_calling": true, @@ -43924,8 +43956,8 @@ "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 0.00000009, - "output_cost_per_token": 0.0000002, + "input_cost_per_token": 9e-08, + "output_cost_per_token": 2e-07, "litellm_provider": "pinstripes", "mode": "chat", "supports_function_calling": true, @@ -43937,8 +43969,8 @@ "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 0.0000003, - "output_cost_per_token": 0.0000006, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 6e-07, "litellm_provider": "pinstripes", "mode": "chat", "supports_function_calling": true, @@ -43950,8 +43982,8 @@ "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, - "input_cost_per_token": 0.0000001, - "output_cost_per_token": 0.0000002, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 2e-07, "litellm_provider": "pinstripes", "mode": "chat", "supports_function_calling": true, @@ -43963,8 +43995,8 @@ "max_tokens": 1000192, "max_input_tokens": 1000192, "max_output_tokens": 1000192, - "input_cost_per_token": 0.000000255, - "output_cost_per_token": 0.00000055, + "input_cost_per_token": 2.55e-07, + "output_cost_per_token": 5.5e-07, "litellm_provider": "pinstripes", "mode": "chat", "supports_function_calling": true, @@ -44006,39 +44038,39 @@ "supports_system_messages": true, "supports_tool_choice": true }, - "fallback_generalizations": { - "rules": [ - { - "name": "anthropic-claude-adaptive-thinking", - "pattern": "(?:opus|sonnet|haiku)[-._](?:4[-._](?:[6-9]|[1-9]\\d)(?!\\d)|(?:[5-9]|[1-9]\\d{1,})[-._]\\d{1,2}(?!\\d))", - "description": "Claude opus/sonnet/haiku at version 4.6 or higher: 4.6 through 4.99, then any 5.x, 6.x or later major. The minor is capped at two digits so an 8-digit date suffix such as claude-opus-4-20250514 is never read as a >= 4.6 minor. Turns on adaptive thinking for new families with no code change.", - "extends": "anthropic-claude", - "model_info": { - "supports_adaptive_thinking": true - } - }, - { - "name": "anthropic-claude", - "pattern": "^claude-[a-z]+-\\d+[-.]\\d+(?:-\\d{8})?$", - "description": "Any Claude family-major-minor id, optionally with an 8-digit date suffix, anchored to the whole name. Version-neutral fallback that gives an unmapped Claude provider routing and baseline capabilities; it carries no pricing, so cost stays on the standard unpriced behavior rather than a guessed number.", - "model_info": { - "litellm_provider": "anthropic", - "mode": "chat", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true, - "supports_assistant_prefill": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_pdf_input": true, - "supports_system_messages": true - } - } - ] - } + "fallback_generalizations": { + "rules": [ + { + "name": "anthropic-claude-adaptive-thinking", + "pattern": "(?:opus|sonnet|haiku)[-._](?:4[-._](?:[6-9]|[1-9]\\d)(?!\\d)|(?:[5-9]|[1-9]\\d{1,})[-._]\\d{1,2}(?!\\d))", + "description": "Claude opus/sonnet/haiku at version 4.6 or higher: 4.6 through 4.99, then any 5.x, 6.x or later major. The minor is capped at two digits so an 8-digit date suffix such as claude-opus-4-20250514 is never read as a >= 4.6 minor. Turns on adaptive thinking for new families with no code change.", + "extends": "anthropic-claude", + "model_info": { + "supports_adaptive_thinking": true + } + }, + { + "name": "anthropic-claude", + "pattern": "^claude-[a-z]+-\\d+[-.]\\d+(?:-\\d{8})?$", + "description": "Any Claude family-major-minor id, optionally with an 8-digit date suffix, anchored to the whole name. Version-neutral fallback that gives an unmapped Claude provider routing and baseline capabilities; it carries no pricing, so cost stays on the standard unpriced behavior rather than a guessed number.", + "model_info": { + "litellm_provider": "anthropic", + "mode": "chat", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_vision": true, + "supports_tool_choice": true, + "supports_assistant_prefill": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_pdf_input": true, + "supports_system_messages": true + } + } + ] + } } diff --git a/provider_endpoints_support.json b/provider_endpoints_support.json index edac8949f28..3034ada56ba 100644 --- a/provider_endpoints_support.json +++ b/provider_endpoints_support.json @@ -2295,6 +2295,24 @@ "text_completion": true } }, + "tencent": { + "display_name": "Tencent TokenHub (`tencent`)", + "url": "https://docs.litellm.ai/docs/providers/tencent", + "endpoints": { + "chat_completions": true, + "messages": true, + "responses": true, + "embeddings": false, + "image_generations": false, + "audio_transcriptions": false, + "audio_speech": false, + "moderations": false, + "batches": false, + "rerank": false, + "a2a": false, + "text_completion": false + } + }, "text-completion-codestral": { "display_name": "Text Completion Codestral (`text-completion-codestral`)", "url": "https://docs.litellm.ai/docs/providers/codestral", diff --git a/pyproject.toml b/pyproject.toml index 5165859b1b6..b5a62e550db 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -62,8 +62,8 @@ proxy = [ "azure-identity>=1.25.2,<2.0", "azure-storage-blob>=12.28.0,<13.0", "mcp>=1.26.0,<2.0", - "litellm-proxy-extras==0.4.74", - "litellm-enterprise==0.1.45", + "litellm-proxy-extras==0.4.75", + "litellm-enterprise==0.1.46", "RestrictedPython>=8.1,<9.0", "rich>=13.9.4,<14.0", "polars>=1.38.1,<2.0", diff --git a/ruff-strict-budget.json b/ruff-strict-budget.json index 85ff7fcbf7d..dcf6e9868b7 100644 --- a/ruff-strict-budget.json +++ b/ruff-strict-budget.json @@ -222,7 +222,7 @@ "limit": 38 }, "RET504": { - "limit": 722 + "limit": 721 }, "RUF010": { "limit": 874 @@ -249,7 +249,7 @@ "limit": 6 }, "RUF059": { - "limit": 74 + "limit": 73 }, "RUF100": { "limit": 480 @@ -264,7 +264,7 @@ "limit": 63 }, "SIM102": { - "limit": 326 + "limit": 325 }, "SIM103": { "limit": 129 @@ -306,7 +306,7 @@ "limit": 9 }, "TID251": { - "limit": 2714 + "limit": 2710 }, "TRY002": { "limit": 548 @@ -324,7 +324,7 @@ "limit": 883 }, "UP006": { - "limit": 13041 + "limit": 12870 }, "UP007": { "limit": 2570 @@ -354,7 +354,7 @@ "limit": 4 }, "UP035": { - "limit": 2300 + "limit": 2295 }, "UP036": { "limit": 4 diff --git a/schema.prisma b/schema.prisma index 5351e0a1470..5e8bb2f37f4 100644 --- a/schema.prisma +++ b/schema.prisma @@ -338,6 +338,7 @@ model LiteLLM_MCPServerTable { byok_api_key_help_url String? source_url String? timeout Float? + max_concurrent_requests Int? // BYOM submission lifecycle approval_status String? @default("active") submitted_by String? diff --git a/scripts/pre_commit_lint.sh b/scripts/pre_commit_lint.sh index d667d6758e1..04a2af56ce2 100755 --- a/scripts/pre_commit_lint.sh +++ b/scripts/pre_commit_lint.sh @@ -111,7 +111,7 @@ if [ -n "$spec_files" ]; then # and an up-to-date Prisma client; check-ui-api-types.yml installs those and runs # prisma generate before gen:api, so mirror that here or a stale client can mask # drift that CI will still flag. - if ! uv run --no-sync prisma generate --schema litellm/proxy/schema.prisma; then + if ! uv run --no-sync python scripts/prisma_generate_if_needed.py; then echo "βœ— Could not regenerate Prisma client (prisma generate failed)." >&2 status=1 elif ( cd ui/litellm-dashboard && LITELLM_PYTHON="uv run --no-sync python" npm run gen:api ); then diff --git a/scripts/prisma_generate_if_needed.py b/scripts/prisma_generate_if_needed.py new file mode 100644 index 00000000000..d2c40adf820 --- /dev/null +++ b/scripts/prisma_generate_if_needed.py @@ -0,0 +1,69 @@ +#!/usr/bin/env python3 +"""Run ``prisma generate`` only when its inputs changed since the last run. + +The generated client is a pure function of ``litellm/proxy/schema.prisma`` and +the installed prisma package version, so a stamp of those two written next to +the venv is enough to prove the client is current. The stamp lives under +``sys.prefix`` so recreating the venv discards it, and a missing generated +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. +""" + +import hashlib +import importlib.metadata +import importlib.util +import subprocess +import sys +from pathlib import Path + +REPO_ROOT = Path(__file__).resolve().parent.parent +SCHEMA = REPO_ROOT / "litellm" / "proxy" / "schema.prisma" +STAMP = Path(sys.prefix) / "litellm-prisma-schema.stamp" + + +def stamp_value(schema_bytes: bytes, prisma_version: str) -> str: + return f"{hashlib.sha256(schema_bytes).hexdigest()}:{prisma_version}" + + +def should_skip(stamp: Path, expected: str, client_generated: bool) -> bool: + if not client_generated: + return False + try: + return stamp.read_text() == expected + except OSError: + return False + + +def client_is_generated() -> bool: + spec = importlib.util.find_spec("prisma") + if spec is None or not spec.submodule_search_locations: + return False + return any( + (Path(location) / "client.py").exists() + for location in spec.submodule_search_locations + ) + + +def main() -> int: + version = importlib.metadata.version("prisma") + expected = stamp_value(SCHEMA.read_bytes(), version) + if should_skip(STAMP, expected, client_is_generated()): + print( + f"Prisma client already generated for {SCHEMA.relative_to(REPO_ROOT)} " + 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 + STAMP.write_text(expected) + return 0 + + +if __name__ == "__main__": + raise SystemExit(main()) diff --git a/scripts/ruff_strict_gate.py b/scripts/ruff_strict_gate.py index 5273e4805f6..25f6c4d29ba 100644 --- a/scripts/ruff_strict_gate.py +++ b/scripts/ruff_strict_gate.py @@ -89,6 +89,18 @@ def base_counts(ref: str) -> dict: shutil.rmtree(parent, ignore_errors=True) +def over_ceiling(head: dict, budget: dict) -> frozenset: + """Rules whose head count already exceeds their limit. + + A rule can only breach when it is over its limit, so when none are the base + comparison cannot change the verdict and the base worktree scan can be skipped. + """ + return frozenset( + rule for rule, spec in budget.items() + if head.get(rule, 0) > spec["limit"] + ) + + def evaluate(head: dict, base: dict, budget: dict) -> list: breaches = [] for rule, spec in budget.items(): @@ -119,8 +131,12 @@ def introduced(violations: list, changed: dict) -> list: def cmd_check(base: str) -> None: budget = json.loads(BUDGET_PATH.read_text()) head = head_violations() + head_counts = count_by_rule(head) + if not over_ceiling(head_counts, budget): + print(f"OK: every strict rule is within its codebase ceiling (base {base})") + return base_point = _run(["git", "merge-base", base, "HEAD"]).strip() or base - breaches = evaluate(count_by_rule(head), base_counts(base_point), budget) + breaches = evaluate(head_counts, base_counts(base_point), budget) if not breaches: print(f"OK: every strict rule is within its codebase ceiling (base {base})") return diff --git a/scripts/type_check_gate.py b/scripts/type_check_gate.py index d3837cc2c0d..2c5306cec7d 100644 --- a/scripts/type_check_gate.py +++ b/scripts/type_check_gate.py @@ -13,9 +13,13 @@ bystander's count equals its base, so it is spared, while any PR that actually grows the rule past its limit still fails. Head counts are read from stdin (the caller runs basedpyright once and pipes -``--outputjson`` in); the base count is a second basedpyright pass over a -detached worktree at the merge-base, run under the same environment so import -resolution matches. ``--update`` ratchets each rule's ``limit`` down by the +``--outputjson`` in). The base count only 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. ``--update`` ratchets each rule's ``limit`` down by the number of errors this branch fixed relative to its branch point (the merge-base), so the headroom you were granted shrinks by exactly what you cleared and never grows. @@ -28,20 +32,24 @@ carries an unambiguous ``rule`` field. import argparse import contextlib +import hashlib import json +import os import shutil import subprocess import sys import tempfile from collections import Counter -from collections.abc import Iterator, Mapping +from collections.abc import Callable, Iterator, Mapping from pathlib import Path from typing import NamedTuple REPO_ROOT = Path(__file__).resolve().parent.parent BUDGET_PATH = REPO_ROOT / "basedpyright-code-budget.json" PYRIGHT_CONFIG = REPO_ROOT / "pyrightconfig.json" +UV_LOCK = REPO_ROOT / "uv.lock" DEFAULT_BASE = "origin/litellm_internal_staging" +CACHE_FILE_PREFIX = "basedpyright-base-" # Bucket for a basedpyright diagnostic with no `rule`. Counted so it's gated. UNCODED = "" @@ -129,6 +137,109 @@ def base_counts(ref: str) -> dict[str, int]: return count_basedpyright(proc.stdout, root=worktree) +def over_ceiling( + head: Mapping[str, int], budget: Mapping[str, Mapping[str, int]] +) -> frozenset[str]: + """Rules whose head count already exceeds their limit. + + A rule can only breach when it is over its limit, so when none are the base + comparison cannot change the verdict and the base worktree pass can be skipped. + """ + return frozenset( + code + for code, total in head.items() + if total > (budget[code]["limit"] if code in budget else DEFAULT_LIMIT) + ) + + +def environment_fingerprints() -> tuple[str, ...]: + return tuple( + hashlib.sha256(path.read_bytes()).hexdigest() + for path in (PYRIGHT_CONFIG, UV_LOCK) + if path.exists() + ) + + +def cache_key(base_point: str, fingerprints: tuple[str, ...]) -> str: + return hashlib.sha256("|".join((base_point, *fingerprints)).encode()).hexdigest()[ + :16 + ] + + +def cache_path( + directory: Path, base_point: str, fingerprints: tuple[str, ...] +) -> Path: + return directory / f"{CACHE_FILE_PREFIX}{cache_key(base_point, fingerprints)}.json" + + +def default_cache_dir() -> Path: + common = Path(_run(["git", "rev-parse", "--git-common-dir"]).strip()) + resolved = common if common.is_absolute() else REPO_ROOT / common + return resolved / "litellm-lint-cache" + + +def load_cached_counts(path: Path) -> dict[str, int] | None: + try: + data = json.loads(path.read_text()) + except (OSError, json.JSONDecodeError): + return None + counts = data.get("counts") if isinstance(data, dict) else None + if not isinstance(counts, dict): + return None + if not all( + isinstance(code, str) and isinstance(total, int) and not isinstance(total, bool) + for code, total in counts.items() + ): + return None + return counts + + +def scratch_path(path: Path) -> Path: + """In-flight scratch for the tmp+rename write. Dot-prefixed so the prune + glob in `store_counts` can never match it (a concurrent run would otherwise + unlink it between write and rename), and pid-suffixed so two concurrent + writers of the same entry never share a scratch.""" + return path.with_name(f".{path.name}.{os.getpid()}.tmp") + + +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( + json.dumps( + {"base_point": base_point, "counts": dict(sorted(counts.items()))}, + indent=2, + ) + + "\n" + ) + scratch.replace(path) + + +def base_counts_cached( + base_point: str, + cache_dir: Path | None = None, + compute: Callable[[str], dict[str, int]] = base_counts, +) -> dict[str, int]: + """`base_counts` memoized on disk. The base tree at a given commit is + immutable, so its counts are a pure function of the merge-base plus the + environment fingerprints in the cache key; an empty result is never stored + because it is the signature of a crashed pass, not a clean tree.""" + directory = default_cache_dir() if cache_dir is None else cache_dir + path = cache_path(directory, base_point, environment_fingerprints()) + cached = load_cached_counts(path) + if cached is not None: + return cached + counts = compute(base_point) + if counts: + store_counts(directory, path, base_point, counts) + return counts + + def evaluate( head: Mapping[str, int], base: Mapping[str, int], @@ -185,7 +296,7 @@ def cmd_update(current: Mapping[str, int], base_ref: str = DEFAULT_BASE) -> None """ budget = json.loads(BUDGET_PATH.read_text()) if BUDGET_PATH.exists() else {} base_point = _run(["git", "merge-base", base_ref, "HEAD"]).strip() or base_ref - updated = ratcheted_budget(budget, current, base_counts(base_point)) + updated = ratcheted_budget(budget, current, base_counts_cached(base_point)) BUDGET_PATH.write_text(json.dumps(updated, indent=2, sort_keys=True) + "\n") cleared = sum(budget[code]["limit"] - updated[code]["limit"] for code in updated) print( @@ -205,8 +316,13 @@ def cmd_check(base_ref: str) -> None: f"nothing; refusing to certify a vacuous run." ) raise SystemExit(1) + if not over_ceiling(head, budget): + print( + f"OK: every rule is within its basedpyright limit ({sum(head.values())} errors total)" + ) + return base_point = _run(["git", "merge-base", base_ref, "HEAD"]).strip() or base_ref - base = base_counts(base_point) + base = base_counts_cached(base_point) if is_vacuous_run(base, budget): print( f"FAIL: basedpyright produced no errors for the base tree at " diff --git a/tests/e2e/CONTRIBUTING.md b/tests/e2e/CONTRIBUTING.md index 12aea6bbc25..4037f324393 100644 --- a/tests/e2e/CONTRIBUTING.md +++ b/tests/e2e/CONTRIBUTING.md @@ -9,15 +9,18 @@ When contributing to this directory, please first discuss the change you wish to ## Setup -The suites run against a live proxy, so bring one up first. `docker-compose.yml` here starts that proxy with its Postgres and Redis, serving `gateway/litellm-config.yml`; add any model, pricing override, or guardrail your test needs to that file and read it back in the test rather than hardcoding values. `gateway/` holds proxy configuration only, so never put tests there +The suites run against a live proxy, so bring one up first. `docker-compose.yml` here starts that proxy with a throwaway Postgres and Redis; `docker compose down -v` resets everything, so no state leaks between runs. The proxy config is inlined in the compose file under `configs`, prewired with example models (`gpt-5.5`, `claude-haiku-4-5`, `gemini-2.5-flash`, `openai-text-embedding-3-small`) whose keys come from your `.env`. If your test needs another model, a pricing override, or a guardrail declared up front, add it to that inline config and read it back in the test rather than hardcoding values ## Running the tests locally -1. Create a .env file and add provider keys: +1. Create a `.env` file in this directory with the provider keys the example models use: + ```bash OPENAI_API_KEY="sk-..." ANTHROPIC_API_KEY="sk-..." - + GEMINI_API_KEY="..." + ``` + 2. Bring the stack up from this directory: ```bash @@ -123,7 +126,17 @@ Mark live tests with `@pytest.mark.e2e` (on the class or the module). Pure cover Before you push -- Run basedpyright over your changes; the harness is fully typed and new code must not add `Any` or widen the budgets -- Bring the stack up with docker-compose from this directory and run your suite locally against it, so you exercise the same skip-vs-fail path CI does -- Use the config at `tests/e2e/gateway/litellm-config.yml` if your feature needs a model, pricing override, guardrail, or other proxy setting declared up front; add the deployment there and read it back in the test rather than hardcoding values -- Capture screenshots of the tests passing and attach them to the PR as proof of fix +1. Run basedpyright over your changes; the harness is fully typed and new code must not add `Any` or widen the budgets + +2. Add the models your test needs to the inline config in `docker-compose.yml` + +3. Bring the stack up and run your suite against it: + + ```bash + docker compose up -d + uv run pytest tests/e2e// -v + ``` + +4. Capture screenshots of the test run and attach them to the PR as proof + +5. If a test fails because it surfaced a real issue in the product, flag that explicitly in the PR rather than reworking the test until it passes diff --git a/tests/e2e/docker-compose.yml b/tests/e2e/docker-compose.yml new file mode 100644 index 00000000000..2de38ca5c91 --- /dev/null +++ b/tests/e2e/docker-compose.yml @@ -0,0 +1,87 @@ +# local setup to run e2e tests +configs: + litellm_config: + content: | + general_settings: + master_key: os.environ/LITELLM_MASTER_KEY + database_url: os.environ/DATABASE_URL + store_prompts_in_spend_logs: true + + litellm_settings: + drop_params: true + num_retries: 3 + request_timeout: 600 + cache: true + cache_params: + type: redis + host: redis + port: 6379 + + router_settings: + routing_strategy: simple-shuffle + num_retries: 3 + allowed_fails: 5 + cooldown_time: 30 + fallbacks: + - gemini-2.5-flash: ["gpt-5.5", "claude-haiku-4-5"] + + model_list: + - model_name: gpt-5.5 + litellm_params: + model: openai/gpt-5.5 + api_key: os.environ/OPENAI_API_KEY + + - model_name: claude-haiku-4-5 + litellm_params: + model: anthropic/claude-haiku-4-5 + api_key: os.environ/ANTHROPIC_API_KEY + + - model_name: gemini-2.5-flash + litellm_params: + model: gemini/gemini-2.5-flash + api_key: os.environ/GEMINI_API_KEY + + - model_name: openai-text-embedding-3-small + litellm_params: + model: openai/text-embedding-3-small + api_key: os.environ/OPENAI_API_KEY + +services: + litellm: + image: ghcr.io/berriai/litellm:main-latest + depends_on: + db: + condition: service_healthy + redis: + condition: service_healthy + env_file: .env + environment: + LITELLM_MASTER_KEY: sk-1234 + DATABASE_URL: postgresql://litellm:litellm@db:5432/litellm + ports: + - "4000:4000" + configs: + - source: litellm_config + target: /app/config.yaml + command: ["--config", "/app/config.yaml", "--port", "4000"] + +# throwaway db + db: + image: postgres:16 + environment: + POSTGRES_USER: litellm + POSTGRES_PASSWORD: litellm + POSTGRES_DB: litellm + healthcheck: + test: ["CMD-SHELL", "pg_isready -U litellm"] + interval: 3s + timeout: 3s + retries: 20 + + redis: + image: redis:7 + healthcheck: + test: ["CMD", "redis-cli", "ping"] + interval: 3s + timeout: 3s + retries: 20 diff --git a/tests/e2e/gateway/litellm-config.yml b/tests/e2e/gateway/litellm-config.yml deleted file mode 100644 index 3e5237b004b..00000000000 --- a/tests/e2e/gateway/litellm-config.yml +++ /dev/null @@ -1,287 +0,0 @@ -# This default config file aims to support most popular model providers out of the box - -#In general, the model name used by the client will be the same as the ones from the provider (For example, you will use "anthropic.claude-3-5-sonnet-20240620-v1:0" when you're calling LiteLLM just like you would when calling Amazon Bedrock directly) -#In the case where there are model name conflicts, a prefix will be used (For example, the Azure and the openAI model names conflict, so when you are using Azure, you will use "azure/gpt-4o-realtime-preview-2024-10-01") - -#Some model providers require additional user-specific configuration (such as Azure which requires you to specify your own api_base with your resource name, and your api_version). -#In this case, the provider is commented out, and you should uncomment it and provide your specific info - -#For more detailed information about each provider, refer to the docs: https://docs.litellm.ai/docs/providers - -#If you are not interested in a particular provider, just remove it from your config.yaml, and redeploy, and it will no longer show up in your LiteLLM deployment - -#If a particular provider is not working, double check your .env file, and make sure you have provided a valid api key for that provider, and then redeploy - -#Full details on guardrails here: https://docs.litellm.ai/docs/proxy/guardrails/bedrock -general_settings: - store_prompts_in_spend_logs: true - master_key: os.environ/LITELLM_MASTER_KEY - proxy_batch_write_at: 60 - database_connection_pool_limit: 10 - # disable_error_logs: True - forward_client_headers_to_llm_api: false - maximum_spend_logs_retention_period: "60d" # GSE-13389: Cleanup logs older than 60 days - maximum_spend_logs_cleanup_cron: "0 1 * * *" # 01:00 UTC daily = 18:00 PDT - database_url: os.environ/DATABASE_URL - control_plane_url: os.environ/CONTROL_PLANE_URL - alerts: ["email"] - - proxy_budget_rescheduler_min_time: 15 - proxy_budget_rescheduler_max_time: 20 - -# fallbacks: [{"gpt-4": ["anthropic.claude-3-5-sonnet-20240620-v1:0"]}] #Configure fallbacks for context window exeeded errors (In this example, we will fall back to Claude Sonnet if over 8000 tokens, which is gpt-4's limit) - # default_fallbacks: ["anthropic.claude-3-haiku-20240307-v1:0"] #Configure fallbacks for any error for every model (the above fallback configurations override this one) -# environment_variables: -# STORE_MODEL_IN_DB: 'True' -# LITELLM_LOG: "DEBUG" -litellm_settings: - drop_params: True - # Spend counters inherit this as their Redis TTL, so an idle counter goes cold and - # the next request reseeds it from the DB; kept short to exercise the cross-pod - # reseed path in test_spend_counter_reseed_e2e. Response-cache writes pass their own - # ttl and are unaffected. - default_redis_ttl: 20 - request_timeout: 600 - num_retries: 3 - json_logs: true - store_audit_logs: True - cache: true - cache_params: - type: redis - host: redis - port: 6379 - password: os.environ/REDIS_PASSWORD - namespace: litellm.caching - ttl: 16600 - # max_budget: 1000000000.0 # (float) sets max budget in dollars across the entire proxy across all API keys. Note, the budget does not apply to the master key. That is the only exception. - # budget_duration: 1mo # (str) frequency of budget reset - You can set duration as seconds ("30s"), minutes ("30m"), hours ("30h"), days ("30d"), months ("1mo"). - # max_internal_user_budget: 1000000000.0 # (float) sets default budget in dollars for each internal user. (Doesn't apply to Admins. Doesn't apply to Teams. Doesn't apply to master key) - # internal_user_budget_duration: "1mo" # (str) frequency of budget reset - You can set duration as seconds ("30s"), minutes ("30m"), hours ("30h"), days ("30d"), months ("1mo"). - # success_callback: ["s3_v2"] - # failure_callback: ["s3_v2"] - # service_callback: ["datadog"] - callbacks: ["arize_phoenix", "datadog", "smtp_email", "prometheus", "otel"] - require_auth_for_metrics_endpoint: false - #type: redis-semantic - #similarity_threshold: 0.8 # similarity threshold for semantic cache - #redis_semantic_cache_embedding_model: text-embedding-ada-002 # only works with text-embedding-ada-002 for now... https://github.com/BerriAI/litellm/issues/4001 - -router_settings: - routing_strategy: simple-shuffle - num_retries: 3 - allowed_fails: 5 - cooldown_time: 30 - # When gemini deployments are exhausted (provider 429 / auth), cross over to - # working models. Exercised by tests/e2e/router/test_rate_limiter.py. - fallbacks: - - gemini-2.5-flash: ["gpt-5.5", "claude-haiku-4-5"] - -#ttl: Optional[float] -#default_in_memory_ttl: Optional[float] -#default_in_redis_ttl: Optional[float] - -model_list: - - model_name: gpt-5.5 - litellm_params: - model: openai/gpt-5.5 - api_key: os.environ/OPENAI_API_KEY - - - model_name: claude-haiku-4-5 - litellm_params: - model: anthropic/claude-haiku-4-5 - api_key: os.environ/ANTHROPIC_API_KEY - - # Same underlying model via Vertex AI β€” distinct routing/auth path - # # (service-account JSON), so it gets its own model_name. - - model_name: gemini-2.5-flash-vertex - litellm_params: - model: vertex_ai/gemini-2.5-flash - vertex_project: os.environ/VERTEXAI_PROJECT - vertex_location: us-central1 - vertex_credentials: os.environ/VERTEXAI_CREDENTIALS - - - model_name: gemini-2.5-flash - litellm_params: - model: gemini/gemini-2.5-flash - api_key: os.environ/GEMINI_API_KEY - - # load balancing to a different deployment, if gemini gets rate limited. - - model_name: gemini-2.5-flash - litellm_params: - model: gemini/gemini-2.5-flash - api_key: os.environ/GEMINI_API_KEY - - # Custom per-token pricing exercised by llm_translation/test_custom_pricing_e2e.py. - # Rates deliberately exceed canonical gemini-2.5-flash (input 3e-7 / output 2.5e-6) - # so an override that is ignored or under-applied reports spend at the base rate - # and fails that test. The test reads these same rates back from this file. - - model_name: custom-priced-flash - litellm_params: - model: gemini/gemini-2.5-flash - api_key: os.environ/GEMINI_API_KEY - input_cost_per_token: 0.00005 - output_cost_per_token: 0.0001 - - # embedding models - - model_name: openai-text-embedding-3-small - litellm_params: - model: openai/text-embedding-3-small - api_key: os.environ/OPENAI_API_KEY - - - model_name: gemini-2-embedding - litellm_params: - model: gemini/gemini-2-embedding - api_key: os.environ/GEMINI_API_KEY - - - model_name: openai-realtime - litellm_params: - model: openai/gpt-realtime - api_key: os.environ/OPENAI_API_KEY - model_info: - mode: realtime - - - model_name: azure-realtime - litellm_params: - model: azure/gpt-realtime-2 - api_key: os.environ/AZURE_API_KEY - api_base: os.environ/AZURE_API_BASE - api_version: "2025-08-28" - realtime_protocol: GA # Possible values: "GA"/ "v1", "beta" - model_info: - mode: realtime - - - model_name: gemini-realtime - litellm_params: - model: gemini/gemini-3.1-flash-live-preview - api_key: os.environ/GEMINI_API_KEY - model_info: - mode: realtime - - - model_name: vertex-realtime - litellm_params: - model: vertex_ai/gemini-live-2.5-flash-preview-native-audio-09-2025 - vertex_project: os.environ/VERTEXAI_PROJECT - vertex_location: us-central1 - vertex_credentials: os.environ/VERTEXAI_CREDENTIALS - model_info: - mode: realtime - - - model_name: bedrock-realtime - litellm_params: - model: bedrock/amazon.nova-sonic-v1:0 - aws_region_name: us-east-1 - model_info: - mode: realtime - - - model_name: xai-realtime - litellm_params: - model: xai/grok-voice-latest - api_key: os.environ/XAI_API_KEY - model_info: - mode: realtime - - model_name: rust-ocr-mistral - litellm_params: - model: mistral/mistral-ocr-latest - api_key: os.environ/MISTRAL_API_KEY - - - model_name: rust-ocr-azure-ai - litellm_params: - model: azure_ai/mistral-document-ai-2505 - api_base: os.environ/AZURE_API_BASE - api_key: os.environ/AZURE_API_KEY - - - model_name: rust-ocr-azure-document-intelligence - litellm_params: - model: azure_ai/doc-intelligence/prebuilt-layout - api_base: os.environ/AZURE_DOCUMENT_INTELLIGENCE_ENDPOINT - api_key: os.environ/AZURE_DOCUMENT_INTELLIGENCE_API_KEY - - - model_name: rust-ocr-vertex-mistral - litellm_params: - model: vertex_ai/mistral-ocr-2505 - vertex_project: os.environ/VERTEXAI_PROJECT - vertex_location: us-central1 - - - model_name: rust-ocr-vertex-deepseek - litellm_params: - model: vertex_ai/deepseek-ocr-maas - vertex_project: os.environ/VERTEXAI_PROJECT - vertex_location: us-central1 - - # batch models exercised by tests/e2e/batches/ - - model_name: openai-batch - litellm_params: - model: openai/gpt-4o-mini - api_key: os.environ/OPENAI_API_KEY - model_info: - mode: batch - - - model_name: azure-batch - litellm_params: - model: azure/gpt-4.1-mini-batch - api_base: os.environ/AZURE_API_BASE - api_key: os.environ/AZURE_API_KEY - api_version: "2024-07-01-preview" - model_info: - mode: batch - - - model_name: vertex-batch - litellm_params: - model: vertex_ai/gemini-2.5-flash - vertex_project: os.environ/VERTEXAI_PROJECT - vertex_location: us-central1 - vertex_credentials: os.environ/VERTEXAI_CREDENTIALS - bucket_name: os.environ/GCS_BUCKET_NAME - model_info: - mode: batch - - - model_name: bedrock-batch - litellm_params: - model: bedrock/us.anthropic.claude-haiku-4-5-20251001-v1:0 - s3_bucket_name: os.environ/AWS_BATCH_S3_BUCKET - s3_region_name: us-west-2 - s3_access_key_id: os.environ/AWS_ACCESS_KEY_ID - s3_secret_access_key: os.environ/AWS_SECRET_ACCESS_KEY - aws_batch_role_arn: os.environ/AWS_BATCH_ROLE_ARN - model_info: - mode: batch - -files_settings: - - custom_llm_provider: openai - api_key: os.environ/OPENAI_API_KEY - - custom_llm_provider: azure - api_base: os.environ/AZURE_API_BASE - api_key: os.environ/AZURE_API_KEY - api_version: "2024-07-01-preview" - - custom_llm_provider: vertex_ai - vertex_project: os.environ/VERTEXAI_PROJECT - vertex_location: us-central1 - vertex_credentials: os.environ/VERTEXAI_CREDENTIALS - bucket_name: os.environ/GCS_BUCKET_NAME - - -mcp_servers: - deepwiki_mcp: - url: "https://mcp.deepwiki.com/mcp" - auth_type: none - description: "just a test" - - atlassian: - url: "https://mcp.atlassian.com/v1/mcp" - auth_type: oauth2 - authorization_url: https://auth.atlassian.com/authorize - - -guardrails: - - guardrail_name: "presidio-pii" - litellm_params: - guardrail: presidio - mode: pre_call - presidio_analyzer_api_base: os.environ/PRESIDIO_ANALYZER_API_BASE - presidio_anonymizer_api_base: os.environ/PRESIDIO_ANONYMIZER_API_BASE - default_on: false - pii_entities_config: - EMAIL_ADDRESS: BLOCK - CREDIT_CARD: BLOCK - US_SSN: BLOCK - PHONE_NUMBER: BLOCK diff --git a/tests/e2e/llm_translation/LLM_TRANSLATION_COVERAGE_MATRIX.md b/tests/e2e/llm_translation/LLM_TRANSLATION_COVERAGE_MATRIX.md index 5e4a448857f..44d6e79122e 100644 --- a/tests/e2e/llm_translation/LLM_TRANSLATION_COVERAGE_MATRIX.md +++ b/tests/e2e/llm_translation/LLM_TRANSLATION_COVERAGE_MATRIX.md @@ -28,7 +28,7 @@ Status: `covered` / `partial` / `gap`. |----------|---------------|-----------|------------|-------------|--------| | Gemini (`/gemini/v1beta/models/{m}:generateContent` / `:streamGenerateContent`) | live | live | live | live | **covered** | | Anthropic (`/anthropic/v1/messages`) | live | live | live | live | **covered** | -| Vertex AI (`/vertex_ai/...`) | - | - | - | - | gap (gcloud auth) | +| Vertex AI (`/vertex_ai/v1/projects/{p}/locations/{loc}/.../models/{m}:generateContent`) | live | - | - | live | **partial** | | OpenAI / Bedrock / Cohere / Mistral / VLLM | - | - | - | - | gap | Each covered cell asserts: `call_type == "pass_through_endpoint"`, `spend > 0`, @@ -60,11 +60,21 @@ most likely to silently break and the one a mock can't prove works. | `test_anthropic_passthrough_nonstreaming_logs_cost` | anthropic native, non-stream, cost | | `test_anthropic_passthrough_streaming_logs_cost` | anthropic native, stream, cost | | `test_anthropic_passthrough_tool_call_logs_cost` | anthropic native, tool call, cost | +| `test_vertex_passthrough_via_managed_model_logs_cost` | vertex_ai native, non-stream, cost | + +Vertex keeps the credential on the proxy like gemini/anthropic, but the deployment is +added at runtime instead of declared in the gateway config: the test POSTs `/model/new` +with `use_in_pass_through`, so the proxy registers that deployment's service account for +the `/vertex_ai` route, then deletes it on teardown. The passthrough call sends only its +litellm virtual key (`x-litellm-api-key`), no upstream bearer, and the proxy mints the +Vertex token itself. Credentials (`VERTEXAI_PROJECT` / `VERTEXAI_CREDENTIALS`) are read +from the same env the proxy uses, so the test never mints a token. ## Gaps -- Vertex / OpenAI / Bedrock / Cohere passthrough (same shape; add once the - provider credential is configured; Vertex is closest - route exists, auth stale). +- Vertex streaming / tool-call passthrough (non-streaming + cost now covered). +- OpenAI / Bedrock / Cohere passthrough (same shape; add once the provider + credential is configured). - Non-passthrough tool calls over `/chat/completions` end to end with cost. - Image / audio / rerank / responses / realtime translation + cost. - Streaming cost-injection (`include_cost_in_streaming_usage`); passthrough on diff --git a/tests/e2e/llm_translation/passthrough_client.py b/tests/e2e/llm_translation/passthrough_client.py index fff4064a328..77dcf68a1e3 100644 --- a/tests/e2e/llm_translation/passthrough_client.py +++ b/tests/e2e/llm_translation/passthrough_client.py @@ -48,6 +48,16 @@ class AnthropicHeaders(Headers): tags: str | None = None +class VertexHeaders(Headers): + # Only the litellm virtual key; the /vertex_ai passthrough mints the Vertex token + # from the proxy's own service account (the deployment marked use_in_pass_through), + # so no upstream Authorization bearer is sent from the client. + x_litellm_api_key: str = Field(serialization_alias="x-litellm-api-key") + content_type: str = Field( + default="application/json", serialization_alias="Content-Type" + ) + + class AltSseParams(BaseModel): alt: str = "sse" @@ -132,6 +142,23 @@ class PassthroughClient: stream=True, ) + # ---- Vertex AI native passthrough (/vertex_ai/v1/projects/...) ------- + + def vertex_generate( + self, key: str, project: str, location: str, model: str, text: str + ) -> StreamingResponse: + path = ( + f"/vertex_ai/v1/projects/{project}/locations/{location}" + f"/publishers/google/models/{model}:generateContent" + ) + return self.gateway.transport.send( + path, + headers=VertexHeaders(x_litellm_api_key=key), + json=GeminiGenerateBody( + contents=[GeminiContent(parts=[GeminiPart(text=text)])] + ), + ) + # ---- Anthropic native passthrough (/anthropic/v1/messages) ---------- def anthropic_message( diff --git a/tests/e2e/llm_translation/test_vertex_passthrough_e2e.py b/tests/e2e/llm_translation/test_vertex_passthrough_e2e.py new file mode 100644 index 00000000000..78d2bb358d2 --- /dev/null +++ b/tests/e2e/llm_translation/test_vertex_passthrough_e2e.py @@ -0,0 +1,166 @@ +"""Live e2e: a native Vertex AI generateContent call over the proxy's /vertex_ai +passthrough is forwarded to Vertex and still logged as a costed SpendLogs row. + +Ports the de-flake of the SDK-based spend test (#31689). That test configured the +vertexai SDK with an api_endpoint override pointing at the proxy, but the SDK +intermittently ignored the override and billed the public Vertex endpoint directly, +so the request never reached LiteLLM and no spend was recorded; the bypass, not +logging lag, was the flake. Driving raw HTTP through the shared transport always +reaches the proxy, which the harness already guarantees, so the only residual +nondeterminism is the ~60s async spend flush the poll absorbs. + +The vertex deployment is added at runtime through the management endpoint rather than +declared in the gateway config: the test POSTs /model/new with use_in_pass_through so +the proxy registers that deployment's service account for the /vertex_ai route, then +deletes it on teardown. The credential is the one the proxy already holds (read from +the same VERTEXAI_CREDENTIALS the deployment uses), so the passthrough call sends only +its litellm virtual key in x-litellm-api-key and no upstream bearer, and the proxy +mints the Vertex token itself. The test never mints a token. + +Asserts both sides of the promise: the forward succeeds (2xx with a candidate) and +the costed row lands (call_type pass_through_endpoint, vertex_ai provider, a gemini +model, spend > 0), correlated by the x-litellm-call-id header. +""" + +import os + +import pytest +from pydantic import BaseModel + +from e2e_config import unique_marker +from e2e_http import NoBody, require_successful_call, unwrap +from lifecycle import ResourceManager +from models import SpendLogRow +from passthrough_client import PassthroughClient + +pytestmark = pytest.mark.e2e + +VERTEX_MODEL = "gemini-2.5-flash" +# The added deployment's region and the passthrough URL's region are the same constant, +# so they always agree; the proxy registers passthrough credentials per project+region. +VERTEX_LOCATION = os.environ.get("VERTEXAI_LOCATION", "us-central1") + + +@pytest.fixture(scope="session") +def vertex_project() -> str: + """The Vertex project to bill, read from the same VERTEXAI_PROJECT the proxy uses. + Skip when unset, since that is an environment gap rather than a behavior failure.""" + project = os.environ.get("VERTEXAI_PROJECT") + if not project: + pytest.skip("set VERTEXAI_PROJECT (the project the vertex deployment bills)") + return project + + +@pytest.fixture(scope="session") +def vertex_credentials() -> str: + """The service-account JSON the added deployment authenticates with, the same + VERTEXAI_CREDENTIALS the proxy holds. Skip when unset.""" + credentials = os.environ.get("VERTEXAI_CREDENTIALS") + if not credentials: + pytest.skip("set VERTEXAI_CREDENTIALS (the vertex service-account JSON)") + return credentials + + +class _VertexDeploymentParams(BaseModel): + model: str + vertex_project: str + vertex_location: str + vertex_credentials: str + use_in_pass_through: bool + + +class _ModelInfoId(BaseModel): + id: str + + +class _ModelNewBody(BaseModel): + model_name: str + litellm_params: _VertexDeploymentParams + model_info: _ModelInfoId + + +class _ModelNewResponse(BaseModel): + model_id: str + + +class _ModelDeleteBody(BaseModel): + id: str + + +def _add_vertex_passthrough_model( + client: PassthroughClient, model_name: str, project: str, credentials: str +) -> str: + return unwrap( + client.gateway.transport.post( + "/model/new", + headers=client.gateway.transport.master, + json=_ModelNewBody( + model_name=model_name, + litellm_params=_VertexDeploymentParams( + model=f"vertex_ai/{VERTEX_MODEL}", + vertex_project=project, + vertex_location=VERTEX_LOCATION, + vertex_credentials=credentials, + use_in_pass_through=True, + ), + model_info=_ModelInfoId(id=model_name), + ), + response_type=_ModelNewResponse, + ) + ).model_id + + +def _delete_model(client: PassthroughClient, model_id: str) -> None: + _ = client.gateway.transport.post( + "/model/delete", + headers=client.gateway.transport.master, + json=_ModelDeleteBody(id=model_id), + response_type=NoBody, + ) + + +def _costed_row(client: PassthroughClient, call_id: str | None) -> SpendLogRow: + """The passthrough call's SpendLogs row, polled until it carries a cost. + + A 2xx passthrough call that produced no costed row is a hard failure, not a skip: + a billed Vertex call that LiteLLM did not track is the exact regression #31689 + guards against.""" + assert call_id, "vertex passthrough response had no x-litellm-call-id header" + rows = client.gateway.poll_logs_for_request_id( + call_id, + predicate=lambda rs: (rs[0].spend or 0) > 0, + ) + assert rows, f"no SpendLogs row for vertex passthrough call_id {call_id}" + row = rows[0] + assert row.call_type == "pass_through_endpoint", f"unexpected call_type: {row}" + assert (row.spend or 0) > 0, f"vertex passthrough call was not costed: {row}" + assert row.status == "success", f"unexpected status: {row}" + return row + + +class TestVertexPassthroughSpendTracking: + def test_vertex_passthrough_via_managed_model_logs_cost( + self, + client: PassthroughClient, + scoped_key: str, + resources: ResourceManager, + vertex_project: str, + vertex_credentials: str, + ) -> None: + model_name = f"e2e-vertex-pt-{unique_marker()}" + model_id = _add_vertex_passthrough_model(client, model_name, vertex_project, vertex_credentials) + resources.defer(lambda: _delete_model(client, model_id)) + + result = client.vertex_generate( + key=scoped_key, + project=vertex_project, + location=VERTEX_LOCATION, + model=VERTEX_MODEL, + text=f"reply with one word {unique_marker()}", + ) + require_successful_call(result) + assert '"candidates"' in result.body, f"vertex passthrough returned no candidates: {result.body[:300]}" + + row = _costed_row(client, result.call_id) + assert row.custom_llm_provider == "vertex_ai", f"passthrough spend logged under the wrong provider: {row}" + assert "gemini" in (row.model or ""), f"unexpected model in spend log: {row}" diff --git a/tests/logging_callback_tests/test_logging_redaction_e2e_test.py b/tests/logging_callback_tests/test_logging_redaction_e2e_test.py index 3f4b446bea5..891e5020f37 100644 --- a/tests/logging_callback_tests/test_logging_redaction_e2e_test.py +++ b/tests/logging_callback_tests/test_logging_redaction_e2e_test.py @@ -56,69 +56,56 @@ async def test_global_redaction_on(): ) -@pytest.mark.parametrize("turn_off_message_logging", [True, False]) +@pytest.mark.parametrize( + "dynamic_turn_off, expect_redacted", + [(True, True), (False, False)], +) @pytest.mark.asyncio -async def test_global_redaction_ignores_dynamic_param(turn_off_message_logging): - """ - Request-body `turn_off_message_logging` is no longer honored as a dynamic - callback param β€” global setting (or admin-configured key/team config) wins. - With global redaction ON, the caller cannot disable redaction via the - request body. - """ +async def test_dynamic_turn_off_message_logging_overrides_global_on(dynamic_turn_off, expect_redacted): litellm.turn_off_message_logging = True test_custom_logger = TestCustomLogger() litellm.callbacks = [test_custom_logger] - response = await litellm.acompletion( + await litellm.acompletion( model="gpt-5-mini", messages=[{"role": "user", "content": "hi"}], - turn_off_message_logging=turn_off_message_logging, + turn_off_message_logging=dynamic_turn_off, mock_response="hello", ) await asyncio.sleep(1) standard_logging_payload = test_custom_logger.logged_standard_logging_payload assert standard_logging_payload is not None - print( - "logged standard logging payload", - json.dumps(standard_logging_payload, indent=2), - ) - response = standard_logging_payload["response"] - assert response["choices"][0]["message"]["content"] == "redacted-by-litellm" - assert standard_logging_payload["messages"][0]["content"] == "redacted-by-litellm" + expected_response_content = "redacted-by-litellm" if expect_redacted else "hello" + expected_message_content = "redacted-by-litellm" if expect_redacted else "hi" + assert standard_logging_payload["response"]["choices"][0]["message"]["content"] == expected_response_content + assert standard_logging_payload["messages"][0]["content"] == expected_message_content -@pytest.mark.parametrize("turn_off_message_logging", [True, False]) +@pytest.mark.parametrize( + "dynamic_turn_off, expect_redacted", + [(True, True), (False, False)], +) @pytest.mark.asyncio -async def test_global_redaction_off_ignores_dynamic_param(turn_off_message_logging): - """ - Request-body `turn_off_message_logging` is no longer honored as a dynamic - callback param β€” global setting (or admin-configured key/team config) wins. - With global redaction OFF, the caller cannot enable redaction via the - request body. - """ +async def test_dynamic_turn_off_message_logging_overrides_global_off(dynamic_turn_off, expect_redacted): litellm.turn_off_message_logging = False test_custom_logger = TestCustomLogger() litellm.callbacks = [test_custom_logger] - response = await litellm.acompletion( + await litellm.acompletion( model="gpt-5-mini", messages=[{"role": "user", "content": "hi"}], - turn_off_message_logging=turn_off_message_logging, + turn_off_message_logging=dynamic_turn_off, mock_response="hello", ) await asyncio.sleep(1) standard_logging_payload = test_custom_logger.logged_standard_logging_payload assert standard_logging_payload is not None - print( - "logged standard logging payload", - json.dumps(standard_logging_payload, indent=2), - ) - assert ( - standard_logging_payload["response"]["choices"][0]["message"]["content"] - == "hello" - ) - assert standard_logging_payload["messages"][0]["content"] == "hi" + + expected_response_content = "redacted-by-litellm" if expect_redacted else "hello" + expected_message_content = "redacted-by-litellm" if expect_redacted else "hi" + assert standard_logging_payload["response"]["choices"][0]["message"]["content"] == expected_response_content + assert standard_logging_payload["messages"][0]["content"] == expected_message_content @pytest.mark.asyncio diff --git a/tests/ocr_tests/test_ocr_azure_document_intelligence.py b/tests/ocr_tests/test_ocr_azure_document_intelligence.py index 7269890b7b6..09c21842ad7 100644 --- a/tests/ocr_tests/test_ocr_azure_document_intelligence.py +++ b/tests/ocr_tests/test_ocr_azure_document_intelligence.py @@ -61,8 +61,8 @@ class TestAzureDocumentIntelligencePagesParam: def cfg(self) -> AzureDocumentIntelligenceOCRConfig: return AzureDocumentIntelligenceOCRConfig() - def test_get_supported_ocr_params_includes_pages(self, cfg): - assert cfg.get_supported_ocr_params("prebuilt-layout") == ["pages"] + def test_get_supported_ocr_params_includes_pages_and_features(self, cfg): + assert cfg.get_supported_ocr_params("prebuilt-layout") == ["pages", "features"] def test_map_ocr_params_mistral_zero_based_int_list(self, cfg): mapped = cfg.map_ocr_params({"pages": [0, 1, 2]}, {}, "prebuilt-layout") diff --git a/tests/test_litellm/a2a_protocol/__init__.py b/tests/test_litellm/a2a_protocol/__init__.py new file mode 100644 index 00000000000..e69de29bb2d diff --git a/tests/test_litellm/a2a_protocol/test_cost_calculator.py b/tests/test_litellm/a2a_protocol/test_cost_calculator.py index bf03562f8ae..a29f012170f 100644 --- a/tests/test_litellm/a2a_protocol/test_cost_calculator.py +++ b/tests/test_litellm/a2a_protocol/test_cost_calculator.py @@ -103,9 +103,7 @@ async def _mock_stream_messages(a2a_client: Any, request: Any) -> AsyncIterator[ kind="message", ) for _ in range(2): - yield SendStreamingMessageResponse( - root=SendStreamingMessageSuccessResponse(id=request.id, result=msg) - ) + yield SendStreamingMessageResponse(root=SendStreamingMessageSuccessResponse(id=request.id, result=msg)) class CostLogger(CustomLogger): @@ -119,9 +117,7 @@ class CostLogger(CustomLogger): slp = kwargs.get("standard_logging_object") if slp: self.response_cost = ( - slp.get("response_cost") - if isinstance(slp, dict) - else getattr(slp, "response_cost", None) + slp.get("response_cost") if isinstance(slp, dict) else getattr(slp, "response_cost", None) ) @@ -160,6 +156,43 @@ async def test_asend_message_uses_cost_per_query(): assert cost_logger.response_cost == 0.05 +@pytest.mark.asyncio +async def test_asend_message_uses_cost_per_query_from_litellm_params_dict(): + """ + Proxy passes agent pricing as the litellm_params dict param (not top-level + kwargs). Regression for cost_per_query landing at $0 on the native path. + """ + from litellm.a2a_protocol import asend_message + + litellm.logging_callback_manager._reset_all_callbacks() + cost_logger = CostLogger() + litellm.callbacks = [cost_logger] + + mock_client = MagicMock() + mock_client._litellm_agent_card = MagicMock() + mock_client._litellm_agent_card.name = "test-agent" + + mock_request = _make_send_message_request("test-123") + + with patch( + "litellm.a2a_protocol.main._execute_a2a_send_with_retry", + new=_mock_execute_a2a_send, + ): + await asend_message( + a2a_client=mock_client, + request=mock_request, + litellm_params={ + "cost_per_query": 0.5, + "input_cost_per_token": 0.099999, + "output_cost_per_token": 0.1, + }, + ) + + await asyncio.sleep(0.1) + + assert cost_logger.response_cost == 0.5 + + class TokenAndCostLogger(CustomLogger): """Custom logger to capture both token counts and cost.""" @@ -173,19 +206,13 @@ class TokenAndCostLogger(CustomLogger): slp = kwargs.get("standard_logging_object") if slp: self.response_cost = ( - slp.get("response_cost") - if isinstance(slp, dict) - else getattr(slp, "response_cost", None) + slp.get("response_cost") if isinstance(slp, dict) else getattr(slp, "response_cost", None) ) self.prompt_tokens = ( - slp.get("prompt_tokens") - if isinstance(slp, dict) - else getattr(slp, "prompt_tokens", None) + slp.get("prompt_tokens") if isinstance(slp, dict) else getattr(slp, "prompt_tokens", None) ) self.completion_tokens = ( - slp.get("completion_tokens") - if isinstance(slp, dict) - else getattr(slp, "completion_tokens", None) + slp.get("completion_tokens") if isinstance(slp, dict) else getattr(slp, "completion_tokens", None) ) @@ -207,9 +234,7 @@ async def test_asend_message_uses_input_output_cost_per_token(): mock_client._litellm_agent_card = MagicMock() mock_client._litellm_agent_card.name = "test-agent" - mock_request = _make_send_message_request( - "test-123", user_text="Hello, what can you do?" - ) + mock_request = _make_send_message_request("test-123", user_text="Hello, what can you do?") # Define specific cost per token values input_cost_per_token = 0.00001 # $0.01 per 1000 tokens @@ -246,15 +271,11 @@ async def test_asend_message_uses_input_output_cost_per_token(): assert response_cost is not None, "response_cost should be captured" # Calculate expected cost - expected_cost = (prompt_tokens * input_cost_per_token) + ( - completion_tokens * output_cost_per_token - ) + expected_cost = (prompt_tokens * input_cost_per_token) + (completion_tokens * output_cost_per_token) print(f"expected_cost: {expected_cost}") # Verify exact cost calculation - assert ( - response_cost == expected_cost - ), f"response_cost {response_cost} should equal expected {expected_cost}" + assert response_cost == expected_cost, f"response_cost {response_cost} should equal expected {expected_cost}" class AgentIdLogger(CustomLogger): @@ -305,9 +326,9 @@ async def test_asend_message_passes_agent_id_to_callback(): await asyncio.sleep(0.1) # Verify agent_id was passed to callback - assert ( - agent_id_logger.agent_id == test_agent_id - ), f"Expected agent_id '{test_agent_id}', got '{agent_id_logger.agent_id}'" + assert agent_id_logger.agent_id == test_agent_id, ( + f"Expected agent_id '{test_agent_id}', got '{agent_id_logger.agent_id}'" + ) class MetadataLogger(CustomLogger): @@ -418,9 +439,7 @@ async def test_asend_message_streaming_triggers_callbacks(): assert len(chunks) == 2 # Verify callbacks WERE triggered after stream completed - assert ( - callback_logger.kwargs is not None - ), "Streaming should trigger callbacks after completion" - assert ( - callback_logger.agent_id == test_agent_id - ), f"Expected agent_id '{test_agent_id}', got '{callback_logger.agent_id}'" + assert callback_logger.kwargs is not None, "Streaming should trigger callbacks after completion" + assert callback_logger.agent_id == test_agent_id, ( + f"Expected agent_id '{test_agent_id}', got '{callback_logger.agent_id}'" + ) diff --git a/tests/test_litellm/a2a_protocol/test_utils.py b/tests/test_litellm/a2a_protocol/test_utils.py new file mode 100644 index 00000000000..8a219211c62 --- /dev/null +++ b/tests/test_litellm/a2a_protocol/test_utils.py @@ -0,0 +1,41 @@ +"""Tests for litellm/a2a_protocol/utils.py token/usage extraction.""" + +import pytest + +pytest.importorskip("a2a.compat.v0_3.types") + +from a2a.compat.v0_3.types import MessageSendParams, SendMessageRequest + +from litellm.a2a_protocol.utils import A2ARequestUtils + + +def _request(user_text: str) -> SendMessageRequest: + return SendMessageRequest( + id="r1", + params=MessageSendParams( + message={ + "messageId": "m1", + "role": "user", + "parts": [{"kind": "text", "text": user_text}], + } + ), + ) + + +def test_calculate_usage_counts_input_tokens_from_request_object(): + """Regression: request-side Part is a RootModel; input tokens must be counted.""" + request = _request("count these input tokens please") + response_dict = { + "result": { + "kind": "message", + "parts": [{"kind": "text", "text": "ok"}], + } + } + + prompt_tokens, completion_tokens, total_tokens = A2ARequestUtils.calculate_usage_from_request_response( + request=request, response_dict=response_dict + ) + + assert prompt_tokens > 0 + assert completion_tokens > 0 + assert total_tokens == prompt_tokens + completion_tokens diff --git a/tests/test_litellm/integrations/test_prometheus_budget_metrics_timeout.py b/tests/test_litellm/integrations/test_prometheus_budget_metrics_timeout.py new file mode 100644 index 00000000000..a4d245e9dc0 --- /dev/null +++ b/tests/test_litellm/integrations/test_prometheus_budget_metrics_timeout.py @@ -0,0 +1,168 @@ +""" +Unit tests for the per-request budget-metric emission timeout in +PrometheusLogger._increment_remaining_budget_metrics. + +A slow Redis/DB lookup in one of the budget branches must not let the gather run +unbounded; it is wrapped in asyncio.wait_for so the success-logging coroutine +cannot exceed the LoggingWorker watchdog and get the whole event cancelled. +""" + +import asyncio +from unittest.mock import AsyncMock, patch + +import pytest +from prometheus_client import REGISTRY + +from litellm.integrations.prometheus import ( + PrometheusLogger, + _DEFAULT_BUDGET_METRICS_PER_REQUEST_TIMEOUT, + _get_budget_metrics_per_request_timeout, +) + +TIMEOUT_ENV = "PROMETHEUS_BUDGET_METRICS_PER_REQUEST_TIMEOUT" + + +@pytest.fixture(autouse=True) +def cleanup_prometheus_registry(): + collectors = list(REGISTRY._collector_to_names.keys()) + for collector in collectors: + try: + REGISTRY.unregister(collector) + except Exception: + pass + yield + collectors = list(REGISTRY._collector_to_names.keys()) + for collector in collectors: + try: + REGISTRY.unregister(collector) + except Exception: + pass + + +@pytest.fixture +def prometheus_logger(): + return PrometheusLogger() + + +def _call_increment(logger: PrometheusLogger): + return logger._increment_remaining_budget_metrics( + user_api_team="team-1", + user_api_team_alias="team-alias", + user_api_key="key-1", + user_api_key_alias="key-alias", + litellm_params={"metadata": {}}, + response_cost=0.01, + user_id="user-1", + user_api_key_org_id="org-1", + ) + + +def _skip_logged(debug_mock) -> bool: + return any("skipping" in str(call.args[0]) for call in debug_mock.call_args_list if call.args) + + +@pytest.mark.asyncio +async def test_budget_metric_emission_skips_on_timeout(prometheus_logger, monkeypatch): + """A branch slower than the timeout is skipped without propagating, and the + skip is logged instead of cancelling the success-logging event.""" + monkeypatch.setenv(TIMEOUT_ENV, "0.05") + + async def _slow_branch(**kwargs): + await asyncio.sleep(30) + + prometheus_logger._set_api_key_budget_metrics_after_api_request = _slow_branch + prometheus_logger._set_team_budget_metrics_after_api_request = AsyncMock() + prometheus_logger._set_user_budget_metrics_after_api_request = AsyncMock() + prometheus_logger._set_org_budget_metrics_after_api_request = AsyncMock() + + with patch("litellm.integrations.prometheus.verbose_logger") as mock_logger: + await _call_increment(prometheus_logger) + + assert _skip_logged(mock_logger.debug) + + +@pytest.mark.asyncio +async def test_budget_metric_emission_completes_within_timeout(prometheus_logger, monkeypatch): + """With a generous timeout every branch is awaited and no skip is logged.""" + monkeypatch.setenv(TIMEOUT_ENV, "5.0") + + prometheus_logger._set_api_key_budget_metrics_after_api_request = AsyncMock() + prometheus_logger._set_team_budget_metrics_after_api_request = AsyncMock() + prometheus_logger._set_user_budget_metrics_after_api_request = AsyncMock() + prometheus_logger._set_org_budget_metrics_after_api_request = AsyncMock() + + with patch("litellm.integrations.prometheus.verbose_logger") as mock_logger: + await _call_increment(prometheus_logger) + + assert prometheus_logger._set_api_key_budget_metrics_after_api_request.await_count == 1 + assert prometheus_logger._set_team_budget_metrics_after_api_request.await_count == 1 + assert prometheus_logger._set_user_budget_metrics_after_api_request.await_count == 1 + assert prometheus_logger._set_org_budget_metrics_after_api_request.await_count == 1 + assert not _skip_logged(mock_logger.debug) + + +@pytest.mark.asyncio +async def test_invalid_timeout_env_falls_back_to_default(prometheus_logger, monkeypatch): + """A malformed timeout env value must not raise (which would recreate the + failure mode); it falls back to the default and every branch still runs.""" + monkeypatch.setenv(TIMEOUT_ENV, "not-a-number") + + prometheus_logger._set_api_key_budget_metrics_after_api_request = AsyncMock() + prometheus_logger._set_team_budget_metrics_after_api_request = AsyncMock() + prometheus_logger._set_user_budget_metrics_after_api_request = AsyncMock() + prometheus_logger._set_org_budget_metrics_after_api_request = AsyncMock() + + await _call_increment(prometheus_logger) + + assert prometheus_logger._set_api_key_budget_metrics_after_api_request.await_count == 1 + assert prometheus_logger._set_org_budget_metrics_after_api_request.await_count == 1 + + +@pytest.mark.parametrize("value", ["not-a-number", "0", "-1", "nan", "inf", "-inf"]) +def test_unusable_timeout_env_falls_back_to_default(value, monkeypatch): + """Values that parse but disable or unbound the timeout (0, negative, nan, + inf) must fall back to the default instead of being used; otherwise they + either skip every emission or recreate the unbounded-wait failure mode.""" + monkeypatch.setenv(TIMEOUT_ENV, value) + + assert _get_budget_metrics_per_request_timeout() == _DEFAULT_BUDGET_METRICS_PER_REQUEST_TIMEOUT + + +@pytest.mark.parametrize("value,expected", [("0.05", 0.05), ("5.0", 5.0), ("30", 30.0)]) +def test_valid_timeout_env_is_used(value, expected, monkeypatch): + """A finite positive value is parsed and returned unchanged.""" + monkeypatch.setenv(TIMEOUT_ENV, value) + + assert _get_budget_metrics_per_request_timeout() == expected + + +def test_missing_timeout_env_uses_default(monkeypatch): + """With the env unset the default is returned.""" + monkeypatch.delenv(TIMEOUT_ENV, raising=False) + + assert _get_budget_metrics_per_request_timeout() == _DEFAULT_BUDGET_METRICS_PER_REQUEST_TIMEOUT + + +@pytest.mark.asyncio +async def test_outer_cancellation_still_propagates(prometheus_logger, monkeypatch): + """Only asyncio.TimeoutError is swallowed; an outer cancellation (cooperative + shutdown / watchdog) injected while awaiting must still propagate.""" + monkeypatch.setenv(TIMEOUT_ENV, "30") + + started = asyncio.Event() + + async def _slow_branch(**kwargs): + started.set() + await asyncio.sleep(30) + + prometheus_logger._set_api_key_budget_metrics_after_api_request = _slow_branch + prometheus_logger._set_team_budget_metrics_after_api_request = AsyncMock() + prometheus_logger._set_user_budget_metrics_after_api_request = AsyncMock() + prometheus_logger._set_org_budget_metrics_after_api_request = AsyncMock() + + task = asyncio.create_task(_call_increment(prometheus_logger)) + await started.wait() + task.cancel() + + with pytest.raises(asyncio.CancelledError): + await task diff --git a/tests/test_litellm/integrations/test_s3_v2.py b/tests/test_litellm/integrations/test_s3_v2.py index 3f21de41c53..246b378c982 100644 --- a/tests/test_litellm/integrations/test_s3_v2.py +++ b/tests/test_litellm/integrations/test_s3_v2.py @@ -1194,3 +1194,156 @@ def test_s3_callback_params_override_empty_dict_is_opt_in(): assert logger.s3_bucket_name is None finally: litellm.s3_callback_params = original + + +def _expected_content_md5(payload: dict) -> str: + import base64 + import hashlib + + from litellm.litellm_core_utils.safe_json_dumps import safe_dumps + + json_string = safe_dumps(payload) + return base64.b64encode( + hashlib.md5(json_string.encode("utf-8"), usedforsecurity=False).digest() + ).decode() + + +def _require_non_security_md5(monkeypatch): + import hashlib + + original_md5 = hashlib.md5 + + def fips_md5(data=b"", *, usedforsecurity=True): + if usedforsecurity: + raise ValueError("MD5 blocked for security use") + return original_md5(data, usedforsecurity=usedforsecurity) + + monkeypatch.setattr(hashlib, "md5", fips_md5) + + +@pytest.mark.asyncio +async def test_async_upload_sets_content_md5_header(monkeypatch): + """ + Object Lock buckets reject PUTs without a Content-MD5 header (AWS spec). + The async upload must send a base64 md5 of the exact signed body. + """ + from unittest.mock import AsyncMock, MagicMock + + from litellm.types.integrations.s3_v2 import s3BatchLoggingElement + + logger = S3Logger( + s3_bucket_name="test-bucket", + s3_aws_access_key_id="test-key", + s3_aws_secret_access_key="test-secret", + s3_region_name="us-east-1", + ) + + payload = {"test": "content-md5"} + test_element = s3BatchLoggingElement( + s3_object_key="2025-09-14/test-md5.json", + payload=payload, + s3_object_download_filename="test-md5.json", + ) + _require_non_security_md5(monkeypatch) + + response = MagicMock() + response.status_code = 200 + response.raise_for_status = MagicMock() + logger.async_httpx_client = AsyncMock() + logger.async_httpx_client.put.return_value = response + + await logger.async_upload_data_to_s3(test_element) + + headers = logger.async_httpx_client.put.call_args.kwargs["headers"] + assert headers["Content-MD5"] == _expected_content_md5(payload) + assert "x-amz-server-side-encryption" not in headers + + +def test_sync_upload_sets_content_md5_header(monkeypatch): + """The sync upload path must also send Content-MD5 for Object Lock buckets.""" + from unittest.mock import MagicMock + + from litellm.types.integrations.s3_v2 import s3BatchLoggingElement + + logger = S3Logger( + s3_bucket_name="test-bucket", + s3_aws_access_key_id="test-key", + s3_aws_secret_access_key="test-secret", + s3_region_name="us-east-1", + ) + + payload = {"test": "sync-content-md5"} + test_element = s3BatchLoggingElement( + s3_object_key="2025-09-14/test-sync-md5.json", + payload=payload, + s3_object_download_filename="test-sync-md5.json", + ) + _require_non_security_md5(monkeypatch) + + response = MagicMock() + response.status_code = 200 + response.raise_for_status = MagicMock() + mock_sync_client = MagicMock() + mock_sync_client.put.return_value = response + + with patch( + "litellm.integrations.s3_v2._get_httpx_client", + return_value=mock_sync_client, + ): + logger.upload_data_to_s3(test_element) + + headers = mock_sync_client.put.call_args.kwargs["headers"] + assert headers["Content-MD5"] == _expected_content_md5(payload) + assert "x-amz-server-side-encryption" not in headers + + +@pytest.mark.asyncio +async def test_async_upload_sets_server_side_encryption_header_when_configured(): + """ + When s3_server_side_encryption is set (e.g. buckets with a KMS default + encryption policy), the PUT must carry x-amz-server-side-encryption. + """ + from unittest.mock import AsyncMock, MagicMock + + from litellm.types.integrations.s3_v2 import s3BatchLoggingElement + + logger = S3Logger( + s3_bucket_name="test-bucket", + s3_aws_access_key_id="test-key", + s3_aws_secret_access_key="test-secret", + s3_region_name="us-east-1", + s3_server_side_encryption="aws:kms", + ) + + test_element = s3BatchLoggingElement( + s3_object_key="2025-09-14/test-sse.json", + payload={"test": "sse"}, + s3_object_download_filename="test-sse.json", + ) + + response = MagicMock() + response.status_code = 200 + response.raise_for_status = MagicMock() + logger.async_httpx_client = AsyncMock() + logger.async_httpx_client.put.return_value = response + + await logger.async_upload_data_to_s3(test_element) + + headers = logger.async_httpx_client.put.call_args.kwargs["headers"] + assert headers["x-amz-server-side-encryption"] == "aws:kms" + + +def test_s3_server_side_encryption_read_from_callback_params(): + """s3_server_side_encryption can be configured via s3_callback_params.""" + import litellm + + original = litellm.s3_callback_params + litellm.s3_callback_params = { + "s3_bucket_name": "from-global", + "s3_server_side_encryption": "aws:kms", + } + try: + logger = S3Logger() + assert logger.s3_server_side_encryption == "aws:kms" + finally: + litellm.s3_callback_params = original diff --git a/tests/test_litellm/litellm_core_utils/prompt_templates/test_litellm_core_utils_prompt_templates_factory.py b/tests/test_litellm/litellm_core_utils/prompt_templates/test_litellm_core_utils_prompt_templates_factory.py index 864f685e7c9..1d5289737f1 100644 --- a/tests/test_litellm/litellm_core_utils/prompt_templates/test_litellm_core_utils_prompt_templates_factory.py +++ b/tests/test_litellm/litellm_core_utils/prompt_templates/test_litellm_core_utils_prompt_templates_factory.py @@ -1,5 +1,6 @@ import base64 import json +import os from unittest.mock import MagicMock, patch import pytest @@ -2744,102 +2745,132 @@ def test_add_cache_point_tool_block_passes_ttl_for_claude_4_5(): TTL ordering constraint (tools -> system -> messages). Ref: https://github.com/BerriAI/litellm/issues/XXXXX + + Forces the bundled local cost map so ttl eligibility (driven by + `cache_creation_input_token_cost_above_1hr` in litellm.model_cost) reads + this branch's pricing data rather than the network-fetched `main` copy, + which lacks the fix until merge. """ from litellm.litellm_core_utils.prompt_templates.factory import ( add_cache_point_tool_block, ) - tool_with_1h = { - "type": "function", - "function": {"name": "get_weather", "parameters": {"type": "object"}}, - "cache_control": {"type": "ephemeral", "ttl": "1h"}, - } + old_env = os.environ.get("LITELLM_LOCAL_MODEL_COST_MAP") + old_cost = litellm.model_cost + os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = "True" + litellm.model_cost = litellm.get_model_cost_map(url="") + try: + tool_with_1h = { + "type": "function", + "function": {"name": "get_weather", "parameters": {"type": "object"}}, + "cache_control": {"type": "ephemeral", "ttl": "1h"}, + } - # Claude 4.5 model: ttl should be preserved - result = add_cache_point_tool_block( - tool_with_1h, model="us.anthropic.claude-sonnet-4-5-20250514-v1:0" - ) - assert result is not None - assert result["cachePoint"]["type"] == "default" - assert result["cachePoint"]["ttl"] == "1h" + # Claude 4.5 model: ttl should be preserved + result = add_cache_point_tool_block( + tool_with_1h, model="jp.anthropic.claude-opus-4-7" + ) + assert result is not None + assert result["cachePoint"]["type"] == "default" + assert result["cachePoint"]["ttl"] == "1h" - # Claude 4.5 model with 5m ttl: also preserved - tool_with_5m = { - "cache_control": {"type": "ephemeral", "ttl": "5m"}, - } - result_5m = add_cache_point_tool_block( - tool_with_5m, model="us.anthropic.claude-sonnet-4-5-20250514-v1:0" - ) - assert result_5m is not None - assert result_5m["cachePoint"]["ttl"] == "5m" + # Claude 4.5 model with 5m ttl: also preserved + tool_with_5m = { + "cache_control": {"type": "ephemeral", "ttl": "5m"}, + } + result_5m = add_cache_point_tool_block( + tool_with_5m, model="jp.anthropic.claude-opus-4-7" + ) + assert result_5m is not None + assert result_5m["cachePoint"]["ttl"] == "5m" - # Older model: ttl should be stripped - result_old = add_cache_point_tool_block( - tool_with_1h, model="anthropic.claude-3-5-sonnet-20241022-v2:0" - ) - assert result_old is not None - assert result_old["cachePoint"]["type"] == "default" - assert "ttl" not in result_old["cachePoint"] + # Older model: ttl should be stripped + result_old = add_cache_point_tool_block( + tool_with_1h, model="anthropic.claude-3-5-sonnet-20241022-v2:0" + ) + assert result_old is not None + assert result_old["cachePoint"]["type"] == "default" + assert "ttl" not in result_old["cachePoint"] - # No model provided: ttl should be stripped (safe default) - result_no_model = add_cache_point_tool_block(tool_with_1h, model=None) - assert result_no_model is not None - assert "ttl" not in result_no_model["cachePoint"] + # No model provided: ttl should be stripped (safe default) + result_no_model = add_cache_point_tool_block(tool_with_1h, model=None) + assert result_no_model is not None + assert "ttl" not in result_no_model["cachePoint"] - # No cache_control: returns None (unchanged behavior) - tool_no_cache = { - "type": "function", - "function": {"name": "get_weather", "parameters": {"type": "object"}}, - } - assert add_cache_point_tool_block(tool_no_cache) is None + # No cache_control: returns None (unchanged behavior) + tool_no_cache = { + "type": "function", + "function": {"name": "get_weather", "parameters": {"type": "object"}}, + } + assert add_cache_point_tool_block(tool_no_cache) is None - # cache_control without ttl: returns default cachePoint (unchanged behavior) - tool_no_ttl = {"cache_control": {"type": "ephemeral"}} - result_no_ttl = add_cache_point_tool_block( - tool_no_ttl, model="us.anthropic.claude-sonnet-4-5-20250514-v1:0" - ) - assert result_no_ttl is not None - assert result_no_ttl["cachePoint"]["type"] == "default" - assert "ttl" not in result_no_ttl["cachePoint"] + # cache_control without ttl: returns default cachePoint (unchanged behavior) + tool_no_ttl = {"cache_control": {"type": "ephemeral"}} + result_no_ttl = add_cache_point_tool_block( + tool_no_ttl, model="us.anthropic.claude-sonnet-4-5-20250929-v1:0" + ) + assert result_no_ttl is not None + assert result_no_ttl["cachePoint"]["type"] == "default" + assert "ttl" not in result_no_ttl["cachePoint"] + finally: + litellm.model_cost = old_cost + if old_env is None: + os.environ.pop("LITELLM_LOCAL_MODEL_COST_MAP", None) + else: + os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = old_env def test_bedrock_tools_pt_passes_ttl_for_claude_4_5(): """ End-to-end: _bedrock_tools_pt should produce cachePoint blocks with ttl for Claude 4.5+ models when tools have cache_control with ttl. + + Forces the bundled local cost map so ttl eligibility (driven by + `cache_creation_input_token_cost_above_1hr` in litellm.model_cost) reads + this branch's pricing data rather than the network-fetched `main` copy, + which lacks the fix until merge. """ from litellm.litellm_core_utils.prompt_templates.factory import _bedrock_tools_pt - tools = [ - { - "type": "function", - "function": { - "name": "get_weather", - "description": "Get weather", - "parameters": { - "type": "object", - "properties": {"city": {"type": "string"}}, + old_env = os.environ.get("LITELLM_LOCAL_MODEL_COST_MAP") + old_cost = litellm.model_cost + os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = "True" + litellm.model_cost = litellm.get_model_cost_map(url="") + try: + tools = [ + { + "type": "function", + "function": { + "name": "get_weather", + "description": "Get weather", + "parameters": { + "type": "object", + "properties": {"city": {"type": "string"}}, + }, }, - }, - "cache_control": {"type": "ephemeral", "ttl": "1h"}, - } - ] + "cache_control": {"type": "ephemeral", "ttl": "1h"}, + } + ] - # Claude 4.5: cachePoint should have ttl - result = _bedrock_tools_pt( - tools, model="us.anthropic.claude-sonnet-4-5-20250514-v1:0" - ) - cache_blocks = [b for b in result if "cachePoint" in b] - assert len(cache_blocks) == 1 - assert cache_blocks[0]["cachePoint"]["ttl"] == "1h" + # Claude 4.5: cachePoint should have ttl + result = _bedrock_tools_pt(tools, model="jp.anthropic.claude-opus-4-7") + cache_blocks = [b for b in result if "cachePoint" in b] + assert len(cache_blocks) == 1 + assert cache_blocks[0]["cachePoint"]["ttl"] == "1h" - # Older model: cachePoint should not have ttl - result_old = _bedrock_tools_pt( - tools, model="anthropic.claude-3-5-sonnet-20241022-v2:0" - ) - cache_blocks_old = [b for b in result_old if "cachePoint" in b] - assert len(cache_blocks_old) == 1 - assert "ttl" not in cache_blocks_old[0]["cachePoint"] + # Older model: cachePoint should not have ttl + result_old = _bedrock_tools_pt( + tools, model="anthropic.claude-3-5-sonnet-20241022-v2:0" + ) + cache_blocks_old = [b for b in result_old if "cachePoint" in b] + assert len(cache_blocks_old) == 1 + assert "ttl" not in cache_blocks_old[0]["cachePoint"] + finally: + litellm.model_cost = old_cost + if old_env is None: + os.environ.pop("LITELLM_LOCAL_MODEL_COST_MAP", None) + else: + os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = old_env def test_convert_to_anthropic_tool_result_openai_file_pdf_becomes_document(): diff --git a/tests/test_litellm/litellm_core_utils/test_initialize_dynamic_callback_params.py b/tests/test_litellm/litellm_core_utils/test_initialize_dynamic_callback_params.py index f63216b96d4..0dca4f3a1b1 100644 --- a/tests/test_litellm/litellm_core_utils/test_initialize_dynamic_callback_params.py +++ b/tests/test_litellm/litellm_core_utils/test_initialize_dynamic_callback_params.py @@ -7,9 +7,53 @@ sys.path.insert(0, os.path.abspath("../../..")) from litellm.litellm_core_utils.initialize_dynamic_callback_params import ( initialize_standard_callback_dynamic_params, + iter_client_callback_metadata_dicts, ) +def test_iter_client_callback_metadata_dicts_covers_all_read_paths(): + md = {"m": 1} + lm = {"lm": 1} + lp_md = {"lp": 1} + slots = dict( + iter_client_callback_metadata_dicts( + { + "metadata": md, + "litellm_metadata": lm, + "litellm_params": {"metadata": lp_md}, + } + ) + ) + assert slots == { + "metadata": md, + "litellm_metadata": lm, + "litellm_params.metadata": lp_md, + } + + +def test_iter_client_callback_metadata_dicts_skips_non_dict_slots(): + slots = list( + iter_client_callback_metadata_dicts( + { + "metadata": "not-a-dict", + "litellm_metadata": None, + "litellm_params": {"metadata": []}, + } + ) + ) + assert slots == [] + + +def test_extractor_reads_turn_off_message_logging_from_every_slot(): + for kwargs in ( + {"metadata": {"turn_off_message_logging": True}}, + {"litellm_metadata": {"turn_off_message_logging": True}}, + {"litellm_params": {"metadata": {"turn_off_message_logging": True}}}, + ): + params = initialize_standard_callback_dynamic_params(kwargs) + assert params.get("turn_off_message_logging") is True, kwargs + + def test_resolves_plain_values_at_top_level(): kwargs = { "langfuse_public_key": "pk-test", @@ -36,6 +80,33 @@ def test_resolves_plain_values_from_metadata(): assert params.get("langfuse_host") == "https://test.langfuse.com" +def test_litellm_params_metadata_overrides_metadata(): + kwargs = { + "metadata": { + "langfuse_public_key": "pk-meta", + }, + "litellm_params": { + "metadata": { + "langfuse_public_key": "pk-litellm-params", + } + }, + } + + params = initialize_standard_callback_dynamic_params(kwargs) + + assert params.get("langfuse_public_key") == "pk-litellm-params" + + +def test_top_level_kwargs_overrides_metadata_slots(): + kwargs = { + "langfuse_public_key": "from-top-level", + "metadata": {"langfuse_public_key": "from-metadata"}, + "litellm_params": {"metadata": {"langfuse_public_key": "from-litellm-params"}}, + } + params = initialize_standard_callback_dynamic_params(kwargs) + assert params.get("langfuse_public_key") == "from-top-level" + + def test_env_reference_at_top_level_raises_with_guidance(): kwargs = {"langfuse_public_key": "os.environ/LANGFUSE_PUBLIC_KEY"} @@ -100,11 +171,17 @@ def test_non_string_values_are_not_flagged(): assert params.get("langsmith_sampling_rate") == 0.5 -def test_turn_off_message_logging_not_extracted_from_request(): - """turn_off_message_logging is admin-only β€” must not be settable via request.""" - kwargs = {"turn_off_message_logging": True} +@pytest.mark.parametrize( + "kwargs,expected", + [ + ({"turn_off_message_logging": False}, False), + ({"turn_off_message_logging": "False"}, "False"), + ({"metadata": {"turn_off_message_logging": True}}, True), + ], +) +def test_turn_off_message_logging_extracted_from_kwargs(kwargs, expected): params = initialize_standard_callback_dynamic_params(kwargs) - assert params.get("turn_off_message_logging") is None + assert params.get("turn_off_message_logging") == expected def test_empty_kwargs_returns_empty_params(): diff --git a/tests/test_litellm/llms/a2a/chat/test_a2a_chat_transformation.py b/tests/test_litellm/llms/a2a/chat/test_a2a_chat_transformation.py new file mode 100644 index 00000000000..2e11c68244c --- /dev/null +++ b/tests/test_litellm/llms/a2a/chat/test_a2a_chat_transformation.py @@ -0,0 +1,42 @@ +"""Tests for litellm/llms/a2a/chat/transformation.py response transform.""" + +from unittest.mock import MagicMock + +from litellm.llms.a2a.chat.transformation import A2AConfig +from litellm.types.utils import ModelResponse + + +def _raw_response(text: str) -> MagicMock: + raw = MagicMock() + raw.status_code = 200 + raw.headers = {} + raw.json.return_value = { + "jsonrpc": "2.0", + "id": "resp-1", + "result": { + "kind": "message", + "parts": [{"kind": "text", "text": text}], + }, + } + return raw + + +def test_transform_response_sets_usage(): + """Regression: A2AConfig.transform_response must populate usage so per-token + pricing computes real cost and callers don't get usage 0/0/0.""" + result = A2AConfig().transform_response( + model="a2a/test-agent", + raw_response=_raw_response("hello from the agent"), + model_response=ModelResponse(), + logging_obj=MagicMock(), + request_data={}, + messages=[{"role": "user", "content": "hi there agent"}], + optional_params={}, + litellm_params={}, + encoding=None, + ) + + assert result.usage is not None + assert result.usage.prompt_tokens > 0 + assert result.usage.completion_tokens > 0 + assert result.usage.total_tokens == (result.usage.prompt_tokens + result.usage.completion_tokens) diff --git a/tests/test_litellm/llms/azure_ai/test_azure_document_intelligence_ocr_transformation.py b/tests/test_litellm/llms/azure_ai/test_azure_document_intelligence_ocr_transformation.py index e638be68ec0..39d6f1dc355 100644 --- a/tests/test_litellm/llms/azure_ai/test_azure_document_intelligence_ocr_transformation.py +++ b/tests/test_litellm/llms/azure_ai/test_azure_document_intelligence_ocr_transformation.py @@ -1,3 +1,6 @@ +from unittest.mock import MagicMock + +import httpx import pytest from litellm.llms.azure_ai.ocr.document_intelligence.transformation import ( @@ -31,3 +34,217 @@ def test_should_reject_dot_segment_azure_document_intelligence_model_id(): optional_params={}, litellm_params={}, ) + + +AZURE_TABLES = [ + { + "rowCount": 2, + "columnCount": 2, + "cells": [ + {"kind": "columnHeader", "rowIndex": 0, "columnIndex": 0, "content": "Item"}, + {"kind": "columnHeader", "rowIndex": 0, "columnIndex": 1, "content": "Price"}, + {"rowIndex": 1, "columnIndex": 0, "content": "Widget"}, + {"rowIndex": 1, "columnIndex": 1, "content": "$100.00"}, + ], + }, + { + "rowCount": 1, + "columnCount": 1, + "cells": [{"rowIndex": 0, "columnIndex": 0, "content": "Totals"}], + }, +] + +AZURE_KEY_VALUE_PAIRS = [ + {"key": {"content": "Invoice No"}, "value": {"content": "INV-12345"}, "confidence": 0.98}, + {"key": {"content": "Total"}, "value": {"content": "$100.00"}, "confidence": 0.95}, +] + +AZURE_ANALYZE_SUCCEEDED = { + "status": "succeeded", + "createdDateTime": "2026-07-02T00:00:00Z", + "lastUpdatedDateTime": "2026-07-02T00:00:05Z", + "analyzeResult": { + "apiVersion": "2024-11-30", + "modelId": "prebuilt-layout", + "content": "Invoice\nInvoice No: INV-12345\nTotal: $100.00", + "pages": [ + { + "pageNumber": 1, + "width": 8.5, + "height": 11, + "unit": "inch", + "lines": [ + {"content": "Invoice"}, + {"content": "Invoice No: INV-12345"}, + {"content": "Total: $100.00"}, + ], + } + ], + "tables": AZURE_TABLES, + "keyValuePairs": AZURE_KEY_VALUE_PAIRS, + }, +} + + +def _completed_response(payload: dict) -> httpx.Response: + return httpx.Response( + status_code=200, + json=payload, + request=httpx.Request("GET", "https://example.cognitiveservices.azure.com/analyzeResults/xyz"), + ) + + +def _assert_native_fields_preserved(serialized: dict) -> None: + assert serialized["content"] == "Invoice\nInvoice No: INV-12345\nTotal: $100.00" + assert serialized["tables"] == AZURE_TABLES + assert serialized["keyValuePairs"] == AZURE_KEY_VALUE_PAIRS + assert serialized["object"] == "ocr" + assert serialized["usage_info"]["pages_processed"] == 1 + assert serialized["pages"][0]["index"] == 0 + assert serialized["pages"][0]["markdown"] == "Invoice\nInvoice No: INV-12345\nTotal: $100.00" + assert serialized["pages"][0]["dimensions"] == {"width": 816, "height": 1056, "dpi": 96} + + +def test_transform_ocr_response_preserves_azure_native_fields(): + config = AzureDocumentIntelligenceOCRConfig() + + result = config.transform_ocr_response( + model="azure_ai/doc-intelligence/prebuilt-layout", + raw_response=_completed_response(AZURE_ANALYZE_SUCCEEDED), + logging_obj=MagicMock(), + ) + + _assert_native_fields_preserved(result.model_dump()) + + +@pytest.mark.asyncio +async def test_async_transform_ocr_response_preserves_azure_native_fields(): + config = AzureDocumentIntelligenceOCRConfig() + + result = await config.async_transform_ocr_response( + model="azure_ai/doc-intelligence/prebuilt-layout", + raw_response=_completed_response(AZURE_ANALYZE_SUCCEEDED), + logging_obj=MagicMock(), + ) + + _assert_native_fields_preserved(result.model_dump()) + + +def test_transform_ocr_response_tolerates_missing_native_fields(): + config = AzureDocumentIntelligenceOCRConfig() + payload = { + "status": "succeeded", + "analyzeResult": { + "pages": [ + { + "pageNumber": 1, + "width": 8.5, + "height": 11, + "unit": "inch", + "lines": [{"content": "hello"}], + } + ], + }, + } + + result = config.transform_ocr_response( + model="azure_ai/doc-intelligence/prebuilt-read", + raw_response=_completed_response(payload), + logging_obj=MagicMock(), + ) + + serialized = result.model_dump() + assert serialized["pages"][0]["markdown"] == "hello" + assert serialized["content"] is None + assert serialized["tables"] is None + assert serialized["keyValuePairs"] is None + + +def test_transform_ocr_response_non_succeeded_status_raises(): + config = AzureDocumentIntelligenceOCRConfig() + + with pytest.raises(ValueError, match="failed with status: failed"): + config.transform_ocr_response( + model="azure_ai/doc-intelligence/prebuilt-layout", + raw_response=_completed_response({"status": "failed"}), + logging_obj=MagicMock(), + ) + + +def test_get_supported_ocr_params_includes_features(): + config = AzureDocumentIntelligenceOCRConfig() + + assert config.get_supported_ocr_params("prebuilt-layout") == ["pages", "features"] + + +@pytest.mark.parametrize( + "features,expected", + [ + (["keyValuePairs"], "keyValuePairs"), + (["keyValuePairs", "languages"], "keyValuePairs,languages"), + ("keyValuePairs", "keyValuePairs"), + ("keyValuePairs,languages", "keyValuePairs,languages"), + ("keyValuePairs, languages", "keyValuePairs,languages"), + ], +) +def test_map_ocr_params_features(features, expected): + config = AzureDocumentIntelligenceOCRConfig() + + mapped = config.map_ocr_params({"features": features}, {}, "prebuilt-layout") + + assert mapped == {"features": expected} + + +def test_map_ocr_params_empty_features_list_omitted(): + config = AzureDocumentIntelligenceOCRConfig() + + assert config.map_ocr_params({"features": []}, {}, "prebuilt-layout") == {} + + +@pytest.mark.parametrize( + "features", + [ + "keyValuePairs&pages=9", + "key value pairs", + "", + [1, 2], + [["keyValuePairs"]], + {"feature": "keyValuePairs"}, + 5, + ], +) +def test_map_ocr_params_invalid_features_raises(features): + config = AzureDocumentIntelligenceOCRConfig() + + with pytest.raises(ValueError, match="Invalid `features`"): + config.map_ocr_params({"features": features}, {}, "prebuilt-layout") + + +def test_get_complete_url_appends_features_query(): + config = AzureDocumentIntelligenceOCRConfig() + + url = config.get_complete_url( + api_base="https://example.cognitiveservices.azure.com", + model="azure_ai/doc-intelligence/prebuilt-layout", + optional_params={"features": "keyValuePairs"}, + ) + + assert "&features=keyValuePairs" in url + + +def test_get_complete_url_combines_pages_and_features(): + config = AzureDocumentIntelligenceOCRConfig() + + optional_params = config.map_ocr_params( + {"pages": [0, 1, 2], "features": ["keyValuePairs", "languages"]}, + {}, + "prebuilt-layout", + ) + url = config.get_complete_url( + api_base="https://example.cognitiveservices.azure.com", + model="prebuilt-layout", + optional_params=optional_params, + ) + + assert "&pages=1,2,3" in url + assert "&features=keyValuePairs,languages" in url diff --git a/tests/test_litellm/llms/bedrock/chat/invoke_transformations/test_base_invoke_transformation.py b/tests/test_litellm/llms/bedrock/chat/invoke_transformations/test_base_invoke_transformation.py index aff89f02ff2..5fefae7e411 100644 --- a/tests/test_litellm/llms/bedrock/chat/invoke_transformations/test_base_invoke_transformation.py +++ b/tests/test_litellm/llms/bedrock/chat/invoke_transformations/test_base_invoke_transformation.py @@ -14,6 +14,7 @@ from litellm.llms.bedrock.chat.invoke_transformations.anthropic_claude3_transfor from litellm.llms.bedrock.chat.invoke_transformations.base_invoke_transformation import ( AmazonInvokeConfig, ) +from litellm.llms.bedrock.common_utils import BedrockError @pytest.mark.parametrize( @@ -39,3 +40,145 @@ def test_transform_request_drops_stream_chunk_size(config, model): ) assert "stream_chunk_size" not in json.dumps(request_body) + + +def test_validate_environment_maps_guardrail_config_to_invoke_headers(): + """The InvokeModel API takes the guardrail identifier/version/trace as + X-Amzn-Bedrock-* request headers, unlike Converse which takes them in the + body. https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_InvokeModel.html""" + optional_params = { + "guardrailConfig": { + "guardrailIdentifier": "ff6ujrregl1q", + "guardrailVersion": "DRAFT", + "trace": "enabled", + }, + "max_tokens": 10, + } + + headers = AmazonInvokeConfig().validate_environment( + headers={}, + model="anthropic.claude-3-sonnet-20240229-v1:0", + messages=[{"role": "user", "content": "hi"}], + optional_params=optional_params, + litellm_params={}, + ) + + assert headers["X-Amzn-Bedrock-GuardrailIdentifier"] == "ff6ujrregl1q" + assert headers["X-Amzn-Bedrock-GuardrailVersion"] == "DRAFT" + assert headers["X-Amzn-Bedrock-Trace"] == "ENABLED" + assert "guardrailConfig" not in optional_params + + +def test_validate_environment_without_guardrail_config_leaves_headers_untouched(): + headers = AmazonInvokeConfig().validate_environment( + headers={"foo": "bar"}, + model="anthropic.claude-3-sonnet-20240229-v1:0", + messages=[{"role": "user", "content": "hi"}], + optional_params={"max_tokens": 10}, + litellm_params={}, + ) + + assert headers == {"foo": "bar"} + + +def test_validate_environment_skips_absent_guardrail_fields(): + headers = AmazonInvokeConfig().validate_environment( + headers={}, + model="amazon.titan-text-express-v1", + messages=[{"role": "user", "content": "hi"}], + optional_params={"guardrailConfig": {"guardrailIdentifier": "gr-id", "guardrailVersion": "1"}}, + litellm_params={}, + ) + + assert headers == { + "X-Amzn-Bedrock-GuardrailIdentifier": "gr-id", + "X-Amzn-Bedrock-GuardrailVersion": "1", + } + + +def test_validate_environment_does_not_clobber_explicit_guardrail_headers(): + """Users worked around the missing guardrailConfig support by passing the + AWS headers directly; an explicit header must keep winning over + guardrailConfig regardless of casing.""" + headers = AmazonInvokeConfig().validate_environment( + headers={"x-amzn-bedrock-guardrailidentifier": "explicit-id"}, + model="anthropic.claude-3-sonnet-20240229-v1:0", + messages=[{"role": "user", "content": "hi"}], + optional_params={ + "guardrailConfig": {"guardrailIdentifier": "config-id", "guardrailVersion": "2"}, + }, + litellm_params={}, + ) + + assert headers["x-amzn-bedrock-guardrailidentifier"] == "explicit-id" + assert "X-Amzn-Bedrock-GuardrailIdentifier" not in headers + assert headers["X-Amzn-Bedrock-GuardrailVersion"] == "2" + + +@pytest.mark.parametrize( + "bad_guardrail_config", + [ + {"guardrailIdentifier": "gr-id", "trace": "verbose"}, + {"guardrailIdentifier": ["gr-id"]}, + "gr-id", + {}, + {"trace": "enabled"}, + ], +) +def test_validate_environment_rejects_malformed_guardrail_config(bad_guardrail_config): + with pytest.raises(BedrockError) as excinfo: + AmazonInvokeConfig().validate_environment( + headers={}, + model="anthropic.claude-3-sonnet-20240229-v1:0", + messages=[{"role": "user", "content": "hi"}], + optional_params={"guardrailConfig": bad_guardrail_config}, + litellm_params={}, + ) + + assert excinfo.value.status_code == 400 + assert "guardrailConfig" in str(excinfo.value) + + +@pytest.mark.parametrize( + "model", + [ + "anthropic.claude-3-sonnet-20240229-v1:0", + "amazon.titan-text-express-v1", + "mistral.mistral-7b-instruct-v0:2", + "meta.llama3-8b-instruct-v1:0", + ], +) +def test_guardrail_config_flows_to_headers_not_request_body(model): + """Mirrors the handler flow (validate_environment then transform_request): + guardrailConfig must end up in the signed headers and never leak into the + request body, where Bedrock rejects it as an extra input.""" + config = AmazonInvokeConfig() + optional_params = { + "guardrailConfig": { + "guardrailIdentifier": "ff6ujrregl1q", + "guardrailVersion": "DRAFT", + "trace": "disabled", + }, + "max_tokens": 10, + } + messages = [{"role": "user", "content": "hi"}] + + headers = config.validate_environment( + headers={}, + model=model, + messages=messages, + optional_params=optional_params, + litellm_params={}, + ) + request_body = config.transform_request( + model=model, + messages=messages, + optional_params=optional_params, + litellm_params={}, + headers=headers, + ) + + assert "guardrailConfig" not in json.dumps(request_body) + assert headers["X-Amzn-Bedrock-GuardrailIdentifier"] == "ff6ujrregl1q" + assert headers["X-Amzn-Bedrock-GuardrailVersion"] == "DRAFT" + assert headers["X-Amzn-Bedrock-Trace"] == "DISABLED" diff --git a/tests/test_litellm/llms/bedrock/chat/test_converse_transformation.py b/tests/test_litellm/llms/bedrock/chat/test_converse_transformation.py index d940f9f47a6..fe060e2e40d 100644 --- a/tests/test_litellm/llms/bedrock/chat/test_converse_transformation.py +++ b/tests/test_litellm/llms/bedrock/chat/test_converse_transformation.py @@ -611,6 +611,65 @@ def test_transform_request_helper_includes_anthropic_beta_and_tools(): assert fields["tools"][0]["type"] == "computer_20250124" +def test_parallel_tool_calls_config_kept_for_sonnet_5(): + old_env = os.environ.get("LITELLM_LOCAL_MODEL_COST_MAP") + old_cost = litellm.model_cost + os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = "True" + litellm.model_cost = litellm.get_model_cost_map(url="") + try: + config = AmazonConverseConfig() + optional_params = config.map_openai_params( + model="anthropic.claude-sonnet-5", + non_default_params={"parallel_tool_calls": False}, + optional_params={}, + drop_params=False, + ) + + data = config._transform_request_helper( + model="anthropic.claude-sonnet-5", + system_content_blocks=[], + optional_params=optional_params, + messages=None, + ) + + assert data["additionalModelRequestFields"]["tool_choice"] == { + "disable_parallel_tool_use": True + } + finally: + litellm.model_cost = old_cost + if old_env is None: + os.environ.pop("LITELLM_LOCAL_MODEL_COST_MAP", None) + else: + os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = old_env + + +def test_parallel_tool_calls_config_dropped_for_ttl_only_model( + monkeypatch: pytest.MonkeyPatch, +): + model = "anthropic.claude-fable-5" + monkeypatch.setitem( + litellm.model_cost, + model, + {"cache_creation_input_token_cost_above_1hr": 2e-05}, + ) + config = AmazonConverseConfig() + optional_params = config.map_openai_params( + model=model, + non_default_params={"parallel_tool_calls": False}, + optional_params={}, + drop_params=False, + ) + + data = config._transform_request_helper( + model=model, + system_content_blocks=[], + optional_params=optional_params, + messages=None, + ) + + assert "tool_choice" not in data.get("additionalModelRequestFields", {}) + + def test_transform_response_with_computer_use_tool(): """Test response transformation with computer use tool call.""" import httpx @@ -4130,6 +4189,42 @@ def test_parallel_tool_calls_newer_model_adds_disable_flag(): assert "parallel_tool_calls" not in request_data["additionalModelRequestFields"] +def test_parallel_tool_calls_flag_decoupled_from_ttl_pricing(monkeypatch): + """ + The disable_parallel_tool_use gate must read supports_parallel_tool_use_config, + not the 1h-TTL pricing field: a model carrying only the former still gets the flag. + """ + from litellm.llms.bedrock.common_utils import is_claude_4_5_on_bedrock + + config = AmazonConverseConfig() + model = "anthropic.claude-parallel-tool-use-only" + monkeypatch.setitem(litellm.model_cost, model, {"supports_parallel_tool_use_config": True}) + assert is_claude_4_5_on_bedrock(model) is False + messages = [{"role": "user", "content": "What's the weather in SF and NYC?"}] + + optional_params = config.map_openai_params( + non_default_params={"parallel_tool_calls": False, "tools": _TOOL_PARAM}, + optional_params={}, + model=model, + drop_params=False, + ) + + request_data = config.transform_request( + model=model, + messages=messages, + optional_params=optional_params, + litellm_params={}, + headers={}, + ) + + assert ( + request_data["additionalModelRequestFields"]["tool_choice"][ + "disable_parallel_tool_use" + ] + is True + ) + + def test_parallel_tool_calls_older_model_drops_disable_flag(): """Older Claude models (pre-4.5) must NOT receive disable_parallel_tool_use β€” Bedrock rejects it.""" config = AmazonConverseConfig() @@ -4554,6 +4649,154 @@ def test_cache_control_injection_tool_config_not_added_without_injection_point() assert all("cachePoint" not in tool for tool in tools) +def test_cache_control_injection_tool_config_honors_ttl_for_supported_model(): + """ + Regression test: cache_control_injection_points with location=tool_config + must honor the requested `control.ttl`, mirroring the message/system + cache_control behavior, instead of always emitting a bare + {"type": "default"} cachePoint with no ttl. + + Forces the bundled local cost map so `is_claude_4_5_on_bedrock` (which + reads `cache_creation_input_token_cost_above_1hr` from litellm.model_cost) + sees this branch's pricing data rather than the network-fetched `main` + copy, which lacks it until merge. + """ + old_env = os.environ.get("LITELLM_LOCAL_MODEL_COST_MAP") + old_cost = litellm.model_cost + os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = "True" + litellm.model_cost = litellm.get_model_cost_map(url="") + try: + config = AmazonConverseConfig() + messages = [ + {"role": "user", "content": "What is the weather?"}, + ] + optional_params = { + "tools": [ + { + "type": "function", + "function": { + "name": "get_weather", + "description": "Get weather for a location", + "parameters": { + "type": "object", + "properties": {"location": {"type": "string"}}, + "required": ["location"], + }, + }, + } + ], + "cache_control_injection_points": [ + {"location": "tool_config", "control": {"type": "ephemeral", "ttl": "1h"}}, + ], + } + result = config._transform_request( + model="us.anthropic.claude-sonnet-4-5-20250929-v1:0", + messages=messages, + optional_params=optional_params, + litellm_params={}, + ) + tools = result["toolConfig"]["tools"] + assert tools[-1] == {"cachePoint": {"type": "default", "ttl": "1h"}} + finally: + litellm.model_cost = old_cost + if old_env is None: + os.environ.pop("LITELLM_LOCAL_MODEL_COST_MAP", None) + else: + os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = old_env + + +def test_cache_control_injection_tool_config_honors_ttl_for_regional_model_lacking_own_pricing(): + """ + Regression test: a regional pricing entry that omits + `cache_creation_input_token_cost_above_1hr` (e.g. `jp.anthropic.claude-opus-4-7`) + must not shadow the base model entry that carries it; the requested ttl + survives through the base-model fallback. + """ + old_env = os.environ.get("LITELLM_LOCAL_MODEL_COST_MAP") + old_cost = litellm.model_cost + os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = "True" + litellm.model_cost = litellm.get_model_cost_map(url="") + try: + assert "cache_creation_input_token_cost_above_1hr" not in litellm.model_cost["jp.anthropic.claude-opus-4-7"] + assert "cache_creation_input_token_cost_above_1hr" in litellm.model_cost["anthropic.claude-opus-4-7"] + config = AmazonConverseConfig() + messages = [ + {"role": "user", "content": "What is the weather?"}, + ] + optional_params = { + "tools": [ + { + "type": "function", + "function": { + "name": "get_weather", + "description": "Get weather for a location", + "parameters": { + "type": "object", + "properties": {"location": {"type": "string"}}, + "required": ["location"], + }, + }, + } + ], + "cache_control_injection_points": [ + {"location": "tool_config", "control": {"type": "ephemeral", "ttl": "1h"}}, + ], + } + result = config._transform_request( + model="jp.anthropic.claude-opus-4-7", + messages=messages, + optional_params=optional_params, + litellm_params={}, + ) + tools = result["toolConfig"]["tools"] + assert tools[-1] == {"cachePoint": {"type": "default", "ttl": "1h"}} + finally: + litellm.model_cost = old_cost + if old_env is None: + os.environ.pop("LITELLM_LOCAL_MODEL_COST_MAP", None) + else: + os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = old_env + + +def test_cache_control_injection_tool_config_drops_ttl_for_unsupported_model(): + """ + Models that don't support extended TTL caching (only Claude 4.5+ on + Bedrock does) must fall back to the default cachePoint with no ttl, + even if the caller requested one, matching message/system behavior. + """ + config = AmazonConverseConfig() + messages = [ + {"role": "user", "content": "What is the weather?"}, + ] + optional_params = { + "tools": [ + { + "type": "function", + "function": { + "name": "get_weather", + "description": "Get weather for a location", + "parameters": { + "type": "object", + "properties": {"location": {"type": "string"}}, + "required": ["location"], + }, + }, + } + ], + "cache_control_injection_points": [ + {"location": "tool_config", "control": {"type": "ephemeral", "ttl": "1h"}}, + ], + } + result = config._transform_request( + model="anthropic.claude-3-5-haiku-20241022-v1:0", + messages=messages, + optional_params=optional_params, + litellm_params={}, + ) + tools = result["toolConfig"]["tools"] + assert tools[-1] == {"cachePoint": {"type": "default"}} + + def test_translate_response_format_json_schema_still_injects_tool(): """ response_format with an explicit json_schema should still use the diff --git a/tests/test_litellm/llms/bedrock/messages/invoke_transformations/test_anthropic_claude3_transformation.py b/tests/test_litellm/llms/bedrock/messages/invoke_transformations/test_anthropic_claude3_transformation.py index c3191f5b5cb..03d0d87a58c 100644 --- a/tests/test_litellm/llms/bedrock/messages/invoke_transformations/test_anthropic_claude3_transformation.py +++ b/tests/test_litellm/llms/bedrock/messages/invoke_transformations/test_anthropic_claude3_transformation.py @@ -492,7 +492,7 @@ def test_bedrock_invoke_messages_transform_converts_custom_tool_schema_type_to_o assert result["tools"][0]["type"] == "custom" -def test_remove_ttl_from_cache_control_processes_tools(): +def test_remove_ttl_from_cache_control_processes_tools(local_model_cost_map): """ Ensure _remove_ttl_from_cache_control also sanitizes cache_control on tools. @@ -538,7 +538,7 @@ def test_remove_ttl_from_cache_control_processes_tools(): assert "ttl" not in request["system"][0]["cache_control"] -def test_remove_ttl_from_cache_control_preserves_tools_ttl_for_claude_4_5(): +def test_remove_ttl_from_cache_control_preserves_tools_ttl_for_claude_4_5(local_model_cost_map): """ For Claude 4.5+ models, ttl in ["5m", "1h"] should be preserved on tools, just like it is for system and messages. @@ -564,7 +564,7 @@ def test_remove_ttl_from_cache_control_preserves_tools_ttl_for_claude_4_5(): } cfg._remove_ttl_from_cache_control( - request, model="us.anthropic.claude-sonnet-4-5-20250514-v1:0" + request, model="us.anthropic.claude-sonnet-4-5-20250929-v1:0" ) # Both tools and system should preserve ttl for Claude 4.5 diff --git a/tests/test_litellm/llms/bedrock/test_bedrock_common_utils.py b/tests/test_litellm/llms/bedrock/test_bedrock_common_utils.py index 301bcba99f4..8cc6e4ff25d 100644 --- a/tests/test_litellm/llms/bedrock/test_bedrock_common_utils.py +++ b/tests/test_litellm/llms/bedrock/test_bedrock_common_utils.py @@ -445,3 +445,31 @@ def test_explicit_invoke_route_does_not_match_async_invoke(): BedrockModelInfo._explicit_async_invoke_route(f"bedrock/{async_invoke_model}") is True ) + + +def test_capability_lookups_fall_back_to_base_model_when_regional_entry_lacks_field(monkeypatch): + """ + Regression test: a regional model_cost entry without the capability field + must not shadow a base entry that has it (`get(model) or get(base)` used to + short-circuit on the truthy regional dict and drop the capability). + """ + import litellm + from litellm.llms.bedrock.common_utils import ( + bedrock_converse_supports_parallel_tool_use_config, + is_claude_4_5_on_bedrock, + ) + + base = "anthropic.claude-fallback-test" + regional = f"eu.{base}" + monkeypatch.setitem(litellm.model_cost, regional, {"input_cost_per_token": 1e-06}) + monkeypatch.setitem( + litellm.model_cost, + base, + { + "cache_creation_input_token_cost_above_1hr": 1e-05, + "supports_parallel_tool_use_config": True, + }, + ) + + assert is_claude_4_5_on_bedrock(regional) is True + assert bedrock_converse_supports_parallel_tool_use_config(regional) is True diff --git a/tests/test_litellm/llms/tencent/__init__.py b/tests/test_litellm/llms/tencent/__init__.py new file mode 100644 index 00000000000..e69de29bb2d diff --git a/tests/test_litellm/llms/tencent/chat/__init__.py b/tests/test_litellm/llms/tencent/chat/__init__.py new file mode 100644 index 00000000000..e69de29bb2d diff --git a/tests/test_litellm/llms/tencent/chat/test_tencent_chat_transformation.py b/tests/test_litellm/llms/tencent/chat/test_tencent_chat_transformation.py new file mode 100644 index 00000000000..00a82041c20 --- /dev/null +++ b/tests/test_litellm/llms/tencent/chat/test_tencent_chat_transformation.py @@ -0,0 +1,207 @@ +from unittest.mock import patch + +from litellm.llms.tencent.chat.transformation import TencentChatConfig + + +def test_supported_openai_params_includes_thinking_and_reasoning_effort(): + config = TencentChatConfig() + + with patch( + "litellm.llms.tencent.chat.transformation.supports_reasoning", + return_value=True, + ): + params = config.get_supported_openai_params(model="tencent/deepseek-v4-pro") + + assert "thinking" in params + assert "reasoning_effort" in params + assert "stream" in params + assert "temperature" in params + + +def test_supported_openai_params_excludes_thinking_without_reasoning_support(): + config = TencentChatConfig() + + with patch( + "litellm.llms.tencent.chat.transformation.supports_reasoning", + return_value=False, + ): + params = config.get_supported_openai_params(model="tencent/non-reasoning-model") + + assert "thinking" not in params + assert "reasoning_effort" not in params + assert "stream" in params + + +def test_map_openai_params_passes_thinking_dict_through(): + config = TencentChatConfig() + with patch( + "litellm.llms.tencent.chat.transformation.supports_reasoning", + return_value=True, + ): + result = config.map_openai_params( + non_default_params={"thinking": {"type": "enabled", "budget_tokens": 1024}}, + optional_params={}, + model="tencent/deepseek-v4-pro", + drop_params=False, + ) + + assert result["thinking"] == {"type": "enabled", "budget_tokens": 1024} + + +def test_map_openai_params_converts_reasoning_effort_to_thinking(): + config = TencentChatConfig() + with patch( + "litellm.llms.tencent.chat.transformation.supports_reasoning", + return_value=True, + ): + result = config.map_openai_params( + non_default_params={"reasoning_effort": "medium"}, + optional_params={}, + model="tencent/deepseek-v4-pro", + drop_params=False, + ) + + assert result["thinking"] == {"type": "enabled"} + + +def test_map_openai_params_drops_none_reasoning_effort(): + config = TencentChatConfig() + with patch( + "litellm.llms.tencent.chat.transformation.supports_reasoning", + return_value=True, + ): + result = config.map_openai_params( + non_default_params={"reasoning_effort": "none"}, + optional_params={}, + model="tencent/deepseek-v4-pro", + drop_params=False, + ) + + assert "thinking" not in result + assert "reasoning_effort" not in result + + +def test_map_openai_params_thinking_priority_over_reasoning_effort(): + config = TencentChatConfig() + with patch( + "litellm.llms.tencent.chat.transformation.supports_reasoning", + return_value=True, + ): + result = config.map_openai_params( + non_default_params={ + "thinking": {"type": "enabled", "budget_tokens": 2048}, + "reasoning_effort": "high", + }, + optional_params={}, + model="tencent/deepseek-v4-pro", + drop_params=False, + ) + + assert result["thinking"] == {"type": "enabled", "budget_tokens": 2048} + + +def test_map_openai_params_extracts_thinking_and_effort_from_optional_params(): + config = TencentChatConfig() + result = config.map_openai_params( + non_default_params={}, + optional_params={"thinking": {"type": "enabled"}, "reasoning_effort": "medium"}, + model="tencent/deepseek-v4-pro", + drop_params=False, + ) + + assert "thinking" in result + assert "reasoning_effort" not in result + + +def test_get_complete_url_default(): + config = TencentChatConfig() + + url = config.get_complete_url( + api_base=None, + api_key=None, + model="tencent/deepseek-v4-pro", + optional_params={}, + litellm_params={}, + ) + + assert url == "https://tokenhub-intl.tencentcloudmaas.com/v1/chat/completions" + + +def test_get_complete_url_strips_trailing_slash(): + config = TencentChatConfig() + + url = config.get_complete_url( + api_base="https://tokenhub-intl.tencentcloudmaas.com/v1/", + api_key=None, + model="tencent/deepseek-v4-pro", + optional_params={}, + litellm_params={}, + ) + + assert url == "https://tokenhub-intl.tencentcloudmaas.com/v1/chat/completions" + + +def test_get_complete_url_custom_base_preserves_v1(): + config = TencentChatConfig() + + url = config.get_complete_url( + api_base="https://tokenhub.tencentcloudmaas.com/v1", + api_key=None, + model="tencent/deepseek-v4-pro", + optional_params={}, + litellm_params={}, + ) + + assert url == "https://tokenhub.tencentcloudmaas.com/v1/chat/completions" + + +def test_get_complete_url_adds_v1_to_custom_base(): + config = TencentChatConfig() + + url = config.get_complete_url( + api_base="https://tokenhub.tencentcloudmaas.com", + api_key=None, + model="tencent/deepseek-v4-pro", + optional_params={}, + litellm_params={}, + ) + + assert url == "https://tokenhub.tencentcloudmaas.com/v1/chat/completions" + + +def test_get_complete_url_does_not_append_to_full_url(): + config = TencentChatConfig() + + url = config.get_complete_url( + api_base="https://tokenhub.tencentcloudmaas.com/v1/chat/completions", + api_key=None, + model="tencent/deepseek-v4-pro", + optional_params={}, + litellm_params={}, + ) + + assert url == "https://tokenhub.tencentcloudmaas.com/v1/chat/completions" + + +def test_provider_info_falls_back_to_default_base(): + config = TencentChatConfig() + + with patch("litellm.llms.tencent.chat.transformation.get_secret_str", return_value=None): + api_base, api_key = config._get_openai_compatible_provider_info(api_base=None, api_key="sk-arg") + + assert api_base == "https://tokenhub-intl.tencentcloudmaas.com/v1" + assert api_key == "sk-arg" + + +def test_provider_info_reads_env_secrets(): + config = TencentChatConfig() + + secrets = {"TENCENT_API_BASE": "https://env.tencent/v1", "TENCENT_API_KEY": "sk-env"} + with patch( + "litellm.llms.tencent.chat.transformation.get_secret_str", + side_effect=lambda key: secrets.get(key), + ): + api_base, api_key = config._get_openai_compatible_provider_info(api_base=None, api_key=None) + + assert api_base == "https://env.tencent/v1" + assert api_key == "sk-env" diff --git a/tests/test_litellm/llms/tencent/messages/__init__.py b/tests/test_litellm/llms/tencent/messages/__init__.py new file mode 100644 index 00000000000..e69de29bb2d diff --git a/tests/test_litellm/llms/tencent/messages/test_tencent_anthropic_messages_transformation.py b/tests/test_litellm/llms/tencent/messages/test_tencent_anthropic_messages_transformation.py new file mode 100644 index 00000000000..70c965a6190 --- /dev/null +++ b/tests/test_litellm/llms/tencent/messages/test_tencent_anthropic_messages_transformation.py @@ -0,0 +1,173 @@ +import litellm +from litellm.llms.anthropic.experimental_pass_through.messages.transformation import ( + AnthropicMessagesConfig, +) +from litellm.llms.tencent.messages.transformation import ( + TencentAnthropicMessagesConfig, +) +from litellm.utils import ProviderConfigManager + + +def test_tencent_provider_uses_anthropic_messages_config(): + config = ProviderConfigManager.get_provider_anthropic_messages_config( + model="deepseek-v4-pro", + provider=litellm.LlmProviders.TENCENT, + ) + + assert isinstance(config, TencentAnthropicMessagesConfig) + assert config.custom_llm_provider == "tencent" + + +def test_anthropic_provider_keeps_default_config_for_tencent_named_model(): + config = ProviderConfigManager.get_provider_anthropic_messages_config( + model="deepseek-v4-pro", + provider=litellm.LlmProviders.ANTHROPIC, + ) + + assert isinstance(config, AnthropicMessagesConfig) + assert not isinstance(config, TencentAnthropicMessagesConfig) + + +def test_strips_billing_metadata(): + config = TencentAnthropicMessagesConfig() + + assert config.should_strip_billing_metadata() is True + + +def test_get_api_base_default(): + config = TencentAnthropicMessagesConfig() + + assert config.get_api_base() == "https://tokenhub-intl.tencentcloudmaas.com" + + +def test_get_api_base_from_arg(): + config = TencentAnthropicMessagesConfig() + + assert config.get_api_base(api_base="https://custom.example.com") == "https://custom.example.com" + + +def test_messages_url_default(): + config = TencentAnthropicMessagesConfig() + + assert ( + config.get_complete_url( + api_base=None, + api_key=None, + model="deepseek-v4-pro", + optional_params={}, + litellm_params={}, + ) + == "https://tokenhub-intl.tencentcloudmaas.com/v1/messages" + ) + + +def test_messages_url_with_base_ending_in_v1(): + config = TencentAnthropicMessagesConfig() + + assert ( + config.get_complete_url( + api_base="https://tokenhub-intl.tencentcloudmaas.com/v1", + api_key=None, + model="deepseek-v4-pro", + optional_params={}, + litellm_params={}, + ) + == "https://tokenhub-intl.tencentcloudmaas.com/v1/messages" + ) + + +def test_messages_url_with_base_ending_in_v1_messages(): + config = TencentAnthropicMessagesConfig() + + url = config.get_complete_url( + api_base="https://tokenhub-intl.tencentcloudmaas.com/v1/messages", + api_key=None, + model="deepseek-v4-pro", + optional_params={}, + litellm_params={}, + ) + + assert url == "https://tokenhub-intl.tencentcloudmaas.com/v1/messages" + + +def test_messages_url_with_base_ending_in_v1_chat_completions(): + config = TencentAnthropicMessagesConfig() + + assert ( + config.get_complete_url( + api_base="https://tokenhub-intl.tencentcloudmaas.com/v1/chat/completions", + api_key=None, + model="deepseek-v4-pro", + optional_params={}, + litellm_params={}, + ) + == "https://tokenhub-intl.tencentcloudmaas.com/v1/messages" + ) + + +def test_messages_url_with_custom_base_no_v1(): + config = TencentAnthropicMessagesConfig() + + assert ( + config.get_complete_url( + api_base="https://tokenhub.tencentcloudmaas.com", + api_key=None, + model="deepseek-v4-pro", + optional_params={}, + litellm_params={}, + ) + == "https://tokenhub.tencentcloudmaas.com/v1/messages" + ) + + +def test_validate_environment_sets_headers(): + config = TencentAnthropicMessagesConfig() + + headers, api_base = config.validate_anthropic_messages_environment( + headers={}, + model="deepseek-v4-pro", + messages=[], + optional_params={}, + litellm_params={}, + api_key="sk-tencent-key", + api_base="https://custom.test", + ) + + assert headers["x-api-key"] == "sk-tencent-key" + assert headers["anthropic-version"] == "2023-06-01" + assert headers["content-type"] == "application/json" + assert api_base == "https://custom.test" + + +def test_validate_environment_injects_anthropic_beta_headers(): + config = TencentAnthropicMessagesConfig() + + headers, _ = config.validate_anthropic_messages_environment( + headers={}, + model="deepseek-v4-pro", + messages=[], + optional_params={"speed": "fast"}, + litellm_params={}, + api_key="sk-tencent-key", + api_base=None, + ) + + assert "anthropic-beta" in headers + + +def test_validate_environment_preserves_existing_headers(): + config = TencentAnthropicMessagesConfig() + + headers, _ = config.validate_anthropic_messages_environment( + headers={"authorization": "Bearer existing", "anthropic-version": "2024-01-01"}, + model="deepseek-v4-pro", + messages=[], + optional_params={}, + litellm_params={}, + api_key="sk-tencent-key", + api_base=None, + ) + + assert headers["authorization"] == "Bearer existing" + assert headers["anthropic-version"] == "2024-01-01" + assert "x-api-key" not in headers diff --git a/tests/test_litellm/llms/tencent/test_cost_calculator.py b/tests/test_litellm/llms/tencent/test_cost_calculator.py new file mode 100644 index 00000000000..c2e905fab85 --- /dev/null +++ b/tests/test_litellm/llms/tencent/test_cost_calculator.py @@ -0,0 +1,41 @@ +import pytest + +import litellm +from litellm.llms.tencent.cost_calculator import cost_per_token +from litellm.types.utils import Usage + + +@pytest.fixture +def local_model_cost_map(monkeypatch): + original_model_cost = litellm.model_cost + monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True") + litellm.model_cost = litellm.get_model_cost_map(url="") + litellm.get_model_info.cache_clear() + try: + yield + finally: + litellm.model_cost = original_model_cost + litellm.get_model_info.cache_clear() + + +def test_cost_per_token_uses_tencent_model_pricing(local_model_cost_map): + usage = Usage(prompt_tokens=1000, completion_tokens=2000, total_tokens=3000) + + prompt_cost, completion_cost = cost_per_token(model="tencent/deepseek-v4-pro", usage=usage) + + assert prompt_cost == pytest.approx(1000 * 4.35e-07) + assert completion_cost == pytest.approx(2000 * 8.7e-07) + + +def test_top_level_dispatcher_routes_tencent_to_wrapper(local_model_cost_map): + from litellm.cost_calculator import cost_per_token as dispatch_cost_per_token + + prompt_cost, completion_cost = dispatch_cost_per_token( + model="tencent/deepseek-v4-pro", + prompt_tokens=1000, + completion_tokens=1000, + custom_llm_provider="tencent", + ) + + assert prompt_cost == pytest.approx(1000 * 4.35e-07) + assert completion_cost == pytest.approx(1000 * 8.7e-07) diff --git a/tests/test_litellm/proxy/_experimental/mcp_server/test_mcp_max_concurrent_requests.py b/tests/test_litellm/proxy/_experimental/mcp_server/test_mcp_max_concurrent_requests.py new file mode 100644 index 00000000000..8c4d81223aa --- /dev/null +++ b/tests/test_litellm/proxy/_experimental/mcp_server/test_mcp_max_concurrent_requests.py @@ -0,0 +1,184 @@ +import asyncio +from typing import Dict, Optional + +import pytest +from unittest.mock import patch + +from litellm.proxy._experimental.mcp_server.mcp_server_manager import MCPServerManager +from litellm.types.mcp import MCPAuth, MCPTransport +from litellm.types.mcp_server.mcp_server_manager import MCPServer + +HOLD_SECONDS = 0.1 + + +class _ConcurrencyTracker: + """Records how many call_tool invocations are simultaneously in flight.""" + + def __init__(self) -> None: + self.current_by_server: Dict[str, int] = {} + self.peak_by_server: Dict[str, int] = {} + self.global_current = 0 + self.global_peak = 0 + + def enter(self, server_id: str) -> None: + self.current_by_server[server_id] = self.current_by_server.get(server_id, 0) + 1 + self.peak_by_server[server_id] = max(self.peak_by_server.get(server_id, 0), self.current_by_server[server_id]) + self.global_current += 1 + self.global_peak = max(self.global_peak, self.global_current) + + def exit(self, server_id: str) -> None: + self.current_by_server[server_id] -= 1 + self.global_current -= 1 + + +def _make_server(server_id: str, max_concurrent_requests: Optional[int]) -> MCPServer: + return MCPServer( + server_id=server_id, + name=server_id, + server_name=server_id, + url="https://example.com", + transport=MCPTransport.http, + auth_type=MCPAuth.none, + max_concurrent_requests=max_concurrent_requests, + ) + + +def _patch_client_with_tracker(manager: MCPServerManager, tracker: _ConcurrencyTracker): + async def fake_create_mcp_client(server, **kwargs): + class _ProbeClient: + async def call_tool(self, params, host_progress_callback=None): + tracker.enter(server.server_id) + try: + await asyncio.sleep(HOLD_SECONDS) + return "ok" + finally: + tracker.exit(server.server_id) + + return _ProbeClient() + + return patch.object(manager, "_create_mcp_client", side_effect=fake_create_mcp_client) + + +async def _fire(manager: MCPServerManager, server: MCPServer, n: int) -> None: + await asyncio.gather( + *[ + manager._call_regular_mcp_tool( + mcp_server=server, + original_tool_name="tool", + arguments={}, + tasks=[], + mcp_auth_header=None, + mcp_server_auth_headers=None, + oauth2_headers=None, + raw_headers=None, + proxy_logging_obj=None, + ) + for _ in range(n) + ] + ) + + +@pytest.mark.asyncio +async def test_max_concurrent_requests_caps_in_flight_tool_calls(): + """A configured cap of 2 must never let more than 2 calls hit one server at once.""" + manager = MCPServerManager() + tracker = _ConcurrencyTracker() + server = _make_server("srv-limited", max_concurrent_requests=2) + + with _patch_client_with_tracker(manager, tracker): + await _fire(manager, server, n=8) + + assert tracker.peak_by_server["srv-limited"] == 2 + + +@pytest.mark.asyncio +async def test_unset_limit_allows_unbounded_concurrency(): + """With no cap, all calls run concurrently (backward-compatible default).""" + manager = MCPServerManager() + tracker = _ConcurrencyTracker() + server = _make_server("srv-unbounded", max_concurrent_requests=None) + + with _patch_client_with_tracker(manager, tracker): + await _fire(manager, server, n=6) + + assert tracker.peak_by_server["srv-unbounded"] == 6 + + +@pytest.mark.asyncio +async def test_non_positive_limit_is_treated_as_unlimited(): + """A cap of 0 must not deadlock; it means unlimited, not a zero-permit semaphore.""" + manager = MCPServerManager() + tracker = _ConcurrencyTracker() + server = _make_server("srv-zero", max_concurrent_requests=0) + + with _patch_client_with_tracker(manager, tracker): + await asyncio.wait_for(_fire(manager, server, n=5), timeout=5) + + assert tracker.peak_by_server["srv-zero"] == 5 + + +@pytest.mark.asyncio +async def test_limit_is_scoped_per_server(): + """Each server gets its own limiter; one server's cap must not throttle another.""" + manager = MCPServerManager() + tracker = _ConcurrencyTracker() + server_a = _make_server("srv-a", max_concurrent_requests=1) + server_b = _make_server("srv-b", max_concurrent_requests=1) + + with _patch_client_with_tracker(manager, tracker): + await asyncio.gather( + _fire(manager, server_a, n=3), + _fire(manager, server_b, n=3), + ) + + assert tracker.peak_by_server["srv-a"] == 1 + assert tracker.peak_by_server["srv-b"] == 1 + assert tracker.global_peak == 2 + + +@pytest.mark.asyncio +async def test_openapi_backed_server_also_respects_the_cap(): + """OpenAPI (spec_path) servers dispatch through a different handler; the cap + must apply there too, not only on the regular MCP client path.""" + manager = MCPServerManager() + tracker = _ConcurrencyTracker() + server = _make_server("srv-openapi", max_concurrent_requests=2) + server.spec_path = "/fake/openapi.json" + + async def fake_openapi_handler(mcp_server, name, arguments): + tracker.enter(mcp_server.server_id) + try: + await asyncio.sleep(HOLD_SECONDS) + return "ok" + finally: + tracker.exit(mcp_server.server_id) + + with ( + patch.object(manager, "_resolve_mcp_server_for_tool_call", return_value=server), + patch.object(manager, "_call_openapi_tool_handler", side_effect=fake_openapi_handler), + ): + await asyncio.gather( + *[manager.call_tool(server_name="srv-openapi", name="tool", arguments={}) for _ in range(6)] + ) + + assert tracker.peak_by_server["srv-openapi"] == 2 + + +def test_semaphore_is_reused_per_server_and_distinct_across_servers(): + manager = MCPServerManager() + server_a = _make_server("srv-a", max_concurrent_requests=3) + server_b = _make_server("srv-b", max_concurrent_requests=3) + + sem_a_first = manager._get_call_semaphore(server_a) + sem_a_second = manager._get_call_semaphore(server_a) + sem_b = manager._get_call_semaphore(server_b) + + assert sem_a_first is sem_a_second + assert sem_a_first is not sem_b + + +def test_no_semaphore_created_when_limit_absent(): + manager = MCPServerManager() + server = _make_server("srv-none", max_concurrent_requests=None) + + assert manager._get_call_semaphore(server) is None diff --git a/tests/test_litellm/proxy/_experimental/mcp_server/test_mcp_oauth_passthrough_tools.py b/tests/test_litellm/proxy/_experimental/mcp_server/test_mcp_oauth_passthrough_tools.py index b836c3aef33..16c36af5156 100644 --- a/tests/test_litellm/proxy/_experimental/mcp_server/test_mcp_oauth_passthrough_tools.py +++ b/tests/test_litellm/proxy/_experimental/mcp_server/test_mcp_oauth_passthrough_tools.py @@ -76,9 +76,7 @@ async def test_fetch_tools_from_passthrough_raises_on_upstream_401(): mock_client.list_tools = AsyncMock(side_effect=upstream_error) with pytest.raises(MCPUpstreamAuthError) as exc_info: - await manager._fetch_tools_with_timeout( - mock_client, passthrough_server.name, server=passthrough_server - ) + await manager._fetch_tools_with_timeout(mock_client, passthrough_server.name) assert exc_info.value.status_code == 401 assert exc_info.value.www_authenticate == ( @@ -113,9 +111,7 @@ async def test_fetch_tools_from_delegated_oauth2_raises_on_upstream_401(): mock_client.list_tools = AsyncMock(side_effect=upstream_error) with pytest.raises(MCPUpstreamAuthError) as exc_info: - await manager._fetch_tools_with_timeout( - mock_client, delegated_server.name, server=delegated_server - ) + await manager._fetch_tools_with_timeout(mock_client, delegated_server.name) assert exc_info.value.status_code == 401 assert exc_info.value.www_authenticate == ( @@ -126,7 +122,10 @@ async def test_fetch_tools_from_delegated_oauth2_raises_on_upstream_401(): @pytest.mark.asyncio -async def test_fetch_tools_from_client_credentials_oauth2_keeps_swallow_behavior(): +async def test_fetch_tools_from_client_credentials_oauth2_surfaces_upstream_401(): + """The auth_type carve-out was removed: a client_credentials (M2M) server now + surfaces an upstream 401 as MCPUpstreamAuthError too, instead of swallowing it + to an empty list, so single-server routes can return a 401 challenge.""" manager = MCPServerManager() m2m_server = MCPServer( server_id="oauth-m2m", @@ -150,12 +149,12 @@ async def test_fetch_tools_from_client_credentials_oauth2_keeps_swallow_behavior mock_client = MagicMock() mock_client.list_tools = AsyncMock(side_effect=upstream_error) - tools = await manager._fetch_tools_with_timeout( - mock_client, m2m_server.name, server=m2m_server - ) + with pytest.raises(MCPUpstreamAuthError) as exc_info: + await manager._fetch_tools_with_timeout(mock_client, m2m_server.name) - assert tools == [] - mock_client.list_tools.assert_awaited_with(raise_on_error=False) + assert exc_info.value.status_code == 401 + assert exc_info.value.server_name == "m2m_docs" + mock_client.list_tools.assert_awaited_with(raise_on_error=True) @pytest.mark.asyncio @@ -176,9 +175,7 @@ async def test_fetch_tools_from_passthrough_returns_tools_on_success(): mock_client = MagicMock() mock_client.list_tools = AsyncMock(return_value=[tool]) - tools = await manager._fetch_tools_with_timeout( - mock_client, passthrough_server.name, server=passthrough_server - ) + tools = await manager._fetch_tools_with_timeout(mock_client, passthrough_server.name) assert tools == [tool] @@ -238,8 +235,11 @@ def test_to_http_exception_skips_challenge_for_non_401_status(): @pytest.mark.asyncio -async def test_fetch_tools_from_gateway_managed_swallows_errors(): - """Regression guard: non-pass-through servers keep returning [] on errors.""" +async def test_fetch_tools_from_gateway_managed_surfaces_upstream_401(): + """An oauth2 server that is neither pass-through nor delegate now surfaces an + upstream 401 as MCPUpstreamAuthError as well; the auth_type carve-out that + swallowed it to [] was removed. A missing upstream WWW-Authenticate is carried + through as None (the single-server route fabricates one from the gateway URL).""" manager = MCPServerManager() oauth2_server = MCPServer( server_id="o1", @@ -260,11 +260,13 @@ async def test_fetch_tools_from_gateway_managed_swallows_errors(): mock_client = MagicMock() mock_client.list_tools = AsyncMock(side_effect=upstream_error) - tools = await manager._fetch_tools_with_timeout( - mock_client, oauth2_server.name, server=oauth2_server - ) - assert tools == [] - mock_client.list_tools.assert_awaited_with(raise_on_error=False) + with pytest.raises(MCPUpstreamAuthError) as exc_info: + await manager._fetch_tools_with_timeout(mock_client, oauth2_server.name) + + assert exc_info.value.status_code == 401 + assert exc_info.value.www_authenticate is None + assert exc_info.value.server_name == "keycloak_whoami" + mock_client.list_tools.assert_awaited_with(raise_on_error=True) def _http_server(server_id: str, name: str, **kwargs) -> MCPServer: diff --git a/tests/test_litellm/proxy/_experimental/mcp_server/test_mcp_server_manager.py b/tests/test_litellm/proxy/_experimental/mcp_server/test_mcp_server_manager.py index c258ed1035f..b7a7917eac1 100644 --- a/tests/test_litellm/proxy/_experimental/mcp_server/test_mcp_server_manager.py +++ b/tests/test_litellm/proxy/_experimental/mcp_server/test_mcp_server_manager.py @@ -5228,5 +5228,139 @@ class TestCreateMcpClientV2Graft: assert client._get_auth_headers()["Authorization"] == "Bearer hook-jwt" +def _upstream_status_error(status_code: int, challenge: str) -> httpx.HTTPStatusError: + request = httpx.Request("POST", "https://upstream.example/mcp") + response = httpx.Response( + status_code, + headers={"WWW-Authenticate": challenge}, + request=request, + ) + return httpx.HTTPStatusError( + "upstream rejected token", request=request, response=response + ) + + +class TestMCPToolsListAuthSurfacing: + """Regression: MCP tools/list 401 auth failures must surface as MCPUpstreamAuthError. + + Previously a missing/expired per-user OAuth token, or an upstream 401 for any + non-carveout auth_type, was swallowed to an empty tool list, so a single-server + client saw a 200 with no tools instead of a 401 challenge. The listing helpers + now raise MCPUpstreamAuthError on a 401 regardless of auth_type; the single-server + routes turn it into a 401 + WWW-Authenticate while the aggregator absorbs it to an + empty list. Only a 401 challenges; a 403 (forbidden) degrades like any other error. + """ + + @pytest.mark.asyncio + async def test_fetch_tools_with_timeout_surfaces_upstream_401(self): + from litellm.proxy._experimental.mcp_server.exceptions import ( + MCPUpstreamAuthError, + ) + + manager = MCPServerManager() + challenge = 'Bearer resource_metadata="https://upstream.example/.well-known/oauth-protected-resource"' + client = MagicMock() + client.list_tools = AsyncMock(side_effect=_upstream_status_error(401, challenge)) + + with pytest.raises(MCPUpstreamAuthError) as exc_info: + await manager._fetch_tools_with_timeout(client, "static-key-server") + + assert exc_info.value.status_code == 401 + assert exc_info.value.www_authenticate == challenge + assert exc_info.value.server_name == "static-key-server" + + @pytest.mark.asyncio + async def test_fetch_tools_with_timeout_absorbs_upstream_403(self): + """Only a 401 drives the re-auth challenge. A 403 (authenticated but + forbidden, e.g. insufficient scope) is not a re-auth signal, so even + with a WWW-Authenticate header it degrades to an empty list rather than + surfacing a challenge.""" + manager = MCPServerManager() + challenge = 'Bearer error="insufficient_scope", scope="read:tools"' + client = MagicMock() + client.list_tools = AsyncMock(side_effect=_upstream_status_error(403, challenge)) + + assert await manager._fetch_tools_with_timeout(client, "forbidden-server") == [] + + @pytest.mark.asyncio + async def test_fetch_tools_with_timeout_returns_empty_on_non_auth_error(self): + manager = MCPServerManager() + client = MagicMock() + client.list_tools = AsyncMock(side_effect=RuntimeError("upstream 500")) + + assert await manager._fetch_tools_with_timeout(client, "srv") == [] + + @pytest.mark.asyncio + async def test_get_tools_from_server_surfaces_unusable_user_token(self): + from litellm.proxy._experimental.mcp_server.exceptions import ( + MCPUpstreamAuthError, + ) + + manager = MCPServerManager() + server = MCPServer( + server_id="oauth-srv", name="oauth-srv", transport=MCPTransport.http + ) + challenge = 'Bearer resource_metadata="/.well-known/oauth-protected-resource/mcp/oauth-srv"' + manager._create_mcp_client = AsyncMock( + side_effect=HTTPException( + status_code=401, + detail="Unauthorized", + headers={"WWW-Authenticate": challenge}, + ) + ) + + with pytest.raises(MCPUpstreamAuthError) as exc_info: + await manager._get_tools_from_server(server) + + assert exc_info.value.status_code == 401 + assert exc_info.value.www_authenticate == challenge + assert exc_info.value.server_name == "oauth-srv" + + @pytest.mark.asyncio + async def test_get_tools_from_server_absorbs_non_challenge_http_error(self): + manager = MCPServerManager() + server = MCPServer( + server_id="stdio-srv", name="stdio-srv", transport=MCPTransport.http + ) + manager._create_mcp_client = AsyncMock( + side_effect=HTTPException( + status_code=403, + detail="MCP stdio command 'foo' is not in the allowlist", + ) + ) + + assert await manager._get_tools_from_server(server) == [] + + @pytest.mark.asyncio + async def test_aggregate_list_tools_absorbs_unauthenticated_server(self): + from litellm.proxy._experimental.mcp_server.exceptions import ( + MCPUpstreamAuthError, + ) + + manager = MCPServerManager() + good = MCPServer(server_id="good", name="good", transport=MCPTransport.http) + bad = MCPServer(server_id="bad", name="bad", transport=MCPTransport.http) + manager.get_allowed_mcp_servers = AsyncMock(return_value=["good", "bad"]) + manager.get_mcp_server_by_id = MagicMock( + side_effect=lambda server_id: {"good": good, "bad": bad}.get(server_id) + ) + good_tool = MCPTool(name="good-do_thing", description="do thing", inputSchema={}) + + async def fake_get_tools(server, **kwargs): + if server.server_id == "bad": + raise MCPUpstreamAuthError( + status_code=401, + www_authenticate='Bearer realm="x"', + server_name="bad", + ) + return [good_tool] + + manager._get_tools_from_server = fake_get_tools + + result = await manager.list_tools() + + assert [t.name for t in result] == ["good-do_thing"] + + if __name__ == "__main__": pytest.main([__file__]) diff --git a/tests/test_litellm/proxy/_experimental/mcp_server/test_rest_endpoints.py b/tests/test_litellm/proxy/_experimental/mcp_server/test_rest_endpoints.py index 46a51f8fe61..fb4eee54e1d 100644 --- a/tests/test_litellm/proxy/_experimental/mcp_server/test_rest_endpoints.py +++ b/tests/test_litellm/proxy/_experimental/mcp_server/test_rest_endpoints.py @@ -843,6 +843,76 @@ class TestListToolsRestAPI: assert exc_info.value.status_code == upstream_status assert exc_info.value.headers == {"www-authenticate": challenge} + async def test_aggregate_list_absorbs_one_server_auth_failure(self, monkeypatch): + """The multi-server aggregate listing degrades a server whose upstream + rejects auth to an empty contribution and still returns the healthy + server's tools with a 200, rather than surfacing a 401.""" + from litellm.proxy._experimental.mcp_server.exceptions import ( + MCPUpstreamAuthError, + ) + + class StubServer: + def __init__(self, name): + self.alias = name + self.server_name = name + self.name = name + self.allowed_tools = None + self.mcp_info = {"server_name": name} + self.available_on_public_internet = True + + good = StubServer("good") + bad = StubServer("bad") + + async def fake_contexts(user_api_key_auth): + return [user_api_key_auth] + + async def fake_get_allowed_mcp_servers(*args, **kwargs): + return ["good", "bad"] + + async def fake_get_tools(server, *args, **kwargs): + if server.server_name == "bad": + raise MCPUpstreamAuthError( + status_code=401, + www_authenticate='Bearer realm="x"', + server_name="bad", + ) + return ["good-tool"] + + monkeypatch.setattr( + rest_endpoints, + "build_effective_auth_contexts", + fake_contexts, + raising=False, + ) + monkeypatch.setattr( + rest_endpoints.global_mcp_server_manager, + "get_allowed_mcp_servers", + fake_get_allowed_mcp_servers, + raising=False, + ) + monkeypatch.setattr( + rest_endpoints.global_mcp_server_manager, + "get_mcp_server_by_id", + lambda server_id: {"good": good, "bad": bad}.get(server_id), + raising=False, + ) + monkeypatch.setattr( + rest_endpoints, + "_get_tools_for_single_server", + fake_get_tools, + raising=False, + ) + + request = _build_request(path="/mcp-rest/tools/list", method="GET") + result = await rest_endpoints.list_tool_rest_api( + request, + server_id=None, + user_api_key_dict=UserAPIKeyAuth(), + ) + + assert result["tools"] == ["good-tool"] + assert result["error"] is None + async def test_name_resolution_finds_server_by_uuid(self, monkeypatch): """When server_id is a name string, it should be resolved to its UUID and used for the tools lookup when the UUID is in allowed_server_ids.""" diff --git a/tests/test_litellm/proxy/anthropic_endpoints/test_endpoints.py b/tests/test_litellm/proxy/anthropic_endpoints/test_endpoints.py index a4da4587b7f..69d90a8b59b 100644 --- a/tests/test_litellm/proxy/anthropic_endpoints/test_endpoints.py +++ b/tests/test_litellm/proxy/anthropic_endpoints/test_endpoints.py @@ -58,15 +58,71 @@ class TestAnthropicEndpoints(unittest.TestCase): self.assertEqual(result, expected_result) # Assert safe_dumps was called for dictionary objects - mock_safe_dumps.assert_any_call( - {"type": "message_start", "message": {"id": "msg_123"}} + mock_safe_dumps.assert_any_call({"type": "message_start", "message": {"id": "msg_123"}}) + mock_safe_dumps.assert_any_call({"type": "content_block_delta", "delta": {"text": "more data"}}) + assert mock_safe_dumps.call_count == 2 # Called twice, once for each dict object + + +class TestBlockedResponseUsage: + """Blocked responses report the blocked LLM response's real usage.""" + + def test_uses_original_response_usage(self): + from litellm.proxy.anthropic_endpoints.endpoints import _blocked_response_usage + + # original_response is the AnthropicMessagesResponse the LLM produced + # before the guardrail blocked it; its usage is real. + original = {"usage": {"input_tokens": 31, "output_tokens": 9}} + assert _blocked_response_usage(original) == { + "input_tokens": 31, + "output_tokens": 9, + } + + def test_zero_usage_when_no_original_response(self): + from litellm.proxy.anthropic_endpoints.endpoints import _blocked_response_usage + + # Pre-call blocks never invoked the LLM -> nothing consumed. + assert _blocked_response_usage(None) == { + "input_tokens": 0, + "output_tokens": 0, + } + + @pytest.mark.asyncio + async def test_blocked_endpoint_response_carries_original_usage(self): + """The /v1/messages block handler reports the blocked response's real + usage, carried on ModifyResponseException.original_response.""" + from unittest.mock import AsyncMock, MagicMock + + import litellm.proxy.anthropic_endpoints.endpoints as ep + import litellm.proxy.proxy_server as proxy_server + from litellm.integrations.custom_guardrail import ModifyResponseException + + exc = ModifyResponseException( + message="blocked by guardrail", + model="claude-3-5-sonnet-20240620", + request_data={"messages": [{"role": "user", "content": "hi"}]}, + guardrail_name="rubrik", + original_response={"usage": {"input_tokens": 12, "output_tokens": 5}}, ) - mock_safe_dumps.assert_any_call( - {"type": "content_block_delta", "delta": {"text": "more data"}} - ) - assert ( - mock_safe_dumps.call_count == 2 - ) # Called twice, once for each dict object + + with ( + patch.object(ep, "_read_request_body", new=AsyncMock(return_value={})), + patch.object( + ep.ProxyBaseLLMRequestProcessing, + "base_process_llm_request", + new=AsyncMock(side_effect=exc), + ), + patch.object(proxy_server, "proxy_logging_obj") as mock_logging, + ): + mock_logging.post_call_failure_hook = AsyncMock() + response = await ep.anthropic_response( + fastapi_response=MagicMock(), + request=MagicMock(), + user_api_key_dict=MagicMock(), + ) + + assert response["content"][0]["text"] == "blocked by guardrail" + assert response["usage"] == {"input_tokens": 12, "output_tokens": 5} + mock_logging.post_call_failure_hook.assert_awaited_once() class TestEventLoggingBatchEndpoint: @@ -159,9 +215,7 @@ class TestStripTotalTokens(unittest.TestCase): # SimpleNamespace mimics the .usage attribute access pattern; the # helper's contract: if .usage is dict-shaped, strip total_tokens. - response = SimpleNamespace( - usage={"input_tokens": 100, "output_tokens": 50, "total_tokens": 150} - ) + response = SimpleNamespace(usage={"input_tokens": 100, "output_tokens": 50, "total_tokens": 150}) _strip_total_tokens_from_anthropic_response(response) assert "total_tokens" not in response.usage assert response.usage == {"input_tokens": 100, "output_tokens": 50} diff --git a/tests/test_litellm/proxy/auth/test_auth_checks.py b/tests/test_litellm/proxy/auth/test_auth_checks.py index 7e34cdf29bc..0f6cae28761 100644 --- a/tests/test_litellm/proxy/auth/test_auth_checks.py +++ b/tests/test_litellm/proxy/auth/test_auth_checks.py @@ -355,6 +355,58 @@ async def test_can_key_call_model_all_team_models_no_team_id_is_denied(): assert exc_info.value.type == ProxyErrorTypes.key_model_access_denied +@pytest.mark.asyncio +async def test_enforce_key_access_teamless_all_team_models_denied(): + """_enforce_key_and_fallback_model_access must not skip key-level + model checks for a teamless key that carries all-team-models.""" + from litellm.proxy._types import SpecialModelNames + from litellm.proxy.auth.user_api_key_auth import ( + _enforce_key_and_fallback_model_access, + ) + + valid_token = UserAPIKeyAuth( + api_key="sk-orphan-key", + models=[SpecialModelNames.all_team_models.value], + team_models=[], + ) + + with pytest.raises(ProxyException) as exc_info: + await _enforce_key_and_fallback_model_access( + valid_token=valid_token, + request_data={"model": "gpt-4o"}, + route="/v1/chat/completions", + request=None, + llm_model_list=None, + llm_router=None, + ) + + assert exc_info.value.type == ProxyErrorTypes.key_model_access_denied + + +@pytest.mark.asyncio +async def test_can_key_call_resolved_model_teamless_all_team_models_denied(): + """can_key_call_resolved_model must not skip key-level model checks + for a teamless key that carries all-team-models.""" + from litellm.proxy._types import SpecialModelNames + from litellm.proxy.auth.auth_checks import can_key_call_resolved_model + + valid_token = UserAPIKeyAuth( + api_key="sk-orphan-key", + models=[SpecialModelNames.all_team_models.value], + team_models=[], + ) + + with pytest.raises(ProxyException) as exc_info: + await can_key_call_resolved_model( + model="gpt-4o", + llm_model_list=None, + valid_token=valid_token, + llm_router=None, + ) + + assert exc_info.value.type == ProxyErrorTypes.key_model_access_denied + + @pytest.mark.asyncio async def test_can_team_access_model_all_team_models_expands_router_models(): from litellm import Router diff --git a/tests/test_litellm/proxy/auth/test_auth_utils.py b/tests/test_litellm/proxy/auth/test_auth_utils.py index d5d2d27cb7e..21a001d77d7 100644 --- a/tests/test_litellm/proxy/auth/test_auth_utils.py +++ b/tests/test_litellm/proxy/auth/test_auth_utils.py @@ -2104,6 +2104,21 @@ class TestObservabilityCallbackBans: ) assert field in str(exc.value) + def test_observability_field_in_litellm_params_metadata_is_rejected(self): + with pytest.raises(ValueError) as exc: + is_request_body_safe( + request_body={ + "model": "gpt-4", + "litellm_params": { + "metadata": {"turn_off_message_logging": False} + }, + }, + general_settings={}, + llm_router=None, + model="gpt-4", + ) + assert "turn_off_message_logging" in str(exc.value) + @pytest.mark.parametrize( "metadata_key", ["metadata", "litellm_metadata"], diff --git a/tests/test_litellm/proxy/guardrails/guardrail_hooks/unified_guardrails/test_anthropic_streaming_block.py b/tests/test_litellm/proxy/guardrails/guardrail_hooks/unified_guardrails/test_anthropic_streaming_block.py new file mode 100644 index 00000000000..865b4164e5e --- /dev/null +++ b/tests/test_litellm/proxy/guardrails/guardrail_hooks/unified_guardrails/test_anthropic_streaming_block.py @@ -0,0 +1,362 @@ +""" +Regression tests for blocking an Anthropic streaming response from the +unified guardrail post-call streaming iterator hook. + +When a guardrail's ``apply_guardrail`` raises ``ModifyResponseException`` while +(or at the end of) an Anthropic ``/v1/messages`` stream is being relayed, the +hook must emit a well-formed Anthropic SSE termination sequence carrying the +block message - NOT a bare ``data: {"error": ...}`` blob that truncates the +stream and causes the Anthropic SDK parser to discard the response. +""" + +import json +from typing import Any, List, Literal, Optional + +import pytest + +from litellm.integrations.custom_guardrail import ( + CustomGuardrail, + ModifyResponseException, +) +from litellm.proxy._types import UserAPIKeyAuth +from litellm.proxy.guardrails.guardrail_hooks.unified_guardrail.unified_guardrail import ( + UnifiedLLMGuardrails, +) +from litellm.types.utils import GenericGuardrailAPIInputs + +BLOCK_MESSAGE = "Blocked by policy: this response was withheld." + + +class _BlockingGuardrail(CustomGuardrail): + """Mock guardrail that always blocks by raising ModifyResponseException.""" + + async def apply_guardrail( + self, + inputs: GenericGuardrailAPIInputs, + request_data: dict, + input_type: Literal["request", "response"], + logging_obj: Optional[Any] = None, + ) -> GenericGuardrailAPIInputs: + raise ModifyResponseException( + message=BLOCK_MESSAGE, + model="claude-3-5-sonnet", + request_data=request_data, + guardrail_name=self.guardrail_name, + ) + + +def _sse_event(event_type: str, data: dict) -> bytes: + return f"event: {event_type}\ndata: {json.dumps(data)}\n\n".encode() + + +async def _anthropic_stream(end: bool): + """Yield Anthropic SSE byte chunks. If end=True, include a terminating + message_delta (stop_reason set) so the hook's end-of-stream path runs.""" + yield _sse_event( + "message_start", + { + "type": "message_start", + "message": { + "id": "msg_orig", + "type": "message", + "role": "assistant", + "model": "claude-3-5-sonnet", + "content": [], + "stop_reason": None, + "usage": {"input_tokens": 1, "output_tokens": 0}, + }, + }, + ) + yield _sse_event( + "content_block_start", + { + "type": "content_block_start", + "index": 0, + "content_block": {"type": "text", "text": ""}, + }, + ) + for text in ["This ", "is ", "the ", "original ", "answer."]: + yield _sse_event( + "content_block_delta", + { + "type": "content_block_delta", + "index": 0, + "delta": {"type": "text_delta", "text": text}, + }, + ) + if end: + yield _sse_event("content_block_stop", {"type": "content_block_stop", "index": 0}) + yield _sse_event( + "message_delta", + { + "type": "message_delta", + "delta": {"stop_reason": "end_turn", "stop_sequence": None}, + "usage": {"output_tokens": 5}, + }, + ) + yield _sse_event("message_stop", {"type": "message_stop"}) + + +def _decode(chunks: List[Any]) -> str: + parts = [] + for chunk in chunks: + parts.append(chunk.decode() if isinstance(chunk, bytes) else str(chunk)) + return "".join(parts) + + +def _parse_sse_event_types(raw: str) -> List[str]: + event_types = [] + for block in raw.split("\n\n"): + for line in block.strip().split("\n"): + if line.startswith("data:"): + payload = line[len("data:") :].strip() + try: + event_types.append(json.loads(payload).get("type")) + except json.JSONDecodeError: + pass + return event_types + + +async def _run_hook(end: bool, sampling_rate: int = 1, end_of_stream_only: bool = False) -> str: + guardrail = _BlockingGuardrail(guardrail_name="test-blocking-guardrail", event_hook="post_call") + # sampling_rate controls how many chunks are forwarded before the block + # fires: 1 blocks on the first chunk (nothing sent yet); >1 forwards earlier + # chunks first, exercising the mid-stream "continue the message" path. + guardrail.streaming_sampling_rate = sampling_rate + guardrail.streaming_end_of_stream_only = end_of_stream_only + + unified_guardrail = UnifiedLLMGuardrails() + user_api_key_dict = UserAPIKeyAuth(api_key="test", request_route="/v1/messages") + request_data = { + "messages": [{"role": "user", "content": "hi"}], + "guardrail_to_apply": guardrail, + "metadata": {"guardrails": ["test-blocking-guardrail"]}, + } + + collected: List[Any] = [] + async for chunk in unified_guardrail.async_post_call_streaming_iterator_hook( + user_api_key_dict=user_api_key_dict, + response=_anthropic_stream(end=end), + request_data=request_data, + ): + collected.append(chunk) + return _decode(collected) + + +def _assert_clean_block_termination(raw: str) -> None: + # No bare error blob that would truncate the stream. + assert '"error"' not in raw, f"unexpected error blob in stream: {raw!r}" + # The block message is delivered as assistant text. + assert BLOCK_MESSAGE in raw, f"block message missing from stream: {raw!r}" + # A complete, parseable Anthropic SSE termination sequence is present. + event_types = _parse_sse_event_types(raw) + assert "message_start" in event_types + assert "content_block_delta" in event_types + # Exactly one message_start: a block must never inject a second + # message envelope into an already-started stream (clients reject it). + assert event_types.count("message_start") == 1, f"expected a single message_start, got: {event_types}" + assert event_types[-1] == "message_stop", f"stream did not end cleanly: {event_types}" + # message_delta carries a stop_reason. + assert any('"stop_reason"' in block and "message_delta" in block for block in raw.split("\n\n")) + + +def _parse_sse_payloads(raw: str) -> List[dict]: + payloads = [] + for block in raw.split("\n\n"): + for line in block.strip().split("\n"): + if line.startswith("data:"): + payload = line[len("data:") :].strip() + try: + parsed = json.loads(payload) + except json.JSONDecodeError: + continue + if isinstance(parsed, dict): + payloads.append(parsed) + return payloads + + +@pytest.mark.asyncio +async def test_mid_stream_block_emits_clean_anthropic_sse(): + """Per-chunk block: a clean SSE termination with the block message, no error blob.""" + raw = await _run_hook(end=False) + _assert_clean_block_termination(raw) + + +@pytest.mark.asyncio +async def test_end_of_stream_block_emits_clean_anthropic_sse(): + """End-of-stream block: same clean SSE termination guarantees.""" + raw = await _run_hook(end=True) + _assert_clean_block_termination(raw) + + +@pytest.mark.asyncio +async def test_mid_stream_block_after_prior_chunks_continues_message(): + """Regression: when real chunks were already forwarded (sampling_rate>1), + the block must continue the in-progress message, not start a second one.""" + raw = await _run_hook(end=False, sampling_rate=5) + # Some original content was forwarded before the block... + assert "message_start" in raw + # ...and the block continues that same message (single message_start) with + # the block message appended, ending cleanly. + _assert_clean_block_termination(raw) + + +@pytest.mark.asyncio +async def test_end_of_stream_only_block_does_not_append_after_message_stop(): + raw = await _run_hook(end=True, end_of_stream_only=True) + event_types = _parse_sse_event_types(raw) + message_delta_usages = [ + payload.get("usage", {}).get("output_tokens") + for payload in _parse_sse_payloads(raw) + if payload.get("type") == "message_delta" + ] + + assert BLOCK_MESSAGE in raw + assert event_types.count("message_stop") == 1 + assert event_types[-1] == "message_stop" + assert message_delta_usages[-1] == 5 + + +def test_blocked_stream_reports_usage_from_original_chunks(): + from litellm.integrations.custom_guardrail import ModifyResponseException + from litellm.llms.anthropic.chat.guardrail_translation.handler import ( + AnthropicMessagesHandler, + ) + from litellm.llms.base_llm.guardrail_translation.utils import ( + blocked_response_usage, + ) + + original_chunks: List[Any] = [ + _sse_event( + "message_start", + { + "type": "message_start", + "message": { + "id": "msg_orig", + "type": "message", + "role": "assistant", + "model": "claude-3-5-sonnet", + "content": [], + "stop_reason": None, + "usage": {"input_tokens": 12, "output_tokens": 0}, + }, + }, + ), + {"type": "message_delta", "delta": {"stop_reason": "end_turn"}, "usage": {"output_tokens": 5}}, + ] + seen_chunks = [ + _sse_event( + "content_block_start", + {"type": "content_block_start", "index": 0, "content_block": {"type": "text", "text": ""}}, + ) + ] + exc = ModifyResponseException( + message=BLOCK_MESSAGE, + model="claude-3-5-sonnet", + request_data={}, + guardrail_name="g", + original_response=original_chunks, + ) + + usage = blocked_response_usage(original_chunks) + raw = b"".join( + AnthropicMessagesHandler().build_block_sse_chunks(exc, stream_started=True, responses_so_far=seen_chunks) + ).decode() + message_delta_usages = [ + payload.get("usage", {}).get("output_tokens") + for payload in _parse_sse_payloads(raw) + if payload.get("type") == "message_delta" + ] + + assert usage == {"input_tokens": 12, "output_tokens": 5} + assert message_delta_usages[-1] == 5 + + +class TestContentBlockState: + """`_content_block_state` must reflect the true open/last block index across + the two chunk formats the stream can carry (multi-event bytes, parsed dict), + so a mid-stream block closes/opens the right indices.""" + + def _handler(self): + from litellm.llms.anthropic.chat.guardrail_translation.handler import ( + AnthropicMessagesHandler, + ) + + return AnthropicMessagesHandler() + + def test_multi_event_bytes_chunk_is_fully_parsed(self): + # One item bundles start(0) + delta + stop(0): the block is already + # closed, so open_index is None (not 0) and max_index is 0. + bundled = ( + _sse_event( + "content_block_start", + {"type": "content_block_start", "index": 0, "content_block": {"type": "text", "text": ""}}, + ) + + _sse_event( + "content_block_delta", + {"type": "content_block_delta", "index": 0, "delta": {"type": "text_delta", "text": "hi"}}, + ) + + _sse_event("content_block_stop", {"type": "content_block_stop", "index": 0}) + ) + open_index, max_index = self._handler()._content_block_state([bundled]) + assert open_index is None + assert max_index == 0 + + def test_open_block_across_separate_chunks(self): + chunks = [ + _sse_event( + "content_block_start", + {"type": "content_block_start", "index": 0, "content_block": {"type": "text", "text": ""}}, + ), + _sse_event("content_block_stop", {"type": "content_block_stop", "index": 0}), + _sse_event( + "content_block_start", + {"type": "content_block_start", "index": 1, "content_block": {"type": "text", "text": ""}}, + ), + ] + open_index, max_index = self._handler()._content_block_state(chunks) + assert open_index == 1 + assert max_index == 1 + + def test_dict_format_chunks_are_parsed(self): + # The backwards-compat parsed-dict format must be understood too. + chunks = [ + {"type": "content_block_start", "index": 0, "content_block": {"type": "text", "text": ""}}, + {"type": "content_block_delta", "index": 0, "delta": {"type": "text_delta", "text": "x"}}, + ] + open_index, max_index = self._handler()._content_block_state(chunks) + assert open_index == 0 + assert max_index == 0 + + def test_continuation_closes_open_block_and_appends_after_it(self): + from litellm.integrations.custom_guardrail import ModifyResponseException + + handler = self._handler() + # Client has seen an open text block at index 0. + seen = [ + _sse_event( + "content_block_start", + {"type": "content_block_start", "index": 0, "content_block": {"type": "text", "text": ""}}, + ), + _sse_event( + "content_block_delta", + {"type": "content_block_delta", "index": 0, "delta": {"type": "text_delta", "text": "partial"}}, + ), + ] + exc = ModifyResponseException( + message=BLOCK_MESSAGE, model="claude-3-5-sonnet", request_data={}, guardrail_name="g" + ) + raw = b"".join(handler.build_block_sse_chunks(exc, stream_started=True, responses_so_far=seen)).decode() + events = _parse_sse_event_types(raw) + # No new message envelope, closes block 0, appends block text at index 1. + assert "message_start" not in events + assert events == [ + "content_block_stop", + "content_block_start", + "content_block_delta", + "content_block_stop", + "message_delta", + "message_stop", + ] + assert BLOCK_MESSAGE in raw + assert '"index": 1' in raw diff --git a/tests/test_litellm/proxy/guardrails/guardrail_hooks/unified_guardrails/test_streaming_buffer_until_moderated.py b/tests/test_litellm/proxy/guardrails/guardrail_hooks/unified_guardrails/test_streaming_buffer_until_moderated.py new file mode 100644 index 00000000000..2b163ee5233 --- /dev/null +++ b/tests/test_litellm/proxy/guardrails/guardrail_hooks/unified_guardrails/test_streaming_buffer_until_moderated.py @@ -0,0 +1,173 @@ +""" +Tests for ``streaming_buffer_until_moderated`` on the unified guardrail +post-call streaming iterator hook. + +With this flag set, the hook must withhold every upstream chunk until +end-of-stream moderation has run. The decisive guarantee versus the +detect-only ``streaming_end_of_stream_only`` behavior: when the guardrail +blocks, the original (objectionable) content is NEVER yielded to the client -- +only the block message is. On a clean response, all original chunks are +released unchanged after moderation passes. +""" + +import json +from typing import Any, List, Literal, Optional + +import pytest + +from litellm.integrations.custom_guardrail import ( + CustomGuardrail, + ModifyResponseException, +) +from litellm.proxy._types import UserAPIKeyAuth +from litellm.proxy.guardrails.guardrail_hooks.unified_guardrail.unified_guardrail import ( + UnifiedLLMGuardrails, +) +from litellm.types.utils import GenericGuardrailAPIInputs + +BLOCK_MESSAGE = "Blocked by policy: this response was withheld." +ORIGINAL_MARKER = "ORIGINAL-SECRET-ANSWER" + + +class _BlockingGuardrail(CustomGuardrail): + """Always blocks at moderation time.""" + + async def apply_guardrail( + self, + inputs: GenericGuardrailAPIInputs, + request_data: dict, + input_type: Literal["request", "response"], + logging_obj: Optional[Any] = None, + ) -> GenericGuardrailAPIInputs: + raise ModifyResponseException( + message=BLOCK_MESSAGE, + model="claude-3-5-sonnet", + request_data=request_data, + guardrail_name=self.guardrail_name, + ) + + +class _PassingGuardrail(CustomGuardrail): + """Never blocks; returns inputs unchanged.""" + + async def apply_guardrail( + self, + inputs: GenericGuardrailAPIInputs, + request_data: dict, + input_type: Literal["request", "response"], + logging_obj: Optional[Any] = None, + ) -> GenericGuardrailAPIInputs: + return inputs + + +def _sse_event(event_type: str, data: dict) -> bytes: + return f"event: {event_type}\ndata: {json.dumps(data)}\n\n".encode() + + +async def _anthropic_stream(): + """A complete Anthropic /v1/messages SSE stream whose assistant text + contains ORIGINAL_MARKER so leakage is unambiguous to assert.""" + yield _sse_event( + "message_start", + { + "type": "message_start", + "message": { + "id": "msg_orig", + "type": "message", + "role": "assistant", + "model": "claude-3-5-sonnet", + "content": [], + "stop_reason": None, + "usage": {"input_tokens": 1, "output_tokens": 0}, + }, + }, + ) + yield _sse_event( + "content_block_start", + { + "type": "content_block_start", + "index": 0, + "content_block": {"type": "text", "text": ""}, + }, + ) + for text in ["Here is ", "the ", ORIGINAL_MARKER, " for you."]: + yield _sse_event( + "content_block_delta", + { + "type": "content_block_delta", + "index": 0, + "delta": {"type": "text_delta", "text": text}, + }, + ) + yield _sse_event("content_block_stop", {"type": "content_block_stop", "index": 0}) + yield _sse_event( + "message_delta", + { + "type": "message_delta", + "delta": {"stop_reason": "end_turn", "stop_sequence": None}, + "usage": {"output_tokens": 5}, + }, + ) + yield _sse_event("message_stop", {"type": "message_stop"}) + + +def _decode(chunks: List[Any]) -> str: + return "".join(c.decode() if isinstance(c, bytes) else str(c) for c in chunks) + + +async def _run(guardrail: CustomGuardrail) -> str: + # Rubrik's real config: end-of-stream-only moderation. Without buffering + # this releases every chunk before moderation runs (content leaks on + # block); the buffer flag must change that to moderate-then-release. + guardrail.streaming_end_of_stream_only = True + guardrail.streaming_buffer_until_moderated = True + unified = UnifiedLLMGuardrails() + user_api_key_dict = UserAPIKeyAuth(api_key="test", request_route="/v1/messages") + request_data = { + "messages": [{"role": "user", "content": "hi"}], + "guardrail_to_apply": guardrail, + "metadata": {"guardrails": [guardrail.guardrail_name]}, + } + collected: List[Any] = [] + async for chunk in unified.async_post_call_streaming_iterator_hook( + user_api_key_dict=user_api_key_dict, + response=_anthropic_stream(), + request_data=request_data, + ): + collected.append(chunk) + return _decode(collected) + + +@pytest.mark.asyncio +async def test_buffered_block_withholds_original_content(): + raw = await _run(_BlockingGuardrail(guardrail_name="blk", event_hook="post_call")) + # The original content must never reach the client... + assert ORIGINAL_MARKER not in raw, f"original content leaked: {raw!r}" + # ...only the block message, in a clean terminating stream. + assert BLOCK_MESSAGE in raw + assert '"error"' not in raw + + +@pytest.mark.asyncio +async def test_buffered_clean_releases_all_content(): + raw = await _run(_PassingGuardrail(guardrail_name="pass", event_hook="post_call")) + # A clean response is released in full after moderation passes. + assert ORIGINAL_MARKER in raw + assert ( + raw.rstrip().endswith('event: message_stop\ndata: {"type": "message_stop"}'.rstrip()) or "message_stop" in raw + ) + assert BLOCK_MESSAGE not in raw + + +@pytest.mark.asyncio +async def test_buffered_mode_disabled_for_content_rewriting_guardrail(): + """Buffered replay yields the withheld *original* chunks verbatim, which + is unsafe for a guardrail that rewrites response text (e.g. PII masking): + the client would get the unredacted original instead of the moderated + output. mask_response_content=True must force buffering off so the + request falls back to the (correctly moderated) non-buffered path.""" + guardrail = _PassingGuardrail(guardrail_name="masker", event_hook="post_call", mask_response_content=True) + raw = await _run(guardrail) + assert guardrail.streaming_buffer_until_moderated is True # request asked for buffering + assert ORIGINAL_MARKER in raw + assert BLOCK_MESSAGE not in raw 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 56eeea82223..ce2d04f0d26 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 @@ -1000,6 +1000,259 @@ async def test_new_user_non_admin_cannot_create_admin(mocker): assert str(LitellmUserRoles.PROXY_ADMIN_VIEW_ONLY) in str(exc_info2.value.message) +@pytest.mark.asyncio +async def test_new_user_non_admin_permissions_non_empty_rejected(mocker): + """`new_user` rejects a non-admin when `permissions` is present in the + request body. `/user/new` propagates the value into the auto-created + key via `generate_key_helper_fn`.""" + from litellm.proxy.management_endpoints.internal_user_endpoints import new_user + + mock_prisma_client = mocker.MagicMock() + + async def mock_count(*args, **kwargs): + return 5 + + mock_prisma_client.db.litellm_usertable.count = mock_count + + async def mock_check(*_args, **_kwargs): + return None + + mocker.patch( + "litellm.proxy.management_endpoints.internal_user_endpoints._check_duplicate_user_email", + mock_check, + ) + mocker.patch( + "litellm.proxy.management_endpoints.internal_user_endpoints._check_duplicate_user_id", + mock_check, + ) + mock_license_check = mocker.MagicMock() + mock_license_check.is_over_limit.return_value = False + mocker.patch("litellm.proxy.proxy_server.prisma_client", mock_prisma_client) + mocker.patch("litellm.proxy.proxy_server._license_check", mock_license_check) + + data = NewUserRequest( + user_email="alice@example.com", + user_role=LitellmUserRoles.INTERNAL_USER, + permissions={"get_spend_routes": True}, + ) + caller = UserAPIKeyAuth( + user_id="org-admin", user_role=LitellmUserRoles.ORG_ADMIN + ) + + with pytest.raises(ProxyException) as exc_info: + await new_user(data=data, user_api_key_dict=caller) + assert str(exc_info.value.code) == "403" + assert "permissions" in str(exc_info.value.message) + + +@pytest.mark.asyncio +async def test_new_user_non_admin_permissions_explicit_empty_rejected(mocker): + """`new_user` rejects a non-admin when `permissions` is present as + `{}` in the request body. The value matches the model default but + `model_fields_set` distinguishes the two.""" + from litellm.proxy.management_endpoints.internal_user_endpoints import new_user + + mock_prisma_client = mocker.MagicMock() + + async def mock_count(*args, **kwargs): + return 5 + + mock_prisma_client.db.litellm_usertable.count = mock_count + + async def mock_check(*_args, **_kwargs): + return None + + mocker.patch( + "litellm.proxy.management_endpoints.internal_user_endpoints._check_duplicate_user_email", + mock_check, + ) + mocker.patch( + "litellm.proxy.management_endpoints.internal_user_endpoints._check_duplicate_user_id", + mock_check, + ) + mock_license_check = mocker.MagicMock() + mock_license_check.is_over_limit.return_value = False + mocker.patch("litellm.proxy.proxy_server.prisma_client", mock_prisma_client) + mocker.patch("litellm.proxy.proxy_server._license_check", mock_license_check) + + data = NewUserRequest( + user_email="alice@example.com", + user_role=LitellmUserRoles.INTERNAL_USER, + permissions={}, + ) + assert "permissions" in data.model_fields_set + caller = UserAPIKeyAuth( + user_id="org-admin", user_role=LitellmUserRoles.ORG_ADMIN + ) + + with pytest.raises(ProxyException) as exc_info: + await new_user(data=data, user_api_key_dict=caller) + assert str(exc_info.value.code) == "403" + assert "permissions" in str(exc_info.value.message) + + +@pytest.mark.asyncio +async def test_new_user_non_admin_omits_permissions_succeeds(mocker): + """`new_user` does not fire the permissions gate when `permissions` + is absent from the request body. The model-level default `{}` is not + in `model_fields_set`.""" + from litellm.proxy.management_endpoints.internal_user_endpoints import new_user + + mock_prisma_client = mocker.MagicMock() + + async def mock_count(*args, **kwargs): + return 5 + + mock_prisma_client.db.litellm_usertable.count = mock_count + + async def mock_check(*_args, **_kwargs): + return None + + mocker.patch( + "litellm.proxy.management_endpoints.internal_user_endpoints._check_duplicate_user_email", + mock_check, + ) + mocker.patch( + "litellm.proxy.management_endpoints.internal_user_endpoints._check_duplicate_user_id", + mock_check, + ) + mock_license_check = mocker.MagicMock() + mock_license_check.is_over_limit.return_value = False + mocker.patch("litellm.proxy.proxy_server.prisma_client", mock_prisma_client) + mocker.patch("litellm.proxy.proxy_server._license_check", mock_license_check) + + stub_response = {"user_id": "alice", "key": "sk-alice", "expires": None} + + async def stub_helper(**_kwargs): + return stub_response + + mocker.patch( + "litellm.proxy.management_endpoints.internal_user_endpoints.generate_key_helper_fn", + stub_helper, + ) + + data = NewUserRequest( + user_email="alice@example.com", + user_role=LitellmUserRoles.INTERNAL_USER, + ) + assert "permissions" not in data.model_fields_set + caller = UserAPIKeyAuth( + user_id="org-admin", user_role=LitellmUserRoles.ORG_ADMIN + ) + + result = await new_user(data=data, user_api_key_dict=caller) + assert result is not None + + +@pytest.mark.asyncio +async def test_new_user_admin_can_set_permissions(mocker): + """`new_user` accepts a PROXY_ADMIN caller for any shape of + `permissions` in the request body.""" + from litellm.proxy.management_endpoints.internal_user_endpoints import new_user + + mock_prisma_client = mocker.MagicMock() + + async def mock_count(*args, **kwargs): + return 5 + + mock_prisma_client.db.litellm_usertable.count = mock_count + + async def mock_check(*_args, **_kwargs): + return None + + mocker.patch( + "litellm.proxy.management_endpoints.internal_user_endpoints._check_duplicate_user_email", + mock_check, + ) + mocker.patch( + "litellm.proxy.management_endpoints.internal_user_endpoints._check_duplicate_user_id", + mock_check, + ) + mock_license_check = mocker.MagicMock() + mock_license_check.is_over_limit.return_value = False + mocker.patch("litellm.proxy.proxy_server.prisma_client", mock_prisma_client) + mocker.patch("litellm.proxy.proxy_server._license_check", mock_license_check) + + async def stub_helper(**_kwargs): + return {"user_id": "alice", "key": "sk-alice", "expires": None} + + mocker.patch( + "litellm.proxy.management_endpoints.internal_user_endpoints.generate_key_helper_fn", + stub_helper, + ) + + admin = UserAPIKeyAuth(user_id="admin", user_role=LitellmUserRoles.PROXY_ADMIN) + for permissions_value in ({"get_spend_routes": True}, {}, None): + data = NewUserRequest( + user_email=f"alice-{permissions_value}@example.com", + user_role=LitellmUserRoles.INTERNAL_USER, + permissions=permissions_value, + ) + result = await new_user(data=data, user_api_key_dict=admin) + assert result is not None + + +@pytest.mark.asyncio +async def test_update_single_user_non_admin_permissions_rejected(mocker): + """`_update_single_user_helper` rejects a non-admin when `permissions` + is present in the request body. Covers both `/user/update` and + `/user/bulk_update`, which share this helper.""" + from fastapi import HTTPException + + from litellm.proxy._types import UpdateUserRequest + from litellm.proxy.management_endpoints.internal_user_endpoints import ( + _update_single_user_helper, + ) + + mock_prisma_client = mocker.MagicMock() + mocker.patch("litellm.proxy.proxy_server.prisma_client", mock_prisma_client) + mocker.patch("litellm.proxy.proxy_server.litellm_proxy_admin_name", "admin") + + data = UpdateUserRequest( + user_id="alice", + permissions={"get_spend_routes": True}, + ) + caller = UserAPIKeyAuth( + user_id="org-admin", user_role=LitellmUserRoles.ORG_ADMIN + ) + + with pytest.raises(HTTPException) as exc_info: + await _update_single_user_helper( + user_request=data, user_api_key_dict=caller + ) + assert exc_info.value.status_code == 403 + assert "permissions" in str(exc_info.value.detail) + + +@pytest.mark.asyncio +async def test_update_single_user_non_admin_permissions_explicit_empty_rejected(mocker): + """`_update_single_user_helper` rejects a non-admin when `permissions` + is present as `{}` in the request body.""" + from fastapi import HTTPException + + from litellm.proxy._types import UpdateUserRequest + from litellm.proxy.management_endpoints.internal_user_endpoints import ( + _update_single_user_helper, + ) + + mock_prisma_client = mocker.MagicMock() + mocker.patch("litellm.proxy.proxy_server.prisma_client", mock_prisma_client) + mocker.patch("litellm.proxy.proxy_server.litellm_proxy_admin_name", "admin") + + data = UpdateUserRequest(user_id="alice", permissions={}) + assert "permissions" in data.model_fields_set + caller = UserAPIKeyAuth( + user_id="org-admin", user_role=LitellmUserRoles.ORG_ADMIN + ) + + with pytest.raises(HTTPException) as exc_info: + await _update_single_user_helper( + user_request=data, user_api_key_dict=caller + ) + assert exc_info.value.status_code == 403 + assert "permissions" in str(exc_info.value.detail) + + @pytest.mark.asyncio async def test_user_info_url_encoding_plus_character(mocker): """ diff --git a/tests/test_litellm/proxy/management_endpoints/test_key_management_endpoints.py b/tests/test_litellm/proxy/management_endpoints/test_key_management_endpoints.py index 601fa2c6d78..ee9202f522e 100644 --- a/tests/test_litellm/proxy/management_endpoints/test_key_management_endpoints.py +++ b/tests/test_litellm/proxy/management_endpoints/test_key_management_endpoints.py @@ -11141,6 +11141,249 @@ class TestAllowedRoutesCallerPermission: assert str(exc_info.value.code) == "403" assert "allowed_routes" in str(exc_info.value.message) + @pytest.mark.asyncio + async def test_non_admin_update_key_explicit_empty_allowed_routes_rejected(self): + """`update_key_fn` rejects a non-admin when `allowed_routes` is + present as `[]` in the request body. The value matches the model + default but `model_fields_set` distinguishes the two.""" + from litellm.proxy.management_endpoints.key_management_endpoints import ( + update_key_fn, + ) + + data = UpdateKeyRequest(key="sk-test", allowed_routes=[]) + assert "allowed_routes" in data.model_fields_set + user_api_key_dict = UserAPIKeyAuth( + user_id="internal-user-123", + user_role=LitellmUserRoles.INTERNAL_USER, + ) + mock_prisma_client = AsyncMock() + + with ( + patch("litellm.proxy.proxy_server.prisma_client", mock_prisma_client), + patch("litellm.proxy.proxy_server.user_api_key_cache", MagicMock()), + patch("litellm.proxy.proxy_server.user_custom_key_update", None), + patch("litellm.proxy.proxy_server.llm_router", None), + patch("litellm.proxy.proxy_server.premium_user", True), + patch("litellm.proxy.proxy_server.proxy_logging_obj", MagicMock()), + patch( + "litellm.proxy.management_endpoints.key_management_endpoints._get_and_validate_existing_key", + new_callable=AsyncMock, + return_value=MagicMock(), + ), + ): + with pytest.raises(ProxyException) as exc_info: + await update_key_fn( + request=MagicMock(), + data=data, + user_api_key_dict=user_api_key_dict, + litellm_changed_by=None, + ) + assert str(exc_info.value.code) == "403" + assert "allowed_routes" in str(exc_info.value.message) + + @pytest.mark.asyncio + async def test_non_admin_update_key_explicit_null_allowed_routes_rejected(self): + """`update_key_fn` rejects a non-admin when `allowed_routes` is + present as `null` in the request body.""" + from litellm.proxy.management_endpoints.key_management_endpoints import ( + update_key_fn, + ) + + data = UpdateKeyRequest(key="sk-test", allowed_routes=None) + assert "allowed_routes" in data.model_fields_set + user_api_key_dict = UserAPIKeyAuth( + user_id="internal-user-123", + user_role=LitellmUserRoles.INTERNAL_USER, + ) + mock_prisma_client = AsyncMock() + + with ( + patch("litellm.proxy.proxy_server.prisma_client", mock_prisma_client), + patch("litellm.proxy.proxy_server.user_api_key_cache", MagicMock()), + patch("litellm.proxy.proxy_server.user_custom_key_update", None), + patch("litellm.proxy.proxy_server.llm_router", None), + patch("litellm.proxy.proxy_server.premium_user", True), + patch("litellm.proxy.proxy_server.proxy_logging_obj", MagicMock()), + patch( + "litellm.proxy.management_endpoints.key_management_endpoints._get_and_validate_existing_key", + new_callable=AsyncMock, + return_value=MagicMock(), + ), + ): + with pytest.raises(ProxyException) as exc_info: + await update_key_fn( + request=MagicMock(), + data=data, + user_api_key_dict=user_api_key_dict, + litellm_changed_by=None, + ) + assert str(exc_info.value.code) == "403" + assert "allowed_routes" in str(exc_info.value.message) + + @pytest.mark.asyncio + async def test_non_admin_regenerate_key_explicit_empty_allowed_routes_rejected(self): + """`regenerate_key_fn` rejects a non-admin when `allowed_routes` is + present as `[]` in the request body.""" + from litellm.proxy._types import RegenerateKeyRequest + from litellm.proxy.management_endpoints.key_management_endpoints import ( + regenerate_key_fn, + ) + + data = RegenerateKeyRequest(key="sk-test", allowed_routes=[]) + assert "allowed_routes" in data.model_fields_set + user_api_key_dict = UserAPIKeyAuth( + user_id="internal-user-123", + user_role=LitellmUserRoles.INTERNAL_USER, + ) + + with patch("litellm.proxy.proxy_server.premium_user", True): + with pytest.raises(ProxyException) as exc_info: + await regenerate_key_fn( + key=None, + data=data, + user_api_key_dict=user_api_key_dict, + litellm_changed_by=None, + ) + assert str(exc_info.value.code) == "403" + assert "allowed_routes" in str(exc_info.value.message) + + @pytest.mark.asyncio + async def test_non_admin_regenerate_key_allowed_routes_rejected_before_enterprise_gate(self): + """`regenerate_key_fn` runs `_check_allowed_routes_caller_permission` + before the `premium_user` check, so a non-premium proxy still returns + the allowed_routes rejection (403) rather than the enterprise-license + error (500) when a non-admin sends `allowed_routes`.""" + from litellm.proxy._types import RegenerateKeyRequest + from litellm.proxy.management_endpoints.key_management_endpoints import ( + regenerate_key_fn, + ) + + data = RegenerateKeyRequest(key="sk-test", allowed_routes=["/*"]) + user_api_key_dict = UserAPIKeyAuth( + user_id="internal-user-123", + user_role=LitellmUserRoles.INTERNAL_USER, + ) + + with patch("litellm.proxy.proxy_server.premium_user", False): + with pytest.raises(ProxyException) as exc_info: + await regenerate_key_fn( + key=None, + data=data, + user_api_key_dict=user_api_key_dict, + litellm_changed_by=None, + ) + assert str(exc_info.value.code) == "403" + assert "allowed_routes" in str(exc_info.value.message) + assert "Enterprise" not in str(exc_info.value.message) + + @pytest.mark.asyncio + async def test_non_admin_generate_key_explicit_empty_allowed_routes_rejected(self): + """`generate_key_fn` rejects a non-admin when `allowed_routes` is + present as `[]` in the request body. The value matches the model + default but `model_fields_set` distinguishes the two, so the + explicit-empty case on the create path is caught.""" + data = GenerateKeyRequest(key_alias="plain-key", allowed_routes=[]) + assert "allowed_routes" in data.model_fields_set + user_api_key_dict = UserAPIKeyAuth( + user_id="internal-user-123", + user_role=LitellmUserRoles.INTERNAL_USER, + ) + mock_prisma_client = AsyncMock() + + with ( + patch("litellm.proxy.proxy_server.prisma_client", mock_prisma_client), + patch("litellm.proxy.proxy_server.user_api_key_cache", MagicMock()), + patch("litellm.proxy.proxy_server.user_custom_key_generate", None), + patch( + "litellm.proxy.management_endpoints.key_management_endpoints._common_key_generation_helper", + new_callable=AsyncMock, + return_value=MagicMock(), + ), + ): + with pytest.raises(ProxyException) as exc_info: + await generate_key_fn( + data=data, + user_api_key_dict=user_api_key_dict, + litellm_changed_by=None, + ) + assert str(exc_info.value.code) == "403" + assert "allowed_routes" in str(exc_info.value.message) + + def test_helper_accepts_derived_safe_preset_for_non_admin(self): + """`_check_allowed_routes_caller_permission` accepts a non-admin + when `allow_safe_presets=True` and `allowed_routes` is entirely + composed of `_NON_ADMIN_SAFE_ALLOWED_ROUTES_PRESETS` tokens. This + is the shape the post-`handle_key_type` recheck at line 914 uses + after deriving `["llm_api_routes"]` from `key_type=llm_api`.""" + from litellm.proxy.management_endpoints.key_management_endpoints import ( + _check_allowed_routes_caller_permission, + ) + + _check_allowed_routes_caller_permission( + allowed_routes=["llm_api_routes"], + user_api_key_dict=UserAPIKeyAuth( + user_id="internal-user-123", + user_role=LitellmUserRoles.INTERNAL_USER, + ), + allow_safe_presets=True, + ) + _check_allowed_routes_caller_permission( + allowed_routes=["info_routes"], + user_api_key_dict=UserAPIKeyAuth( + user_id="internal-user-123", + user_role=LitellmUserRoles.INTERNAL_USER, + ), + allow_safe_presets=True, + ) + + def test_helper_rejects_derived_unsafe_preset_for_non_admin(self): + """`_check_allowed_routes_caller_permission` rejects a non-admin + when `allow_safe_presets=True` but the derived value is outside + `_NON_ADMIN_SAFE_ALLOWED_ROUTES_PRESETS` (for example + `["management_routes"]` from `key_type=management`).""" + from fastapi import HTTPException + + from litellm.proxy.management_endpoints.key_management_endpoints import ( + _check_allowed_routes_caller_permission, + ) + + with pytest.raises(HTTPException) as exc_info: + _check_allowed_routes_caller_permission( + allowed_routes=["management_routes"], + user_api_key_dict=UserAPIKeyAuth( + user_id="internal-user-123", + user_role=LitellmUserRoles.INTERNAL_USER, + ), + allow_safe_presets=True, + ) + assert exc_info.value.status_code == 403 + assert "allowed_routes" in str(exc_info.value.detail) + + def test_helper_rejects_when_provided_and_none_without_typeerror(self): + """`_check_allowed_routes_caller_permission` returns a 403 (not a + TypeError from iterating `None`) when a caller ever combines + `allowed_routes_was_provided=True` with `allowed_routes=None` and + `allow_safe_presets=True`. Pins the `and allowed_routes` guard on + the safe-preset branch.""" + from fastapi import HTTPException + + from litellm.proxy.management_endpoints.key_management_endpoints import ( + _check_allowed_routes_caller_permission, + ) + + with pytest.raises(HTTPException) as exc_info: + _check_allowed_routes_caller_permission( + allowed_routes=None, + user_api_key_dict=UserAPIKeyAuth( + user_id="internal-user-123", + user_role=LitellmUserRoles.INTERNAL_USER, + ), + allowed_routes_was_provided=True, + allow_safe_presets=True, + ) + assert exc_info.value.status_code == 403 + assert "allowed_routes" in str(exc_info.value.detail) + def test_jinja_prompt_manager_is_sandboxed(): """ @@ -11264,6 +11507,67 @@ async def test_process_single_key_update_cache_invalidation_with_token_hash(): assert call_kwargs["hashed_token"] == token_hash +@pytest.mark.asyncio +async def test_process_single_key_update_non_admin_permissions_rejected(): + """`_process_single_key_update` rejects a non-admin when `permissions` + is present in the constructed `UpdateKeyRequest`. Guards the bulk path + against a future widening of the `BulkUpdateKeyRequestItem` or + `KeyUpdateFields` allowlists reopening the class.""" + update_key_request = UpdateKeyRequest( + key="abc123", + permissions={"get_spend_routes": True}, + ) + assert "permissions" in update_key_request.model_fields_set + + non_admin = UserAPIKeyAuth( + user_role=LitellmUserRoles.INTERNAL_USER, + api_key="sk-non-admin", + user_id="user-1", + ) + + with pytest.raises(HTTPException) as exc_info: + await _process_single_key_update( + update_key_request=update_key_request, + user_api_key_dict=non_admin, + litellm_changed_by=None, + prisma_client=AsyncMock(), + user_api_key_cache=MagicMock(), + proxy_logging_obj=MagicMock(), + llm_router=MagicMock(), + ) + assert exc_info.value.status_code == 403 + assert "permissions" in str(exc_info.value.detail) + + +@pytest.mark.asyncio +async def test_process_single_key_update_non_admin_permissions_explicit_empty_rejected(): + """`_process_single_key_update` rejects a non-admin when `permissions` + is present as `{}` in the constructed `UpdateKeyRequest`. Presence + check on `model_fields_set` catches the explicit-empty case the same + as any other value.""" + update_key_request = UpdateKeyRequest(key="abc123", permissions={}) + assert "permissions" in update_key_request.model_fields_set + + non_admin = UserAPIKeyAuth( + user_role=LitellmUserRoles.INTERNAL_USER, + api_key="sk-non-admin", + user_id="user-1", + ) + + with pytest.raises(HTTPException) as exc_info: + await _process_single_key_update( + update_key_request=update_key_request, + user_api_key_dict=non_admin, + litellm_changed_by=None, + prisma_client=AsyncMock(), + user_api_key_cache=MagicMock(), + proxy_logging_obj=MagicMock(), + llm_router=MagicMock(), + ) + assert exc_info.value.status_code == 403 + assert "permissions" in str(exc_info.value.detail) + + @pytest.mark.asyncio async def test_execute_virtual_key_regeneration_cache_invalidation_with_token_hash(): """ diff --git a/tests/test_litellm/proxy/test_blocked_response_usage.py b/tests/test_litellm/proxy/test_blocked_response_usage.py new file mode 100644 index 00000000000..d486431ca3e --- /dev/null +++ b/tests/test_litellm/proxy/test_blocked_response_usage.py @@ -0,0 +1,84 @@ +""" +Token usage on synthetic guardrail-blocked responses for the OpenAI-format +proxy endpoints (/v1/chat/completions and /v1/completions). + +A post-call block replaces the LLM response with the violation message, but the +upstream call already consumed tokens. `_blocked_response_usage` reports that +real usage (carried on `ModifyResponseException.original_response`) rather than +zero; a pre-call block never invoked the LLM, so usage is zero. +""" + +import pytest + +import litellm +from litellm.proxy.proxy_server import _blocked_response_usage + + +def test_uses_original_response_usage(): + resp = litellm.ModelResponse() + resp.usage = litellm.Usage(prompt_tokens=42, completion_tokens=7, total_tokens=49) + + usage = _blocked_response_usage(resp) + + assert usage.prompt_tokens == 42 + assert usage.completion_tokens == 7 + assert usage.total_tokens == 49 + + +def test_zero_usage_when_no_original_response(): + usage = _blocked_response_usage(None) + + assert usage.prompt_tokens == 0 + assert usage.completion_tokens == 0 + assert usage.total_tokens == 0 + + +@pytest.mark.asyncio +async def test_success_hook_attaches_original_response_on_block(): + """The unified guardrail's post-call success hook must attach the blocked + LLM response to ModifyResponseException so its real usage isn't discarded.""" + from unittest.mock import AsyncMock, MagicMock, patch + + import litellm.proxy.guardrails.guardrail_hooks.unified_guardrail.unified_guardrail as ug + from litellm.integrations.custom_guardrail import ModifyResponseException + from litellm.proxy._types import UserAPIKeyAuth + from litellm.types.utils import CallTypes + + response = litellm.ModelResponse() + response.usage = litellm.Usage(prompt_tokens=15, completion_tokens=3, total_tokens=18) + + guardrail = MagicMock() + guardrail.should_run_guardrail.return_value = True + guardrail.guardrail_name = "rubrik" + + # The translation layer raises a block without pre-setting original_response. + translation = MagicMock() + translation.process_output_response = AsyncMock( + side_effect=ModifyResponseException( + message="blocked", + model="gpt-4o", + request_data={}, + guardrail_name="rubrik", + ) + ) + + unified = ug.UnifiedLLMGuardrails() + user_api_key_dict = UserAPIKeyAuth(api_key="test", request_route="/chat/completions") + data = {"guardrail_to_apply": guardrail, "model": "gpt-4o"} + + # Inject our translation for the inferred call type (the module global is + # cached across tests, so patch it directly rather than the loader). + with patch.object( + ug, + "endpoint_guardrail_translation_mappings", + { + CallTypes.acompletion: lambda: translation, + CallTypes.completion: lambda: translation, + }, + ): + with pytest.raises(ModifyResponseException) as excinfo: + await unified.async_post_call_success_hook( + data=data, user_api_key_dict=user_api_key_dict, response=response + ) + + assert excinfo.value.original_response is response diff --git a/tests/test_litellm/proxy/test_litellm_pre_call_utils.py b/tests/test_litellm/proxy/test_litellm_pre_call_utils.py index 74f681bb97e..913ac116866 100644 --- a/tests/test_litellm/proxy/test_litellm_pre_call_utils.py +++ b/tests/test_litellm/proxy/test_litellm_pre_call_utils.py @@ -856,10 +856,19 @@ async def test_add_litellm_data_to_request_strips_client_redaction_bypass_contro "model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "hello"}], "turn_off_message_logging": False, - "metadata": {"headers": {"litellm-disable-message-redaction": "true"}}, + "metadata": { + "headers": {"litellm-disable-message-redaction": "true"}, + "turn_off_message_logging": False, + }, "litellm_metadata": json.dumps( - {"headers": {"LiteLLM-Disable-Message-Redaction": "true"}} + { + "headers": {"LiteLLM-Disable-Message-Redaction": "true"}, + "turn_off_message_logging": "false", + } ), + "litellm_params": { + "metadata": {"turn_off_message_logging": False}, + }, }, request=request_mock, user_api_key_dict=UserAPIKeyAuth(api_key="hashed-key"), @@ -871,6 +880,9 @@ async def test_add_litellm_data_to_request_strips_client_redaction_bypass_contro litellm.turn_off_message_logging = original_turn_off_message_logging assert "turn_off_message_logging" not in updated + assert "turn_off_message_logging" not in (updated.get("litellm_params") or {}).get("metadata", {}) + assert "turn_off_message_logging" not in updated["metadata"] + assert "turn_off_message_logging" not in (updated.get("litellm_metadata") or {}) assert "litellm-disable-message-redaction" not in { header.lower() for header in updated["metadata"]["headers"] } @@ -891,6 +903,158 @@ async def test_add_litellm_data_to_request_strips_client_redaction_bypass_contro } +@pytest.mark.parametrize( + "admin_metadata_kwargs", + [ + { + "metadata": { + "logging": [ + { + "callback_name": "langfuse", + "callback_type": "success_and_failure", + "callback_vars": {"turn_off_message_logging": False}, + } + ] + } + }, + { + "team_metadata": { + "logging": [ + { + "callback_name": "langfuse", + "callback_type": "success_and_failure", + "callback_vars": {"turn_off_message_logging": False}, + } + ] + } + }, + ], +) +@pytest.mark.asyncio +async def test_add_litellm_data_to_request_admin_callback_vars_turn_off_message_logging_overrides_global( + admin_metadata_kwargs, +): + from litellm.litellm_core_utils.initialize_dynamic_callback_params import ( + initialize_standard_callback_dynamic_params, + ) + from litellm.litellm_core_utils.redact_messages import should_redact_message_logging + + request_mock = MagicMock(spec=Request) + request_mock.url.path = "/v1/chat/completions" + request_mock.url = MagicMock() + request_mock.url.__str__.return_value = "http://localhost/v1/chat/completions" + request_mock.method = "POST" + request_mock.query_params = {} + request_mock.headers = {"Content-Type": "application/json"} + request_mock.client = MagicMock() + request_mock.client.host = "127.0.0.1" + + original_turn_off_message_logging = litellm.turn_off_message_logging + litellm.turn_off_message_logging = True + try: + updated = await add_litellm_data_to_request( + data={ + "model": "gpt-3.5-turbo", + "messages": [{"role": "user", "content": "hello"}], + }, + request=request_mock, + user_api_key_dict=UserAPIKeyAuth(api_key="hashed-key", **admin_metadata_kwargs), + proxy_config=MagicMock(), + general_settings={}, + version="test-version", + ) + + assert updated.get("turn_off_message_logging") == "False" + + dynamic_params = initialize_standard_callback_dynamic_params(updated) + assert dynamic_params.get("turn_off_message_logging") == "False" + + assert ( + should_redact_message_logging( + {"standard_callback_dynamic_params": dynamic_params} + ) + is False + ) + finally: + litellm.turn_off_message_logging = original_turn_off_message_logging + + +@pytest.mark.parametrize( + "admin_metadata_kwargs", + [ + { + "metadata": { + "logging": [ + { + "callback_name": "langfuse", + "callback_type": "success_and_failure", + "callback_vars": {"turn_off_message_logging": True}, + } + ] + } + }, + { + "team_metadata": { + "logging": [ + { + "callback_name": "langfuse", + "callback_type": "success_and_failure", + "callback_vars": {"turn_off_message_logging": True}, + } + ] + } + }, + ], +) +@pytest.mark.asyncio +async def test_add_litellm_data_to_request_admin_callback_vars_turn_off_message_logging_enables_redaction_when_global_off( + admin_metadata_kwargs, +): + from litellm.litellm_core_utils.initialize_dynamic_callback_params import ( + initialize_standard_callback_dynamic_params, + ) + from litellm.litellm_core_utils.redact_messages import should_redact_message_logging + + request_mock = MagicMock(spec=Request) + request_mock.url.path = "/v1/chat/completions" + request_mock.url = MagicMock() + request_mock.url.__str__.return_value = "http://localhost/v1/chat/completions" + request_mock.method = "POST" + request_mock.query_params = {} + request_mock.headers = {"Content-Type": "application/json"} + request_mock.client = MagicMock() + request_mock.client.host = "127.0.0.1" + + original_turn_off_message_logging = litellm.turn_off_message_logging + litellm.turn_off_message_logging = False + try: + updated = await add_litellm_data_to_request( + data={ + "model": "gpt-3.5-turbo", + "messages": [{"role": "user", "content": "hello"}], + }, + request=request_mock, + user_api_key_dict=UserAPIKeyAuth(api_key="hashed-key", **admin_metadata_kwargs), + proxy_config=MagicMock(), + general_settings={}, + version="test-version", + ) + + assert updated.get("turn_off_message_logging") == "True" + + dynamic_params = initialize_standard_callback_dynamic_params(updated) + assert dynamic_params.get("turn_off_message_logging") == "True" + + assert ( + should_redact_message_logging( + {"standard_callback_dynamic_params": dynamic_params} + ) + is True + ) + finally: + litellm.turn_off_message_logging = original_turn_off_message_logging + + @pytest.mark.parametrize( "auth_kwargs", [ @@ -923,7 +1087,10 @@ async def test_add_litellm_data_to_request_allows_redaction_opt_out_with_admin_o "model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "hello"}], "turn_off_message_logging": False, - "metadata": {"headers": {"litellm-disable-message-redaction": "true"}}, + "metadata": { + "headers": {"litellm-disable-message-redaction": "true"}, + "turn_off_message_logging": False, + }, "litellm_metadata": json.dumps( {"headers": {"LiteLLM-Disable-Message-Redaction": "true"}} ), @@ -938,6 +1105,7 @@ async def test_add_litellm_data_to_request_allows_redaction_opt_out_with_admin_o litellm.turn_off_message_logging = original_turn_off_message_logging assert updated["turn_off_message_logging"] is False + assert updated["metadata"]["turn_off_message_logging"] is False assert "litellm-disable-message-redaction" in { header.lower() for header in updated["metadata"]["headers"] } @@ -4798,3 +4966,91 @@ async def test_add_litellm_data_to_request_claude_code_drop_params( ) assert updated.get("drop_params") == expected_drop_params + + +@pytest.mark.asyncio +async def test_add_litellm_data_to_request_merges_metadata_tags_on_responses_route(): + """Regression for #31584: user-supplied metadata.tags must be merged into + litellm_metadata.tags on /v1/responses so they reach SpendLogs.request_tags.""" + from litellm.proxy.litellm_pre_call_utils import add_litellm_data_to_request + + request_mock = MagicMock(spec=Request) + request_mock.url = MagicMock() + request_mock.url.path = "/v1/responses" + request_mock.url.__str__.return_value = "http://localhost/v1/responses" + request_mock.method = "POST" + request_mock.query_params = {} + request_mock.headers = {"Content-Type": "application/json"} + request_mock.client = MagicMock() + request_mock.client.host = "127.0.0.1" + request_mock.state = MagicMock() + + data = { + "model": "gpt-4o", + "input": "hello", + "metadata": {"tags": ["cost-center-1", "team-alpha"]}, + } + + user_api_key_dict = UserAPIKeyAuth( + api_key="hashed-key", + metadata={}, + team_metadata={}, + ) + + updated = await add_litellm_data_to_request( + data=data, + request=request_mock, + user_api_key_dict=user_api_key_dict, + proxy_config=MagicMock(), + general_settings={}, + version="test-version", + ) + + assert "cost-center-1" in updated["litellm_metadata"]["tags"] + assert "team-alpha" in updated["litellm_metadata"]["tags"] + + +@pytest.mark.asyncio +async def test_add_litellm_data_to_request_unions_metadata_tags_with_header_tags_on_responses_route(): + """On /v1/responses, tags from metadata.tags AND x-litellm-tags header + must both appear in litellm_metadata.tags.""" + from litellm.proxy.litellm_pre_call_utils import add_litellm_data_to_request + + request_mock = MagicMock(spec=Request) + request_mock.url = MagicMock() + request_mock.url.path = "/v1/responses" + request_mock.url.__str__.return_value = "http://localhost/v1/responses" + request_mock.method = "POST" + request_mock.query_params = {} + request_mock.headers = { + "Content-Type": "application/json", + "x-litellm-tags": "header-tag", + } + request_mock.client = MagicMock() + request_mock.client.host = "127.0.0.1" + request_mock.state = MagicMock() + + data = { + "model": "gpt-4o", + "input": "hello", + "metadata": {"tags": ["body-tag"]}, + } + + user_api_key_dict = UserAPIKeyAuth( + api_key="hashed-key", + metadata={}, + team_metadata={}, + ) + + updated = await add_litellm_data_to_request( + data=data, + request=request_mock, + user_api_key_dict=user_api_key_dict, + proxy_config=MagicMock(), + general_settings={}, + version="test-version", + ) + + tags = updated["litellm_metadata"]["tags"] + assert "header-tag" in tags + assert "body-tag" in tags diff --git a/tests/test_litellm/test_prisma_generate_if_needed.py b/tests/test_litellm/test_prisma_generate_if_needed.py new file mode 100644 index 00000000000..39b9fcc4202 --- /dev/null +++ b/tests/test_litellm/test_prisma_generate_if_needed.py @@ -0,0 +1,35 @@ +import importlib.util +from pathlib import Path + +_MODULE_PATH = ( + Path(__file__).resolve().parents[2] / "scripts" / "prisma_generate_if_needed.py" +) +_spec = importlib.util.spec_from_file_location("prisma_generate_if_needed", _MODULE_PATH) +mod = importlib.util.module_from_spec(_spec) +_spec.loader.exec_module(mod) + + +def test_stamp_changes_with_schema_and_with_prisma_version(): + stamp = mod.stamp_value(b"model A {}", "0.11.0") + assert mod.stamp_value(b"model A {}", "0.11.0") == stamp + assert mod.stamp_value(b"model B {}", "0.11.0") != stamp + assert mod.stamp_value(b"model A {}", "0.12.0") != stamp + + +def test_skip_requires_a_matching_stamp(tmp_path): + stamp = tmp_path / "stamp" + expected = mod.stamp_value(b"schema", "0.11.0") + assert mod.should_skip(stamp, expected, client_generated=True) is False + stamp.write_text(expected) + assert mod.should_skip(stamp, expected, client_generated=True) is True + assert ( + mod.should_skip(stamp, mod.stamp_value(b"other", "0.11.0"), client_generated=True) + is False + ) + + +def test_skip_requires_a_generated_client_even_with_a_matching_stamp(tmp_path): + stamp = tmp_path / "stamp" + expected = mod.stamp_value(b"schema", "0.11.0") + stamp.write_text(expected) + assert mod.should_skip(stamp, expected, client_generated=False) is False diff --git a/tests/test_litellm/test_ruff_strict_gate.py b/tests/test_litellm/test_ruff_strict_gate.py index ec8f49730dd..aad0e1bc9f9 100644 --- a/tests/test_litellm/test_ruff_strict_gate.py +++ b/tests/test_litellm/test_ruff_strict_gate.py @@ -94,3 +94,19 @@ def test_introduced_keeps_only_violations_on_changed_lines(): @pytest.mark.parametrize("hunk", ["@@ -1 +1 @@", "@@ -1,0 +1,2 @@"]) def test_parse_changed_lines_handles_single_and_ranged_hunks(hunk): assert gate.parse_changed_lines(f"+++ b/litellm/a.py\n{hunk}\n")["litellm/a.py"] + + +def test_over_ceiling_flags_only_counts_above_the_limit(): + budget = rule("C901", 10) + assert gate.over_ceiling({"C901": 10}, budget) == frozenset() + assert gate.over_ceiling({"C901": 11}, budget) == frozenset({"C901"}) + assert gate.over_ceiling({}, budget) == frozenset() + + +def test_over_ceiling_ignores_rules_missing_from_the_budget(): + assert gate.over_ceiling({"NEW99": 100}, rule("C901", 10)) == frozenset() + + +def test_over_ceiling_is_independent_across_rules(): + budget = {**rule("ANN001", 150), **rule("C901", 10)} + assert gate.over_ceiling({"ANN001": 130, "C901": 11}, budget) == frozenset({"C901"}) diff --git a/tests/test_litellm/test_type_check_gate.py b/tests/test_litellm/test_type_check_gate.py index e602bf6e66f..66a28360af9 100644 --- a/tests/test_litellm/test_type_check_gate.py +++ b/tests/test_litellm/test_type_check_gate.py @@ -173,3 +173,117 @@ def test_empty_basedpyright_payload_counts_zero(): # Empty (not malformed) output parses to zero; the vacuous-run guard, not the # parser, is what rejects an empty run. assert gate.count_basedpyright("") == {} + + +def test_over_ceiling_flags_only_rules_above_their_limit(): + budget = {"reportAny": {"limit": 10}} + assert gate.over_ceiling({"reportAny": 10}, budget) == frozenset() + assert gate.over_ceiling({"reportAny": 11}, budget) == frozenset({"reportAny"}) + assert gate.over_ceiling({}, budget) == frozenset() + + +def test_over_ceiling_holds_unbudgeted_rules_to_the_default_limit(): + assert gate.over_ceiling({"brand-new": gate.DEFAULT_LIMIT}, {}) == frozenset() + assert gate.over_ceiling({"brand-new": gate.DEFAULT_LIMIT + 1}, {}) == frozenset( + {"brand-new"} + ) + + +def test_over_ceiling_is_independent_across_rules(): + budget = {"reportAny": {"limit": 10}, "reportArgumentType": {"limit": 5}} + assert gate.over_ceiling( + {"reportAny": 9, "reportArgumentType": 6}, budget + ) == frozenset({"reportArgumentType"}) + + +def test_cache_key_changes_with_base_point_and_each_fingerprint(): + key = gate.cache_key("abc", ("cfg", "lock")) + assert gate.cache_key("abc", ("cfg", "lock")) == key + assert gate.cache_key("def", ("cfg", "lock")) != key + assert gate.cache_key("abc", ("cfg2", "lock")) != key + assert gate.cache_key("abc", ("cfg", "lock2")) != key + + +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}) + assert gate.load_cached_counts(path) == {"reportAny": 3, "reportCall": 1} + + +def test_missing_corrupt_or_misshapen_cache_reads_as_none(tmp_path): + path = tmp_path / "cache.json" + assert gate.load_cached_counts(path) is None + path.write_text("{not json") + assert gate.load_cached_counts(path) is None + path.write_text(json.dumps(["counts"])) + assert gate.load_cached_counts(path) is None + path.write_text(json.dumps({"base_point": "abc"})) + assert gate.load_cached_counts(path) is None + path.write_text(json.dumps({"counts": {"reportAny": "three"}})) + assert gate.load_cached_counts(path) is None + path.write_text(json.dumps({"counts": {"reportAny": True}})) + assert gate.load_cached_counts(path) is None + + +def test_scratch_is_invisible_to_the_prune_glob(): + import fnmatch + + scratch = gate.scratch_path(gate.cache_path(Path("/c"), "abc", ("f",))) + assert not fnmatch.fnmatch(scratch.name, f"{gate.CACHE_FILE_PREFIX}*") + + +def test_store_prune_spares_a_concurrent_runs_in_flight_scratch(tmp_path): + foreign = gate.scratch_path(gate.cache_path(tmp_path, "other", ("f",))) + foreign.parent.mkdir(parents=True, exist_ok=True) + foreign.write_text("{}") + mine = gate.cache_path(tmp_path, "mine", ("f",)) + gate.store_counts(tmp_path, mine, "mine", {"reportAny": 1}) + assert foreign.exists() + assert gate.load_cached_counts(mine) == {"reportAny": 1} + + +def test_store_prunes_entries_for_other_branch_points(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(new) == {"reportAny": 2} + + +def test_base_counts_cached_returns_the_hit_without_recomputing(tmp_path): + path = gate.cache_path(tmp_path, "abc123", gate.environment_fingerprints()) + gate.store_counts(tmp_path, path, "abc123", {"reportAny": 7}) + + def explode(ref): + raise AssertionError("a cache hit must not re-run the base pass") + + assert gate.base_counts_cached("abc123", cache_dir=tmp_path, compute=explode) == { + "reportAny": 7 + } + + +def test_base_counts_cached_computes_once_then_hits(tmp_path): + calls = [] + + def fake(ref): + calls.append(ref) + return {"reportAny": 4} + + first = gate.base_counts_cached("abc123", cache_dir=tmp_path, compute=fake) + second = gate.base_counts_cached("abc123", cache_dir=tmp_path, compute=fake) + assert first == second == {"reportAny": 4} + assert calls == ["abc123"] + + +def test_an_empty_base_pass_is_never_cached(tmp_path): + calls = [] + + def crashed(ref): + calls.append(ref) + return {} + + assert gate.base_counts_cached("abc123", cache_dir=tmp_path, compute=crashed) == {} + assert gate.base_counts_cached("abc123", cache_dir=tmp_path, compute=crashed) == {} + assert calls == ["abc123", "abc123"] + assert list(tmp_path.iterdir()) == [] diff --git a/tests/test_litellm/test_utils.py b/tests/test_litellm/test_utils.py index 2432b377d54..c35fb2fcbe2 100644 --- a/tests/test_litellm/test_utils.py +++ b/tests/test_litellm/test_utils.py @@ -833,6 +833,7 @@ def test_aaamodel_prices_and_context_window_json_is_valid(): "supports_image_input": {"type": "boolean"}, "supports_nova_canvas_image_edit": {"type": "boolean"}, "supports_parallel_function_calling": {"type": "boolean"}, + "supports_parallel_tool_use_config": {"type": "boolean"}, "supports_pdf_input": {"type": "boolean"}, "supports_prompt_caching": {"type": "boolean"}, "supports_response_schema": {"type": "boolean"}, @@ -4576,3 +4577,95 @@ def test_aws_bedrock_project_id_excluded_from_bedrock_optional_params(): assert "aws_bedrock_project_id" not in result assert result["aws_region_name"] == "us-east-1" + + +class TestGetOptionalParamsTencent: + """Tests that tencent provider uses TencentChatConfig for parameter mapping.""" + + def test_tencent_supports_thinking_param(self): + """Verify get_optional_params for tencent accepts the 'thinking' param.""" + from unittest.mock import patch + + from litellm.utils import get_optional_params + + with patch( + "litellm.llms.tencent.chat.transformation.supports_reasoning", + return_value=True, + ): + result = get_optional_params( + model="tencent/deepseek-v4-pro", + custom_llm_provider="tencent", + thinking={"type": "enabled"}, + ) + assert result.get("thinking") == {"type": "enabled"} + + def test_tencent_supports_reasoning_effort(self): + """Verify get_optional_params for tencent converts reasoning_effort to thinking.""" + from unittest.mock import patch + + from litellm.utils import get_optional_params + + with patch( + "litellm.llms.tencent.chat.transformation.supports_reasoning", + return_value=True, + ): + result = get_optional_params( + model="tencent/deepseek-v4-pro", + custom_llm_provider="tencent", + reasoning_effort="medium", + ) + assert result.get("thinking") == {"type": "enabled"} + + def test_tencent_supported_params_includes_thinking_and_reasoning_effort(self): + """Verify get_supported_openai_params for tencent includes custom params.""" + from unittest.mock import patch + + from litellm.litellm_core_utils.get_supported_openai_params import ( + get_supported_openai_params, + ) + + with patch( + "litellm.llms.tencent.chat.transformation.supports_reasoning", + return_value=True, + ): + params = get_supported_openai_params( + model="tencent/deepseek-v4-pro", + custom_llm_provider="tencent", + ) + assert "thinking" in params + assert "reasoning_effort" in params + + def test_tencent_messages_config_routing(self): + """Verify ProviderConfigManager routes tencent to TencentAnthropicMessagesConfig.""" + import litellm + from litellm.llms.tencent.messages.transformation import ( + TencentAnthropicMessagesConfig, + ) + from litellm.utils import ProviderConfigManager + + config = ProviderConfigManager.get_provider_anthropic_messages_config( + model="deepseek-v4-pro", + provider=litellm.LlmProviders.TENCENT, + ) + assert isinstance(config, TencentAnthropicMessagesConfig) + assert config.custom_llm_provider == "tencent" + + +class TestValidateEnvironmentTencent: + """Tests that validate_environment resolves TENCENT_API_KEY for the tencent provider.""" + + def test_reports_key_present(self): + with patch.dict(os.environ, {"TENCENT_API_KEY": "sk-tencent"}): + result = litellm.validate_environment(model="tencent/deepseek-v4-pro") + + assert result["keys_in_environment"] is True + assert result["missing_keys"] == [] + + def test_reports_key_missing(self): + with patch.dict(os.environ, {}, clear=True): + result = litellm.validate_environment(model="tencent/deepseek-v4-pro") + + assert result["keys_in_environment"] is False + assert "TENCENT_API_KEY" in result["missing_keys"] + + diff --git a/ui/litellm-dashboard/build_ui.sh b/ui/litellm-dashboard/build_ui.sh index aa346c12edc..a3ab475dc58 100755 --- a/ui/litellm-dashboard/build_ui.sh +++ b/ui/litellm-dashboard/build_ui.sh @@ -31,9 +31,6 @@ if [ $? -ne 0 ]; then exit 1 fi -# print contents of ui_colors.json -echo "Contents of ui_colors.json:" -cat ui_colors.json # Run npm build npm run build diff --git a/ui/litellm-dashboard/components.json b/ui/litellm-dashboard/components.json new file mode 100644 index 00000000000..c4d45aa0989 --- /dev/null +++ b/ui/litellm-dashboard/components.json @@ -0,0 +1,21 @@ +{ + "$schema": "https://ui.shadcn.com/schema.json", + "style": "new-york", + "rsc": true, + "tsx": true, + "tailwind": { + "config": "", + "css": "src/app/globals.css", + "baseColor": "gray", + "cssVariables": true, + "prefix": "" + }, + "iconLibrary": "lucide", + "aliases": { + "components": "@/components", + "ui": "@/components/ui", + "lib": "@/lib", + "hooks": "@/hooks", + "utils": "@/lib/cva.config" + } +} diff --git a/ui/litellm-dashboard/eslint-metrics.json b/ui/litellm-dashboard/eslint-metrics.json index 92c5a991eb6..4475ce0e74b 100644 --- a/ui/litellm-dashboard/eslint-metrics.json +++ b/ui/litellm-dashboard/eslint-metrics.json @@ -1,5 +1,5 @@ { - "@typescript-eslint/no-explicit-any": 2013, + "@typescript-eslint/no-explicit-any": 1991, "complexity": 126, - "max-depth": 61 + "max-depth": 59 } diff --git a/ui/litellm-dashboard/eslint-suppressions.json b/ui/litellm-dashboard/eslint-suppressions.json index 7ea13deb934..1c8f92b720f 100644 --- a/ui/litellm-dashboard/eslint-suppressions.json +++ b/ui/litellm-dashboard/eslint-suppressions.json @@ -4,6 +4,150 @@ "count": 1 } }, + "src/app/(dashboard)/budgets/components/budget_modal.tsx": { + "no-restricted-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/budgets/components/budget_panel.test.tsx": { + "unused-imports/no-unused-imports": { + "count": 2 + } + }, + "src/app/(dashboard)/budgets/components/budget_panel.tsx": { + "no-restricted-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/budgets/components/edit_budget_modal.tsx": { + "no-restricted-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/caching/components/cache_dashboard.tsx": { + "no-restricted-imports": { + "count": 1 + }, + "react-hooks/purity": { + "count": 1 + }, + "react-hooks/set-state-in-effect": { + "count": 2 + } + }, + "src/app/(dashboard)/caching/components/cache_health.tsx": { + "no-restricted-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/caching/components/cache_settings/RedisTypeSelector.tsx": { + "no-restricted-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/caching/components/cache_settings/index.tsx": { + "no-restricted-imports": { + "count": 1 + }, + "react-hooks/set-state-in-effect": { + "count": 1 + } + }, + "src/app/(dashboard)/cost-tracking/components/add_margin_form.tsx": { + "no-restricted-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/cost-tracking/components/add_provider_form.tsx": { + "no-restricted-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/cost-tracking/components/cost_tracking_settings.tsx": { + "no-restricted-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/cost-tracking/components/how_it_works.tsx": { + "no-restricted-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/cost-tracking/components/pricing_calculator/multi_cost_results.test.tsx": { + "unused-imports/no-unused-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/cost-tracking/components/pricing_calculator/multi_cost_results.tsx": { + "no-restricted-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/cost-tracking/components/pricing_calculator/multi_export_dropdown.test.tsx": { + "unused-imports/no-unused-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/cost-tracking/components/pricing_calculator/multi_export_dropdown.tsx": { + "no-restricted-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/cost-tracking/components/pricing_calculator/use_multi_cost_estimate.ts": { + "no-restricted-syntax": { + "count": 1 + } + }, + "src/app/(dashboard)/cost-tracking/components/provider_discount_table.test.tsx": { + "unused-imports/no-unused-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/cost-tracking/components/provider_discount_table.tsx": { + "no-restricted-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/cost-tracking/components/provider_display_helpers.test.ts": { + "unused-imports/no-unused-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/cost-tracking/components/provider_margin_table.tsx": { + "no-restricted-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/cost-tracking/components/use_discount_config.ts": { + "no-restricted-syntax": { + "count": 2 + } + }, + "src/app/(dashboard)/cost-tracking/components/use_margin_config.ts": { + "no-restricted-syntax": { + "count": 2 + } + }, + "src/app/(dashboard)/guardrails-monitor/components/EvaluationSettingsModal.tsx": { + "react-hooks/set-state-in-effect": { + "count": 1 + } + }, + "src/app/(dashboard)/guardrails-monitor/components/GuardrailsMonitorView.tsx": { + "no-restricted-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/guardrails-monitor/components/ScoreChart.test.tsx": { + "react/display-name": { + "count": 1 + } + }, + "src/app/(dashboard)/guardrails-monitor/components/ScoreChart.tsx": { + "no-restricted-imports": { + "count": 1 + } + }, "src/app/(dashboard)/hooks/accessGroups/useAccessGroupDetails.ts": { "no-restricted-syntax": { "count": 1 @@ -164,6 +308,11 @@ "count": 2 } }, + "src/app/(dashboard)/memory/components/MemoryView.tsx": { + "react-hooks/set-state-in-effect": { + "count": 1 + } + }, "src/app/(dashboard)/models-and-endpoints/ModelsAndEndpointsView.tsx": { "no-restricted-imports": { "count": 1 @@ -203,11 +352,338 @@ "count": 1 } }, + "src/app/(dashboard)/playground/components/chat_ui/AdditionalModelSettings.tsx": { + "no-restricted-imports": { + "count": 1 + }, + "react-hooks/set-state-in-effect": { + "count": 2 + } + }, + "src/app/(dashboard)/playground/components/chat_ui/AgentBuilderView.tsx": { + "react-hooks/set-state-in-effect": { + "count": 5 + } + }, + "src/app/(dashboard)/playground/components/chat_ui/ChatImageUtils.test.tsx": { + "max-nested-callbacks": { + "count": 1 + } + }, + "src/app/(dashboard)/playground/components/chat_ui/ChatUI.tsx": { + "no-restricted-imports": { + "count": 1 + }, + "react-hooks/set-state-in-effect": { + "count": 4 + }, + "unused-imports/no-unused-imports": { + "count": 13 + } + }, + "src/app/(dashboard)/playground/components/chat_ui/CodeInterpreterOutput.tsx": { + "no-restricted-syntax": { + "count": 2 + } + }, + "src/app/(dashboard)/playground/components/chat_ui/CodeInterpreterTool.tsx": { + "no-restricted-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/playground/components/chat_ui/RealtimePlayground.tsx": { + "react-hooks/immutability": { + "count": 2 + }, + "react-hooks/preserve-manual-memoization": { + "count": 1 + } + }, + "src/app/(dashboard)/playground/components/compareUI/CompareUI.tsx": { + "react-hooks/set-state-in-effect": { + "count": 1 + } + }, + "src/app/(dashboard)/playground/components/compareUI/components/ModelSelector.tsx": { + "no-restricted-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/playground/components/complianceUI/ComplianceUI.tsx": { + "react-hooks/preserve-manual-memoization": { + "count": 3 + } + }, + "src/app/(dashboard)/playground/llm_calls/a2a_send_message.tsx": { + "max-params": { + "count": 2 + }, + "no-restricted-syntax": { + "count": 2 + } + }, + "src/app/(dashboard)/playground/llm_calls/anthropic_messages.tsx": { + "max-params": { + "count": 1 + } + }, + "src/app/(dashboard)/playground/llm_calls/audio_speech.tsx": { + "max-params": { + "count": 1 + } + }, + "src/app/(dashboard)/playground/llm_calls/audio_transcriptions.tsx": { + "max-params": { + "count": 1 + } + }, + "src/app/(dashboard)/playground/llm_calls/embeddings_api.tsx": { + "max-params": { + "count": 1 + }, + "no-restricted-syntax": { + "count": 1 + } + }, + "src/app/(dashboard)/playground/llm_calls/fetch_agents.tsx": { + "no-restricted-syntax": { + "count": 1 + } + }, + "src/app/(dashboard)/playground/llm_calls/image_edits.tsx": { + "max-params": { + "count": 1 + } + }, + "src/app/(dashboard)/playground/llm_calls/image_generation.tsx": { + "max-params": { + "count": 1 + } + }, + "src/app/(dashboard)/playground/llm_calls/interactions_api.tsx": { + "max-params": { + "count": 1 + }, + "no-restricted-syntax": { + "count": 1 + } + }, "src/app/(dashboard)/playground/page.tsx": { "no-restricted-imports": { "count": 1 } }, + "src/app/(dashboard)/projects/components/ProjectDetailsPage.tsx": { + "no-restricted-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/projects/components/ProjectKeysSection.tsx": { + "react-hooks/set-state-in-effect": { + "count": 1 + } + }, + "src/app/(dashboard)/projects/components/ProjectModals/ProjectBaseForm.tsx": { + "react-hooks/set-state-in-effect": { + "count": 2 + } + }, + "src/app/(dashboard)/projects/components/ProjectsPage.tsx": { + "react-hooks/set-state-in-effect": { + "count": 1 + } + }, + "src/app/(dashboard)/prompts/components/add_prompt_form.tsx": { + "no-restricted-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/prompts/components/index.tsx": { + "no-restricted-imports": { + "count": 1 + }, + "react-hooks/set-state-in-effect": { + "count": 1 + } + }, + "src/app/(dashboard)/prompts/components/prompt_editor_view/DeveloperMessageCard.tsx": { + "no-restricted-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/prompts/components/prompt_editor_view/ModelConfigCard.tsx": { + "no-restricted-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/prompts/components/prompt_editor_view/PromptCodeSnippets.tsx": { + "no-restricted-imports": { + "count": 1 + }, + "react-hooks/set-state-in-effect": { + "count": 1 + } + }, + "src/app/(dashboard)/prompts/components/prompt_editor_view/PromptEditorHeader.tsx": { + "no-restricted-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/prompts/components/prompt_editor_view/PromptMessagesCard.tsx": { + "no-restricted-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/prompts/components/prompt_editor_view/PublishModal.tsx": { + "no-restricted-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/prompts/components/prompt_editor_view/ToolsCard.tsx": { + "no-restricted-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/prompts/components/prompt_editor_view/VersionHistorySidePanel.test.tsx": { + "max-nested-callbacks": { + "count": 1 + } + }, + "src/app/(dashboard)/prompts/components/prompt_editor_view/VersionHistorySidePanel.tsx": { + "react-hooks/immutability": { + "count": 1 + } + }, + "src/app/(dashboard)/prompts/components/prompt_editor_view/conversation_panel/MessageInput.tsx": { + "no-restricted-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/prompts/components/prompt_editor_view/conversation_panel/index.tsx": { + "no-restricted-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/prompts/components/prompt_editor_view/conversation_panel/useConversation.ts": { + "no-restricted-syntax": { + "count": 1 + } + }, + "src/app/(dashboard)/prompts/components/prompt_info.tsx": { + "no-restricted-imports": { + "count": 1 + }, + "react-hooks/set-state-in-effect": { + "count": 2 + } + }, + "src/app/(dashboard)/prompts/components/prompt_table.tsx": { + "no-restricted-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/search-tools/_components/CreateSearchTools.tsx": { + "no-restricted-imports": { + "count": 1 + }, + "react-hooks/set-state-in-effect": { + "count": 1 + } + }, + "src/app/(dashboard)/search-tools/_components/SearchToolTester.tsx": { + "no-restricted-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/search-tools/_components/SearchToolView.tsx": { + "no-restricted-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/search-tools/_components/SearchTools.tsx": { + "no-restricted-imports": { + "count": 1 + }, + "react-hooks/static-components": { + "count": 1 + } + }, + "src/app/(dashboard)/transform-request/TransformRequestPanel.tsx": { + "no-restricted-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/ui-theme/UIThemeSettings.tsx": { + "no-restricted-imports": { + "count": 1 + }, + "no-restricted-syntax": { + "count": 3 + }, + "react-hooks/immutability": { + "count": 1 + } + }, + "src/app/(dashboard)/users/_components/DefaultUserSettings.tsx": { + "no-restricted-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/users/_components/edit_user.tsx": { + "no-restricted-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/users/_components/user_edit_view.test.tsx": { + "react/display-name": { + "count": 1 + } + }, + "src/app/(dashboard)/users/_components/user_edit_view.tsx": { + "no-restricted-imports": { + "count": 1 + }, + "react-hooks/set-state-in-effect": { + "count": 1 + } + }, + "src/app/(dashboard)/users/_components/view_users.tsx": { + "no-restricted-imports": { + "count": 1 + }, + "react-hooks/set-state-in-effect": { + "count": 1 + } + }, + "src/app/(dashboard)/users/_components/view_users/columns.tsx": { + "max-params": { + "count": 1 + }, + "no-restricted-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/users/_components/view_users/table.tsx": { + "no-restricted-imports": { + "count": 1 + } + }, + "src/app/(dashboard)/users/_components/view_users/user_info_view.tsx": { + "no-restricted-imports": { + "count": 1 + }, + "react-hooks/set-state-in-effect": { + "count": 1 + } + }, + "src/app/(dashboard)/workflows/WorkflowRuns.tsx": { + "no-restricted-syntax": { + "count": 3 + }, + "react-hooks/set-state-in-effect": { + "count": 1 + } + }, "src/app/login/LoginPage.tsx": { "react-hooks/set-state-in-effect": { "count": 2 @@ -293,81 +769,6 @@ "count": 1 } }, - "src/app/(dashboard)/cost-tracking/components/add_margin_form.tsx": { - "no-restricted-imports": { - "count": 1 - } - }, - "src/app/(dashboard)/cost-tracking/components/add_provider_form.tsx": { - "no-restricted-imports": { - "count": 1 - } - }, - "src/app/(dashboard)/cost-tracking/components/cost_tracking_settings.tsx": { - "no-restricted-imports": { - "count": 1 - } - }, - "src/app/(dashboard)/cost-tracking/components/how_it_works.tsx": { - "no-restricted-imports": { - "count": 1 - } - }, - "src/app/(dashboard)/cost-tracking/components/pricing_calculator/multi_cost_results.test.tsx": { - "unused-imports/no-unused-imports": { - "count": 1 - } - }, - "src/app/(dashboard)/cost-tracking/components/pricing_calculator/multi_cost_results.tsx": { - "no-restricted-imports": { - "count": 1 - } - }, - "src/app/(dashboard)/cost-tracking/components/pricing_calculator/multi_export_dropdown.test.tsx": { - "unused-imports/no-unused-imports": { - "count": 1 - } - }, - "src/app/(dashboard)/cost-tracking/components/pricing_calculator/multi_export_dropdown.tsx": { - "no-restricted-imports": { - "count": 1 - } - }, - "src/app/(dashboard)/cost-tracking/components/pricing_calculator/use_multi_cost_estimate.ts": { - "no-restricted-syntax": { - "count": 1 - } - }, - "src/app/(dashboard)/cost-tracking/components/provider_discount_table.test.tsx": { - "unused-imports/no-unused-imports": { - "count": 1 - } - }, - "src/app/(dashboard)/cost-tracking/components/provider_discount_table.tsx": { - "no-restricted-imports": { - "count": 1 - } - }, - "src/app/(dashboard)/cost-tracking/components/provider_display_helpers.test.ts": { - "unused-imports/no-unused-imports": { - "count": 1 - } - }, - "src/app/(dashboard)/cost-tracking/components/provider_margin_table.tsx": { - "no-restricted-imports": { - "count": 1 - } - }, - "src/app/(dashboard)/cost-tracking/components/use_discount_config.ts": { - "no-restricted-syntax": { - "count": 2 - } - }, - "src/app/(dashboard)/cost-tracking/components/use_margin_config.ts": { - "no-restricted-syntax": { - "count": 2 - } - }, "src/components/CreateUserButton.tsx": { "no-restricted-imports": { "count": 1 @@ -376,11 +777,6 @@ "count": 1 } }, - "src/app/(dashboard)/users/_components/DefaultUserSettings.tsx": { - "no-restricted-imports": { - "count": 1 - } - }, "src/components/DeletedKeysPage/DeletedKeysTable/DeletedKeysTable.tsx": { "no-restricted-imports": { "count": 1 @@ -419,36 +815,11 @@ "count": 1 } }, - "src/app/(dashboard)/guardrails-monitor/components/EvaluationSettingsModal.tsx": { - "react-hooks/set-state-in-effect": { - "count": 1 - } - }, - "src/app/(dashboard)/guardrails-monitor/components/GuardrailsMonitorView.tsx": { - "no-restricted-imports": { - "count": 1 - } - }, - "src/app/(dashboard)/guardrails-monitor/components/ScoreChart.test.tsx": { - "react/display-name": { - "count": 1 - } - }, - "src/app/(dashboard)/guardrails-monitor/components/ScoreChart.tsx": { - "no-restricted-imports": { - "count": 1 - } - }, "src/components/HelpLink.test.tsx": { "unused-imports/no-unused-imports": { "count": 1 } }, - "src/app/(dashboard)/memory/components/MemoryView.tsx": { - "react-hooks/set-state-in-effect": { - "count": 1 - } - }, "src/components/Navbar/BlogDropdown/BlogDropdown.test.tsx": { "max-nested-callbacks": { "count": 12 @@ -472,26 +843,6 @@ "count": 4 } }, - "src/app/(dashboard)/projects/components/ProjectDetailsPage.tsx": { - "no-restricted-imports": { - "count": 1 - } - }, - "src/app/(dashboard)/projects/components/ProjectKeysSection.tsx": { - "react-hooks/set-state-in-effect": { - "count": 1 - } - }, - "src/app/(dashboard)/projects/components/ProjectModals/ProjectBaseForm.tsx": { - "react-hooks/set-state-in-effect": { - "count": 2 - } - }, - "src/app/(dashboard)/projects/components/ProjectsPage.tsx": { - "react-hooks/set-state-in-effect": { - "count": 1 - } - }, "src/components/SCIM.tsx": { "no-restricted-imports": { "count": 1 @@ -505,32 +856,6 @@ "count": 1 } }, - "src/app/(dashboard)/search-tools/_components/CreateSearchTools.tsx": { - "no-restricted-imports": { - "count": 1 - }, - "react-hooks/set-state-in-effect": { - "count": 1 - } - }, - "src/app/(dashboard)/search-tools/_components/SearchToolTester.tsx": { - "no-restricted-imports": { - "count": 1 - } - }, - "src/app/(dashboard)/search-tools/_components/SearchToolView.tsx": { - "no-restricted-imports": { - "count": 1 - } - }, - "src/app/(dashboard)/search-tools/_components/SearchTools.tsx": { - "no-restricted-imports": { - "count": 1 - }, - "react-hooks/static-components": { - "count": 1 - } - }, "src/components/Settings/AdminSettings/MCPSemanticFilterSettings/MCPSemanticFilterSettings.tsx": { "react-hooks/set-state-in-effect": { "count": 1 @@ -750,7 +1075,7 @@ "count": 1 }, "react-hooks/set-state-in-effect": { - "count": 2 + "count": 1 } }, "src/components/agents/add_agent_form.tsx": { @@ -790,26 +1115,6 @@ "count": 1 } }, - "src/app/(dashboard)/budgets/components/budget_modal.tsx": { - "no-restricted-imports": { - "count": 1 - } - }, - "src/app/(dashboard)/budgets/components/budget_panel.test.tsx": { - "unused-imports/no-unused-imports": { - "count": 2 - } - }, - "src/app/(dashboard)/budgets/components/budget_panel.tsx": { - "no-restricted-imports": { - "count": 1 - } - }, - "src/app/(dashboard)/budgets/components/edit_budget_modal.tsx": { - "no-restricted-imports": { - "count": 1 - } - }, "src/components/bulk_create_users_button.tsx": { "no-restricted-imports": { "count": 1 @@ -818,40 +1123,6 @@ "count": 1 } }, - "src/app/(dashboard)/caching/components/cache_dashboard.tsx": { - "no-restricted-imports": { - "count": 1 - }, - "react-hooks/purity": { - "count": 1 - }, - "react-hooks/set-state-in-effect": { - "count": 2 - } - }, - "src/app/(dashboard)/caching/components/cache_health.tsx": { - "no-restricted-imports": { - "count": 1 - } - }, - "src/app/(dashboard)/caching/components/cache_settings/CacheFieldRenderer.tsx": { - "no-restricted-imports": { - "count": 1 - } - }, - "src/app/(dashboard)/caching/components/cache_settings/RedisTypeSelector.tsx": { - "no-restricted-imports": { - "count": 1 - } - }, - "src/app/(dashboard)/caching/components/cache_settings/index.tsx": { - "no-restricted-imports": { - "count": 1 - }, - "react-hooks/set-state-in-effect": { - "count": 1 - } - }, "src/components/claude_code_plugins.tsx": { "no-restricted-imports": { "count": 1 @@ -1001,11 +1272,6 @@ "count": 1 } }, - "src/app/(dashboard)/users/_components/edit_user.tsx": { - "no-restricted-imports": { - "count": 1 - } - }, "src/components/email_events/email_event_settings.tsx": { "no-restricted-imports": { "count": 1 @@ -1138,6 +1404,16 @@ "count": 1 } }, + "src/components/llm_calls/chat_completion.tsx": { + "max-params": { + "count": 1 + } + }, + "src/components/llm_calls/responses_api.tsx": { + "max-params": { + "count": 1 + } + }, "src/components/mcp_hub_table_columns.tsx": { "no-restricted-imports": { "count": 1 @@ -1464,132 +1740,6 @@ "count": 1 } }, - "src/app/(dashboard)/playground/components/chat_ui/AdditionalModelSettings.tsx": { - "no-restricted-imports": { - "count": 1 - }, - "react-hooks/set-state-in-effect": { - "count": 2 - } - }, - "src/app/(dashboard)/playground/components/chat_ui/AgentBuilderView.tsx": { - "react-hooks/set-state-in-effect": { - "count": 5 - } - }, - "src/app/(dashboard)/playground/components/chat_ui/ChatImageUtils.test.tsx": { - "max-nested-callbacks": { - "count": 1 - } - }, - "src/app/(dashboard)/playground/components/chat_ui/ChatUI.tsx": { - "no-restricted-imports": { - "count": 1 - }, - "react-hooks/set-state-in-effect": { - "count": 4 - }, - "unused-imports/no-unused-imports": { - "count": 13 - } - }, - "src/app/(dashboard)/playground/components/chat_ui/CodeInterpreterOutput.tsx": { - "no-restricted-syntax": { - "count": 2 - } - }, - "src/app/(dashboard)/playground/components/chat_ui/CodeInterpreterTool.tsx": { - "no-restricted-imports": { - "count": 1 - } - }, - "src/app/(dashboard)/playground/components/chat_ui/RealtimePlayground.tsx": { - "react-hooks/immutability": { - "count": 2 - }, - "react-hooks/preserve-manual-memoization": { - "count": 1 - } - }, - "src/app/(dashboard)/playground/components/compareUI/CompareUI.tsx": { - "react-hooks/set-state-in-effect": { - "count": 1 - } - }, - "src/app/(dashboard)/playground/components/compareUI/components/ModelSelector.tsx": { - "no-restricted-imports": { - "count": 1 - } - }, - "src/app/(dashboard)/playground/components/complianceUI/ComplianceUI.tsx": { - "react-hooks/preserve-manual-memoization": { - "count": 3 - } - }, - "src/app/(dashboard)/playground/llm_calls/a2a_send_message.tsx": { - "max-params": { - "count": 2 - }, - "no-restricted-syntax": { - "count": 2 - } - }, - "src/app/(dashboard)/playground/llm_calls/anthropic_messages.tsx": { - "max-params": { - "count": 1 - } - }, - "src/app/(dashboard)/playground/llm_calls/audio_speech.tsx": { - "max-params": { - "count": 1 - } - }, - "src/app/(dashboard)/playground/llm_calls/audio_transcriptions.tsx": { - "max-params": { - "count": 1 - } - }, - "src/components/llm_calls/chat_completion.tsx": { - "max-params": { - "count": 1 - } - }, - "src/app/(dashboard)/playground/llm_calls/embeddings_api.tsx": { - "max-params": { - "count": 1 - }, - "no-restricted-syntax": { - "count": 1 - } - }, - "src/app/(dashboard)/playground/llm_calls/fetch_agents.tsx": { - "no-restricted-syntax": { - "count": 1 - } - }, - "src/app/(dashboard)/playground/llm_calls/image_edits.tsx": { - "max-params": { - "count": 1 - } - }, - "src/app/(dashboard)/playground/llm_calls/image_generation.tsx": { - "max-params": { - "count": 1 - } - }, - "src/app/(dashboard)/playground/llm_calls/interactions_api.tsx": { - "max-params": { - "count": 1 - }, - "no-restricted-syntax": { - "count": 1 - } - }, - "src/components/llm_calls/responses_api.tsx": { - "max-params": { - "count": 1 - } - }, "src/components/policies/add_attachment_form.tsx": { "no-restricted-imports": { "count": 1 @@ -1705,87 +1855,6 @@ "count": 2 } }, - "src/app/(dashboard)/prompts/components/add_prompt_form.tsx": { - "no-restricted-imports": { - "count": 1 - } - }, - "src/app/(dashboard)/prompts/components/prompt_editor_view/DeveloperMessageCard.tsx": { - "no-restricted-imports": { - "count": 1 - } - }, - "src/app/(dashboard)/prompts/components/prompt_editor_view/ModelConfigCard.tsx": { - "no-restricted-imports": { - "count": 1 - } - }, - "src/app/(dashboard)/prompts/components/prompt_editor_view/PromptCodeSnippets.tsx": { - "no-restricted-imports": { - "count": 1 - }, - "react-hooks/set-state-in-effect": { - "count": 1 - } - }, - "src/app/(dashboard)/prompts/components/prompt_editor_view/PromptEditorHeader.tsx": { - "no-restricted-imports": { - "count": 1 - } - }, - "src/app/(dashboard)/prompts/components/prompt_editor_view/PromptMessagesCard.tsx": { - "no-restricted-imports": { - "count": 1 - } - }, - "src/app/(dashboard)/prompts/components/prompt_editor_view/PublishModal.tsx": { - "no-restricted-imports": { - "count": 1 - } - }, - "src/app/(dashboard)/prompts/components/prompt_editor_view/ToolsCard.tsx": { - "no-restricted-imports": { - "count": 1 - } - }, - "src/app/(dashboard)/prompts/components/prompt_editor_view/VersionHistorySidePanel.test.tsx": { - "max-nested-callbacks": { - "count": 1 - } - }, - "src/app/(dashboard)/prompts/components/prompt_editor_view/VersionHistorySidePanel.tsx": { - "react-hooks/immutability": { - "count": 1 - } - }, - "src/app/(dashboard)/prompts/components/prompt_editor_view/conversation_panel/MessageInput.tsx": { - "no-restricted-imports": { - "count": 1 - } - }, - "src/app/(dashboard)/prompts/components/prompt_editor_view/conversation_panel/index.tsx": { - "no-restricted-imports": { - "count": 1 - } - }, - "src/app/(dashboard)/prompts/components/prompt_editor_view/conversation_panel/useConversation.ts": { - "no-restricted-syntax": { - "count": 1 - } - }, - "src/app/(dashboard)/prompts/components/prompt_info.tsx": { - "no-restricted-imports": { - "count": 1 - }, - "react-hooks/set-state-in-effect": { - "count": 2 - } - }, - "src/app/(dashboard)/prompts/components/prompt_table.tsx": { - "no-restricted-imports": { - "count": 1 - } - }, "src/components/public_model_hub.tsx": { "no-restricted-imports": { "count": 1 @@ -1914,22 +1983,6 @@ "count": 1 } }, - "src/app/(dashboard)/transform-request/TransformRequestPanel.tsx": { - "no-restricted-imports": { - "count": 1 - } - }, - "src/app/(dashboard)/ui-theme/UIThemeSettings.tsx": { - "no-restricted-imports": { - "count": 1 - }, - "no-restricted-syntax": { - "count": 3 - }, - "react-hooks/immutability": { - "count": 1 - } - }, "src/components/usage.tsx": { "no-restricted-imports": { "count": 2 @@ -1957,19 +2010,6 @@ "count": 2 } }, - "src/app/(dashboard)/users/_components/user_edit_view.test.tsx": { - "react/display-name": { - "count": 1 - } - }, - "src/app/(dashboard)/users/_components/user_edit_view.tsx": { - "no-restricted-imports": { - "count": 1 - }, - "react-hooks/set-state-in-effect": { - "count": 1 - } - }, "src/components/vector_store_management/CreateVectorStore.tsx": { "no-restricted-imports": { "count": 1 @@ -2047,43 +2087,6 @@ "count": 2 } }, - "src/app/(dashboard)/users/_components/view_users.tsx": { - "no-restricted-imports": { - "count": 1 - }, - "react-hooks/set-state-in-effect": { - "count": 1 - } - }, - "src/app/(dashboard)/users/_components/view_users/columns.tsx": { - "max-params": { - "count": 1 - }, - "no-restricted-imports": { - "count": 1 - } - }, - "src/app/(dashboard)/users/_components/view_users/table.tsx": { - "no-restricted-imports": { - "count": 1 - } - }, - "src/app/(dashboard)/users/_components/view_users/user_info_view.tsx": { - "no-restricted-imports": { - "count": 1 - }, - "react-hooks/set-state-in-effect": { - "count": 1 - } - }, - "src/app/(dashboard)/workflows/WorkflowRuns.tsx": { - "no-restricted-syntax": { - "count": 3 - }, - "react-hooks/set-state-in-effect": { - "count": 1 - } - }, "src/contexts/AuthContext.tsx": { "react-hooks/set-state-in-effect": { "count": 1 @@ -2137,16 +2140,6 @@ "count": 1 } }, - "tailwind.config.js": { - "@typescript-eslint/no-require-imports": { - "count": 4 - } - }, - "tailwind.config.ts": { - "@typescript-eslint/no-require-imports": { - "count": 3 - } - }, "tests/CreateKeyPage.expiredToken.test.tsx": { "@typescript-eslint/no-require-imports": { "count": 3 @@ -2162,13 +2155,5 @@ "react/display-name": { "count": 1 } - }, - "src/app/(dashboard)/prompts/components/index.tsx": { - "no-restricted-imports": { - "count": 1 - }, - "react-hooks/set-state-in-effect": { - "count": 1 - } } -} +} \ No newline at end of file diff --git a/ui/litellm-dashboard/knip.json b/ui/litellm-dashboard/knip.json index 6f129398981..58fa202a39a 100644 --- a/ui/litellm-dashboard/knip.json +++ b/ui/litellm-dashboard/knip.json @@ -3,7 +3,13 @@ "entry": ["scripts/**/*.{ts,mjs}"], "project": ["src/**/*.{ts,tsx}", "tests/**/*.{ts,tsx}", "scripts/**/*.{ts,mjs}", "e2e_tests/**/*.ts"], "ignore": ["src/lib/http/schema.d.ts"], - "ignoreDependencies": ["openapi-typescript"], + "ignoreDependencies": [ + "openapi-typescript", + "@headlessui/tailwindcss", + "@tailwindcss/forms", + "tailwindcss", + "tw-animate-css" + ], "playwright": { "config": "e2e_tests/playwright.config.ts", "entry": ["e2e_tests/**/*.spec.ts", "e2e_tests/**/*.setup.ts", "e2e_tests/globalSetup.ts"] diff --git a/ui/litellm-dashboard/package-lock.json b/ui/litellm-dashboard/package-lock.json index 828edde278b..298c3f9321a 100644 --- a/ui/litellm-dashboard/package-lock.json +++ b/ui/litellm-dashboard/package-lock.json @@ -8,6 +8,7 @@ "name": "litellm-dashboard", "version": "0.1.0", "dependencies": { + "@ant-design/cssinjs": "1.24.0", "@anthropic-ai/sdk": "0.92.0", "@headlessui/tailwindcss": "0.2.2", "@heroicons/react": "1.0.6", @@ -26,6 +27,7 @@ "next": "16.2.6", "openai": "4.104.0", "papaparse": "5.5.3", + "radix-ui": "1.6.1", "react": "18.3.1", "react-copy-to-clipboard": "5.1.1", "react-dom": "18.3.1", @@ -39,6 +41,7 @@ "@eslint/js": "9.39.2", "@playwright/test": "1.58.1", "@tailwindcss/forms": "0.5.11", + "@tailwindcss/postcss": "4.3.2", "@testing-library/dom": "10.4.1", "@testing-library/jest-dom": "6.9.1", "@testing-library/react": "16.3.2", @@ -51,7 +54,6 @@ "@types/react-syntax-highlighter": "15.5.13", "@vitest/coverage-v8": "3.2.6", "@vitest/ui": "3.2.6", - "autoprefixer": "10.4.24", "eslint": "9.39.2", "eslint-config-next": "16.2.6", "eslint-config-prettier": "10.1.8", @@ -61,7 +63,8 @@ "openapi-typescript": "7.13.0", "postcss": "8.5.13", "prettier": "3.2.5", - "tailwindcss": "3.4.19", + "tailwindcss": "4.3.2", + "tw-animate-css": "1.4.0", "typescript": "5.9.3", "typescript-eslint": "8.60.1", "vitest": "3.2.6" @@ -89,6 +92,7 @@ "version": "5.2.0", "resolved": "https://registry.npmjs.org/@alloc/quick-lru/-/quick-lru-5.2.0.tgz", "integrity": "sha512-UrcABB+4bUrFABwbluTIBErXwvbsU/V7TZWfmbgJfbkwiBuziS9gxdODUyuiecfdGQ85jglMW6juS3+z5TsKLw==", + "dev": true, "license": "MIT", "engines": { "node": ">=10" @@ -2048,6 +2052,7 @@ "version": "0.3.13", "resolved": "https://registry.npmjs.org/@jridgewell/gen-mapping/-/gen-mapping-0.3.13.tgz", "integrity": "sha512-2kkt/7niJ6MgEPxF0bYdQ6etZaA+fQvDcLKckhy1yIQOzaoKjBBjSj63/aLVjYE3qhRt5dvM+uUyfCg6UKCBbA==", + "dev": true, "license": "MIT", "dependencies": { "@jridgewell/sourcemap-codec": "^1.5.0", @@ -2069,6 +2074,7 @@ "version": "3.1.2", "resolved": "https://registry.npmjs.org/@jridgewell/resolve-uri/-/resolve-uri-3.1.2.tgz", "integrity": "sha512-bRISgCIjP20/tbWSPWMEi54QVPRZExkuD9lJL+UIxUKtwVJA8wW1Trb1jMs1RFXo1CBTNZ/5hpC9QvmKWdopKw==", + "dev": true, "license": "MIT", "engines": { "node": ">=6.0.0" @@ -2078,12 +2084,14 @@ "version": "1.5.5", "resolved": "https://registry.npmjs.org/@jridgewell/sourcemap-codec/-/sourcemap-codec-1.5.5.tgz", "integrity": "sha512-cYQ9310grqxueWbl+WuIUIaiUaDcj7WOq5fVhEljNVgRfOUhY9fy2zTvfoqWsnebh8Sl70VScFbICvJnLKB0Og==", + "dev": true, "license": "MIT" }, "node_modules/@jridgewell/trace-mapping": { "version": "0.3.31", "resolved": "https://registry.npmjs.org/@jridgewell/trace-mapping/-/trace-mapping-0.3.31.tgz", "integrity": "sha512-zzNR+SdQSDJzc8joaeP8QQoCQr8NuYx2dIIytl1QeBEZHJ9uW6hebsrYgbz8hJwUQao3TWCMtmfV8Nu1twOLAw==", + "dev": true, "license": "MIT", "dependencies": { "@jridgewell/resolve-uri": "^3.1.0", @@ -2257,6 +2265,7 @@ "version": "2.1.5", "resolved": "https://registry.npmjs.org/@nodelib/fs.scandir/-/fs.scandir-2.1.5.tgz", "integrity": "sha512-vq24Bq3ym5HEQm2NKCr3yXDwjc7vTsEThRDnkp2DK9p1uqLR+DHurm/NOTo0KG7HYHU7eppKZj3MyqYuMBf62g==", + "dev": true, "license": "MIT", "dependencies": { "@nodelib/fs.stat": "2.0.5", @@ -2270,6 +2279,7 @@ "version": "2.0.5", "resolved": "https://registry.npmjs.org/@nodelib/fs.stat/-/fs.stat-2.0.5.tgz", "integrity": "sha512-RkhPPp2zrqDAQA/2jNhnztcPAlv64XdhIp7a7454A5ovI7Bukxgt7MX7udwAu3zg1DcpPU0rz3VV1SeaqvY4+A==", + "dev": true, "license": "MIT", "engines": { "node": ">= 8" @@ -2279,6 +2289,7 @@ "version": "1.2.8", "resolved": "https://registry.npmjs.org/@nodelib/fs.walk/-/fs.walk-1.2.8.tgz", "integrity": "sha512-oGB+UxlgWcgQkgwo8GcEGwemoTFt3FIO9ababBmaGwXIoBKZ+GTy0pP185beGg7Llih/NSHSV2XAs1lnznocSg==", + "dev": true, "license": "MIT", "dependencies": { "@nodelib/fs.scandir": "2.1.5", @@ -2604,6 +2615,1512 @@ "dev": true, "license": "MIT" }, + "node_modules/@radix-ui/number": { + "version": "1.1.2", + "resolved": "https://registry.npmjs.org/@radix-ui/number/-/number-1.1.2.tgz", + "integrity": "sha512-ceTwaxc4I5IOi97DgCotl3pqiyRGvffcc0oOsE2dQYaJOFIDsDt4VWG6xEbg1QePv9QWausCEIppud/tJ1wNig==", + "license": "MIT" + }, + "node_modules/@radix-ui/primitive": { + "version": "1.1.4", + "resolved": "https://registry.npmjs.org/@radix-ui/primitive/-/primitive-1.1.4.tgz", + "integrity": "sha512-7AdCK9PQyiljKoBDbN8OuctCbd/esdwZPQ8RtOE3SsyQtUpiPb+ND75q0jEhC1m1ecBI0MFNeLJvwIh9iKHRcQ==", + "license": "MIT" + }, + "node_modules/@radix-ui/react-accessible-icon": { + "version": "1.1.11", + "resolved": "https://registry.npmjs.org/@radix-ui/react-accessible-icon/-/react-accessible-icon-1.1.11.tgz", + "integrity": "sha512-HQDOFTKwSnmUij6l54wYJJtxTAnxI71+YJLOrjm2ladFB8HAV5Jt7hwaZPhWTGBkYoW4+ZAOfNZrLDh/qvxSYA==", + "license": "MIT", + "dependencies": { + "@radix-ui/react-visually-hidden": "1.2.7" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-accordion": { + "version": "1.2.15", + "resolved": "https://registry.npmjs.org/@radix-ui/react-accordion/-/react-accordion-1.2.15.tgz", + "integrity": "sha512-24Zz/0SYx8F2bSVThBnQrdJs2VbKelyuJordcFRRdA0fRAhrq/wSegGCqaQz34VQoiWqSMGYCYXEhynLSlyQlg==", + "license": "MIT", + "dependencies": { + "@radix-ui/primitive": "1.1.4", + "@radix-ui/react-collapsible": "1.1.15", + "@radix-ui/react-collection": "1.1.11", + "@radix-ui/react-compose-refs": "1.1.3", + "@radix-ui/react-context": "1.1.4", + "@radix-ui/react-direction": "1.1.2", + "@radix-ui/react-id": "1.1.2", + "@radix-ui/react-primitive": "2.1.7", + "@radix-ui/react-use-controllable-state": "1.2.3" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-alert-dialog": { + "version": "1.1.18", + "resolved": "https://registry.npmjs.org/@radix-ui/react-alert-dialog/-/react-alert-dialog-1.1.18.tgz", + "integrity": "sha512-6c2cXpNlAgHDhKguK24XcWHHayMpK+lk7/WwBXBco+ZJ4Dv7xP++GBM280KgTD/HCRu3jSdfe8WQiZssonYaIA==", + "license": "MIT", + "dependencies": { + "@radix-ui/primitive": "1.1.4", + "@radix-ui/react-compose-refs": "1.1.3", + "@radix-ui/react-context": "1.1.4", + "@radix-ui/react-dialog": "1.1.18", + "@radix-ui/react-primitive": "2.1.7" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-arrow": { + "version": "1.1.11", + "resolved": "https://registry.npmjs.org/@radix-ui/react-arrow/-/react-arrow-1.1.11.tgz", + "integrity": "sha512-Kdil9BB1rIFC/khmf4hC35bn8701AJcizTU7G7cUbEbk5XqqbjDuHW60uUfKqO5WojjZcbAW51Q7P0hRmMLw8A==", + "license": "MIT", + "dependencies": { + "@radix-ui/react-primitive": "2.1.7" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-aspect-ratio": { + "version": "1.1.11", + "resolved": "https://registry.npmjs.org/@radix-ui/react-aspect-ratio/-/react-aspect-ratio-1.1.11.tgz", + "integrity": "sha512-IUAhIVpBUvP5NNICjlaB1OFmtRLGqQqTF3ZOSGPoq3XeLXRFtHiWTRxSVEULgOd9GQR2c7tsYqDnhUennapZnw==", + "license": "MIT", + "dependencies": { + "@radix-ui/react-primitive": "2.1.7" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-avatar": { + "version": "1.2.1", + "resolved": "https://registry.npmjs.org/@radix-ui/react-avatar/-/react-avatar-1.2.1.tgz", + "integrity": "sha512-+8PWoLLZv3AVb5m0pvoiOca/bQGzc9vPVb+982HB2x3Un0DpYEPM3zLMl4oqRpBsocJuNqLkiv/HXTnTrlwr4g==", + "license": "MIT", + "dependencies": { + "@radix-ui/react-context": "1.1.4", + "@radix-ui/react-primitive": "2.1.7", + "@radix-ui/react-use-callback-ref": "1.1.2", + "@radix-ui/react-use-is-hydrated": "0.1.1", + "@radix-ui/react-use-layout-effect": "1.1.2" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-checkbox": { + "version": "1.3.6", + "resolved": "https://registry.npmjs.org/@radix-ui/react-checkbox/-/react-checkbox-1.3.6.tgz", + "integrity": "sha512-eUEUoGMDpfkgHWSE97ZZaUJtzR1M7EKnNIpD1Q16+8JR9NWghcaqMulx9PuCQ720w0UclfYn6FEbCdd5Hx087g==", + "license": "MIT", + "dependencies": { + "@radix-ui/primitive": "1.1.4", + "@radix-ui/react-compose-refs": "1.1.3", + "@radix-ui/react-context": "1.1.4", + "@radix-ui/react-presence": "1.1.6", + "@radix-ui/react-primitive": "2.1.7", + "@radix-ui/react-use-controllable-state": "1.2.3", + "@radix-ui/react-use-previous": "1.1.2", + "@radix-ui/react-use-size": "1.1.2" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-collapsible": { + "version": "1.1.15", + "resolved": "https://registry.npmjs.org/@radix-ui/react-collapsible/-/react-collapsible-1.1.15.tgz", + "integrity": "sha512-8A1zibu5skAQ+UVbaeNH5hVMibiFCRJzgMuM14LTWGttnTZKQL9jwYnhAbHRuxrtCqPXa4JvvnVUq1pTNgyZYw==", + "license": "MIT", + "dependencies": { + "@radix-ui/primitive": "1.1.4", + "@radix-ui/react-compose-refs": "1.1.3", + "@radix-ui/react-context": "1.1.4", + "@radix-ui/react-id": "1.1.2", + "@radix-ui/react-presence": "1.1.6", + "@radix-ui/react-primitive": "2.1.7", + "@radix-ui/react-use-controllable-state": "1.2.3", + "@radix-ui/react-use-layout-effect": "1.1.2" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-collection": { + "version": "1.1.11", + "resolved": "https://registry.npmjs.org/@radix-ui/react-collection/-/react-collection-1.1.11.tgz", + "integrity": "sha512-djW9+zeg137KQdlPtmE8xnaD+K2rcXXMWFrSg0hsmYZ6HRbdTA7tDHFgpaW9+huWVEu0RCabL+985T4TA0BE7g==", + "license": "MIT", + "dependencies": { + "@radix-ui/react-compose-refs": "1.1.3", + "@radix-ui/react-context": "1.1.4", + "@radix-ui/react-primitive": "2.1.7", + "@radix-ui/react-slot": "1.3.0" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-compose-refs": { + "version": "1.1.3", + "resolved": "https://registry.npmjs.org/@radix-ui/react-compose-refs/-/react-compose-refs-1.1.3.tgz", + "integrity": "sha512-rYOP8OMnuuPMQF1uhPVlGNcCDlkokKqGFE3JcxFViIkAXP7EvFWUliJAstrapypaBLJNHbZL6jGhbVDGTwmVhA==", + "license": "MIT", + "peerDependencies": { + "@types/react": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-context": { + "version": "1.1.4", + "resolved": "https://registry.npmjs.org/@radix-ui/react-context/-/react-context-1.1.4.tgz", + "integrity": "sha512-QwH4PO5urrbO+FaGd5Aglg+YJgWTyyuZ3g/6mKvsqraLkglDdckw9JafgL5McL5VEJ6EPNduPaT3ZE9BttDAqg==", + "license": "MIT", + "peerDependencies": { + "@types/react": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-context-menu": { + "version": "2.3.2", + "resolved": "https://registry.npmjs.org/@radix-ui/react-context-menu/-/react-context-menu-2.3.2.tgz", + "integrity": "sha512-qzsA/ZPhF6yMxBOTIk1nlCkoy2mswSbwYL+ErBa2iP0s4WWrlxmczArYqMcpVfEjmM7KJj/ADPXky0yZfbSxtQ==", + "license": "MIT", + "dependencies": { + "@radix-ui/primitive": "1.1.4", + "@radix-ui/react-context": "1.1.4", + "@radix-ui/react-menu": "2.1.19", + "@radix-ui/react-primitive": "2.1.7", + "@radix-ui/react-use-controllable-state": "1.2.3" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-dialog": { + "version": "1.1.18", + "resolved": "https://registry.npmjs.org/@radix-ui/react-dialog/-/react-dialog-1.1.18.tgz", + "integrity": "sha512-apa28mldjMgORmE6g/w3sCcA0Y9UAVeeDVoozN4i7kOw12mLl9RBchfzK3Nn6qxOWjrZhK1Lfy7f07kyzxtnBw==", + "license": "MIT", + "dependencies": { + "@radix-ui/primitive": "1.1.4", + "@radix-ui/react-compose-refs": "1.1.3", + "@radix-ui/react-context": "1.1.4", + "@radix-ui/react-dismissable-layer": "1.1.14", + "@radix-ui/react-focus-guards": "1.1.4", + "@radix-ui/react-focus-scope": "1.1.11", + "@radix-ui/react-id": "1.1.2", + "@radix-ui/react-portal": "1.1.13", + "@radix-ui/react-presence": "1.1.6", + "@radix-ui/react-primitive": "2.1.7", + "@radix-ui/react-slot": "1.3.0", + "@radix-ui/react-use-controllable-state": "1.2.3", + "aria-hidden": "^1.2.4", + "react-remove-scroll": "^2.7.2" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-direction": { + "version": "1.1.2", + "resolved": "https://registry.npmjs.org/@radix-ui/react-direction/-/react-direction-1.1.2.tgz", + "integrity": "sha512-C3vFhbyi4SW3PmbAi6Awpu4OzJtd0MxGurvSsYtr7p7nM8RNB3VAF3CUmnp2j50knpkrRcB7+ycVXzgLgF6yNA==", + "license": "MIT", + "peerDependencies": { + "@types/react": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-dismissable-layer": { + "version": "1.1.14", + "resolved": "https://registry.npmjs.org/@radix-ui/react-dismissable-layer/-/react-dismissable-layer-1.1.14.tgz", + "integrity": "sha512-4lUhWTWAjbDIqFrAPWJ3WqBOpO5YchVZ88X3nh6H9Lu5AFi5nCUeTPj3D8FSDmabmFeRe9ME0BDA4MwKTha5GQ==", + "license": "MIT", + "dependencies": { + "@radix-ui/primitive": "1.1.4", + "@radix-ui/react-compose-refs": "1.1.3", + "@radix-ui/react-primitive": "2.1.7", + "@radix-ui/react-use-callback-ref": "1.1.2", + "@radix-ui/react-use-effect-event": "0.0.3" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-dropdown-menu": { + "version": "2.1.19", + "resolved": "https://registry.npmjs.org/@radix-ui/react-dropdown-menu/-/react-dropdown-menu-2.1.19.tgz", + "integrity": "sha512-HZccBkbK0LOi8nYKIp5jll/zIRW0cCOmG6WWyqsSpmXCU+ZlcBbTqIwlBvPCu886C5RVu6c/kHV7xSP8IgYNHw==", + "license": "MIT", + "dependencies": { + "@radix-ui/primitive": "1.1.4", + "@radix-ui/react-compose-refs": "1.1.3", + "@radix-ui/react-context": "1.1.4", + "@radix-ui/react-id": "1.1.2", + "@radix-ui/react-menu": "2.1.19", + "@radix-ui/react-primitive": "2.1.7", + "@radix-ui/react-use-controllable-state": "1.2.3" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-focus-guards": { + "version": "1.1.4", + "resolved": "https://registry.npmjs.org/@radix-ui/react-focus-guards/-/react-focus-guards-1.1.4.tgz", + "integrity": "sha512-cot/aB/mOm0IYVYTTmQcEEK1M48lZWi8FlYe5nDPQQ8NYZUlXEFgncJ9p2Kzer3RKSrY7cTTpEMLZKNo9QoP5Q==", + "license": "MIT", + "peerDependencies": { + "@types/react": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-focus-scope": { + "version": "1.1.11", + "resolved": "https://registry.npmjs.org/@radix-ui/react-focus-scope/-/react-focus-scope-1.1.11.tgz", + "integrity": "sha512-Mn88Vg2whaRocGJNOH+DKFqYm6ySFPQaiwHNxZPyjn99B52KAEJWWY9NP83+nWdk2HM3rdov+STu9AG471Rt9w==", + "license": "MIT", + "dependencies": { + "@radix-ui/react-compose-refs": "1.1.3", + "@radix-ui/react-primitive": "2.1.7", + "@radix-ui/react-use-callback-ref": "1.1.2" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-form": { + "version": "0.1.11", + "resolved": "https://registry.npmjs.org/@radix-ui/react-form/-/react-form-0.1.11.tgz", + "integrity": "sha512-0mTMJHv1gQAuEQoq5VDpTD3MRgmfUFdXAVFhpqR7wBeUr+tyRsof0wv/4XdPHLwQrefhoH2FiGHCggrCJhalIw==", + "license": "MIT", + "dependencies": { + "@radix-ui/primitive": "1.1.4", + "@radix-ui/react-compose-refs": "1.1.3", + "@radix-ui/react-context": "1.1.4", + "@radix-ui/react-id": "1.1.2", + "@radix-ui/react-label": "2.1.11", + "@radix-ui/react-primitive": "2.1.7" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-hover-card": { + "version": "1.1.18", + "resolved": "https://registry.npmjs.org/@radix-ui/react-hover-card/-/react-hover-card-1.1.18.tgz", + "integrity": "sha512-rt+Fx4HoCeEwFL2IdoV2QaPltqDLlzxN77i9nwB3Y70scFlfAHh1QCdE2TXKuFJtA1TNygb0oivnFBZifgtZOw==", + "license": "MIT", + "dependencies": { + "@radix-ui/primitive": "1.1.4", + "@radix-ui/react-compose-refs": "1.1.3", + "@radix-ui/react-context": "1.1.4", + "@radix-ui/react-dismissable-layer": "1.1.14", + "@radix-ui/react-popper": "1.3.2", + "@radix-ui/react-portal": "1.1.13", + "@radix-ui/react-presence": "1.1.6", + "@radix-ui/react-primitive": "2.1.7", + "@radix-ui/react-use-controllable-state": "1.2.3" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-id": { + "version": "1.1.2", + "resolved": "https://registry.npmjs.org/@radix-ui/react-id/-/react-id-1.1.2.tgz", + "integrity": "sha512-orBC88futVpqCmhX1p4cvquNHsELQ+w+vBJnuj3ftETI5bJb0bZn3Tqu3SWN2IOcPycTnMGnhwoermvISt72sA==", + "license": "MIT", + "dependencies": { + "@radix-ui/react-use-layout-effect": "1.1.2" + }, + "peerDependencies": { + "@types/react": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-label": { + "version": "2.1.11", + "resolved": "https://registry.npmjs.org/@radix-ui/react-label/-/react-label-2.1.11.tgz", + "integrity": "sha512-3PKvDDxOn62k0oV1n4QtNtD2vpu+zYjXR7ojLBPaO6SPvhy53yg0vAmgNeBQeJW5rV3dffoRG+HYfLBZuzw0CQ==", + "license": "MIT", + "dependencies": { + "@radix-ui/react-primitive": "2.1.7" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-menu": { + "version": "2.1.19", + "resolved": "https://registry.npmjs.org/@radix-ui/react-menu/-/react-menu-2.1.19.tgz", + "integrity": "sha512-Mht9BVd1AIsNFVQr4KG3bIK7XQn5IXF0TL/2ObsrzOdc1loaly/+kBDL5roSCYn8j8XZkvpOD0WYLz2FQtH1Eg==", + "license": "MIT", + "dependencies": { + "@radix-ui/primitive": "1.1.4", + "@radix-ui/react-collection": "1.1.11", + "@radix-ui/react-compose-refs": "1.1.3", + "@radix-ui/react-context": "1.1.4", + "@radix-ui/react-direction": "1.1.2", + "@radix-ui/react-dismissable-layer": "1.1.14", + "@radix-ui/react-focus-guards": "1.1.4", + "@radix-ui/react-focus-scope": "1.1.11", + "@radix-ui/react-id": "1.1.2", + "@radix-ui/react-popper": "1.3.2", + "@radix-ui/react-portal": "1.1.13", + "@radix-ui/react-presence": "1.1.6", + "@radix-ui/react-primitive": "2.1.7", + "@radix-ui/react-roving-focus": "1.1.14", + "@radix-ui/react-slot": "1.3.0", + "@radix-ui/react-use-callback-ref": "1.1.2", + "aria-hidden": "^1.2.4", + "react-remove-scroll": "^2.7.2" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-menubar": { + "version": "1.1.19", + "resolved": "https://registry.npmjs.org/@radix-ui/react-menubar/-/react-menubar-1.1.19.tgz", + "integrity": "sha512-Glt6mebxcgQvLeVkH3HiqV5bgQubE+31ELxLs7q0GlYI5k0XYkOkeuPrhXoylxK8eufvIt9CJjzY1TfFMXK3qw==", + "license": "MIT", + "dependencies": { + "@radix-ui/primitive": "1.1.4", + "@radix-ui/react-collection": "1.1.11", + "@radix-ui/react-compose-refs": "1.1.3", + "@radix-ui/react-context": "1.1.4", + "@radix-ui/react-direction": "1.1.2", + "@radix-ui/react-id": "1.1.2", + "@radix-ui/react-menu": "2.1.19", + "@radix-ui/react-primitive": "2.1.7", + "@radix-ui/react-roving-focus": "1.1.14", + "@radix-ui/react-use-controllable-state": "1.2.3" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-navigation-menu": { + "version": "1.2.17", + "resolved": "https://registry.npmjs.org/@radix-ui/react-navigation-menu/-/react-navigation-menu-1.2.17.tgz", + "integrity": "sha512-fYeYQvbeNn5AQk2RBbpO7koLm2YbS00UYxC/IL2sgLlninEH5UNIv+X3E0KJ1Vy4WIo+dhN9w8GNqSHhbHWCIg==", + "license": "MIT", + "dependencies": { + "@radix-ui/primitive": "1.1.4", + "@radix-ui/react-collection": "1.1.11", + "@radix-ui/react-compose-refs": "1.1.3", + "@radix-ui/react-context": "1.1.4", + "@radix-ui/react-direction": "1.1.2", + "@radix-ui/react-dismissable-layer": "1.1.14", + "@radix-ui/react-id": "1.1.2", + "@radix-ui/react-presence": "1.1.6", + "@radix-ui/react-primitive": "2.1.7", + "@radix-ui/react-use-callback-ref": "1.1.2", + "@radix-ui/react-use-controllable-state": "1.2.3", + "@radix-ui/react-use-layout-effect": "1.1.2", + "@radix-ui/react-use-previous": "1.1.2", + "@radix-ui/react-visually-hidden": "1.2.7" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-one-time-password-field": { + "version": "0.1.11", + "resolved": "https://registry.npmjs.org/@radix-ui/react-one-time-password-field/-/react-one-time-password-field-0.1.11.tgz", + "integrity": "sha512-Rsgab65u73E5kPVh8OS6PgPwJgPyf08GFfJDGAbMdF4DL7CgDhFOaDnXuk/DiMEVF6kgQwl0oJmFklvipmiOLg==", + "license": "MIT", + "dependencies": { + "@radix-ui/number": "1.1.2", + "@radix-ui/primitive": "1.1.4", + "@radix-ui/react-collection": "1.1.11", + "@radix-ui/react-compose-refs": "1.1.3", + "@radix-ui/react-context": "1.1.4", + "@radix-ui/react-direction": "1.1.2", + "@radix-ui/react-primitive": "2.1.7", + "@radix-ui/react-roving-focus": "1.1.14", + "@radix-ui/react-use-controllable-state": "1.2.3", + "@radix-ui/react-use-effect-event": "0.0.3", + "@radix-ui/react-use-is-hydrated": "0.1.1", + "@radix-ui/react-use-layout-effect": "1.1.2" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-password-toggle-field": { + "version": "0.1.6", + "resolved": "https://registry.npmjs.org/@radix-ui/react-password-toggle-field/-/react-password-toggle-field-0.1.6.tgz", + "integrity": "sha512-pQ3xGp/uemomASPH97Eb3shfXX8QlG11bBJyEvRBV+vwtO4HvQlS06Yj9f31Ao7XepvF98SFrRgVDQ7jv+2xjQ==", + "license": "MIT", + "dependencies": { + "@radix-ui/primitive": "1.1.4", + "@radix-ui/react-compose-refs": "1.1.3", + "@radix-ui/react-context": "1.1.4", + "@radix-ui/react-id": "1.1.2", + "@radix-ui/react-primitive": "2.1.7", + "@radix-ui/react-use-controllable-state": "1.2.3", + "@radix-ui/react-use-effect-event": "0.0.3", + "@radix-ui/react-use-is-hydrated": "0.1.1" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-popover": { + "version": "1.1.18", + "resolved": "https://registry.npmjs.org/@radix-ui/react-popover/-/react-popover-1.1.18.tgz", + "integrity": "sha512-qdXDes+eHlnMUGlBAAAe5EG7oOQvqsXuq4mq585diMudg80iB+jHbsSeG3+Q4eWNsogNyhqU2p/3i+Y0iEepqg==", + "license": "MIT", + "dependencies": { + "@radix-ui/primitive": "1.1.4", + "@radix-ui/react-compose-refs": "1.1.3", + "@radix-ui/react-context": "1.1.4", + "@radix-ui/react-dismissable-layer": "1.1.14", + "@radix-ui/react-focus-guards": "1.1.4", + "@radix-ui/react-focus-scope": "1.1.11", + "@radix-ui/react-id": "1.1.2", + "@radix-ui/react-popper": "1.3.2", + "@radix-ui/react-portal": "1.1.13", + "@radix-ui/react-presence": "1.1.6", + "@radix-ui/react-primitive": "2.1.7", + "@radix-ui/react-slot": "1.3.0", + "@radix-ui/react-use-controllable-state": "1.2.3", + "aria-hidden": "^1.2.4", + "react-remove-scroll": "^2.7.2" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-popper": { + "version": "1.3.2", + "resolved": "https://registry.npmjs.org/@radix-ui/react-popper/-/react-popper-1.3.2.tgz", + "integrity": "sha512-3QXNeMkdshed1MR3LNoiCirBywRFPkD8ETJa/HlPuLwSajaQixf2ro+isoDNJlGABg9ug41XuZpINZJIle4XWg==", + "license": "MIT", + "dependencies": { + "@floating-ui/react-dom": "^2.0.0", + "@radix-ui/react-arrow": "1.1.11", + "@radix-ui/react-compose-refs": "1.1.3", + "@radix-ui/react-context": "1.1.4", + "@radix-ui/react-primitive": "2.1.7", + "@radix-ui/react-use-callback-ref": "1.1.2", + "@radix-ui/react-use-layout-effect": "1.1.2", + "@radix-ui/react-use-rect": "1.1.2", + "@radix-ui/react-use-size": "1.1.2", + "@radix-ui/rect": "1.1.2" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-popper/node_modules/@floating-ui/react-dom": { + "version": "2.1.8", + "resolved": "https://registry.npmjs.org/@floating-ui/react-dom/-/react-dom-2.1.8.tgz", + "integrity": "sha512-cC52bHwM/n/CxS87FH0yWdngEZrjdtLW/qVruo68qg+prK7ZQ4YGdut2GyDVpoGeAYe/h899rVeOVm6Oi40k2A==", + "license": "MIT", + "dependencies": { + "@floating-ui/dom": "^1.7.6" + }, + "peerDependencies": { + "react": ">=16.8.0", + "react-dom": ">=16.8.0" + } + }, + "node_modules/@radix-ui/react-portal": { + "version": "1.1.13", + "resolved": "https://registry.npmjs.org/@radix-ui/react-portal/-/react-portal-1.1.13.tgz", + "integrity": "sha512-z3oXfmaHLJTF1wktbjgD6cn9jiEbq3WSondB10LIuIt2m2Ym4iJlrW04/euMwENDdWDdE7z+OuY7Qyp1YpRSwA==", + "license": "MIT", + "dependencies": { + "@radix-ui/react-primitive": "2.1.7", + "@radix-ui/react-use-layout-effect": "1.1.2" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-presence": { + "version": "1.1.6", + "resolved": "https://registry.npmjs.org/@radix-ui/react-presence/-/react-presence-1.1.6.tgz", + "integrity": "sha512-zdTk4PlUO0E18HnZ3wYbW0KkJJxWCdiNYp6g6X1PtONFhxVkg01vliTJAmwIszU6mHiyBOoW9P0rAugl5/hULQ==", + "license": "MIT", + "dependencies": { + "@radix-ui/react-use-layout-effect": "1.1.2" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-primitive": { + "version": "2.1.7", + "resolved": "https://registry.npmjs.org/@radix-ui/react-primitive/-/react-primitive-2.1.7.tgz", + "integrity": "sha512-bC3NiwsprbxKjuon9l7X6BUTw7FPVzEYaL92MPEY5SCd/9hUTPXVFtVwRix7778wtRsVao+zE062gL79FZleeQ==", + "license": "MIT", + "dependencies": { + "@radix-ui/react-slot": "1.3.0" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-progress": { + "version": "1.1.11", + "resolved": "https://registry.npmjs.org/@radix-ui/react-progress/-/react-progress-1.1.11.tgz", + "integrity": "sha512-KqiGJcFaZDc+BvveAgU3ZhACg2MvSUDrCBx4lRR/ZVRNal0bvt8lBpvnSkep9heeOuF8Qfw3fszLDX4OpQ2NVw==", + "license": "MIT", + "dependencies": { + "@radix-ui/react-context": "1.1.4", + "@radix-ui/react-primitive": "2.1.7" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-radio-group": { + "version": "1.4.2", + "resolved": "https://registry.npmjs.org/@radix-ui/react-radio-group/-/react-radio-group-1.4.2.tgz", + "integrity": "sha512-W8Uo9riHnlzLLWy+r2mVHUyuEWqD/+be4PZzbEvaGoFSBDHkm+GYWjtcE6u3AmPKNyfanWpnVfpZ2GqPCdzzsw==", + "license": "MIT", + "dependencies": { + "@radix-ui/primitive": "1.1.4", + "@radix-ui/react-compose-refs": "1.1.3", + "@radix-ui/react-context": "1.1.4", + "@radix-ui/react-direction": "1.1.2", + "@radix-ui/react-presence": "1.1.6", + "@radix-ui/react-primitive": "2.1.7", + "@radix-ui/react-roving-focus": "1.1.14", + "@radix-ui/react-use-controllable-state": "1.2.3", + "@radix-ui/react-use-previous": "1.1.2", + "@radix-ui/react-use-size": "1.1.2" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-roving-focus": { + "version": "1.1.14", + "resolved": "https://registry.npmjs.org/@radix-ui/react-roving-focus/-/react-roving-focus-1.1.14.tgz", + "integrity": "sha512-8Qcnx9447tx/aCBgw6Jenfqg4Skq+vqab9mCBmuGNipIS5YXvL275wbKEu7+ICYHIlAPgCduUMJH1XOYewKF6Q==", + "license": "MIT", + "dependencies": { + "@radix-ui/primitive": "1.1.4", + "@radix-ui/react-collection": "1.1.11", + "@radix-ui/react-compose-refs": "1.1.3", + "@radix-ui/react-context": "1.1.4", + "@radix-ui/react-direction": "1.1.2", + "@radix-ui/react-id": "1.1.2", + "@radix-ui/react-primitive": "2.1.7", + "@radix-ui/react-use-callback-ref": "1.1.2", + "@radix-ui/react-use-controllable-state": "1.2.3" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-scroll-area": { + "version": "1.2.13", + "resolved": "https://registry.npmjs.org/@radix-ui/react-scroll-area/-/react-scroll-area-1.2.13.tgz", + "integrity": "sha512-7tncSubo2G0UY1e8rk+72qe3XRzrGnOLtZQ1PL1KoBfRUNX0NrJT5akb+0kfwSCc3gVR4wdHqyhAQBDpDNOwDw==", + "license": "MIT", + "dependencies": { + "@radix-ui/number": "1.1.2", + "@radix-ui/primitive": "1.1.4", + "@radix-ui/react-compose-refs": "1.1.3", + "@radix-ui/react-context": "1.1.4", + "@radix-ui/react-direction": "1.1.2", + "@radix-ui/react-presence": "1.1.6", + "@radix-ui/react-primitive": "2.1.7", + "@radix-ui/react-use-callback-ref": "1.1.2", + "@radix-ui/react-use-layout-effect": "1.1.2" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-select": { + "version": "2.3.2", + "resolved": "https://registry.npmjs.org/@radix-ui/react-select/-/react-select-2.3.2.tgz", + "integrity": "sha512-brXD6C/V0fVK0DDbscLVw6LsXrjQ+ay8jdOBaN+tLb4vsHsAMm6Gt6eT77wHX1Eq8GPtD5rJ+RxFtfDozsb4+Q==", + "license": "MIT", + "dependencies": { + "@radix-ui/number": "1.1.2", + "@radix-ui/primitive": "1.1.4", + "@radix-ui/react-collection": "1.1.11", + "@radix-ui/react-compose-refs": "1.1.3", + "@radix-ui/react-context": "1.1.4", + "@radix-ui/react-direction": "1.1.2", + "@radix-ui/react-dismissable-layer": "1.1.14", + "@radix-ui/react-focus-guards": "1.1.4", + "@radix-ui/react-focus-scope": "1.1.11", + "@radix-ui/react-id": "1.1.2", + "@radix-ui/react-popper": "1.3.2", + "@radix-ui/react-portal": "1.1.13", + "@radix-ui/react-presence": "1.1.6", + "@radix-ui/react-primitive": "2.1.7", + "@radix-ui/react-slot": "1.3.0", + "@radix-ui/react-use-callback-ref": "1.1.2", + "@radix-ui/react-use-controllable-state": "1.2.3", + "@radix-ui/react-use-layout-effect": "1.1.2", + "@radix-ui/react-use-previous": "1.1.2", + "@radix-ui/react-visually-hidden": "1.2.7", + "aria-hidden": "^1.2.4", + "react-remove-scroll": "^2.7.2" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-separator": { + "version": "1.1.11", + "resolved": "https://registry.npmjs.org/@radix-ui/react-separator/-/react-separator-1.1.11.tgz", + "integrity": "sha512-jRhe86+8PF7VZ1u14eOWVOuh2BuAhALg/FT1VcMC4OHedMTRUazDnDlKTt+yxo5cRNKHMfmvZ4sSQtWDeMV4CQ==", + "license": "MIT", + "dependencies": { + "@radix-ui/react-primitive": "2.1.7" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-slider": { + "version": "1.4.2", + "resolved": "https://registry.npmjs.org/@radix-ui/react-slider/-/react-slider-1.4.2.tgz", + "integrity": "sha512-qt5C1ppJz66aUDrH1VccjPrq7aFchK0wBrn6xsxlCHNUyE57dRRQ7lp1QFpF7OscMexZF8MCGBTVBlENHPkNiA==", + "license": "MIT", + "dependencies": { + "@radix-ui/number": "1.1.2", + "@radix-ui/primitive": "1.1.4", + "@radix-ui/react-collection": "1.1.11", + "@radix-ui/react-compose-refs": "1.1.3", + "@radix-ui/react-context": "1.1.4", + "@radix-ui/react-direction": "1.1.2", + "@radix-ui/react-primitive": "2.1.7", + "@radix-ui/react-use-controllable-state": "1.2.3", + "@radix-ui/react-use-layout-effect": "1.1.2", + "@radix-ui/react-use-previous": "1.1.2", + "@radix-ui/react-use-size": "1.1.2" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-slot": { + "version": "1.3.0", + "resolved": "https://registry.npmjs.org/@radix-ui/react-slot/-/react-slot-1.3.0.tgz", + "integrity": "sha512-MojKku4U/miO8Av4Dkb+ctMAQx7JmY96LmtDQlAarCRtd7rN52QCSzBF+XAvr5S6coSVj9HEPBgHAHKEJVk/WA==", + "license": "MIT", + "dependencies": { + "@radix-ui/react-compose-refs": "1.1.3" + }, + "peerDependencies": { + "@types/react": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-switch": { + "version": "1.3.2", + "resolved": "https://registry.npmjs.org/@radix-ui/react-switch/-/react-switch-1.3.2.tgz", + "integrity": "sha512-tgRBI3DdNwAJYE4BBZyZcz/HRRCvAsPkRvG1wvKc+41tBGMxPn/a87T/wikXAvyDypNQ9kaZwHbeZe+veHCGpA==", + "license": "MIT", + "dependencies": { + "@radix-ui/primitive": "1.1.4", + "@radix-ui/react-compose-refs": "1.1.3", + "@radix-ui/react-context": "1.1.4", + "@radix-ui/react-primitive": "2.1.7", + "@radix-ui/react-use-controllable-state": "1.2.3", + "@radix-ui/react-use-previous": "1.1.2", + "@radix-ui/react-use-size": "1.1.2" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-tabs": { + "version": "1.1.16", + "resolved": "https://registry.npmjs.org/@radix-ui/react-tabs/-/react-tabs-1.1.16.tgz", + "integrity": "sha512-v3Ab2l7z6U7tRB4xA0IyKdq0OsqaO1o9ZjsIEoKKnSZ/l96mZz8aCTX0NCXw+YVHJXr8Km4d+Mn6/Q8YjXa+gw==", + "license": "MIT", + "dependencies": { + "@radix-ui/primitive": "1.1.4", + "@radix-ui/react-context": "1.1.4", + "@radix-ui/react-direction": "1.1.2", + "@radix-ui/react-id": "1.1.2", + "@radix-ui/react-presence": "1.1.6", + "@radix-ui/react-primitive": "2.1.7", + "@radix-ui/react-roving-focus": "1.1.14", + "@radix-ui/react-use-controllable-state": "1.2.3" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-toast": { + "version": "1.2.18", + "resolved": "https://registry.npmjs.org/@radix-ui/react-toast/-/react-toast-1.2.18.tgz", + "integrity": "sha512-YNEnTHV47hPep+U0QvVM02OJNka9uygREc+k4Nh5VSZBg4MmE+myI442x3hCGfRpX7N2WSSYSJKws4gE+Z8lgg==", + "license": "MIT", + "dependencies": { + "@radix-ui/primitive": "1.1.4", + "@radix-ui/react-collection": "1.1.11", + "@radix-ui/react-compose-refs": "1.1.3", + "@radix-ui/react-context": "1.1.4", + "@radix-ui/react-dismissable-layer": "1.1.14", + "@radix-ui/react-portal": "1.1.13", + "@radix-ui/react-presence": "1.1.6", + "@radix-ui/react-primitive": "2.1.7", + "@radix-ui/react-use-callback-ref": "1.1.2", + "@radix-ui/react-use-controllable-state": "1.2.3", + "@radix-ui/react-use-layout-effect": "1.1.2", + "@radix-ui/react-visually-hidden": "1.2.7" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-toggle": { + "version": "1.1.13", + "resolved": "https://registry.npmjs.org/@radix-ui/react-toggle/-/react-toggle-1.1.13.tgz", + "integrity": "sha512-bI2ILJrzwgmAsH05TsJ9pVrzqQwAip7OM2/krqAdYn0R16bl86UPWbe5VPHsALat0EnqpV01cGtkleaUKPNdNg==", + "license": "MIT", + "dependencies": { + "@radix-ui/primitive": "1.1.4", + "@radix-ui/react-primitive": "2.1.7", + "@radix-ui/react-use-controllable-state": "1.2.3" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-toggle-group": { + "version": "1.1.14", + "resolved": "https://registry.npmjs.org/@radix-ui/react-toggle-group/-/react-toggle-group-1.1.14.tgz", + "integrity": "sha512-TK1vusNKb8IRhF23FTbRgUNZ9zfs5rGIyI7LfR3h26p9LrQ060i0uW9QWeD8baZMddaaP0DBGlIa6pbZG+mitg==", + "license": "MIT", + "dependencies": { + "@radix-ui/primitive": "1.1.4", + "@radix-ui/react-context": "1.1.4", + "@radix-ui/react-direction": "1.1.2", + "@radix-ui/react-primitive": "2.1.7", + "@radix-ui/react-roving-focus": "1.1.14", + "@radix-ui/react-toggle": "1.1.13", + "@radix-ui/react-use-controllable-state": "1.2.3" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-toolbar": { + "version": "1.1.14", + "resolved": "https://registry.npmjs.org/@radix-ui/react-toolbar/-/react-toolbar-1.1.14.tgz", + "integrity": "sha512-L/EkWVqlnj3lL2toHh4C7PwH2jxfa7OCq6lGfXSCii99ve2S4Ux5rc9HnOa7LN9exHa/Nl9kmCAmP9BuDPy5UA==", + "license": "MIT", + "dependencies": { + "@radix-ui/primitive": "1.1.4", + "@radix-ui/react-context": "1.1.4", + "@radix-ui/react-direction": "1.1.2", + "@radix-ui/react-primitive": "2.1.7", + "@radix-ui/react-roving-focus": "1.1.14", + "@radix-ui/react-separator": "1.1.11", + "@radix-ui/react-toggle-group": "1.1.14" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-tooltip": { + "version": "1.2.11", + "resolved": "https://registry.npmjs.org/@radix-ui/react-tooltip/-/react-tooltip-1.2.11.tgz", + "integrity": "sha512-8XZ6Py3y3W2nEzAUGCN5cfVKaUi+CVApcz1d6lrNVVf2hvYEixMRkq8k9ggPKnQUpRRuOV5avt8uvxViH2jLwA==", + "license": "MIT", + "dependencies": { + "@radix-ui/primitive": "1.1.4", + "@radix-ui/react-compose-refs": "1.1.3", + "@radix-ui/react-context": "1.1.4", + "@radix-ui/react-dismissable-layer": "1.1.14", + "@radix-ui/react-id": "1.1.2", + "@radix-ui/react-popper": "1.3.2", + "@radix-ui/react-portal": "1.1.13", + "@radix-ui/react-presence": "1.1.6", + "@radix-ui/react-primitive": "2.1.7", + "@radix-ui/react-slot": "1.3.0", + "@radix-ui/react-use-controllable-state": "1.2.3", + "@radix-ui/react-visually-hidden": "1.2.7" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-use-callback-ref": { + "version": "1.1.2", + "resolved": "https://registry.npmjs.org/@radix-ui/react-use-callback-ref/-/react-use-callback-ref-1.1.2.tgz", + "integrity": "sha512-xCso9j1/u8sEgP1RNHjFrXJLApL8LiqOkI1R4ywuN00rxWdYg4oQXuwKLS3i0j5NWLromUD27/4nlxj2UFVvIw==", + "license": "MIT", + "peerDependencies": { + "@types/react": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-use-controllable-state": { + "version": "1.2.3", + "resolved": "https://registry.npmjs.org/@radix-ui/react-use-controllable-state/-/react-use-controllable-state-1.2.3.tgz", + "integrity": "sha512-PLzC90MS+ReootmjC597dvopoelpZ8Q61HJkDXZSExitIq7PL55vHNnesAHwguHK0aPfBnpdNzQtv1uliaqQrA==", + "license": "MIT", + "dependencies": { + "@radix-ui/react-use-effect-event": "0.0.3", + "@radix-ui/react-use-layout-effect": "1.1.2" + }, + "peerDependencies": { + "@types/react": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-use-effect-event": { + "version": "0.0.3", + "resolved": "https://registry.npmjs.org/@radix-ui/react-use-effect-event/-/react-use-effect-event-0.0.3.tgz", + "integrity": "sha512-6c8ZqvPTWILEKnyVkP53EGRCcpnJiKTC21sS/6R1GF5xKyHJJWQEPfkqlcgUkdRQivd6tb23abUwe4ngWmY0JA==", + "license": "MIT", + "dependencies": { + "@radix-ui/react-use-layout-effect": "1.1.2" + }, + "peerDependencies": { + "@types/react": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-use-escape-keydown": { + "version": "1.1.3", + "resolved": "https://registry.npmjs.org/@radix-ui/react-use-escape-keydown/-/react-use-escape-keydown-1.1.3.tgz", + "integrity": "sha512-3wEkMiPHXha/2VadZ68rYBcmYnPINVGl4Y3gtcM7fKRjANk0OscK+cdqBgUWdozb7YJxsh0vefM7vgAMHXOjqg==", + "license": "MIT", + "dependencies": { + "@radix-ui/react-use-callback-ref": "1.1.2" + }, + "peerDependencies": { + "@types/react": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-use-is-hydrated": { + "version": "0.1.1", + "resolved": "https://registry.npmjs.org/@radix-ui/react-use-is-hydrated/-/react-use-is-hydrated-0.1.1.tgz", + "integrity": "sha512-qwOiz4Tjo8CNnrOLAYUMXeZwDzXgXpvK4TKQPmWLECM9XoWvA6+0Z2/7Ag3A4ivjS4ovbLJPbskkxioFyBhr8A==", + "license": "MIT", + "peerDependencies": { + "@types/react": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-use-layout-effect": { + "version": "1.1.2", + "resolved": "https://registry.npmjs.org/@radix-ui/react-use-layout-effect/-/react-use-layout-effect-1.1.2.tgz", + "integrity": "sha512-jrBWOxZITuGcnjRCM2t2U5ZPkCLxD+Ym6DjfssS5haTj2iiak/DOb64JeN6OdLfLgptb6/e2kKR+ZuTrGoZTPA==", + "license": "MIT", + "peerDependencies": { + "@types/react": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-use-previous": { + "version": "1.1.2", + "resolved": "https://registry.npmjs.org/@radix-ui/react-use-previous/-/react-use-previous-1.1.2.tgz", + "integrity": "sha512-IGBQPtRFdhN6MQ8dbegVmBq1LVZluya3F1jWY+puIcQC3MHctRwTDSBWCkL/3ZcnMJLTMJ++Z+ktmvg0F89iCw==", + "license": "MIT", + "peerDependencies": { + "@types/react": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-use-rect": { + "version": "1.1.2", + "resolved": "https://registry.npmjs.org/@radix-ui/react-use-rect/-/react-use-rect-1.1.2.tgz", + "integrity": "sha512-d8a+bBY/FxikNPlgJJoaBHZX+zKVbWHYJGTLnLvveQgFSTntkGdEKv3JDtHrMS0DNYpllz2nRsTLGLKYttbpmw==", + "license": "MIT", + "dependencies": { + "@radix-ui/rect": "1.1.2" + }, + "peerDependencies": { + "@types/react": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-use-size": { + "version": "1.1.2", + "resolved": "https://registry.npmjs.org/@radix-ui/react-use-size/-/react-use-size-1.1.2.tgz", + "integrity": "sha512-giWQp+4mxjBPt4KZ0MmyuykFNWfbDxKt4x+fPkRYmgRFJSbCZFzUglvMb/Kjn38tm10YP4ufiQZDx3zna4LU6w==", + "license": "MIT", + "dependencies": { + "@radix-ui/react-use-layout-effect": "1.1.2" + }, + "peerDependencies": { + "@types/react": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + } + } + }, + "node_modules/@radix-ui/react-visually-hidden": { + "version": "1.2.7", + "resolved": "https://registry.npmjs.org/@radix-ui/react-visually-hidden/-/react-visually-hidden-1.2.7.tgz", + "integrity": "sha512-1wNZBggTDK3GRuuQ6nP4k2yi7a6l7I5qbMPbZcRsrGsGVead/f/d5FhEzUvqFs0bcrDLx7n1zKQ3JvLR6whaaw==", + "license": "MIT", + "dependencies": { + "@radix-ui/react-primitive": "2.1.7" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, + "node_modules/@radix-ui/rect": { + "version": "1.1.2", + "resolved": "https://registry.npmjs.org/@radix-ui/rect/-/rect-1.1.2.tgz", + "integrity": "sha512-xnXE7wG13PI+cxieVssYXlQJuYVRhH9NBoxt3KNwzghDIA69GMm7d4wXRouHIYjE+KvS6U/MsMO73NdS2MH9ZA==", + "license": "MIT" + }, "node_modules/@rc-component/async-validator": { "version": "5.1.0", "resolved": "https://registry.npmjs.org/@rc-component/async-validator/-/async-validator-5.1.0.tgz", @@ -3221,6 +4738,277 @@ "tailwindcss": ">=3.0.0 || >= 3.0.0-alpha.1 || >= 4.0.0-alpha.20 || >= 4.0.0-beta.1" } }, + "node_modules/@tailwindcss/node": { + "version": "4.3.2", + "resolved": "https://registry.npmjs.org/@tailwindcss/node/-/node-4.3.2.tgz", + "integrity": "sha512-yWP/sqEcBLaD8JuA6zNwxoYKr75qxTioYwlRwekj5Jr/I5GXnoJfjetH/psLUIv74cYTH2lBUEzBkinthoYcBg==", + "dev": true, + "license": "MIT", + "dependencies": { + "@jridgewell/remapping": "^2.3.5", + "enhanced-resolve": "5.21.6", + "jiti": "^2.7.0", + "lightningcss": "1.32.0", + "magic-string": "^0.30.21", + "source-map-js": "^1.2.1", + "tailwindcss": "4.3.2" + } + }, + "node_modules/@tailwindcss/oxide": { + "version": "4.3.2", + "resolved": "https://registry.npmjs.org/@tailwindcss/oxide/-/oxide-4.3.2.tgz", + "integrity": "sha512-z8ZgnzX8gdNoWLBLqBPoh/sjnxkwvf9ZuWjnO0l0yIzbLa5/9S+eC5QxGZKRobVHIC3/1BoMWjHblqWjcgFgag==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">= 20" + }, + "optionalDependencies": { + "@tailwindcss/oxide-android-arm64": "4.3.2", + "@tailwindcss/oxide-darwin-arm64": "4.3.2", + "@tailwindcss/oxide-darwin-x64": "4.3.2", + "@tailwindcss/oxide-freebsd-x64": "4.3.2", + "@tailwindcss/oxide-linux-arm-gnueabihf": "4.3.2", + "@tailwindcss/oxide-linux-arm64-gnu": "4.3.2", + "@tailwindcss/oxide-linux-arm64-musl": "4.3.2", + "@tailwindcss/oxide-linux-x64-gnu": "4.3.2", + "@tailwindcss/oxide-linux-x64-musl": "4.3.2", + "@tailwindcss/oxide-wasm32-wasi": "4.3.2", + "@tailwindcss/oxide-win32-arm64-msvc": "4.3.2", + "@tailwindcss/oxide-win32-x64-msvc": "4.3.2" + } + }, + "node_modules/@tailwindcss/oxide-android-arm64": { + "version": "4.3.2", + "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-android-arm64/-/oxide-android-arm64-4.3.2.tgz", + "integrity": "sha512-WHxqIuHpvZ5VtdX6GTl1Ik/Vp2YuN42Et+0CdeaVd/frQ9jAvGmvR8vLT+jk3e8/Q3x8kECB9+R17pgpp2BulA==", + "cpu": [ + "arm64" + ], + "dev": true, + "license": "MIT", + "optional": true, + "os": [ + "android" + ], + "engines": { + "node": ">= 20" + } + }, + "node_modules/@tailwindcss/oxide-darwin-arm64": { + "version": "4.3.2", + "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-darwin-arm64/-/oxide-darwin-arm64-4.3.2.tgz", + "integrity": "sha512-GZypeUY/IDJW3877KeM+O67vbXr3MBnbtEL4aYhNErv/JWZhye2vGSWWG9tB6iiqR2MqRNkY8IOUy4NdSZV26w==", + "cpu": [ + "arm64" + ], + "dev": true, + "license": "MIT", + "optional": true, + "os": [ + "darwin" + ], + "engines": { + "node": ">= 20" + } + }, + "node_modules/@tailwindcss/oxide-darwin-x64": { + "version": "4.3.2", + "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-darwin-x64/-/oxide-darwin-x64-4.3.2.tgz", + "integrity": "sha512-UIIzmefR6KO1sDU7MzRqAxC8iBpft/VhkGjTjnhoS6k7Z3rQ9wEgA1ODSiyH/tcSYssulNm4Ci3hOeK1jH7ccQ==", + "cpu": [ + "x64" + ], + "dev": true, + "license": "MIT", + "optional": true, + "os": [ + "darwin" + ], + "engines": { + "node": ">= 20" + } + }, + "node_modules/@tailwindcss/oxide-freebsd-x64": { + "version": "4.3.2", + "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-freebsd-x64/-/oxide-freebsd-x64-4.3.2.tgz", + "integrity": "sha512-GN+uAmcI6DNspnCDwtOAZrTz6oukJnp337qZvxqCGLd3BHBzJpO0ZbTLRvJNdztOeAmTzewewGIMPb0tk2R4WA==", + "cpu": [ + "x64" + ], + "dev": true, + "license": "MIT", + "optional": true, + "os": [ + "freebsd" + ], + "engines": { + "node": ">= 20" + } + }, + "node_modules/@tailwindcss/oxide-linux-arm-gnueabihf": { + "version": "4.3.2", + "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-linux-arm-gnueabihf/-/oxide-linux-arm-gnueabihf-4.3.2.tgz", + "integrity": "sha512-4ABn7qSbdHRwTiDiuWNegCyb5+2FJ4vKIKc3DmKrvAFw7MU1Lm11dIkTPwUaFdTzc7IsOpDbqBrlh0x6y36U/w==", + "cpu": [ + "arm" + ], + "dev": true, + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">= 20" + } + }, + "node_modules/@tailwindcss/oxide-linux-arm64-gnu": { + "version": "4.3.2", + "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-linux-arm64-gnu/-/oxide-linux-arm64-gnu-4.3.2.tgz", + "integrity": "sha512-wDgEIGwoM8w8pufh9LVt1PahDgNdKXrLC2qfAnV3vAmococ9RWbxeAw4pxPttd/TsJfwjyLf90Dg1y9y8I6Emw==", + "cpu": [ + "arm64" + ], + "dev": true, + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">= 20" + } + }, + "node_modules/@tailwindcss/oxide-linux-arm64-musl": { + "version": "4.3.2", + "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-linux-arm64-musl/-/oxide-linux-arm64-musl-4.3.2.tgz", + "integrity": "sha512-J5Nuk0uZQIiMTJj3LEx4sAA9tMFUoXQZFv1J6An+QGYe53HKRJuFDi0rpq/tuouCZeAbOBY3kQ6g8qeD4TUjtA==", + "cpu": [ + "arm64" + ], + "dev": true, + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">= 20" + } + }, + "node_modules/@tailwindcss/oxide-linux-x64-gnu": { + "version": "4.3.2", + "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-linux-x64-gnu/-/oxide-linux-x64-gnu-4.3.2.tgz", + "integrity": "sha512-kqCZpSKOBEJO4mz7OqWoofBZeXTAwaVGPj0ErAj7CojmhKpWVWVOnrt9dE8odoIraZq4oj3ausM37kXi+Tow8w==", + "cpu": [ + "x64" + ], + "dev": true, + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">= 20" + } + }, + "node_modules/@tailwindcss/oxide-linux-x64-musl": { + "version": "4.3.2", + "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-linux-x64-musl/-/oxide-linux-x64-musl-4.3.2.tgz", + "integrity": "sha512-cixpqbh2toJDmkuCRI68nXA8ZxNmdK9Y+9v5h3MC3ZQKy/0BO8AWzlkWyRM7JAFSGBlfig4YVTPsK6MVgqz1uw==", + "cpu": [ + "x64" + ], + "dev": true, + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">= 20" + } + }, + "node_modules/@tailwindcss/oxide-wasm32-wasi": { + "version": "4.3.2", + "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-wasm32-wasi/-/oxide-wasm32-wasi-4.3.2.tgz", + "integrity": "sha512-4ec2Z/LOmRsAgU23CS4xeJfcJlmRg94A/XrbGRCF1gyU/zdDfRLYDVsS+ynSZCmGNxQ1jQriQOKMQeQxBA3Isw==", + "bundleDependencies": [ + "@napi-rs/wasm-runtime", + "@emnapi/core", + "@emnapi/runtime", + "@tybys/wasm-util", + "@emnapi/wasi-threads", + "tslib" + ], + "cpu": [ + "wasm32" + ], + "dev": true, + "license": "MIT", + "optional": true, + "dependencies": { + "@emnapi/core": "^1.11.1", + "@emnapi/runtime": "^1.11.1", + "@emnapi/wasi-threads": "^1.2.2", + "@napi-rs/wasm-runtime": "^1.1.4", + "@tybys/wasm-util": "^0.10.2", + "tslib": "^2.8.1" + }, + "engines": { + "node": ">=14.0.0" + } + }, + "node_modules/@tailwindcss/oxide-win32-arm64-msvc": { + "version": "4.3.2", + "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-win32-arm64-msvc/-/oxide-win32-arm64-msvc-4.3.2.tgz", + "integrity": "sha512-Zyr/M0+XcYZu3bZrUytc7TXvrk0ftWfl8gN2MwekNDzhqhKRUucMPSeOzM0o0wH5AWOU49BsKRrfKxI2atCPMQ==", + "cpu": [ + "arm64" + ], + "dev": true, + "license": "MIT", + "optional": true, + "os": [ + "win32" + ], + "engines": { + "node": ">= 20" + } + }, + "node_modules/@tailwindcss/oxide-win32-x64-msvc": { + "version": "4.3.2", + "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-win32-x64-msvc/-/oxide-win32-x64-msvc-4.3.2.tgz", + "integrity": "sha512-QI9BO7KlNZsp2GuO0jwAAj5jCDABOKXRkCk2XuKTSaNEFSdfzqswYVTtCHBNKHLsqyjFyFkqlDiwkNbTYSssMQ==", + "cpu": [ + "x64" + ], + "dev": true, + "license": "MIT", + "optional": true, + "os": [ + "win32" + ], + "engines": { + "node": ">= 20" + } + }, + "node_modules/@tailwindcss/postcss": { + "version": "4.3.2", + "resolved": "https://registry.npmjs.org/@tailwindcss/postcss/-/postcss-4.3.2.tgz", + "integrity": "sha512-rjVWYCa7Ngbi5AarT6k8TkxUG3Wl1QKzHdIZVsjZSzf36Jmo2IKZt/NHRAwly8oDkbBOH0YTu+CHuf9jPxMc+g==", + "dev": true, + "license": "MIT", + "dependencies": { + "@alloc/quick-lru": "^5.2.0", + "@tailwindcss/node": "4.3.2", + "@tailwindcss/oxide": "4.3.2", + "postcss": "^8.5.15", + "tailwindcss": "4.3.2" + } + }, "node_modules/@tanstack/pacer": { "version": "0.2.0", "resolved": "https://registry.npmjs.org/@tanstack/pacer/-/pacer-0.2.0.tgz", @@ -3685,7 +5473,7 @@ "version": "18.3.7", "resolved": "https://registry.npmjs.org/@types/react-dom/-/react-dom-18.3.7.tgz", "integrity": "sha512-MEe3UeoENYVFXzoXEWsvcpg6ZvlrFNlOQ7EOsvhI3CfAXwzPfO8Qwuxd40nepsYKqyyVQnTdEfv68q91yLcKrQ==", - "dev": true, + "devOptional": true, "license": "MIT", "peerDependencies": { "@types/react": "^18.0.0" @@ -4590,43 +6378,6 @@ "react-dom": ">=16.9.0" } }, - "node_modules/any-promise": { - "version": "1.3.0", - "resolved": "https://registry.npmjs.org/any-promise/-/any-promise-1.3.0.tgz", - "integrity": "sha512-7UvmKalWRt1wgjL1RrGxoSJW/0QZFIegpeGvZG9kjp8vrRu55XTHbwnqq2GpXm9uLbcuhxm3IqX9OB4MZR1b2A==", - "license": "MIT" - }, - "node_modules/anymatch": { - "version": "3.1.3", - "resolved": "https://registry.npmjs.org/anymatch/-/anymatch-3.1.3.tgz", - "integrity": "sha512-KMReFUr0B4t+D+OBkjR3KYqvocp2XaSzO55UcB6mgQMd3KbcE+mWTyvVV7D/zsdEbNnV6acZUutkiHQXvTr1Rw==", - "license": "ISC", - "dependencies": { - "normalize-path": "^3.0.0", - "picomatch": "^2.0.4" - }, - "engines": { - "node": ">= 8" - } - }, - "node_modules/anymatch/node_modules/picomatch": { - "version": "2.3.2", - "resolved": "https://registry.npmjs.org/picomatch/-/picomatch-2.3.2.tgz", - "integrity": "sha512-V7+vQEJ06Z+c5tSye8S+nHUfI51xoXIXjHQ99cQtKUkQqqO1kO/KCJUfZXuB47h/YBlDhah2H3hdUGXn8ie0oA==", - "license": "MIT", - "engines": { - "node": ">=8.6" - }, - "funding": { - "url": "https://github.com/sponsors/jonschlinkert" - } - }, - "node_modules/arg": { - "version": "5.0.2", - "resolved": "https://registry.npmjs.org/arg/-/arg-5.0.2.tgz", - "integrity": "sha512-PYjyFOLKQ9y57JvQ6QLo8dAgNqswh8M1RMJYdQduT6xbWSgK36P/Z/v+p888pM69jMMfS8Xd8F6I1kQ/I9HUGg==", - "license": "MIT" - }, "node_modules/argparse": { "version": "2.0.1", "resolved": "https://registry.npmjs.org/argparse/-/argparse-2.0.1.tgz", @@ -4868,43 +6619,6 @@ "integrity": "sha512-Oei9OH4tRh0YqU3GxhX79dM/mwVgvbZJaSNaRk+bshkj0S5cfHcgYakreBjrHwatXKbz+IoIdYLxrKim2MjW0Q==", "license": "MIT" }, - "node_modules/autoprefixer": { - "version": "10.4.24", - "resolved": "https://registry.npmjs.org/autoprefixer/-/autoprefixer-10.4.24.tgz", - "integrity": "sha512-uHZg7N9ULTVbutaIsDRoUkoS8/h3bdsmVJYZ5l3wv8Cp/6UIIoRDm90hZ+BwxUj/hGBEzLxdHNSKuFpn8WOyZw==", - "dev": true, - "funding": [ - { - "type": "opencollective", - "url": "https://opencollective.com/postcss/" - }, - { - "type": "tidelift", - "url": "https://tidelift.com/funding/github/npm/autoprefixer" - }, - { - "type": "github", - "url": "https://github.com/sponsors/ai" - } - ], - "license": "MIT", - "dependencies": { - "browserslist": "^4.28.1", - "caniuse-lite": "^1.0.30001766", - "fraction.js": "^5.3.4", - "picocolors": "^1.1.1", - "postcss-value-parser": "^4.2.0" - }, - "bin": { - "autoprefixer": "bin/autoprefixer" - }, - "engines": { - "node": "^10 || ^12 || >=14" - }, - "peerDependencies": { - "postcss": "^8.1.0" - } - }, "node_modules/available-typed-arrays": { "version": "1.0.7", "resolved": "https://registry.npmjs.org/available-typed-arrays/-/available-typed-arrays-1.0.7.tgz", @@ -4983,18 +6697,6 @@ "require-from-string": "^2.0.2" } }, - "node_modules/binary-extensions": { - "version": "2.3.0", - "resolved": "https://registry.npmjs.org/binary-extensions/-/binary-extensions-2.3.0.tgz", - "integrity": "sha512-Ceh+7ox5qe7LJuLHoY0feh3pHuUDHAcRUeyL2VYghZwfpkNIy/+8Ocg0a3UuSoYzavmylwuLWQOf3hl0jjMMIw==", - "license": "MIT", - "engines": { - "node": ">=8" - }, - "funding": { - "url": "https://github.com/sponsors/sindresorhus" - } - }, "node_modules/brace-expansion": { "version": "5.0.6", "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-5.0.6.tgz", @@ -5012,6 +6714,7 @@ "version": "3.0.3", "resolved": "https://registry.npmjs.org/braces/-/braces-3.0.3.tgz", "integrity": "sha512-yQbXgO/OSZVD2IsiLlro+7Hf6Q18EJrKSEsdoMzKePKXct3gvD8oLcOQdIzGupr5Fj+EDe8gO/lxc1BzfMpxvA==", + "dev": true, "license": "MIT", "dependencies": { "fill-range": "^7.1.1" @@ -5123,15 +6826,6 @@ "node": ">=6" } }, - "node_modules/camelcase-css": { - "version": "2.0.1", - "resolved": "https://registry.npmjs.org/camelcase-css/-/camelcase-css-2.0.1.tgz", - "integrity": "sha512-QOSvevhslijgYwRx6Rv7zKdMF8lbRmx+uQGx2+vDc+KI/eBnsy9kit5aj23AgGu3pa4t9AgwbnXWqS+iOY+2aA==", - "license": "MIT", - "engines": { - "node": ">= 6" - } - }, "node_modules/caniuse-lite": { "version": "1.0.30001791", "resolved": "https://registry.npmjs.org/caniuse-lite/-/caniuse-lite-1.0.30001791.tgz", @@ -5253,42 +6947,6 @@ "node": ">= 16" } }, - "node_modules/chokidar": { - "version": "3.6.0", - "resolved": "https://registry.npmjs.org/chokidar/-/chokidar-3.6.0.tgz", - "integrity": "sha512-7VT13fmjotKpGipCW9JEQAusEPE+Ei8nl6/g4FBAmIm0GOOLMua9NDDo/DWp0ZAxCr3cPq5ZpBqmPAQgDda2Pw==", - "license": "MIT", - "dependencies": { - "anymatch": "~3.1.2", - "braces": "~3.0.2", - "glob-parent": "~5.1.2", - "is-binary-path": "~2.1.0", - "is-glob": "~4.0.1", - "normalize-path": "~3.0.0", - "readdirp": "~3.6.0" - }, - "engines": { - "node": ">= 8.10.0" - }, - "funding": { - "url": "https://paulmillr.com/funding/" - }, - "optionalDependencies": { - "fsevents": "~2.3.2" - } - }, - "node_modules/chokidar/node_modules/glob-parent": { - "version": "5.1.2", - "resolved": "https://registry.npmjs.org/glob-parent/-/glob-parent-5.1.2.tgz", - "integrity": "sha512-AOIgSQCepiJYwP3ARnGx+5VnTu2HBYdzbGP45eLw1vr3zB3vZLeyed1sC9hnbcOc9/SrMyM5RPQrkGz4aS9Zow==", - "license": "ISC", - "dependencies": { - "is-glob": "^4.0.1" - }, - "engines": { - "node": ">= 6" - } - }, "node_modules/classnames": { "version": "2.5.1", "resolved": "https://registry.npmjs.org/classnames/-/classnames-2.5.1.tgz", @@ -5359,15 +7017,6 @@ "url": "https://github.com/sponsors/wooorm" } }, - "node_modules/commander": { - "version": "4.1.1", - "resolved": "https://registry.npmjs.org/commander/-/commander-4.1.1.tgz", - "integrity": "sha512-NOKm8xhkzAjzFx8B2v5OAHT+u5pRQc2UCa2Vq9jYL/31o2wi9mxBA7LIFs3sV5VSC49z6pEhfbMULvShKj26WA==", - "license": "MIT", - "engines": { - "node": ">= 6" - } - }, "node_modules/compute-scroll-into-view": { "version": "3.1.1", "resolved": "https://registry.npmjs.org/compute-scroll-into-view/-/compute-scroll-into-view-3.1.1.tgz", @@ -5426,18 +7075,6 @@ "dev": true, "license": "MIT" }, - "node_modules/cssesc": { - "version": "3.0.0", - "resolved": "https://registry.npmjs.org/cssesc/-/cssesc-3.0.0.tgz", - "integrity": "sha512-/Tb/JcjK111nNScGob5MNtsntNM1aCNUDipB/TkwZFhyDrrE47SOx/18wF2bbjgc3ZzCSKW1T5nt5EbFoAz/Vg==", - "license": "MIT", - "bin": { - "cssesc": "bin/cssesc" - }, - "engines": { - "node": ">=4" - } - }, "node_modules/cssstyle": { "version": "5.3.7", "resolved": "https://registry.npmjs.org/cssstyle/-/cssstyle-5.3.7.tgz", @@ -5820,12 +7457,18 @@ "version": "2.1.2", "resolved": "https://registry.npmjs.org/detect-libc/-/detect-libc-2.1.2.tgz", "integrity": "sha512-Btj2BOOO83o3WyH59e8MgXsxEQVcarkUOpEYrubB0urwnN10yQ364rsiByU11nZlqWYZm05i/of7io4mzihBtQ==", + "devOptional": true, "license": "Apache-2.0", - "optional": true, "engines": { "node": ">=8" } }, + "node_modules/detect-node-es": { + "version": "1.1.0", + "resolved": "https://registry.npmjs.org/detect-node-es/-/detect-node-es-1.1.0.tgz", + "integrity": "sha512-ypdmJU/TbBby2Dxibuv7ZLW3Bs1QEmM7nHjEANfohJLvE0XVujisn1qPJcZxg+qDucsr+bP6fLD1rPS3AhJ7EQ==", + "license": "MIT" + }, "node_modules/devlop": { "version": "1.1.0", "resolved": "https://registry.npmjs.org/devlop/-/devlop-1.1.0.tgz", @@ -5839,18 +7482,6 @@ "url": "https://github.com/sponsors/wooorm" } }, - "node_modules/didyoumean": { - "version": "1.2.2", - "resolved": "https://registry.npmjs.org/didyoumean/-/didyoumean-1.2.2.tgz", - "integrity": "sha512-gxtyfqMg7GKyhQmb056K7M3xszy/myH8w+B4RT+QXBQsvAOdc3XymqDDPHx1BgPgsdAA5SIifona89YtRATDzw==", - "license": "Apache-2.0" - }, - "node_modules/dlv": { - "version": "1.1.3", - "resolved": "https://registry.npmjs.org/dlv/-/dlv-1.1.3.tgz", - "integrity": "sha512-+HlytyjlPKnIG8XuRG8WvmBP8xs8P71y+SKKS6ZXWoEgLuePxtDoUEiH7WkdePWrQ5JBpE6aoVqfZfJUQkjXwA==", - "license": "MIT" - }, "node_modules/doctrine": { "version": "2.1.0", "resolved": "https://registry.npmjs.org/doctrine/-/doctrine-2.1.0.tgz", @@ -5909,6 +7540,20 @@ "dev": true, "license": "MIT" }, + "node_modules/enhanced-resolve": { + "version": "5.21.6", + "resolved": "https://registry.npmjs.org/enhanced-resolve/-/enhanced-resolve-5.21.6.tgz", + "integrity": "sha512-aNnGCvbJ/RIyWo1IuhNdVjnNF+EjH9wpzpNHt+ci/m9He9LJvUN8wrCcXjp9cWsGNAuvSpVFTx/vraAFQ8qGjQ==", + "dev": true, + "license": "MIT", + "dependencies": { + "graceful-fs": "^4.2.4", + "tapable": "^2.3.3" + }, + "engines": { + "node": ">=10.13.0" + } + }, "node_modules/entities": { "version": "8.0.0", "resolved": "https://registry.npmjs.org/entities/-/entities-8.0.0.tgz", @@ -6750,6 +8395,7 @@ "version": "1.20.1", "resolved": "https://registry.npmjs.org/fastq/-/fastq-1.20.1.tgz", "integrity": "sha512-GGToxJ/w1x32s/D2EKND7kTil4n8OVk/9mycTc4VDza13lOvpUZTGX3mFSCtV9ksdGBVzvsyAVLM6mHFThxXxw==", + "dev": true, "license": "ISC", "dependencies": { "reusify": "^1.0.4" @@ -6782,6 +8428,7 @@ "version": "6.5.0", "resolved": "https://registry.npmjs.org/fdir/-/fdir-6.5.0.tgz", "integrity": "sha512-tIbYtZbucOs0BRGqPJkshJUYdL+SDH7dVM8gjy+ERp3WAUjLEFJE+02kanyHtwjWOnwrKYBiwAmM0p4kLJAnXg==", + "dev": true, "license": "MIT", "engines": { "node": ">=12.0.0" @@ -6819,6 +8466,7 @@ "version": "7.1.1", "resolved": "https://registry.npmjs.org/fill-range/-/fill-range-7.1.1.tgz", "integrity": "sha512-YsGpe3WHLK8ZYi4tWDg2Jy3ebRz2rXowDxnld4bkQB00cc/1Zw9AWnC0i9ztDJitivtQvaI9KaLyKrc+hBW0yg==", + "dev": true, "license": "MIT", "dependencies": { "to-regex-range": "^5.0.1" @@ -6940,24 +8588,11 @@ "node": ">= 12.20" } }, - "node_modules/fraction.js": { - "version": "5.3.4", - "resolved": "https://registry.npmjs.org/fraction.js/-/fraction.js-5.3.4.tgz", - "integrity": "sha512-1X1NTtiJphryn/uLQz3whtY6jK3fTqoE3ohKs0tT+Ujr1W59oopxmoEh7Lu5p6vBaPbgoM0bzveAW4Qi5RyWDQ==", - "dev": true, - "license": "MIT", - "engines": { - "node": "*" - }, - "funding": { - "type": "github", - "url": "https://github.com/sponsors/rawify" - } - }, "node_modules/fsevents": { "version": "2.3.2", "resolved": "https://registry.npmjs.org/fsevents/-/fsevents-2.3.2.tgz", "integrity": "sha512-xiqMQR4xAeHTuB9uWm+fFRcIOgKBMiOBP+eXiyT7jsgVCq1bkVygt00oASowB7EdtpOHaaPgKt812P9ab+DDKA==", + "dev": true, "hasInstallScript": true, "license": "MIT", "optional": true, @@ -7052,6 +8687,15 @@ "url": "https://github.com/sponsors/ljharb" } }, + "node_modules/get-nonce": { + "version": "1.0.1", + "resolved": "https://registry.npmjs.org/get-nonce/-/get-nonce-1.0.1.tgz", + "integrity": "sha512-FJhYRoDaiatfEkUK8HKlicmu/3SGFD51q3itKDGoSTysQJBnfOcxU5GxnhE1E6soB76MbT0MBtnKJuXyAx+96Q==", + "license": "MIT", + "engines": { + "node": ">=6" + } + }, "node_modules/get-proto": { "version": "1.0.1", "resolved": "https://registry.npmjs.org/get-proto/-/get-proto-1.0.1.tgz", @@ -7118,6 +8762,7 @@ "version": "6.0.2", "resolved": "https://registry.npmjs.org/glob-parent/-/glob-parent-6.0.2.tgz", "integrity": "sha512-XxwI8EOhVQgWp6iDL+3b0r86f4d6AX6zSU55HfB4ydCEuXLXc5FcYeOu+nnGftS4TEju/11rt4KJPTMgbfmv4A==", + "dev": true, "license": "ISC", "dependencies": { "is-glob": "^4.0.3" @@ -7168,6 +8813,13 @@ "url": "https://github.com/sponsors/ljharb" } }, + "node_modules/graceful-fs": { + "version": "4.2.11", + "resolved": "https://registry.npmjs.org/graceful-fs/-/graceful-fs-4.2.11.tgz", + "integrity": "sha512-RbJ5/jmFcNNCcDV5o9eTnBLJ/HszWV0P73bc+Ff4nS/rJj+YaS6IGyiOL0VoBYX+l1Wrl3k63h/KrH+nhJ0XvQ==", + "dev": true, + "license": "ISC" + }, "node_modules/has-bigints": { "version": "1.1.0", "resolved": "https://registry.npmjs.org/has-bigints/-/has-bigints-1.1.0.tgz", @@ -7641,18 +9293,6 @@ "url": "https://github.com/sponsors/ljharb" } }, - "node_modules/is-binary-path": { - "version": "2.1.0", - "resolved": "https://registry.npmjs.org/is-binary-path/-/is-binary-path-2.1.0.tgz", - "integrity": "sha512-ZMERYes6pDydyuGidse7OsHxtbI7WVeUEozgR/g7rd0xUimYNlvZRE/K2MgZTjWy725IfelLeVcEM97mmtRGXw==", - "license": "MIT", - "dependencies": { - "binary-extensions": "^2.0.0" - }, - "engines": { - "node": ">=8" - } - }, "node_modules/is-boolean-object": { "version": "1.2.2", "resolved": "https://registry.npmjs.org/is-boolean-object/-/is-boolean-object-1.2.2.tgz", @@ -7697,6 +9337,7 @@ "version": "2.16.2", "resolved": "https://registry.npmjs.org/is-core-module/-/is-core-module-2.16.2.tgz", "integrity": "sha512-evOr8xfXKxE6qSR0hSXL2r3sd7ALj8+7jQEUvPYcm5sgZFdJ+AYzT6yNmJenvIYQBgIGwfwz08sL8zoL7yq2BA==", + "dev": true, "license": "MIT", "dependencies": { "hasown": "^2.0.3" @@ -7757,6 +9398,7 @@ "version": "2.1.1", "resolved": "https://registry.npmjs.org/is-extglob/-/is-extglob-2.1.1.tgz", "integrity": "sha512-SbKbANkN603Vi4jEZv49LeVJMn4yGwsbzZworEoyEiutsN3nJYdbO36zfhGJ6QEDpOZIFkDtnq5JRxmvl3jsoQ==", + "dev": true, "license": "MIT", "engines": { "node": ">=0.10.0" @@ -7802,6 +9444,7 @@ "version": "4.0.3", "resolved": "https://registry.npmjs.org/is-glob/-/is-glob-4.0.3.tgz", "integrity": "sha512-xelSayHH36ZgE7ZWhli7pW34hNbNl8Ojv5KVmkJD4hBdD3th8Tfk9vYasLM+mXWOZhFkgZfxhLSnrwRr4elSSg==", + "dev": true, "license": "MIT", "dependencies": { "is-extglob": "^2.1.1" @@ -7850,6 +9493,7 @@ "version": "7.0.0", "resolved": "https://registry.npmjs.org/is-number/-/is-number-7.0.0.tgz", "integrity": "sha512-41Cifkg6e8TylSpdtTpeLVMqvSBEVzTttHvERD741+pnZ8ANv0004MRL43QKPDlK9cGvNp6NZWZUBlbGXYxxng==", + "dev": true, "license": "MIT", "engines": { "node": ">=0.12.0" @@ -8123,10 +9767,10 @@ } }, "node_modules/jiti": { - "version": "2.6.1", - "resolved": "https://registry.npmjs.org/jiti/-/jiti-2.6.1.tgz", - "integrity": "sha512-ekilCSN1jwRvIbgeg/57YFh8qQDNbwDb9xT/qu2DAHbFFZUicIl4ygVaAvzveMhMVr3LnpSKTNnwt8PoOfmKhQ==", - "devOptional": true, + "version": "2.7.0", + "resolved": "https://registry.npmjs.org/jiti/-/jiti-2.7.0.tgz", + "integrity": "sha512-AC/7JofJvZGrrneWNaEnJeOLUx+JlGt7tNa0wZiRPT4MY1wmfKjt2+6O2p2uz2+skll8OZZmJMNqeke7kKbNgQ==", + "dev": true, "license": "MIT", "bin": { "jiti": "lib/jiti-cli.mjs" @@ -8444,23 +10088,266 @@ "node": ">= 0.8.0" } }, - "node_modules/lilconfig": { - "version": "3.1.3", - "resolved": "https://registry.npmjs.org/lilconfig/-/lilconfig-3.1.3.tgz", - "integrity": "sha512-/vlFKAoH5Cgt3Ie+JLhRbwOsCQePABiU3tJ1egGvyQ+33R/vcwM2Zl2QR/LzjsBeItPt3oSVXapn+m4nQDvpzw==", - "license": "MIT", + "node_modules/lightningcss": { + "version": "1.32.0", + "resolved": "https://registry.npmjs.org/lightningcss/-/lightningcss-1.32.0.tgz", + "integrity": "sha512-NXYBzinNrblfraPGyrbPoD19C1h9lfI/1mzgWYvXUTe414Gz/X1FD2XBZSZM7rRTrMA8JL3OtAaGifrIKhQ5yQ==", + "dev": true, + "license": "MPL-2.0", + "dependencies": { + "detect-libc": "^2.0.3" + }, "engines": { - "node": ">=14" + "node": ">= 12.0.0" }, "funding": { - "url": "https://github.com/sponsors/antonk52" + "type": "opencollective", + "url": "https://opencollective.com/parcel" + }, + "optionalDependencies": { + "lightningcss-android-arm64": "1.32.0", + "lightningcss-darwin-arm64": "1.32.0", + "lightningcss-darwin-x64": "1.32.0", + "lightningcss-freebsd-x64": "1.32.0", + "lightningcss-linux-arm-gnueabihf": "1.32.0", + "lightningcss-linux-arm64-gnu": "1.32.0", + "lightningcss-linux-arm64-musl": "1.32.0", + "lightningcss-linux-x64-gnu": "1.32.0", + "lightningcss-linux-x64-musl": "1.32.0", + "lightningcss-win32-arm64-msvc": "1.32.0", + "lightningcss-win32-x64-msvc": "1.32.0" } }, - "node_modules/lines-and-columns": { - "version": "1.2.4", - "resolved": "https://registry.npmjs.org/lines-and-columns/-/lines-and-columns-1.2.4.tgz", - "integrity": "sha512-7ylylesZQ/PV29jhEDl3Ufjo6ZX7gCqJr5F7PKrqc93v7fzSymt1BpwEU8nAUXs8qzzvqhbjhK5QZg6Mt/HkBg==", - "license": "MIT" + "node_modules/lightningcss-android-arm64": { + "version": "1.32.0", + "resolved": "https://registry.npmjs.org/lightningcss-android-arm64/-/lightningcss-android-arm64-1.32.0.tgz", + "integrity": "sha512-YK7/ClTt4kAK0vo6w3X+Pnm0D2cf2vPHbhOXdoNti1Ga0al1P4TBZhwjATvjNwLEBCnKvjJc2jQgHXH0NEwlAg==", + "cpu": [ + "arm64" + ], + "dev": true, + "license": "MPL-2.0", + "optional": true, + "os": [ + "android" + ], + "engines": { + "node": ">= 12.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/parcel" + } + }, + "node_modules/lightningcss-darwin-arm64": { + "version": "1.32.0", + "resolved": "https://registry.npmjs.org/lightningcss-darwin-arm64/-/lightningcss-darwin-arm64-1.32.0.tgz", + "integrity": "sha512-RzeG9Ju5bag2Bv1/lwlVJvBE3q6TtXskdZLLCyfg5pt+HLz9BqlICO7LZM7VHNTTn/5PRhHFBSjk5lc4cmscPQ==", + "cpu": [ + "arm64" + ], + "dev": true, + "license": "MPL-2.0", + "optional": true, + "os": [ + "darwin" + ], + "engines": { + "node": ">= 12.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/parcel" + } + }, + "node_modules/lightningcss-darwin-x64": { + "version": "1.32.0", + "resolved": "https://registry.npmjs.org/lightningcss-darwin-x64/-/lightningcss-darwin-x64-1.32.0.tgz", + "integrity": "sha512-U+QsBp2m/s2wqpUYT/6wnlagdZbtZdndSmut/NJqlCcMLTWp5muCrID+K5UJ6jqD2BFshejCYXniPDbNh73V8w==", + "cpu": [ + "x64" + ], + "dev": true, + "license": "MPL-2.0", + "optional": true, + "os": [ + "darwin" + ], + "engines": { + "node": ">= 12.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/parcel" + } + }, + "node_modules/lightningcss-freebsd-x64": { + "version": "1.32.0", + "resolved": "https://registry.npmjs.org/lightningcss-freebsd-x64/-/lightningcss-freebsd-x64-1.32.0.tgz", + "integrity": "sha512-JCTigedEksZk3tHTTthnMdVfGf61Fky8Ji2E4YjUTEQX14xiy/lTzXnu1vwiZe3bYe0q+SpsSH/CTeDXK6WHig==", + "cpu": [ + "x64" + ], + "dev": true, + "license": "MPL-2.0", + "optional": true, + "os": [ + "freebsd" + ], + "engines": { + "node": ">= 12.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/parcel" + } + }, + "node_modules/lightningcss-linux-arm-gnueabihf": { + "version": "1.32.0", + "resolved": "https://registry.npmjs.org/lightningcss-linux-arm-gnueabihf/-/lightningcss-linux-arm-gnueabihf-1.32.0.tgz", + "integrity": "sha512-x6rnnpRa2GL0zQOkt6rts3YDPzduLpWvwAF6EMhXFVZXD4tPrBkEFqzGowzCsIWsPjqSK+tyNEODUBXeeVHSkw==", + "cpu": [ + "arm" + ], + "dev": true, + "license": "MPL-2.0", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">= 12.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/parcel" + } + }, + "node_modules/lightningcss-linux-arm64-gnu": { + "version": "1.32.0", + "resolved": "https://registry.npmjs.org/lightningcss-linux-arm64-gnu/-/lightningcss-linux-arm64-gnu-1.32.0.tgz", + "integrity": "sha512-0nnMyoyOLRJXfbMOilaSRcLH3Jw5z9HDNGfT/gwCPgaDjnx0i8w7vBzFLFR1f6CMLKF8gVbebmkUN3fa/kQJpQ==", + "cpu": [ + "arm64" + ], + "dev": true, + "license": "MPL-2.0", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">= 12.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/parcel" + } + }, + "node_modules/lightningcss-linux-arm64-musl": { + "version": "1.32.0", + "resolved": "https://registry.npmjs.org/lightningcss-linux-arm64-musl/-/lightningcss-linux-arm64-musl-1.32.0.tgz", + "integrity": "sha512-UpQkoenr4UJEzgVIYpI80lDFvRmPVg6oqboNHfoH4CQIfNA+HOrZ7Mo7KZP02dC6LjghPQJeBsvXhJod/wnIBg==", + "cpu": [ + "arm64" + ], + "dev": true, + "license": "MPL-2.0", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">= 12.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/parcel" + } + }, + "node_modules/lightningcss-linux-x64-gnu": { + "version": "1.32.0", + "resolved": "https://registry.npmjs.org/lightningcss-linux-x64-gnu/-/lightningcss-linux-x64-gnu-1.32.0.tgz", + "integrity": "sha512-V7Qr52IhZmdKPVr+Vtw8o+WLsQJYCTd8loIfpDaMRWGUZfBOYEJeyJIkqGIDMZPwPx24pUMfwSxxI8phr/MbOA==", + "cpu": [ + "x64" + ], + "dev": true, + "license": "MPL-2.0", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">= 12.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/parcel" + } + }, + "node_modules/lightningcss-linux-x64-musl": { + "version": "1.32.0", + "resolved": "https://registry.npmjs.org/lightningcss-linux-x64-musl/-/lightningcss-linux-x64-musl-1.32.0.tgz", + "integrity": "sha512-bYcLp+Vb0awsiXg/80uCRezCYHNg1/l3mt0gzHnWV9XP1W5sKa5/TCdGWaR/zBM2PeF/HbsQv/j2URNOiVuxWg==", + "cpu": [ + "x64" + ], + "dev": true, + "license": "MPL-2.0", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">= 12.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/parcel" + } + }, + "node_modules/lightningcss-win32-arm64-msvc": { + "version": "1.32.0", + "resolved": "https://registry.npmjs.org/lightningcss-win32-arm64-msvc/-/lightningcss-win32-arm64-msvc-1.32.0.tgz", + "integrity": "sha512-8SbC8BR40pS6baCM8sbtYDSwEVQd4JlFTOlaD3gWGHfThTcABnNDBda6eTZeqbofalIJhFx0qKzgHJmcPTnGdw==", + "cpu": [ + "arm64" + ], + "dev": true, + "license": "MPL-2.0", + "optional": true, + "os": [ + "win32" + ], + "engines": { + "node": ">= 12.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/parcel" + } + }, + "node_modules/lightningcss-win32-x64-msvc": { + "version": "1.32.0", + "resolved": "https://registry.npmjs.org/lightningcss-win32-x64-msvc/-/lightningcss-win32-x64-msvc-1.32.0.tgz", + "integrity": "sha512-Amq9B/SoZYdDi1kFrojnoqPLxYhQ4Wo5XiL8EVJrVsB8ARoC1PWW6VGtT0WKCemjy8aC+louJnjS7U18x3b06Q==", + "cpu": [ + "x64" + ], + "dev": true, + "license": "MPL-2.0", + "optional": true, + "os": [ + "win32" + ], + "engines": { + "node": ">= 12.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/parcel" + } }, "node_modules/locate-path": { "version": "6.0.0", @@ -8774,6 +10661,7 @@ "version": "1.4.1", "resolved": "https://registry.npmjs.org/merge2/-/merge2-1.4.1.tgz", "integrity": "sha512-8q7VEgMJW4J8tcfVPy8g09NcQwZdbwFEqhe/WZkoIzjn/3TGDwtOCYtXGxA3O8tPzpczCCDgv+P2P5y00ZJOOg==", + "dev": true, "license": "MIT", "engines": { "node": ">= 8" @@ -9225,6 +11113,7 @@ "version": "4.0.8", "resolved": "https://registry.npmjs.org/micromatch/-/micromatch-4.0.8.tgz", "integrity": "sha512-PXwfBhYu0hBCPw8Dn0E+WDYb7af3dSLVWKi3HGv84IdF4TyFoC0ysxFd0Goxw7nSv4T/PzEJQxsYsEiFCKo2BA==", + "dev": true, "license": "MIT", "dependencies": { "braces": "^3.0.3", @@ -9238,6 +11127,7 @@ "version": "2.3.2", "resolved": "https://registry.npmjs.org/picomatch/-/picomatch-2.3.2.tgz", "integrity": "sha512-V7+vQEJ06Z+c5tSye8S+nHUfI51xoXIXjHQ99cQtKUkQqqO1kO/KCJUfZXuB47h/YBlDhah2H3hdUGXn8ie0oA==", + "dev": true, "license": "MIT", "engines": { "node": ">=8.6" @@ -9348,17 +11238,6 @@ "integrity": "sha512-6FlzubTLZG3J2a/NVCAleEhjzq5oxgHyaCU9yYXvcLsvoVaHJq/s5xXI6/XXP6tz7R9xAOtHnSO/tXtF3WRTlA==", "license": "MIT" }, - "node_modules/mz": { - "version": "2.7.0", - "resolved": "https://registry.npmjs.org/mz/-/mz-2.7.0.tgz", - "integrity": "sha512-z81GNO7nnYMEhrGh9LeymoE4+Yr0Wn5McHIZMK5cfQCl+NDX08sCZgUc9/6MHni9IWuFLm1Z3HTCXu2z9fN62Q==", - "license": "MIT", - "dependencies": { - "any-promise": "^1.0.0", - "object-assign": "^4.0.1", - "thenify-all": "^1.0.0" - } - }, "node_modules/nanoid": { "version": "3.3.12", "resolved": "https://registry.npmjs.org/nanoid/-/nanoid-3.3.12.tgz", @@ -9560,15 +11439,6 @@ "dev": true, "license": "MIT" }, - "node_modules/normalize-path": { - "version": "3.0.0", - "resolved": "https://registry.npmjs.org/normalize-path/-/normalize-path-3.0.0.tgz", - "integrity": "sha512-6eZs5Ls3WtCisHWp9S2GUy8dqkpGi4BVSz3GaqiE6ezub0512ESztXUwUB6C6IKbQkY2Pnb/mD4WYojCRwcwLA==", - "license": "MIT", - "engines": { - "node": ">=0.10.0" - } - }, "node_modules/object-assign": { "version": "4.1.1", "resolved": "https://registry.npmjs.org/object-assign/-/object-assign-4.1.1.tgz", @@ -9578,15 +11448,6 @@ "node": ">=0.10.0" } }, - "node_modules/object-hash": { - "version": "3.0.0", - "resolved": "https://registry.npmjs.org/object-hash/-/object-hash-3.0.0.tgz", - "integrity": "sha512-RSn9F68PjH9HqtltsSnqYC1XXoWe9Bju5+213R98cNGttag9q9yAOTzdbsqvIa7aNm5WffBZFpWYr2aWrklWAw==", - "license": "MIT", - "engines": { - "node": ">= 6" - } - }, "node_modules/object-inspect": { "version": "1.13.4", "resolved": "https://registry.npmjs.org/object-inspect/-/object-inspect-1.13.4.tgz", @@ -9978,6 +11839,7 @@ "version": "1.0.7", "resolved": "https://registry.npmjs.org/path-parse/-/path-parse-1.0.7.tgz", "integrity": "sha512-LDJzPVEEEPR+y48z93A0Ed0yXb8pAByGWo/k5YYdYgpY2/2EsOsksJrq7lOHxryrVOn1ejG6oAp8ahvOIQD8sw==", + "dev": true, "license": "MIT" }, "node_modules/path-scurry": { @@ -10024,6 +11886,7 @@ "version": "4.0.4", "resolved": "https://registry.npmjs.org/picomatch/-/picomatch-4.0.4.tgz", "integrity": "sha512-QP88BAKvMam/3NxH6vj2o21R6MjxZUAd6nlwAS/pnGvN9IVLocLHxGYIzFhg6fUQ+5th6P4dv4eW9jX3DSIj7A==", + "dev": true, "license": "MIT", "engines": { "node": ">=12" @@ -10032,24 +11895,6 @@ "url": "https://github.com/sponsors/jonschlinkert" } }, - "node_modules/pify": { - "version": "2.3.0", - "resolved": "https://registry.npmjs.org/pify/-/pify-2.3.0.tgz", - "integrity": "sha512-udgsAY+fTnvv7kI7aaxbqwWNb0AHiB0qBO89PZKPkoTmGOgdbrHDKD+0B2X4uTfJ/FT1R09r9gTsjUjNJotuog==", - "license": "MIT", - "engines": { - "node": ">=0.10.0" - } - }, - "node_modules/pirates": { - "version": "4.0.7", - "resolved": "https://registry.npmjs.org/pirates/-/pirates-4.0.7.tgz", - "integrity": "sha512-TfySrs/5nm8fQJDcBDuUng3VOUKsd7S+zqvbOTiGXHfxX4wK31ard+hoNuvkicM/2YFzlpDgABOevKSsB4G/FA==", - "license": "MIT", - "engines": { - "node": ">= 6" - } - }, "node_modules/playwright": { "version": "1.58.1", "resolved": "https://registry.npmjs.org/playwright/-/playwright-1.58.1.tgz", @@ -10130,155 +11975,6 @@ "node": "^10 || ^12 || >=14" } }, - "node_modules/postcss-import": { - "version": "15.1.0", - "resolved": "https://registry.npmjs.org/postcss-import/-/postcss-import-15.1.0.tgz", - "integrity": "sha512-hpr+J05B2FVYUAXHeK1YyI267J/dDDhMU6B6civm8hSY1jYJnBXxzKDKDswzJmtLHryrjhnDjqqp/49t8FALew==", - "license": "MIT", - "dependencies": { - "postcss-value-parser": "^4.0.0", - "read-cache": "^1.0.0", - "resolve": "^1.1.7" - }, - "engines": { - "node": ">=14.0.0" - }, - "peerDependencies": { - "postcss": "^8.0.0" - } - }, - "node_modules/postcss-import/node_modules/resolve": { - "version": "1.22.12", - "resolved": "https://registry.npmjs.org/resolve/-/resolve-1.22.12.tgz", - "integrity": "sha512-TyeJ1zif53BPfHootBGwPRYT1RUt6oGWsaQr8UyZW/eAm9bKoijtvruSDEmZHm92CwS9nj7/fWttqPCgzep8CA==", - "license": "MIT", - "dependencies": { - "es-errors": "^1.3.0", - "is-core-module": "^2.16.1", - "path-parse": "^1.0.7", - "supports-preserve-symlinks-flag": "^1.0.0" - }, - "bin": { - "resolve": "bin/resolve" - }, - "engines": { - "node": ">= 0.4" - }, - "funding": { - "url": "https://github.com/sponsors/ljharb" - } - }, - "node_modules/postcss-js": { - "version": "4.1.0", - "resolved": "https://registry.npmjs.org/postcss-js/-/postcss-js-4.1.0.tgz", - "integrity": "sha512-oIAOTqgIo7q2EOwbhb8UalYePMvYoIeRY2YKntdpFQXNosSu3vLrniGgmH9OKs/qAkfoj5oB3le/7mINW1LCfw==", - "funding": [ - { - "type": "opencollective", - "url": "https://opencollective.com/postcss/" - }, - { - "type": "github", - "url": "https://github.com/sponsors/ai" - } - ], - "license": "MIT", - "dependencies": { - "camelcase-css": "^2.0.1" - }, - "engines": { - "node": "^12 || ^14 || >= 16" - }, - "peerDependencies": { - "postcss": "^8.4.21" - } - }, - "node_modules/postcss-load-config": { - "version": "6.0.1", - "resolved": "https://registry.npmjs.org/postcss-load-config/-/postcss-load-config-6.0.1.tgz", - "integrity": "sha512-oPtTM4oerL+UXmx+93ytZVN82RrlY/wPUV8IeDxFrzIjXOLF1pN+EmKPLbubvKHT2HC20xXsCAH2Z+CKV6Oz/g==", - "funding": [ - { - "type": "opencollective", - "url": "https://opencollective.com/postcss/" - }, - { - "type": "github", - "url": "https://github.com/sponsors/ai" - } - ], - "license": "MIT", - "dependencies": { - "lilconfig": "^3.1.1" - }, - "engines": { - "node": ">= 18" - }, - "peerDependencies": { - "jiti": ">=1.21.0", - "postcss": ">=8.0.9", - "tsx": "^4.8.1", - "yaml": "^2.4.2" - }, - "peerDependenciesMeta": { - "jiti": { - "optional": true - }, - "postcss": { - "optional": true - }, - "tsx": { - "optional": true - }, - "yaml": { - "optional": true - } - } - }, - "node_modules/postcss-nested": { - "version": "6.2.0", - "resolved": "https://registry.npmjs.org/postcss-nested/-/postcss-nested-6.2.0.tgz", - "integrity": "sha512-HQbt28KulC5AJzG+cZtj9kvKB93CFCdLvog1WFLf1D+xmMvPGlBstkpTEZfK5+AN9hfJocyBFCNiqyS48bpgzQ==", - "funding": [ - { - "type": "opencollective", - "url": "https://opencollective.com/postcss/" - }, - { - "type": "github", - "url": "https://github.com/sponsors/ai" - } - ], - "license": "MIT", - "dependencies": { - "postcss-selector-parser": "^6.1.1" - }, - "engines": { - "node": ">=12.0" - }, - "peerDependencies": { - "postcss": "^8.2.14" - } - }, - "node_modules/postcss-selector-parser": { - "version": "6.1.2", - "resolved": "https://registry.npmjs.org/postcss-selector-parser/-/postcss-selector-parser-6.1.2.tgz", - "integrity": "sha512-Q8qQfPiZ+THO/3ZrOrO0cJJKfpYCagtMUkXbnEfmgUjwXg6z/WBeOyS9APBBPCTSiDV+s4SwQGu8yFsiMRIudg==", - "license": "MIT", - "dependencies": { - "cssesc": "^3.0.0", - "util-deprecate": "^1.0.2" - }, - "engines": { - "node": ">=4" - } - }, - "node_modules/postcss-value-parser": { - "version": "4.2.0", - "resolved": "https://registry.npmjs.org/postcss-value-parser/-/postcss-value-parser-4.2.0.tgz", - "integrity": "sha512-1NNCs6uurfkVbeXG4S8JFT9t19m45ICnif8zWLd5oPSZ50QnwMfK+H3jv408d4jw/7Bttv5axS5IiHoLaVNHeQ==", - "license": "MIT" - }, "node_modules/prelude-ls": { "version": "1.2.1", "resolved": "https://registry.npmjs.org/prelude-ls/-/prelude-ls-1.2.1.tgz", @@ -10383,6 +12079,7 @@ "version": "1.2.3", "resolved": "https://registry.npmjs.org/queue-microtask/-/queue-microtask-1.2.3.tgz", "integrity": "sha512-NuaNSa6flKT5JaSYQzJok04JzTL1CA6aGhv5rfLW3PgqA+M2ChpZQnAC8h8i4ZFkBS8X5RqkDBHA7r4hej3K9A==", + "dev": true, "funding": [ { "type": "github", @@ -10399,6 +12096,83 @@ ], "license": "MIT" }, + "node_modules/radix-ui": { + "version": "1.6.1", + "resolved": "https://registry.npmjs.org/radix-ui/-/radix-ui-1.6.1.tgz", + "integrity": "sha512-QXDXJtB6sK83mLASONYUZCauatcWb+knFviFpN1EhtdbbmlsRmzCLrbZSKztnNiem2KOHIBbiDbauVB7SORXMw==", + "license": "MIT", + "dependencies": { + "@radix-ui/primitive": "1.1.4", + "@radix-ui/react-accessible-icon": "1.1.11", + "@radix-ui/react-accordion": "1.2.15", + "@radix-ui/react-alert-dialog": "1.1.18", + "@radix-ui/react-arrow": "1.1.11", + "@radix-ui/react-aspect-ratio": "1.1.11", + "@radix-ui/react-avatar": "1.2.1", + "@radix-ui/react-checkbox": "1.3.6", + "@radix-ui/react-collapsible": "1.1.15", + "@radix-ui/react-collection": "1.1.11", + "@radix-ui/react-compose-refs": "1.1.3", + "@radix-ui/react-context": "1.1.4", + "@radix-ui/react-context-menu": "2.3.2", + "@radix-ui/react-dialog": "1.1.18", + "@radix-ui/react-direction": "1.1.2", + "@radix-ui/react-dismissable-layer": "1.1.14", + "@radix-ui/react-dropdown-menu": "2.1.19", + "@radix-ui/react-focus-guards": "1.1.4", + "@radix-ui/react-focus-scope": "1.1.11", + "@radix-ui/react-form": "0.1.11", + "@radix-ui/react-hover-card": "1.1.18", + "@radix-ui/react-label": "2.1.11", + "@radix-ui/react-menu": "2.1.19", + "@radix-ui/react-menubar": "1.1.19", + "@radix-ui/react-navigation-menu": "1.2.17", + "@radix-ui/react-one-time-password-field": "0.1.11", + "@radix-ui/react-password-toggle-field": "0.1.6", + "@radix-ui/react-popover": "1.1.18", + "@radix-ui/react-popper": "1.3.2", + "@radix-ui/react-portal": "1.1.13", + "@radix-ui/react-presence": "1.1.6", + "@radix-ui/react-primitive": "2.1.7", + "@radix-ui/react-progress": "1.1.11", + "@radix-ui/react-radio-group": "1.4.2", + "@radix-ui/react-roving-focus": "1.1.14", + "@radix-ui/react-scroll-area": "1.2.13", + "@radix-ui/react-select": "2.3.2", + "@radix-ui/react-separator": "1.1.11", + "@radix-ui/react-slider": "1.4.2", + "@radix-ui/react-slot": "1.3.0", + "@radix-ui/react-switch": "1.3.2", + "@radix-ui/react-tabs": "1.1.16", + "@radix-ui/react-toast": "1.2.18", + "@radix-ui/react-toggle": "1.1.13", + "@radix-ui/react-toggle-group": "1.1.14", + "@radix-ui/react-toolbar": "1.1.14", + "@radix-ui/react-tooltip": "1.2.11", + "@radix-ui/react-use-callback-ref": "1.1.2", + "@radix-ui/react-use-controllable-state": "1.2.3", + "@radix-ui/react-use-effect-event": "0.0.3", + "@radix-ui/react-use-escape-keydown": "1.1.3", + "@radix-ui/react-use-is-hydrated": "0.1.1", + "@radix-ui/react-use-layout-effect": "1.1.2", + "@radix-ui/react-use-size": "1.1.2", + "@radix-ui/react-visually-hidden": "1.2.7" + }, + "peerDependencies": { + "@types/react": "*", + "@types/react-dom": "*", + "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", + "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } + } + }, "node_modules/rc-cascader": { "version": "3.34.0", "resolved": "https://registry.npmjs.org/rc-cascader/-/rc-cascader-3.34.0.tgz", @@ -11130,6 +12904,53 @@ "react": ">=18" } }, + "node_modules/react-remove-scroll": { + "version": "2.7.2", + "resolved": "https://registry.npmjs.org/react-remove-scroll/-/react-remove-scroll-2.7.2.tgz", + "integrity": "sha512-Iqb9NjCCTt6Hf+vOdNIZGdTiH1QSqr27H/Ek9sv/a97gfueI/5h1s3yRi1nngzMUaOOToin5dI1dXKdXiF+u0Q==", + "license": "MIT", + "dependencies": { + "react-remove-scroll-bar": "^2.3.7", + "react-style-singleton": "^2.2.3", + "tslib": "^2.1.0", + "use-callback-ref": "^1.3.3", + "use-sidecar": "^1.1.3" + }, + "engines": { + "node": ">=10" + }, + "peerDependencies": { + "@types/react": "*", + "react": "^16.8.0 || ^17.0.0 || ^18.0.0 || ^19.0.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + } + } + }, + "node_modules/react-remove-scroll-bar": { + "version": "2.3.8", + "resolved": "https://registry.npmjs.org/react-remove-scroll-bar/-/react-remove-scroll-bar-2.3.8.tgz", + "integrity": "sha512-9r+yi9+mgU33AKcj6IbT9oRCO78WriSj6t/cF8DWBZJ9aOGPOTEDvdUDz1FwKim7QXWwmHqtdHnRJfhAxEG46Q==", + "license": "MIT", + "dependencies": { + "react-style-singleton": "^2.2.2", + "tslib": "^2.0.0" + }, + "engines": { + "node": ">=10" + }, + "peerDependencies": { + "@types/react": "*", + "react": "^16.8.0 || ^17.0.0 || ^18.0.0 || ^19.0.0" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + } + } + }, "node_modules/react-smooth": { "version": "4.0.4", "resolved": "https://registry.npmjs.org/react-smooth/-/react-smooth-4.0.4.tgz", @@ -11162,6 +12983,28 @@ "react": "^16.8.0 || ^17.0.0-rc.1 || ^18.0.0 || ^19.0.0-rc.1" } }, + "node_modules/react-style-singleton": { + "version": "2.2.3", + "resolved": "https://registry.npmjs.org/react-style-singleton/-/react-style-singleton-2.2.3.tgz", + "integrity": "sha512-b6jSvxvVnyptAiLjbkWLE/lOnR4lfTtDAl+eUC7RZy+QQWc6wRzIV2CE6xBuMmDxc2qIihtDCZD5NPOFl7fRBQ==", + "license": "MIT", + "dependencies": { + "get-nonce": "^1.0.0", + "tslib": "^2.0.0" + }, + "engines": { + "node": ">=10" + }, + "peerDependencies": { + "@types/react": "*", + "react": "^16.8.0 || ^17.0.0 || ^18.0.0 || ^19.0.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + } + } + }, "node_modules/react-syntax-highlighter": { "version": "15.6.6", "resolved": "https://registry.npmjs.org/react-syntax-highlighter/-/react-syntax-highlighter-15.6.6.tgz", @@ -11205,39 +13048,6 @@ "react-dom": ">=16.8.0" } }, - "node_modules/read-cache": { - "version": "1.0.0", - "resolved": "https://registry.npmjs.org/read-cache/-/read-cache-1.0.0.tgz", - "integrity": "sha512-Owdv/Ft7IjOgm/i0xvNDZ1LrRANRfew4b2prF3OWMQLxLfu3bS8FVhCsrSCMK4lR56Y9ya+AThoTpDCTxCmpRA==", - "license": "MIT", - "dependencies": { - "pify": "^2.3.0" - } - }, - "node_modules/readdirp": { - "version": "3.6.0", - "resolved": "https://registry.npmjs.org/readdirp/-/readdirp-3.6.0.tgz", - "integrity": "sha512-hOS089on8RduqdbhvQ5Z37A0ESjsqz6qnRcffsMU3495FuTdqSm+7bhJ29JvIOsBDEEnan5DPu9t3To9VRlMzA==", - "license": "MIT", - "dependencies": { - "picomatch": "^2.2.1" - }, - "engines": { - "node": ">=8.10.0" - } - }, - "node_modules/readdirp/node_modules/picomatch": { - "version": "2.3.2", - "resolved": "https://registry.npmjs.org/picomatch/-/picomatch-2.3.2.tgz", - "integrity": "sha512-V7+vQEJ06Z+c5tSye8S+nHUfI51xoXIXjHQ99cQtKUkQqqO1kO/KCJUfZXuB47h/YBlDhah2H3hdUGXn8ie0oA==", - "license": "MIT", - "engines": { - "node": ">=8.6" - }, - "funding": { - "url": "https://github.com/sponsors/jonschlinkert" - } - }, "node_modules/recharts": { "version": "2.15.4", "resolved": "https://registry.npmjs.org/recharts/-/recharts-2.15.4.tgz", @@ -11538,6 +13348,7 @@ "version": "1.1.0", "resolved": "https://registry.npmjs.org/reusify/-/reusify-1.1.0.tgz", "integrity": "sha512-g6QUff04oZpHs0eG5p83rFLhHeV00ug/Yf9nZM6fLeUrPguBTkTQOdpAWWspMh55TZfVQDPaN3NQJfbVRAxdIw==", + "dev": true, "license": "MIT", "engines": { "iojs": ">=1.0.0", @@ -11593,6 +13404,7 @@ "version": "1.2.0", "resolved": "https://registry.npmjs.org/run-parallel/-/run-parallel-1.2.0.tgz", "integrity": "sha512-5l4VyZR86LZ/lDxZTR6jqL8AFE2S0IFLMP26AbjsLVADxHdhB/c0GUsH+y39UfCi3dzz8OlQuPmnaJOMoDHQBA==", + "dev": true, "funding": [ { "type": "github", @@ -12229,28 +14041,6 @@ "integrity": "sha512-5Z9ZpRzfuH6l/UAvCPAPUo3665Nk2wLaZU3x+TLHKVzIz33+sbJqbtrYoC3KD4/uVOr2Zp+L0LySezP9OHV9yA==", "license": "MIT" }, - "node_modules/sucrase": { - "version": "3.35.1", - "resolved": "https://registry.npmjs.org/sucrase/-/sucrase-3.35.1.tgz", - "integrity": "sha512-DhuTmvZWux4H1UOnWMB3sk0sbaCVOoQZjv8u1rDoTV0HTdGem9hkAZtl4JZy8P2z4Bg0nT+YMeOFyVr4zcG5Tw==", - "license": "MIT", - "dependencies": { - "@jridgewell/gen-mapping": "^0.3.2", - "commander": "^4.0.0", - "lines-and-columns": "^1.1.6", - "mz": "^2.7.0", - "pirates": "^4.0.1", - "tinyglobby": "^0.2.11", - "ts-interface-checker": "^0.1.9" - }, - "bin": { - "sucrase": "bin/sucrase", - "sucrase-node": "bin/sucrase-node" - }, - "engines": { - "node": ">=16 || 14 >=14.17" - } - }, "node_modules/supports-color": { "version": "7.2.0", "resolved": "https://registry.npmjs.org/supports-color/-/supports-color-7.2.0.tgz", @@ -12268,6 +14058,7 @@ "version": "1.0.0", "resolved": "https://registry.npmjs.org/supports-preserve-symlinks-flag/-/supports-preserve-symlinks-flag-1.0.0.tgz", "integrity": "sha512-ot0WnXS9fgdkgIcePe6RHNk1WA8+muPa6cSjeR3V8K27q9BB1rTE3R1p7Hv0z1ZyAc8s6Vvv8DIyWf681MAt0w==", + "dev": true, "license": "MIT", "engines": { "node": ">= 0.4" @@ -12300,98 +14091,23 @@ } }, "node_modules/tailwindcss": { - "version": "3.4.19", - "resolved": "https://registry.npmjs.org/tailwindcss/-/tailwindcss-3.4.19.tgz", - "integrity": "sha512-3ofp+LL8E+pK/JuPLPggVAIaEuhvIz4qNcf3nA1Xn2o/7fb7s/TYpHhwGDv1ZU3PkBluUVaF8PyCHcm48cKLWQ==", - "license": "MIT", - "dependencies": { - "@alloc/quick-lru": "^5.2.0", - "arg": "^5.0.2", - "chokidar": "^3.6.0", - "didyoumean": "^1.2.2", - "dlv": "^1.1.3", - "fast-glob": "^3.3.2", - "glob-parent": "^6.0.2", - "is-glob": "^4.0.3", - "jiti": "^1.21.7", - "lilconfig": "^3.1.3", - "micromatch": "^4.0.8", - "normalize-path": "^3.0.0", - "object-hash": "^3.0.0", - "picocolors": "^1.1.1", - "postcss": "^8.4.47", - "postcss-import": "^15.1.0", - "postcss-js": "^4.0.1", - "postcss-load-config": "^4.0.2 || ^5.0 || ^6.0", - "postcss-nested": "^6.2.0", - "postcss-selector-parser": "^6.1.2", - "resolve": "^1.22.8", - "sucrase": "^3.35.0" - }, - "bin": { - "tailwind": "lib/cli.js", - "tailwindcss": "lib/cli.js" - }, - "engines": { - "node": ">=14.0.0" - } + "version": "4.3.2", + "resolved": "https://registry.npmjs.org/tailwindcss/-/tailwindcss-4.3.2.tgz", + "integrity": "sha512-WtctNNSH8A9jlMIqxzuYumOHU5uGZyRv0Q5svQl+oEPy5w84YpBxdb7MdqyiSPQge5jTJ6zFQLq0PFygdccSBA==", + "license": "MIT" }, - "node_modules/tailwindcss/node_modules/fast-glob": { - "version": "3.3.3", - "resolved": "https://registry.npmjs.org/fast-glob/-/fast-glob-3.3.3.tgz", - "integrity": "sha512-7MptL8U0cqcFdzIzwOTHoilX9x5BrNqye7Z/LuC7kCMRio1EMSyqRK3BEAUD7sXRq4iT4AzTVuZdhgQ2TCvYLg==", + "node_modules/tapable": { + "version": "2.3.3", + "resolved": "https://registry.npmjs.org/tapable/-/tapable-2.3.3.tgz", + "integrity": "sha512-uxc/zpqFg6x7C8vOE7lh6Lbda8eEL9zmVm/PLeTPBRhh1xCgdWaQ+J1CUieGpIfm2HdtsUpRv+HshiasBMcc6A==", + "dev": true, "license": "MIT", - "dependencies": { - "@nodelib/fs.stat": "^2.0.2", - "@nodelib/fs.walk": "^1.2.3", - "glob-parent": "^5.1.2", - "merge2": "^1.3.0", - "micromatch": "^4.0.8" - }, "engines": { - "node": ">=8.6.0" - } - }, - "node_modules/tailwindcss/node_modules/fast-glob/node_modules/glob-parent": { - "version": "5.1.2", - "resolved": "https://registry.npmjs.org/glob-parent/-/glob-parent-5.1.2.tgz", - "integrity": "sha512-AOIgSQCepiJYwP3ARnGx+5VnTu2HBYdzbGP45eLw1vr3zB3vZLeyed1sC9hnbcOc9/SrMyM5RPQrkGz4aS9Zow==", - "license": "ISC", - "dependencies": { - "is-glob": "^4.0.1" - }, - "engines": { - "node": ">= 6" - } - }, - "node_modules/tailwindcss/node_modules/jiti": { - "version": "1.21.7", - "resolved": "https://registry.npmjs.org/jiti/-/jiti-1.21.7.tgz", - "integrity": "sha512-/imKNG4EbWNrVjoNC/1H5/9GFy+tqjGBHCaSsN+P2RnPqjsLmv6UD3Ej+Kj8nBWaRAwyk7kK5ZUc+OEatnTR3A==", - "license": "MIT", - "bin": { - "jiti": "bin/jiti.js" - } - }, - "node_modules/tailwindcss/node_modules/resolve": { - "version": "1.22.12", - "resolved": "https://registry.npmjs.org/resolve/-/resolve-1.22.12.tgz", - "integrity": "sha512-TyeJ1zif53BPfHootBGwPRYT1RUt6oGWsaQr8UyZW/eAm9bKoijtvruSDEmZHm92CwS9nj7/fWttqPCgzep8CA==", - "license": "MIT", - "dependencies": { - "es-errors": "^1.3.0", - "is-core-module": "^2.16.1", - "path-parse": "^1.0.7", - "supports-preserve-symlinks-flag": "^1.0.0" - }, - "bin": { - "resolve": "bin/resolve" - }, - "engines": { - "node": ">= 0.4" + "node": ">=6" }, "funding": { - "url": "https://github.com/sponsors/ljharb" + "type": "opencollective", + "url": "https://opencollective.com/webpack" } }, "node_modules/test-exclude": { @@ -12409,27 +14125,6 @@ "node": ">=18" } }, - "node_modules/thenify": { - "version": "3.3.1", - "resolved": "https://registry.npmjs.org/thenify/-/thenify-3.3.1.tgz", - "integrity": "sha512-RVZSIV5IG10Hk3enotrhvz0T9em6cyHBLkH/YAZuKqd8hRkKhSfCGIcP2KUY0EPxndzANBmNllzWPwak+bheSw==", - "license": "MIT", - "dependencies": { - "any-promise": "^1.0.0" - } - }, - "node_modules/thenify-all": { - "version": "1.6.0", - "resolved": "https://registry.npmjs.org/thenify-all/-/thenify-all-1.6.0.tgz", - "integrity": "sha512-RNxQH/qI8/t3thXJDwcstUO4zeqo64+Uy/+sNVRBx4Xn2OX+OZ9oP+iJnNFqplFra2ZUVeKCSa2oVWi3T4uVmA==", - "license": "MIT", - "dependencies": { - "thenify": ">= 3.1.0 < 4" - }, - "engines": { - "node": ">=0.8" - } - }, "node_modules/throttle-debounce": { "version": "5.0.2", "resolved": "https://registry.npmjs.org/throttle-debounce/-/throttle-debounce-5.0.2.tgz", @@ -12463,6 +14158,7 @@ "version": "0.2.16", "resolved": "https://registry.npmjs.org/tinyglobby/-/tinyglobby-0.2.16.tgz", "integrity": "sha512-pn99VhoACYR8nFHhxqix+uvsbXineAasWm5ojXoN8xEwK5Kd3/TrhNn1wByuD52UxWRLy8pu+kRMniEi6Eq9Zg==", + "dev": true, "license": "MIT", "dependencies": { "fdir": "^6.5.0", @@ -12529,6 +14225,7 @@ "version": "5.0.1", "resolved": "https://registry.npmjs.org/to-regex-range/-/to-regex-range-5.0.1.tgz", "integrity": "sha512-65P7iz6X5yEr1cwcgvQxbbIw7Uk3gOy5dIdtZ4rDveLqhrdJP+Li/Hx6tyK0NEb+2GCyneCMJiGqrADCSNk8sQ==", + "dev": true, "license": "MIT", "dependencies": { "is-number": "^7.0.0" @@ -12618,12 +14315,6 @@ "typescript": ">=4.8.4" } }, - "node_modules/ts-interface-checker": { - "version": "0.1.13", - "resolved": "https://registry.npmjs.org/ts-interface-checker/-/ts-interface-checker-0.1.13.tgz", - "integrity": "sha512-Y/arvbn+rrz3JCKl9C4kVNfTfSm2/mEp5FSz5EsZSANGPSlQrpRI5M4PKF+mJnE52jOO90PnPSc3Ur3bTQw0gA==", - "license": "Apache-2.0" - }, "node_modules/tsconfig-paths": { "version": "3.15.0", "resolved": "https://registry.npmjs.org/tsconfig-paths/-/tsconfig-paths-3.15.0.tgz", @@ -12643,6 +14334,16 @@ "integrity": "sha512-oJFu94HQb+KVduSUQL7wnpmqnfmLsOA/nAh6b6EH0wCEoK0/mPeXU6c3wKDV83MkOuHPRHtSXKKU99IBazS/2w==", "license": "0BSD" }, + "node_modules/tw-animate-css": { + "version": "1.4.0", + "resolved": "https://registry.npmjs.org/tw-animate-css/-/tw-animate-css-1.4.0.tgz", + "integrity": "sha512-7bziOlRqH0hJx80h/3mbicLW7o8qLsH5+RaLR2t+OHM3D0JlWGODQKQ4cxbK7WlvmUxpcj6Kgu6EKqjrGFe3QQ==", + "dev": true, + "license": "MIT", + "funding": { + "url": "https://github.com/sponsors/Wombosvideo" + } + }, "node_modules/type-check": { "version": "0.4.0", "resolved": "https://registry.npmjs.org/type-check/-/type-check-0.4.0.tgz", @@ -12980,6 +14681,49 @@ "dev": true, "license": "MIT" }, + "node_modules/use-callback-ref": { + "version": "1.3.3", + "resolved": "https://registry.npmjs.org/use-callback-ref/-/use-callback-ref-1.3.3.tgz", + "integrity": "sha512-jQL3lRnocaFtu3V00JToYz/4QkNWswxijDaCVNZRiRTO3HQDLsdu1ZtmIUvV4yPp+rvWm5j0y0TG/S61cuijTg==", + "license": "MIT", + "dependencies": { + "tslib": "^2.0.0" + }, + "engines": { + "node": ">=10" + }, + "peerDependencies": { + "@types/react": "*", + "react": "^16.8.0 || ^17.0.0 || ^18.0.0 || ^19.0.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + } + } + }, + "node_modules/use-sidecar": { + "version": "1.1.3", + "resolved": "https://registry.npmjs.org/use-sidecar/-/use-sidecar-1.1.3.tgz", + "integrity": "sha512-Fedw0aZvkhynoPYlA5WXrMCAMm+nSWdZt6lzJQ7Ok8S6Q+VsHmHpRWndVRJ8Be0ZbkfPc5LRYH+5XrzXcEeLRQ==", + "license": "MIT", + "dependencies": { + "detect-node-es": "^1.1.0", + "tslib": "^2.0.0" + }, + "engines": { + "node": ">=10" + }, + "peerDependencies": { + "@types/react": "*", + "react": "^16.8.0 || ^17.0.0 || ^18.0.0 || ^19.0.0 || ^19.0.0-rc" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + } + } + }, "node_modules/use-sync-external-store": { "version": "1.6.0", "resolved": "https://registry.npmjs.org/use-sync-external-store/-/use-sync-external-store-1.6.0.tgz", @@ -12989,12 +14733,6 @@ "react": "^16.8.0 || ^17.0.0 || ^18.0.0 || ^19.0.0" } }, - "node_modules/util-deprecate": { - "version": "1.0.2", - "resolved": "https://registry.npmjs.org/util-deprecate/-/util-deprecate-1.0.2.tgz", - "integrity": "sha512-EPD5q1uXyFxJpCrLnCc1nHnq3gOa6DZBocAIiI2TaSCA7VCJ1UJDMagCzIkXNsUYfD1daK//LTEQ8xiIbrHtcw==", - "license": "MIT" - }, "node_modules/uuid": { "version": "14.0.0", "resolved": "https://registry.npmjs.org/uuid/-/uuid-14.0.0.tgz", diff --git a/ui/litellm-dashboard/package.json b/ui/litellm-dashboard/package.json index 0097e8c6559..d4ca1805fb7 100644 --- a/ui/litellm-dashboard/package.json +++ b/ui/litellm-dashboard/package.json @@ -24,6 +24,7 @@ "gen:api": "node scripts/gen-api-types.mjs" }, "dependencies": { + "@ant-design/cssinjs": "1.24.0", "@anthropic-ai/sdk": "0.92.0", "@headlessui/tailwindcss": "0.2.2", "@heroicons/react": "1.0.6", @@ -42,6 +43,7 @@ "next": "16.2.6", "openai": "4.104.0", "papaparse": "5.5.3", + "radix-ui": "1.6.1", "react": "18.3.1", "react-copy-to-clipboard": "5.1.1", "react-dom": "18.3.1", @@ -55,6 +57,7 @@ "@eslint/js": "9.39.2", "@playwright/test": "1.58.1", "@tailwindcss/forms": "0.5.11", + "@tailwindcss/postcss": "4.3.2", "@testing-library/dom": "10.4.1", "@testing-library/jest-dom": "6.9.1", "@testing-library/react": "16.3.2", @@ -67,7 +70,6 @@ "@types/react-syntax-highlighter": "15.5.13", "@vitest/coverage-v8": "3.2.6", "@vitest/ui": "3.2.6", - "autoprefixer": "10.4.24", "eslint": "9.39.2", "eslint-config-next": "16.2.6", "eslint-config-prettier": "10.1.8", @@ -77,7 +79,8 @@ "openapi-typescript": "7.13.0", "postcss": "8.5.13", "prettier": "3.2.5", - "tailwindcss": "3.4.19", + "tailwindcss": "4.3.2", + "tw-animate-css": "1.4.0", "typescript": "5.9.3", "typescript-eslint": "8.60.1", "vitest": "3.2.6" diff --git a/ui/litellm-dashboard/postcss.config.js b/ui/litellm-dashboard/postcss.config.js index 12a703d900d..483f378543c 100644 --- a/ui/litellm-dashboard/postcss.config.js +++ b/ui/litellm-dashboard/postcss.config.js @@ -1,6 +1,5 @@ module.exports = { plugins: { - tailwindcss: {}, - autoprefixer: {}, + "@tailwindcss/postcss": {}, }, }; diff --git a/ui/litellm-dashboard/src/app/(dashboard)/api-reference/components/DocLink.tsx b/ui/litellm-dashboard/src/app/(dashboard)/api-reference/components/DocLink.tsx index a3d0416053e..a3b34360246 100644 --- a/ui/litellm-dashboard/src/app/(dashboard)/api-reference/components/DocLink.tsx +++ b/ui/litellm-dashboard/src/app/(dashboard)/api-reference/components/DocLink.tsx @@ -1,9 +1,7 @@ import React from "react"; import { ExternalLink } from "lucide-react"; -function cn(...parts: Array) { - return parts.filter(Boolean).join(" "); -} +import { cn } from "@/lib/cva.config"; export type DocLinkProps = { href?: string; @@ -18,8 +16,8 @@ const DocLink = ({ href, className }: DocLinkProps) => { rel="noopener noreferrer" title="Open documentation in a new tab" className={cn( - "inline-flex items-center gap-2 rounded-xl border border-zinc-200 bg-white/80 px-3.5 py-2 text-sm font-medium text-zinc-700 shadow-sm", - "hover:bg-white focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-blue-500 active:translate-y-[0.5px]", + "inline-flex items-center gap-2 rounded-xl border border-zinc-200 bg-white/80 px-3.5 py-2 text-sm font-medium text-zinc-700 shadow-xs", + "hover:bg-white focus-visible:outline-hidden focus-visible:ring-2 focus-visible:ring-blue-500 active:translate-y-[0.5px]", className, )} > diff --git a/ui/litellm-dashboard/src/app/(dashboard)/caching/components/cache_health.tsx b/ui/litellm-dashboard/src/app/(dashboard)/caching/components/cache_health.tsx index 92bbc14846f..887c12a4f3d 100644 --- a/ui/litellm-dashboard/src/app/(dashboard)/caching/components/cache_health.tsx +++ b/ui/litellm-dashboard/src/app/(dashboard)/caching/components/cache_health.tsx @@ -151,7 +151,7 @@ const HealthCheckDetails: React.FC<{ response: any }> = ({ response }) => { }; return ( -
+
Summary @@ -225,7 +225,7 @@ const HealthCheckDetails: React.FC<{ response: any }> = ({ response }) => {
- 
+              
                 {(() => {
                   try {
                     const data = {
diff --git a/ui/litellm-dashboard/src/app/(dashboard)/caching/components/cache_settings/CacheFieldGroup.test.tsx b/ui/litellm-dashboard/src/app/(dashboard)/caching/components/cache_settings/CacheFieldGroup.test.tsx
deleted file mode 100644
index 6eba0718948..00000000000
--- a/ui/litellm-dashboard/src/app/(dashboard)/caching/components/cache_settings/CacheFieldGroup.test.tsx
+++ /dev/null
@@ -1,138 +0,0 @@
-import { describe, it, expect, beforeEach, vi } from "vitest";
-import { render, screen, cleanup } from "@testing-library/react";
-import CacheFieldGroup from "./CacheFieldGroup";
-
-describe("CacheFieldGroup", () => {
-  vi.mock("@/app/(dashboard)/hooks/useAuthorized", () => ({
-    default: () => ({
-      token: "mock-token",
-      accessToken: "mock-access-token",
-      userId: "mock-user-id",
-      userEmail: "test@example.com",
-      userRole: "Admin",
-      premiumUser: false,
-      disabledPersonalKeyCreation: false,
-      showSSOBanner: false,
-    }),
-  }));
-
-  beforeEach(() => {
-    cleanup();
-  });
-
-  it("should filter and render fields based on redisType", () => {
-    /**
-     * Tests that CacheFieldGroup filters fields based on redis_type and redisType prop.
-     * This is the core functionality that shows/hides fields based on Redis deployment type.
-     */
-    const fields = [
-      {
-        field_name: "host",
-        field_type: "String",
-        ui_field_name: "Host",
-        redis_type: null, // Applies to all types
-      },
-      {
-        field_name: "redis_startup_nodes",
-        field_type: "List",
-        ui_field_name: "Startup Nodes",
-        redis_type: "cluster", // Only for cluster
-      },
-      {
-        field_name: "sentinel_nodes",
-        field_type: "List",
-        ui_field_name: "Sentinel Nodes",
-        redis_type: "sentinel", // Only for sentinel
-      },
-    ];
-
-    const cacheSettings = {
-      host: "localhost",
-      redis_startup_nodes: [],
-    };
-
-    // Test with cluster type - should show host and redis_startup_nodes
-    const { rerender } = render(
-      ,
-    );
-
-    expect(screen.getByText("Cluster Settings")).toBeInTheDocument();
-    expect(screen.getAllByText("Host")).toHaveLength(1);
-    expect(screen.getByText("Startup Nodes")).toBeInTheDocument();
-    expect(screen.queryByText("Sentinel Nodes")).not.toBeInTheDocument();
-
-    // Test with sentinel type - should show host and sentinel_nodes
-    rerender(
-      ,
-    );
-
-    expect(screen.getByText("Sentinel Settings")).toBeInTheDocument();
-    expect(screen.getAllByText("Host")).toHaveLength(1);
-    expect(screen.getByText("Sentinel Nodes")).toBeInTheDocument();
-    expect(screen.queryByText("Startup Nodes")).not.toBeInTheDocument();
-
-    // Test with node type - should only show host
-    rerender();
-
-    expect(screen.getByText("Node Settings")).toBeInTheDocument();
-    expect(screen.getAllByText("Host")).toHaveLength(1);
-    expect(screen.queryByText("Startup Nodes")).not.toBeInTheDocument();
-    expect(screen.queryByText("Sentinel Nodes")).not.toBeInTheDocument();
-  });
-
-  it("should return null when no fields are visible", () => {
-    /**
-     * Tests that CacheFieldGroup returns null when no fields match the redisType.
-     * This prevents rendering empty sections in the UI.
-     */
-    const fields = [
-      {
-        field_name: "redis_startup_nodes",
-        field_type: "List",
-        ui_field_name: "Startup Nodes",
-        redis_type: "cluster", // Only for cluster
-      },
-    ];
-
-    const cacheSettings = {};
-
-    const { container } = render(
-      ,
-    );
-
-    // Component should return null, so container should be empty
-    expect(container.firstChild).toBeNull();
-  });
-
-  it("should use field_default when currentValue is not available", () => {
-    /**
-     * Tests that CacheFieldGroup falls back to field_default when currentValue is missing.
-     * This ensures fields display default values when cache settings are not set.
-     */
-    const fields = [
-      {
-        field_name: "port",
-        field_type: "Integer",
-        ui_field_name: "Port",
-        field_default: 6379,
-        redis_type: null,
-      },
-    ];
-
-    const cacheSettings = {}; // No port value set
-
-    render(
-      ,
-    );
-
-    const input = screen.getByRole("spinbutton", { name: "" });
-    expect(input).toBeInTheDocument();
-    expect(input).toHaveAttribute("name", "port");
-    expect(input).toHaveValue(6379);
-  });
-});
diff --git a/ui/litellm-dashboard/src/app/(dashboard)/caching/components/cache_settings/CacheFieldGroup.tsx b/ui/litellm-dashboard/src/app/(dashboard)/caching/components/cache_settings/CacheFieldGroup.tsx
deleted file mode 100644
index 21eb0199853..00000000000
--- a/ui/litellm-dashboard/src/app/(dashboard)/caching/components/cache_settings/CacheFieldGroup.tsx
+++ /dev/null
@@ -1,47 +0,0 @@
-import React from "react";
-import CacheFieldRenderer from "./CacheFieldRenderer";
-
-interface CacheFieldGroupProps {
-  title: string;
-  fields: any[];
-  cacheSettings: { [key: string]: any };
-  redisType: string;
-  gridCols?: string;
-}
-
-const CacheFieldGroup: React.FC = ({
-  title,
-  fields,
-  cacheSettings,
-  redisType,
-  gridCols = "grid-cols-1 gap-6 sm:grid-cols-2",
-}) => {
-  const shouldShowField = (field: any): boolean => {
-    // Show field if it applies to all types (redis_type is null/undefined) or to current selected type
-    if (field.redis_type === null || field.redis_type === undefined) {
-      return true;
-    }
-
-    return field.redis_type === redisType;
-  };
-
-  const visibleFields = fields.filter(shouldShowField);
-
-  if (visibleFields.length === 0) {
-    return null;
-  }
-
-  return (
-    

-      
{title}

-      

-        {visibleFields.map((field) => {
-          const currentValue = cacheSettings[field.field_name] ?? field.field_default ?? "";
-          return ;
-        })}
-      

-    

-  );
-};
-
-export default CacheFieldGroup;
diff --git a/ui/litellm-dashboard/src/app/(dashboard)/caching/components/cache_settings/CacheFieldRenderer.test.tsx b/ui/litellm-dashboard/src/app/(dashboard)/caching/components/cache_settings/CacheFieldRenderer.test.tsx
deleted file mode 100644
index 3cfacac7fda..00000000000
--- a/ui/litellm-dashboard/src/app/(dashboard)/caching/components/cache_settings/CacheFieldRenderer.test.tsx
+++ /dev/null
@@ -1,126 +0,0 @@
-import { describe, it, expect, vi } from "vitest";
-import { render, screen } from "@testing-library/react";
-import CacheFieldRenderer from "./CacheFieldRenderer";
-
-// Mock the useAuthorized hook to avoid Next.js router dependency
-vi.mock("@/app/(dashboard)/hooks/useAuthorized", () => ({
-  default: () => ({
-    token: "mock-token",
-    accessToken: "mock-access-token",
-    userId: "mock-user-id",
-    userEmail: "test@example.com",
-    userRole: "Admin",
-    premiumUser: false,
-    disabledPersonalKeyCreation: false,
-    showSSOBanner: false,
-  }),
-}));
-
-describe("CacheFieldRenderer", () => {
-  it("should render a checkbox for Boolean field type", () => {
-    /**
-     * Tests that Boolean fields render as checkboxes with proper defaultChecked value.
-     * This is the core functionality for boolean cache settings.
-     */
-    const field = {
-      field_name: "ssl",
-      field_type: "Boolean",
-      ui_field_name: "Enable SSL",
-      field_description: "Enable SSL encryption",
-    };
-
-    render();
-
-    const checkbox = screen.getByRole("checkbox", { name: "" });
-    expect(checkbox).toBeInTheDocument();
-    expect(checkbox).toBeChecked();
-    expect(screen.getByText("Enable SSL")).toBeInTheDocument();
-    expect(screen.getByText("Enable SSL encryption")).toBeInTheDocument();
-  });
-
-  it("should render a textarea for List field type", () => {
-    /**
-     * Tests that List fields render as textareas with JSON stringified values.
-     * This handles array/list cache settings like redis_startup_nodes.
-     */
-    const field = {
-      field_name: "redis_startup_nodes",
-      field_type: "List",
-      ui_field_name: "Redis Startup Nodes",
-      field_description: "List of Redis cluster nodes",
-    };
-
-    const currentValue = [
-      { host: "localhost", port: 6379 },
-      { host: "localhost", port: 6380 },
-    ];
-
-    render();
-
-    const textarea = screen.getByRole("textbox");
-    expect(textarea).toBeInTheDocument();
-    expect(textarea.tagName).toBe("TEXTAREA");
-    expect(textarea).toHaveValue(JSON.stringify(currentValue, null, 2));
-    expect(screen.getByText("Redis Startup Nodes")).toBeInTheDocument();
-  });
-
-  it("should render a password input for password field", () => {
-    /**
-     * Tests that password fields render as password inputs.
-     * This ensures sensitive data is masked in the UI.
-     */
-    const field = {
-      field_name: "password",
-      field_type: "String",
-      ui_field_name: "Password",
-      field_description: "Redis password",
-    };
-
-    render();
-
-    const input = screen.getByPlaceholderText("Redis password");
-    expect(input).toBeInTheDocument();
-    expect(input).toHaveAttribute("type", "password");
-    expect(input).toHaveValue("secret123");
-  });
-
-  it("should render a number input for Integer field type", () => {
-    /**
-     * Tests that Integer fields render as number inputs.
-     * This ensures proper validation for numeric cache settings.
-     */
-    const field = {
-      field_name: "port",
-      field_type: "Integer",
-      ui_field_name: "Port",
-      field_description: "Redis port number",
-    };
-
-    render();
-
-    const input = screen.getByPlaceholderText("Redis port number");
-    expect(input).toBeInTheDocument();
-    expect(input).toHaveAttribute("type", "number");
-    expect(input).toHaveValue(6379);
-  });
-
-  it("should render a text input for String field type", () => {
-    /**
-     * Tests that String fields render as text inputs.
-     * This is the default rendering for text-based cache settings.
-     */
-    const field = {
-      field_name: "host",
-      field_type: "String",
-      ui_field_name: "Host",
-      field_description: "Redis host address",
-    };
-
-    render();
-
-    const input = screen.getByPlaceholderText("Redis host address");
-    expect(input).toBeInTheDocument();
-    expect(input).toHaveAttribute("type", "text");
-    expect(input).toHaveValue("localhost");
-  });
-});
diff --git a/ui/litellm-dashboard/src/app/(dashboard)/caching/components/cache_settings/CacheFieldRenderer.tsx b/ui/litellm-dashboard/src/app/(dashboard)/caching/components/cache_settings/CacheFieldRenderer.tsx
deleted file mode 100644
index 27d9fc57200..00000000000
--- a/ui/litellm-dashboard/src/app/(dashboard)/caching/components/cache_settings/CacheFieldRenderer.tsx
+++ /dev/null
@@ -1,149 +0,0 @@
-"use client";
-
-import useAuthorized from "@/app/(dashboard)/hooks/useAuthorized";
-import { NumberInput, TextInput } from "@tremor/react";
-import { Select } from "antd";
-import React, { useEffect, useState } from "react";
-import { fetchAvailableModels, ModelGroup } from "@/components/llm_calls/fetch_models";
-import NumericalInput from "@/components/shared/numerical_input";
-
-interface CacheFieldRendererProps {
-  field: any;
-  currentValue: any;
-}
-
-const CacheFieldRenderer: React.FC = ({ field, currentValue }) => {
-  const [modelInfo, setModelInfo] = useState([]);
-  const [selectedModel, setSelectedModel] = useState(currentValue || "");
-  const { accessToken } = useAuthorized();
-
-  useEffect(() => {
-    if (!accessToken) return;
-
-    const loadModels = async () => {
-      try {
-        const uniqueModels = await fetchAvailableModels(accessToken);
-        console.log("Fetched models for selector:", uniqueModels);
-
-        if (uniqueModels.length > 0) {
-          setModelInfo(uniqueModels);
-        }
-      } catch (error) {
-        console.error("Error fetching model info:", error);
-      }
-    };
-
-    loadModels();
-  }, [accessToken]);
-
-  if (field.field_type === "Boolean") {
-    return (
-      

-        
-        

-          
-          {field.field_description}
-        

-      

-    );
-  }
-
-  if (field.field_type === "Integer" || field.field_type === "Float") {
-    return (
-      

-        
-        
-        
{field.field_description}

-      

-    );
-  }
-
-  if (field.field_type === "List") {
-    return (
-      

-        
-