diff --git a/.git-blame-ignore-revs b/.git-blame-ignore-revs
index 7e705ec4f8f..2527239b904 100644
--- a/.git-blame-ignore-revs
+++ b/.git-blame-ignore-revs
@@ -13,7 +13,7 @@
7edf3a9cb55548b143df1692f4ed7c4681d7fcf7
# style: reformat litellm/ with ruff format (#31317)
-430b5b8f1b12dc261a49fda99ac5d1b22381a428
+17bfd415aeb5a57fb646b5cc67da1c730aa7c50b
# style: unify ruff format width on 120 (#31518)
-3dfbeabe626d203ac9de86024519d9a96c484ce4
+48b5a5a0cc5a694a11219416ee0b6eb6e620e74e
diff --git a/.gitignore b/.gitignore
index 24b251c0628..59fa5803abe 100644
--- a/.gitignore
+++ b/.gitignore
@@ -22,7 +22,6 @@ litellm_results.jsonl
secrets.toml
litellm/proxy/litellm_secrets.toml
litellm/proxy/api_log.json
-litellm/proxy/_experimental/out/
.idea/
router_config.yaml
litellm_server/config.yaml
@@ -51,7 +50,8 @@ litellm/proxy/tests/package-lock.json
ui/litellm-dashboard/.next
ui/litellm-dashboard/node_modules
ui/litellm-dashboard/next-env.d.ts
-
+ui/litellm-dashboard/package.json
+ui/litellm-dashboard/package-lock.json
deploy/charts/litellm/*.tgz
deploy/charts/litellm/charts/*
deploy/charts/*.tgz
@@ -87,12 +87,17 @@ litellm/proxy/db/migrations/*
litellm/proxy/migrations/*config.yaml
litellm/proxy/migrations/*
litellm/proxy/to_delete_loadtest_work/*
+config.yaml
tests/litellm/litellm_core_utils/llm_cost_calc/log.txt
tests/test_custom_dir/*
+test.py
+litellm_config.yaml
+!.github/observatory/litellm_config.yaml
.cursor
litellm/proxy/to_delete_loadtest_work/*
update_model_cost_map.py
+tests/test_litellm/proxy/_experimental/mcp_server/test_mcp_server_manager.py
scripts/test_vertex_ai_search.py
LAZY_LOADING_IMPROVEMENTS.md
STABILIZATION_TODO.md
@@ -125,7 +130,3 @@ crash.*.log
# pytest coverage data
.coverage
-
-# _experimental/out UI build output
-# (both componentized and non-componentized build the UI on project release)
-litellm/proxy/_experimental/out/
diff --git a/CLAUDE.md b/CLAUDE.md
index 83bf3e22d27..7d9a6367f18 100644
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -33,9 +33,11 @@ If you ever make public-facing PR descriptions, comments, issues, commit message
Don't hesitate to use values in .env to get needed API keys and other secrets, as long as you never add them to conversation history, commit them, or include them in GitHub issues / PRs
-Run tests before you commit. Also, run `make pre-commit` right before each commit, which generates types (as needed) and formats/lints your code. Any errors found must be fixed
+Python max line length is 120, not 88
-When you fix violations gated by `ruff-strict-budget.json` or `basedpyright-code-budget.json`, run `make lint-budget-update` and commit the lowered baselines so the ceilings ratchet down instead of leaving stale headroom
+Run tests before you commit. Also, run `make pre-commit` right before each commit, which generates types (as needed) and formats/lints your code. Any errors found must be fixed. It only runs when there are staged frontend and/or backend changes and calculates violations, generates types, etc. based on the worktree, so stage what you need or stash/delete unwanted files in litellm/ or ui/ (where backend and frontend lint run, respectively) before running it. If it fails because dashboard api types are stale, it already regenerated them for you. You just need to stage the schema.d.ts, re-run `make pre-commit` to confirm it passes, and commit
+
+When you fix violations gated by `ruff-strict-budget.json`, `type-discipline-budget.json`, or `basedpyright-code-budget.json`, run `make lint-budget-update` and commit the lowered limits so the ceilings ratchet down instead of leaving stale headroom. It measures the working tree, so it must contain exactly the fixes you're committing
If you're trying to create a new function that relies on untyped stuff, instead of adding more Any's and pushing `reportAny` / `reportExplicitAny` closer to their basedpyright ceilings, just validate it in the caller with Pydantic (a model or `TypeAdapter` that returns the typed thing or raises will do) and then pass the now typed variable in
diff --git a/Makefile b/Makefile
index 78aa042fdac..10d1081d7bf 100644
--- a/Makefile
+++ b/Makefile
@@ -5,7 +5,7 @@
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 \
- lint-basedpyright lint-basedpyright-budget-update \
+ 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 \
install-helm-unittest check-circular-imports check-import-safety pre-commit \
@@ -27,12 +27,12 @@ help:
@echo " make lint - Run all linting (Ruff, basedpyright, format check, circular imports, import safety)"
@echo " make lint-ruff - Run Ruff linting only"
@echo " make lint-basedpyright - Run basedpyright strict, gated by per-rule error counts"
- @echo " make lint-basedpyright-budget-update - Re-capture the basedpyright per-rule budget (ratchet)"
+ @echo " make lint-basedpyright-budget-update - Ratchet basedpyright limits down by what this branch fixed"
@echo " make lint-format - Check ruff format formatting (matches CI)"
- @echo " make lint-ruff-budget - Gate the codebase total of each strict ruff rule against its ceiling"
+ @echo " make lint-ruff-budget - Gate the codebase total of each strict ruff rule against its limit"
@echo " make lint-gate - Strict ruff gate in CI-parity mode (fetches staging, simulates the merge)"
- @echo " make lint-ruff-budget-update - Re-capture per-rule baselines in ruff-strict-budget.json (ratchet)"
- @echo " make lint-budget-update - Re-capture all ratchet budgets (ruff + basedpyright)"
+ @echo " make lint-ruff-budget-update - Ratchet ruff-strict-budget.json limits down by what this branch fixed"
+ @echo " make lint-budget-update - Ratchet all budgets down (ruff + type-discipline + basedpyright)"
@echo " make check-circular-imports - Check for circular imports"
@echo " make check-import-safety - Check import safety"
@echo " make test - Run all tests"
@@ -88,7 +88,7 @@ install-hooks:
# Formatting
# Wrap width is ruff.toml's single source of truth (line-length = 120), shared by the
-# formatter, E501, and the import sorter so there's no 88-vs-120 split to reconcile.
+# formatter and the import sorter so there's no 88-vs-120 split to reconcile.
format: install-dev
cd litellm && $(UV_RUN) ruff format --exclude '/enterprise/' . && cd ..
@@ -164,7 +164,9 @@ lint-basedpyright: install-dev lint-fetch-base
lint-type-discipline: install-dev lint-fetch-base
$(UV_RUN) python scripts/type_discipline_gate.py --base origin/litellm_internal_staging
-lint-basedpyright-budget-update: install-dev
+# --update lowers each limit by what this branch fixed since its branch point, so
+# it needs the base ref fetched to resolve the merge-base.
+lint-basedpyright-budget-update: install-dev lint-fetch-base
($(UV_RUN) basedpyright --outputjson || true) | $(UV_RUN) python scripts/type_check_gate.py --update
lint-format: format-check
@@ -180,11 +182,14 @@ lint-ruff-budget: install-dev
lint-gate: install-dev lint-fetch-base
$(UV_RUN) python scripts/ruff_strict_gate.py --base origin/litellm_internal_staging
-lint-ruff-budget-update: install-dev
+lint-ruff-budget-update: install-dev lint-fetch-base
$(UV_RUN) python scripts/ruff_strict_gate.py --update
-# Ratchet all budgets in one shot (ruff strict + basedpyright)
-lint-budget-update: lint-ruff-budget-update lint-basedpyright-budget-update
+lint-type-discipline-budget-update: install-dev lint-fetch-base
+ $(UV_RUN) python scripts/type_discipline_gate.py --update
+
+# 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
cd litellm && $(UV_RUN) python ../tests/documentation_tests/test_circular_imports.py && cd ..
diff --git a/basedpyright-code-budget.json b/basedpyright-code-budget.json
index f2b54e1f889..79e6af05978 100644
--- a/basedpyright-code-budget.json
+++ b/basedpyright-code-budget.json
@@ -1,194 +1,146 @@
{
"reportAny": {
- "baseline": 24989,
- "slack": 2500
+ "limit": 37484
},
"reportArgumentType": {
- "baseline": 1814,
- "slack": 180
+ "limit": 2721
},
"reportAssignmentType": {
- "baseline": 220,
- "slack": 22
+ "limit": 330
},
"reportAttributeAccessIssue": {
- "baseline": 346,
- "slack": 35
+ "limit": 519
},
"reportCallIssue": {
- "baseline": 87,
- "slack": 10
+ "limit": 131
},
"reportConstantRedefinition": {
- "baseline": 39,
- "slack": 4
+ "limit": 59
},
"reportDeprecated": {
- "baseline": 217,
- "slack": 22
+ "limit": 326
},
"reportDuplicateImport": {
- "baseline": 28,
- "slack": 3
+ "limit": 42
},
"reportExplicitAny": {
- "baseline": 6931,
- "slack": 700
+ "limit": 10397
},
"reportFunctionMemberAccess": {
- "baseline": 7,
- "slack": 3
+ "limit": 11
},
"reportGeneralTypeIssues": {
- "baseline": 151,
- "slack": 15
+ "limit": 227
},
"reportIncompatibleMethodOverride": {
- "baseline": 52,
- "slack": 5
+ "limit": 78
},
"reportIncompatibleVariableOverride": {
- "baseline": 8,
- "slack": 3
+ "limit": 12
},
"reportInconsistentOverload": {
- "baseline": 12,
- "slack": 3
+ "limit": 18
},
"reportIndexIssue": {
- "baseline": 26,
- "slack": 3
+ "limit": 39
},
"reportInvalidTypeForm": {
- "baseline": 23,
- "slack": 3
+ "limit": 35
},
"reportInvalidTypeVarUse": {
- "baseline": 2,
- "slack": 3
+ "limit": 5
},
"reportMatchNotExhaustive": {
- "baseline": 1,
- "slack": 0
+ "limit": 2
},
"reportMissingParameterType": {
- "baseline": 3933,
- "slack": 390
+ "limit": 5900
},
"reportMissingTypeArgument": {
- "baseline": 10612,
- "slack": 1000
+ "limit": 15918
},
"reportMissingTypeStubs": {
- "baseline": 27,
- "slack": 10
+ "limit": 41
},
"reportOperatorIssue": {
- "baseline": 6,
- "slack": 3
+ "limit": 9
},
"reportOptionalCall": {
- "baseline": 4,
- "slack": 3
+ "limit": 7
},
"reportOptionalIterable": {
- "baseline": 3,
- "slack": 3
+ "limit": 6
},
"reportOptionalMemberAccess": {
- "baseline": 724,
- "slack": 72
+ "limit": 1086
},
"reportOptionalOperand": {
- "baseline": 3,
- "slack": 3
+ "limit": 6
},
"reportOptionalSubscript": {
- "baseline": 11,
- "slack": 3
+ "limit": 17
},
"reportPossiblyUnboundVariable": {
- "baseline": 52,
- "slack": 10
+ "limit": 78
},
"reportPrivateUsage": {
- "baseline": 1625,
- "slack": 160
+ "limit": 2438
},
"reportRedeclaration": {
- "baseline": 8,
- "slack": 3
+ "limit": 12
},
"reportReturnType": {
- "baseline": 126,
- "slack": 100
+ "limit": 226
},
"reportTypedDictNotRequiredAccess": {
- "baseline": 20,
- "slack": 3
+ "limit": 30
},
"reportUndefinedVariable": {
- "baseline": 2,
- "slack": 3
+ "limit": 5
},
"reportUnknownArgumentType": {
- "baseline": 30603,
- "slack": 3000
+ "limit": 45905
},
"reportUnknownLambdaType": {
- "baseline": 75,
- "slack": 10
+ "limit": 113
},
"reportUnknownMemberType": {
- "baseline": 27037,
- "slack": 2500
+ "limit": 40556
},
"reportUnknownParameterType": {
- "baseline": 13612,
- "slack": 1000
+ "limit": 20418
},
"reportUnknownVariableType": {
- "baseline": 21445,
- "slack": 2000
+ "limit": 32168
},
"reportUnnecessaryCast": {
- "baseline": 118,
- "slack": 10
+ "limit": 177
},
"reportUnnecessaryComparison": {
- "baseline": 683,
- "slack": 100
+ "limit": 1025
},
"reportUnnecessaryContains": {
- "baseline": 4,
- "slack": 3
+ "limit": 7
},
"reportUnnecessaryIsInstance": {
- "baseline": 808,
- "slack": 80
+ "limit": 1212
},
"reportUntypedBaseClass": {
- "baseline": 110,
- "slack": 11
+ "limit": 165
},
"reportUntypedFunctionDecorator": {
- "baseline": 22,
- "slack": 3
+ "limit": 33
},
"reportUnusedClass": {
- "baseline": 22,
- "slack": 3
+ "limit": 33
},
"reportUnusedFunction": {
- "baseline": 137,
- "slack": 10
+ "limit": 206
},
"reportUnusedImport": {
- "baseline": 670,
- "slack": 50
+ "limit": 1005
},
"reportUnusedVariable": {
- "baseline": 865,
- "slack": 50
+ "limit": 1298
}
}
diff --git a/litellm/__init__.py b/litellm/__init__.py
index 15e95ded906..9327e121b1d 100644
--- a/litellm/__init__.py
+++ b/litellm/__init__.py
@@ -263,6 +263,8 @@ azure_key: Optional[str] = None
anthropic_key: Optional[str] = None
replicate_key: Optional[str] = None
bytez_key: Optional[str] = None
+gdc_key: Optional[str] = None
+gdc_api_base: Optional[str] = None
cohere_key: Optional[str] = None
infinity_key: Optional[str] = None
clarifai_key: Optional[str] = None
@@ -1787,6 +1789,7 @@ if TYPE_CHECKING:
from .llms.nvidia_nim.embed import (
NvidiaNimEmbeddingConfig as NvidiaNimEmbeddingConfig,
)
+ from .llms.gdc.chat.transformation import GDCGeminiConfig as GDCGeminiConfig
# Type stubs for lazy-loaded config instances
openaiOSeriesConfig: OpenAIOSeriesConfig
diff --git a/litellm/_lazy_imports_registry.py b/litellm/_lazy_imports_registry.py
index 4f131354d2e..0f9d3a560d1 100644
--- a/litellm/_lazy_imports_registry.py
+++ b/litellm/_lazy_imports_registry.py
@@ -323,6 +323,7 @@ LLM_CONFIG_NAMES = (
"SnowflakeEmbeddingConfig",
"AmazonNovaChatConfig",
"SonioxAudioTranscriptionConfig",
+ "GDCGeminiConfig",
)
# Types that support lazy loading via _lazy_import_types
@@ -1157,6 +1158,10 @@ _LLM_CONFIGS_IMPORT_MAP = {
".llms.dashscope.chat.transformation",
"DashScopeChatConfig",
),
+ "GDCGeminiConfig": (
+ ".llms.gdc.chat.transformation",
+ "GDCGeminiConfig",
+ ),
"ModelScopeChatConfig": (
".llms.modelscope.chat.transformation",
"ModelScopeChatConfig",
diff --git a/litellm/constants.py b/litellm/constants.py
index 93aed83852b..6eb2779dcae 100644
--- a/litellm/constants.py
+++ b/litellm/constants.py
@@ -460,6 +460,7 @@ LITELLM_CHAT_PROVIDERS = [
"openai",
"openai_like",
"bytez",
+ "gdc",
"xai",
"custom_openai",
"text-completion-openai",
diff --git a/litellm/integrations/prometheus.py b/litellm/integrations/prometheus.py
index 8eb6eaa8e2b..4ebe312e301 100644
--- a/litellm/integrations/prometheus.py
+++ b/litellm/integrations/prometheus.py
@@ -593,6 +593,21 @@ class PrometheusLogger(CustomLogger):
labelnames=[],
)
+ ########################################
+ # MCP Tool Call Metrics
+ ########################################
+ self.litellm_mcp_tool_calls_total = self._counter_factory(
+ name="litellm_mcp_tool_calls_total",
+ documentation="Total MCP tool calls, segmented by tool and server name",
+ labelnames=self.get_labels_for_metric("litellm_mcp_tool_calls_total"),
+ )
+
+ self.litellm_mcp_tool_call_spend_metric = self._counter_factory(
+ name="litellm_mcp_tool_call_spend_metric",
+ documentation="Total spend on MCP tool calls, segmented by tool and server name",
+ labelnames=self.get_labels_for_metric("litellm_mcp_tool_call_spend_metric"),
+ )
+
except Exception as e:
print_verbose(f"Got exception on init prometheus client {str(e)}")
raise e
@@ -1300,6 +1315,13 @@ class PrometheusLogger(CustomLogger):
label_context=label_context,
)
+ # MCP tool call metrics
+ self._increment_mcp_tool_call_metrics(
+ standard_logging_payload=standard_logging_payload,
+ enum_values=enum_values,
+ response_cost=response_cost,
+ )
+
# increment litellm_proxy_total_requests_metric for all successful requests
# (both streaming and non-streaming) in this single location to prevent
# double-counting that occurs when async_post_call_success_hook also increments
@@ -1521,6 +1543,49 @@ class PrometheusLogger(CustomLogger):
amount=float(provider_cache_creation_tokens),
)
+ def _increment_mcp_tool_call_metrics(
+ self,
+ standard_logging_payload: StandardLoggingPayload,
+ enum_values: UserAPIKeyLabelValues,
+ response_cost: float,
+ ) -> None:
+ metadata = standard_logging_payload.get("metadata")
+ if not isinstance(metadata, dict):
+ return
+ mcp_meta = metadata.get("mcp_tool_call_metadata")
+ if not isinstance(mcp_meta, dict):
+ return
+
+ mcp_enum_values = UserAPIKeyLabelValues(
+ mcp_tool_name=mcp_meta.get("name"),
+ mcp_server_name=mcp_meta.get("mcp_server_name"),
+ hashed_api_key=enum_values.hashed_api_key,
+ api_key_alias=enum_values.api_key_alias,
+ team=enum_values.team,
+ team_alias=enum_values.team_alias,
+ user=enum_values.user,
+ end_user=enum_values.end_user,
+ )
+ mcp_label_context = PrometheusLabelFactoryContext(mcp_enum_values)
+
+ PrometheusLogger._inc_labeled_counter(
+ self,
+ self.litellm_mcp_tool_calls_total,
+ "litellm_mcp_tool_calls_total",
+ mcp_enum_values,
+ label_context=mcp_label_context,
+ )
+
+ if response_cost > 0:
+ PrometheusLogger._inc_labeled_counter(
+ self,
+ self.litellm_mcp_tool_call_spend_metric,
+ "litellm_mcp_tool_call_spend_metric",
+ mcp_enum_values,
+ label_context=mcp_label_context,
+ amount=response_cost,
+ )
+
async def _increment_remaining_budget_metrics(
self,
user_api_team: Optional[str],
diff --git a/litellm/integrations/websearch_interception/handler.py b/litellm/integrations/websearch_interception/handler.py
index bfae6d5b7b0..60100e8c2fd 100644
--- a/litellm/integrations/websearch_interception/handler.py
+++ b/litellm/integrations/websearch_interception/handler.py
@@ -120,21 +120,26 @@ class WebSearchInterceptionLogger(CustomLogger):
if self.enabled_providers is not None and provider_str not in self.enabled_providers:
return None
- # Only short-circuit for providers without native Anthropic Messages
- # support. Providers that have a BaseAnthropicMessagesConfig (bedrock,
- # vertex_ai, azure_ai, anthropic) already use the agentic loop, which
- # includes a follow-up LLM call to synthesize the answer from search
- # results. Short-circuiting those would skip that synthesis step and
- # return raw search text — a regression for existing users.
+ # Only short-circuit for providers whose Anthropic Messages agentic loop
+ # does not run web_search itself. Providers that have a
+ # BaseAnthropicMessagesConfig which handles web search natively (bedrock,
+ # vertex_ai, azure_ai, anthropic) already perform the search plus a
+ # follow-up LLM synthesis step; short-circuiting those would skip that
+ # synthesis and return raw search text — a regression for existing users.
+ #
+ # github_copilot has a BaseAnthropicMessagesConfig (added for thinking
+ # passthrough) but does not handle web_search natively, so its config
+ # returns handles_web_search_natively() == False and we still short-circuit
+ # web-search-only requests against it.
try:
provider_enum = LlmProviders(provider_str)
anthropic_config = ProviderConfigManager.get_provider_anthropic_messages_config(
model=model, provider=provider_enum
)
- if anthropic_config is not None:
+ if anthropic_config is not None and anthropic_config.handles_web_search_natively():
verbose_logger.debug(
f"WebSearchInterception: Skipping short-circuit for {provider_str} "
- "(provider has native Anthropic Messages support, using agentic loop)"
+ "(provider handles web search natively via the agentic loop)"
)
return None
except (ValueError, Exception):
diff --git a/litellm/litellm_core_utils/get_llm_provider_logic.py b/litellm/litellm_core_utils/get_llm_provider_logic.py
index 122d09c855b..a7a576ff167 100644
--- a/litellm/litellm_core_utils/get_llm_provider_logic.py
+++ b/litellm/litellm_core_utils/get_llm_provider_logic.py
@@ -446,6 +446,8 @@ def get_llm_provider(
# bytez models
elif model.startswith("bytez/"):
custom_llm_provider = "bytez"
+ elif model.startswith("gdc/"):
+ custom_llm_provider = "gdc"
elif model.startswith("lemonade/"):
custom_llm_provider = "lemonade"
elif model.startswith("heroku/"):
diff --git a/litellm/litellm_core_utils/prompt_templates/factory.py b/litellm/litellm_core_utils/prompt_templates/factory.py
index c2448430387..c1635158d3b 100644
--- a/litellm/litellm_core_utils/prompt_templates/factory.py
+++ b/litellm/litellm_core_utils/prompt_templates/factory.py
@@ -5035,15 +5035,18 @@ def _bedrock_tools_pt(tools: List, model: Optional[str] = None) -> List[BedrockT
]
"""
from litellm.llms.bedrock.common_utils import (
- get_bedrock_base_model,
+ bedrock_converse_supports_strict_tools,
normalize_json_schema_custom_types_to_object,
)
from litellm.litellm_core_utils.prompt_templates.common_utils import unpack_defs
_valid_json_schema_root_types = frozenset(("array", "boolean", "integer", "null", "number", "object", "string"))
# Only Claude on Bedrock honours strict tool schemas; other families
- # (Nova, Llama, GPT-OSS) reject the strict field outright.
- supports_strict_tools = bool(model and get_bedrock_base_model(model).startswith("anthropic"))
+ # (Nova, Llama, GPT-OSS) reject the strict field outright. Opus 4.7/4.8
+ # also reject `strict` on Bedrock Converse (see #31582) — their validator
+ # maps toolSpec to the native Anthropic tool shape, which has no strict
+ # field, even though Anthropic's native API accepts it as a top-level key.
+ supports_strict_tools = bool(model and bedrock_converse_supports_strict_tools(model))
tool_block_list: List[BedrockToolBlock] = []
for tool_idx, tool in enumerate(tools):
# Check if tool is already a BedrockToolBlock (e.g., systemTool for Nova grounding)
diff --git a/litellm/llms/base_llm/anthropic_messages/transformation.py b/litellm/llms/base_llm/anthropic_messages/transformation.py
index 966995bc571..448c1d07009 100644
--- a/litellm/llms/base_llm/anthropic_messages/transformation.py
+++ b/litellm/llms/base_llm/anthropic_messages/transformation.py
@@ -114,6 +114,19 @@ class BaseAnthropicMessagesConfig(ABC):
"""
return True
+ def handles_web_search_natively(self) -> bool:
+ """
+ Whether the upstream this config routes to executes ``web_search`` tools
+ itself as part of its Anthropic Messages agentic loop.
+
+ The web-search interception handler short-circuits web-search-only
+ requests (running the search itself and returning synthetic results) only
+ for providers that do NOT. Providers whose agentic loop already performs
+ the search plus a follow-up synthesis step (bedrock, vertex_ai, ...)
+ return True so those requests flow through untouched.
+ """
+ return True
+
def get_async_streaming_response_iterator(
self,
model: str,
diff --git a/litellm/llms/bedrock/common_utils.py b/litellm/llms/bedrock/common_utils.py
index 467e1050c99..df432a4d7e3 100644
--- a/litellm/llms/bedrock/common_utils.py
+++ b/litellm/llms/bedrock/common_utils.py
@@ -4,9 +4,11 @@ from __future__ import annotations
Common utilities used across bedrock chat/embedding/image generation
"""
+import contextlib
import functools
import json
import os
+import re
from typing import (
TYPE_CHECKING,
Any,
@@ -718,6 +720,51 @@ def is_claude_4_5_on_bedrock(model: str) -> bool:
return any(pattern in model_lower for pattern in claude_4_5_patterns)
+_BEDROCK_MODEL_VERSION_SUFFIX_RE = re.compile(r"-v\d+(?::\d+)?$")
+
+
+def bedrock_converse_supports_strict_tools(model: str) -> bool:
+ """
+ Whether ``toolSpec.strict`` can be forwarded to Bedrock Converse for ``model``.
+
+ Non-Anthropic Bedrock families (Nova, Llama, GPT-OSS) reject the field
+ outright. Anthropic models forward it unless their entry in
+ ``model_prices_and_context_window.json`` sets
+ ``bedrock_converse_supports_strict_tools: false`` — Bedrock routes those
+ (Opus 4.7/4.8, see #31582) through a stricter validator that rejects the
+ ``strict`` key on ``toolSpec`` even though Anthropic's native API accepts
+ it as a top-level tool field.
+ """
+ base = get_bedrock_base_model(model)
+ if not base.startswith("anthropic"):
+ return False
+ flag = _get_bedrock_converse_strict_tools_flag(base)
+ return flag if flag is not None else True
+
+
+def _get_bedrock_converse_strict_tools_flag(base_model: str) -> Optional[bool]:
+ candidates = dict.fromkeys((base_model, _BEDROCK_MODEL_VERSION_SUFFIX_RE.sub("", base_model)))
+ for candidate in candidates:
+ with contextlib.suppress(Exception):
+ model_info = get_cached_model_info()(
+ model=candidate,
+ custom_llm_provider="bedrock",
+ )
+
+ flag = model_info.get("bedrock_converse_supports_strict_tools")
+ if isinstance(flag, bool):
+ return flag
+
+ model_cost_key = model_info.get("key")
+ if isinstance(model_cost_key, str):
+ local_flag = (
+ _get_local_model_cost_map().get(model_cost_key, {}).get("bedrock_converse_supports_strict_tools")
+ )
+ if isinstance(local_flag, bool):
+ return local_flag
+ return None
+
+
def normalize_bedrock_opus_output_config_effort(model: str, output_config: Any) -> None:
"""
Normalize Anthropic ``output_config.effort`` values for Bedrock Opus ids.
diff --git a/litellm/llms/bedrock/realtime/handler.py b/litellm/llms/bedrock/realtime/handler.py
index 6db2571090a..557ee3348d5 100644
--- a/litellm/llms/bedrock/realtime/handler.py
+++ b/litellm/llms/bedrock/realtime/handler.py
@@ -5,6 +5,7 @@ This uses aws_sdk_bedrock_runtime for bidirectional streaming with Nova Sonic.
"""
import asyncio
+import contextlib
import json
from typing import Any, Optional
@@ -156,12 +157,19 @@ class BedrockRealtime(BaseAWSLLM):
session_state: dict,
):
"""Forward messages from client WebSocket to Bedrock stream."""
- try:
- from aws_sdk_bedrock_runtime.models import (
- BidirectionalInputPayloadPart,
- InvokeModelWithBidirectionalStreamInputChunk,
- )
+ from aws_sdk_bedrock_runtime.models import (
+ BidirectionalInputPayloadPart,
+ InvokeModelWithBidirectionalStreamInputChunk,
+ )
+ async def send_to_bedrock(bedrock_message: str) -> None:
+ event = InvokeModelWithBidirectionalStreamInputChunk(
+ value=BidirectionalInputPayloadPart(bytes_=bedrock_message.encode("utf-8"))
+ )
+ await bedrock_stream.input_stream.send(event)
+ verbose_proxy_logger.debug(f"Bedrock Realtime: Sent to Bedrock: {bedrock_message[:200]}")
+
+ try:
while True:
# Receive message from client
message = await client_ws.receive_text()
@@ -176,19 +184,15 @@ class BedrockRealtime(BaseAWSLLM):
# Send transformed messages to Bedrock
for bedrock_message in transformed_messages:
- event = InvokeModelWithBidirectionalStreamInputChunk(
- value=BidirectionalInputPayloadPart(bytes_=bedrock_message.encode("utf-8"))
- )
- await bedrock_stream.input_stream.send(event)
- verbose_proxy_logger.debug(f"Bedrock Realtime: Sent to Bedrock: {bedrock_message[:200]}")
+ await send_to_bedrock(bedrock_message)
except Exception as e:
verbose_proxy_logger.debug(f"Client to Bedrock forwarding ended: {e}", exc_info=True)
- # Close the Bedrock stream input
- try:
+ for close_message in transformation_config.session_close_messages():
+ with contextlib.suppress(Exception):
+ await send_to_bedrock(close_message)
+ with contextlib.suppress(Exception):
await bedrock_stream.input_stream.close()
- except Exception:
- pass
async def _forward_bedrock_to_client(
self,
@@ -206,6 +210,10 @@ class BedrockRealtime(BaseAWSLLM):
output = await bedrock_stream.await_output()
result = await output[1].receive()
+ if result is None:
+ verbose_proxy_logger.debug("Bedrock Realtime: Bedrock stream ended")
+ break
+
if result.value and result.value.bytes_:
bedrock_response = result.value.bytes_.decode("utf-8")
verbose_proxy_logger.debug(f"Bedrock Realtime: Received from Bedrock: {bedrock_response[:200]}")
@@ -252,6 +260,7 @@ class BedrockRealtime(BaseAWSLLM):
except Exception as e:
verbose_proxy_logger.debug(f"Bedrock to client forwarding ended: {e}", exc_info=True)
+ finally:
# Close the client WebSocket
try:
await client_ws.close()
diff --git a/litellm/llms/bedrock/realtime/transformation.py b/litellm/llms/bedrock/realtime/transformation.py
index 498567a4ecf..fe5f0584e03 100644
--- a/litellm/llms/bedrock/realtime/transformation.py
+++ b/litellm/llms/bedrock/realtime/transformation.py
@@ -4,14 +4,18 @@ This file contains the transformation logic for Bedrock Nova Sonic realtime API.
Transforms between OpenAI Realtime API format and Bedrock Nova Sonic format.
"""
+import base64
import json
import uuid as uuid_lib
from typing import Any, List, Optional, Union
+from pydantic import BaseModel
+
from litellm._logging import verbose_logger
from litellm._uuid import uuid
from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
from litellm.llms.base_llm.realtime.transformation import BaseRealtimeConfig
+from litellm.llms.bedrock.realtime.trigger_audio import ready_trigger_pcm
from litellm.types.llms.openai import (
OpenAIRealtimeContentPartDone,
OpenAIRealtimeDoneEvent,
@@ -35,6 +39,17 @@ from litellm.types.realtime import (
from litellm.utils import get_empty_usage
+class BedrockContentEnd(BaseModel):
+ stopReason: Optional[str] = None
+
+
+TRIGGER_AUDIO_SAMPLE_RATE_HERTZ = 16000
+TRIGGER_AUDIO_BYTES_PER_SECOND = TRIGGER_AUDIO_SAMPLE_RATE_HERTZ * 2
+TRIGGER_LEADING_SILENCE = bytes(TRIGGER_AUDIO_BYTES_PER_SECOND // 2)
+TRIGGER_TRAILING_SILENCE = bytes(TRIGGER_AUDIO_BYTES_PER_SECOND * 3)
+TRIGGER_AUDIO_CHUNK_SIZE = 1024
+
+
class BedrockRealtimeConfig(BaseRealtimeConfig):
"""Configuration for Bedrock Nova Sonic realtime transformations."""
@@ -43,6 +58,8 @@ class BedrockRealtimeConfig(BaseRealtimeConfig):
self.prompt_name = str(uuid_lib.uuid4())
self.content_name = str(uuid_lib.uuid4())
self.audio_content_name = str(uuid_lib.uuid4())
+ self.prompt_started = False
+ self.client_audio_streamed = False
# Default configuration values
# Inference configuration
@@ -247,6 +264,7 @@ class BedrockRealtimeConfig(BaseRealtimeConfig):
prompt_start = {"event": {"promptStart": prompt_start_config}}
messages.append(json.dumps(prompt_start))
+ self.prompt_started = True
# Send system prompt if provided
instructions = session_config.get("instructions")
@@ -304,8 +322,22 @@ class BedrockRealtimeConfig(BaseRealtimeConfig):
List of Bedrock format messages (JSON strings)
"""
verbose_logger.debug("Handling input_audio_buffer.append")
+ self.client_audio_streamed = True
messages: List[str] = []
+ if hasattr(self, "_audio_content_started") and self._audio_content_sample_rate != self.input_sample_rate_hertz:
+ mismatched_content_end = {
+ "event": {
+ "contentEnd": {
+ "promptName": self.prompt_name,
+ "contentName": self.audio_content_name,
+ }
+ }
+ }
+ messages.append(json.dumps(mismatched_content_end))
+ delattr(self, "_audio_content_started")
+ self.audio_content_name = str(uuid_lib.uuid4())
+
# Check if we need to start audio content
if not hasattr(self, "_audio_content_started"):
audio_content_start = {
@@ -329,6 +361,7 @@ class BedrockRealtimeConfig(BaseRealtimeConfig):
}
messages.append(json.dumps(audio_content_start))
self._audio_content_started = True
+ self._audio_content_sample_rate = self.input_sample_rate_hertz
# Send audio chunk
audio_data = json_message.get("audio", "")
@@ -383,7 +416,6 @@ class BedrockRealtimeConfig(BaseRealtimeConfig):
List of Bedrock format messages (JSON strings)
"""
verbose_logger.debug("Handling conversation.item.create")
- messages: List[str] = []
item = json_message.get("item", {})
item_type = item.get("type")
@@ -392,6 +424,8 @@ class BedrockRealtimeConfig(BaseRealtimeConfig):
if item_type == "function_call_output":
return self.transform_conversation_item_create_tool_result_event(json_message)
+ messages: list[str] = []
+
# Handle regular message
if item_type == "message":
content = item.get("content", [])
@@ -443,6 +477,12 @@ class BedrockRealtimeConfig(BaseRealtimeConfig):
"""
Transform response.create event to Bedrock format.
+ Nova Sonic only starts generating after it detects user speech, so text-only
+ sessions never get a response on their own. Injecting a short spoken "ready"
+ utterance (followed by silence) makes the model respond to the pending
+ interactive text input. Sessions where the client streams its own audio rely
+ on Nova Sonic's built-in turn detection instead.
+
Args:
json_message: OpenAI response.create message
@@ -450,8 +490,53 @@ class BedrockRealtimeConfig(BaseRealtimeConfig):
List of Bedrock format messages (JSON strings)
"""
verbose_logger.debug("Handling response.create")
- # Bedrock starts generating automatically, no explicit trigger needed
- return []
+ if not self.prompt_started or self.client_audio_streamed:
+ return []
+
+ messages: list[str] = []
+ if not hasattr(self, "_audio_content_started"):
+ trigger_content_start = {
+ "event": {
+ "contentStart": {
+ "promptName": self.prompt_name,
+ "contentName": self.audio_content_name,
+ "type": "AUDIO",
+ "interactive": True,
+ "role": "USER",
+ "audioInputConfiguration": {
+ "mediaType": self.input_media_type,
+ "sampleRateHertz": TRIGGER_AUDIO_SAMPLE_RATE_HERTZ,
+ "sampleSizeBits": self.input_sample_size_bits,
+ "channelCount": self.input_channel_count,
+ "audioType": self.input_audio_type,
+ "encoding": self.input_encoding,
+ },
+ }
+ }
+ }
+ messages.append(json.dumps(trigger_content_start))
+ self._audio_content_started = True
+ self._audio_content_sample_rate = TRIGGER_AUDIO_SAMPLE_RATE_HERTZ
+
+ messages.extend(self._response_trigger_audio_messages())
+ return messages
+
+ def _response_trigger_audio_messages(self) -> list[str]:
+ pcm = TRIGGER_LEADING_SILENCE + ready_trigger_pcm() + TRIGGER_TRAILING_SILENCE
+ return [
+ json.dumps(
+ {
+ "event": {
+ "audioInput": {
+ "promptName": self.prompt_name,
+ "contentName": self.audio_content_name,
+ "content": base64.b64encode(pcm[offset : offset + TRIGGER_AUDIO_CHUNK_SIZE]).decode(),
+ }
+ }
+ }
+ )
+ for offset in range(0, len(pcm), TRIGGER_AUDIO_CHUNK_SIZE)
+ ]
def transform_response_cancel_event(self, json_message: dict) -> List[str]:
"""
@@ -467,6 +552,35 @@ class BedrockRealtimeConfig(BaseRealtimeConfig):
# Send interrupt signal if needed
return []
+ def session_close_messages(self) -> list[str]:
+ """
+ Build the Bedrock events that gracefully close the session
+ (contentEnd for any open audio content, promptEnd, sessionEnd).
+
+ Returns:
+ List of Bedrock format messages (JSON strings)
+ """
+ if not self.prompt_started:
+ return []
+
+ messages: list[str] = []
+ if hasattr(self, "_audio_content_started"):
+ audio_content_end = {
+ "event": {
+ "contentEnd": {
+ "promptName": self.prompt_name,
+ "contentName": self.audio_content_name,
+ }
+ }
+ }
+ messages.append(json.dumps(audio_content_end))
+ delattr(self, "_audio_content_started")
+
+ messages.append(json.dumps({"event": {"promptEnd": {"promptName": self.prompt_name}}}))
+ messages.append(json.dumps({"event": {"sessionEnd": {}}}))
+ self.prompt_started = False
+ return messages
+
def transform_realtime_request(
self,
message: str,
@@ -837,10 +951,11 @@ class BedrockRealtimeConfig(BaseRealtimeConfig):
Optional[ALL_DELTA_TYPES],
]:
"""
- Transform Bedrock promptEnd event to OpenAI response.done.
+ Transform a Bedrock end-of-response event (promptEnd, completionEnd, or an
+ END_TURN contentEnd) to OpenAI response.done.
Args:
- event: Bedrock promptEnd event
+ event: Bedrock event that ends the response
current_response_id: Current response ID
current_conversation_id: Current conversation ID
@@ -848,7 +963,18 @@ class BedrockRealtimeConfig(BaseRealtimeConfig):
Tuple of (events, reset_output_item_id, reset_response_id, reset_delta_type)
"""
verbose_logger.debug("Handling promptEnd")
+ return self._response_done_events(current_response_id, current_conversation_id)
+ def _response_done_events(
+ self,
+ current_response_id: Optional[str],
+ current_conversation_id: Optional[str],
+ ) -> tuple[
+ List[OpenAIRealtimeEvents],
+ Optional[str],
+ Optional[str],
+ Optional[ALL_DELTA_TYPES],
+ ]:
if not current_response_id or not current_conversation_id:
return [], None, None, None
@@ -1084,6 +1210,14 @@ class BedrockRealtimeConfig(BaseRealtimeConfig):
current_delta_chunks,
)
returned_messages.extend(events)
+ if BedrockContentEnd.model_validate(event["contentEnd"]).stopReason == "END_TURN":
+ (
+ done_events,
+ current_output_item_id,
+ current_response_id,
+ current_delta_type,
+ ) = self._response_done_events(current_response_id, current_conversation_id)
+ returned_messages.extend(done_events)
elif "toolUse" in event:
events, tool_call_id, tool_name = self.transform_tool_use_event(
@@ -1093,7 +1227,7 @@ class BedrockRealtimeConfig(BaseRealtimeConfig):
# Store tool call info for potential use
verbose_logger.debug(f"Tool use event: {tool_name} (ID: {tool_call_id})")
- elif "promptEnd" in event:
+ elif "promptEnd" in event or "completionEnd" in event:
(
events,
current_output_item_id,
diff --git a/litellm/llms/bedrock/realtime/trigger_audio.py b/litellm/llms/bedrock/realtime/trigger_audio.py
new file mode 100644
index 00000000000..5783dae54bb
--- /dev/null
+++ b/litellm/llms/bedrock/realtime/trigger_audio.py
@@ -0,0 +1,208 @@
+"""
+Pre-rendered spoken "ready" trigger audio (16kHz, 16-bit, mono PCM), generated with Amazon Polly.
+
+Amazon Nova Sonic v1 only starts generating after it hears the user speak, so text-only realtime
+sessions inject this short utterance to trigger a response (same approach as Pipecat's
+AWSNovaSonicLLMService assistant-response trigger).
+"""
+
+import base64
+import gzip
+from functools import lru_cache
+
+READY_TRIGGER_PCM_16KHZ_MONO_GZIP_B64 = (
+ "H4sIANGpRWoC/517dXQcR9Bnw+Duis3MzMwkc8xsxxTZMTMzM0PMmJhBjpmZmWKQZSaxFrQ80H0lJXf3vXf/nev17ExPQ3Xh"
+ "r2wPQv8/f/D/uMP/zxv8f64YkSyiWU1AIpCcRSqyICtQCApF4SgSRaHsKCfKjfKhgqgIKo5KobKoPKqEqqFaqC5qgBqjFqg1"
+ "ao86o+6oF+qDYtAgNBSNQKPQODQeTUZT0Uw0B81D89ECtAgtRcvRMrQCrQRahVajNWgtWo/+QBvQJrQRbQbagraibWg70Da4"
+ "2/rf7zbozxyxCcaug1krYZXFaCGai2ajGWgKmgi7jYFdh6ABqB/qjXqgLqgd8NUcNQUe66CaqDJwXQaVhDMUgNNkh7NZ4bSc"
+ "69zLXTyVJ/Kv/BN/z9/w5/w+0B1+g1/kZ/gpfoL/zQ/xA/wvvovv5Jv5Fmjr+Tq+lq/iS/kioPl8Fp+eRRP4KKBhfBDvw3vw"
+ "Lrw978jb8Fa8JW8B1JQ34PV5Q2iZ1wa8Ea/Da/Ja0Gpm9TTmzXgT3hzGt+a/wNz2vBPM78TbwtyW0NuIV+fVeCWgCrwyUHmg"
+ "yll9NWClOrwurNA0a42GMLYerFoN3pf7j8rwYkBFeWFehOcHKshz8dw8Ow/nUTyCh/IwaDYuc4mrPATIBs8WeJMNxmTnOWF0"
+ "Tp4DnsK4lYscc8405mNulsFc0FKYg9lZKjQX3KXDcxJck+E5haWxRPYd2k/2hX2G9gkonr1nX6H3C7RkGOmB1QjsGckLAK+1"
+ "QAqdeQwfD7Jdz3fzk/we/4f/5D4uoVyoGOizOdjbMLCw+WBBO1Esuo7uoZfoE/qJnCgARq7iUByGs+G8OGcWReAQbMUCDqBk"
+ "FI9eoGvoGFjVSrCdAWAr9VBhsHsHf8EP87m8F8gV88dsBxvFajKJvTS3mjFmOdNnXDMWG12NUoZPf6jv0afpnfRKejadaena"
+ "B+219kqL0xK0oBamV9E761P1I3qcLhhVjL7GEuOckWAUMHube02nWZ/NY7dYBFjJZR4JNnsRqbgr3o7f4WykNZlJDpEH5AfR"
+ "SRgtQMvTarQJbUZb0JZA7Wjr/1o7+gs8N6K1aRmal9qoSRLJC3KF7CHLyUTSl7QhtUkxkptkIyEklOQghUgF0oh0IINg/WVk"
+ "O9lLjsI+u8kfZC4ZQ/qQZqQ6jM9DchIbkQglfpyKP+Cb+DDejBfiEbgDrogx/gftQWNRbaTx23wBjwYbuMwmsfLsq7nZ7Ghi"
+ "84IxHs7r1A/rA/Wiery2UeukRWiPg4uD0UEeuBSYFWgQEAPP/dv9k/xd/K387fy9/DP9x/2p/mqB1QEjMCvIg/M1m75Tr2m8"
+ "NuaZ5dhrNoaHQnzIDpzUIzdJLXqS5hEmCVcFJpQXu4gjxelAk8XBYgexgiiLP4XLwmphkNBAyCkk0yt0Be1HK1JCX5JdZDSp"
+ "D2d7htfhLmAXX9FR0H5XVAPlQDp4/xN+BezsCHj6Xrge4cfA9y/wS/w6nPUxWN97/h2ihIObXISoWASiXwxEtDPIjRriTTiA"
+ "B5N3pD19RH8RbgilxWXiZ7GI1EUaLU2QxkojpcHSUGmGtEO6KX2UXkvbpYaSQ7wq/iXuEleKQ8XS4gdhsVBXEISjoNd3ZBzJ"
+ "S27hCbgMfgeRTUGHeXfuY6tZFfbQ7G+mGmOMJH2UTvRNWnZtfjA8eBjk+srfx+/x7fQ18/m8+739veW8yPvec8nzl2ejZzXQ"
+ "Ns9pz2dPiLeld4+3iO+pb6t/RWBr8IL2UY8wm7Pp/AC6huPIF/pOuC1ul4bKuZVDSnF1kfpUDbPUs/xq6WmpaZEtD9TJaqi6"
+ "QymlHJAj5KnSM7GYOF64SYvTtSSC7MB1cALE6WbIC/GyG8QaESJKAfDm2TyWx3EZInAryA9LQfZvwOor4c54PF4B8juGn+A0"
+ "HEWqgAf0JkPIeDKFTCOryA5yiaQSG42mI+hf9DvNLvQXrgg2sZ+4V/wilpH6SFulT1JReYJ8WU6QsynFlbxASPkiX5S3yNPk"
+ "0fJkebm8RO4ox0lNpbNia/Gj0BEsYxxYhZ1cJOdJE3IWM8h0vfgpFsVGmaeNaOOL3kK/ohXV2gfnBL74R/q/+rr57N6V3ibe"
+ "gGevp4fnm3uuu7T7bcaJjJkZTTMsGfddm11jXF1dfVyzXBdcpTOeZFx2f/HU8j33rww207Obz9l0VJqcoBXEQ1KyXEgtYgla"
+ "TlgL2ZbZ/rGl2GwheUKUkHhbN9t1a6S1iWWM2kepJxeTUoQLdD5pgWuiWnwWe282Ac3vNhZBNBllTDBWGDuNNwYzmpixZgTb"
+ "ysqBhJtDDOyL43E0nCw/HUPP0jTwlipCKaGQQIR4eotupcNoPcrJY3KP3CEmaUKnUZ22F24KMeItcbKUXf5DrqUsUxxKe3Wc"
+ "+lBNVQVLW8twy2kLs2S3NrY2tFqsryytLN/VieoLpaEyV/ZLG6VGUlDcKo4VO4uR4mOhs3CI/iQyyY3t/CmLNfcaF/TT2sXg"
+ "+0BUoLd/r4/4fvde80ieTu6/M1Jc0a5LzvzOBY4P9qH2bPaE9Pj0T+mivaZ9sv20XbfncNR3vHY8dHbPWOQp6v9VSzXX4wpi"
+ "HWWK5Zw1xtbd9t46yeq0PLHkt26y9rXlDukSEh1yz5ZgPWwppw6VN4qKsIL0wQPQJH6WtQH9Kmwge8em8ZFoNP6NtKDXAf5E"
+ "Co/AunLQzPiZi26gFYTzgiSGiYeEdHqKNMKneW0WahY2Ruo+7Yi2SzsBkT6P3lZfol/Tdb2+McLYblw2TNDEA/MhU5FANgnD"
+ "5BWWniEnw6ZHDIqcGZk7ck7EzfAe4ZXDK4WvCufhvSPORFyJGBnxPJyHpYW+DEm1mdYm1o2WoDpCjVOqKmvlEvJtaaqUXWom"
+ "NhLiSS5cmzczF+rZtBzBsYEE/xV/G/8nXz/feu87j+zp5l6TkTfjlquFq4DrunOUs6bzo2OsQ3Vst3ezlwdJNrBXg2uUXU8v"
+ "YRccp5293WX85fSd/C4tIt9UW1jnW7mljWWk2k5NV1Msw21KaL6wa2F/hrUPXWOba/lFmShlE2/SPeQNfoZsaDS/xtYyCRAS"
+ "Q71IN+qhbYRswl+0Ab1N/OQcfSa0l47Km5X3ynilh/xSjBIakivoL/6aDWcCm21+MmoYO/WC+m1tnrZUO6p91urq8/THeg8j"
+ "YHw28/Ih6DO+TW+KcfJE4KVw6O2wHeHFImIi9PDocCNsadiksPSwjLA3YTfCqoZ1Cz0fcsrmsi6ydrXOtn6z5rAxqwJetNBa"
+ "w/qPpYflndoRYtVpeYpUW/TRu2QktqKebJtxR7se8Phue85nNHGZjuoOh32MvYy9kP1D+iOgielqesv0kukF0wdCs6ZPT7+V"
+ "Xsf+1Z5gz+ko6Ryc8dHr19aiuaKpbrC1BaA02rpcfaNUV7tbGtkehFQJ9YSk2aKsK9SH8hWxibCFzEM9WG/Dqbm02UYCy0W+"
+ "CbOlmfJ4eZf0U7whrpAaKVUsH6wOW/mQt7bBtlfWn5azqqjYxao0G+pu1tK7a39px/U4Y7hZzaxvJGoDg7kCp/yJ/seBGE00"
+ "jplTeE9cmhYSp0mfpXjJK54RHgmzxDxyjCU8pFrYwvBLYUbIV2tXdYjslC5IyZJPPqUsVwOWYrZFIQmhxcECK4d+tcVa21kr"
+ "2mJDDobVi4iNiIooGUZCcljnqcWUSPmBGCGEkv68jtle7x787v/V53UnuD44CtuT0r+m77B3dMQ4tzvDnDmcC+3v01ukR6Tt"
+ "TU1NiUlpnKKkzk4bm97GUdn5wFHa2cQx3jnE0zJoQy7Rp26x9rP+Zsmh7lJKKHOVEeoPJUbpLn8SL4rVwffO0R0oYAwPCv6u"
+ "vqf+/noV/ogchlKFC7eFH+JB+YCabmliZdZctiW2DiH3Q1qFjg2Js2ZT44VpaKJRVOOBtYGMwG/BaUF74GwgIrg9uF7bodcF"
+ "9HZTb2M8Z+GkjlhfGaJ6lRVyZbEEnYC9fBZCdKT4WZYtsyDnzVRtymepqFQTOLog51Z3WIbZzoa8CG0YViwsLLRqyGXbUlux"
+ "0Blh9cIPRoRHvo14H/4+9KXtpkVTHssnpcLSafEvYSe1ksm8tnldEwN7vf3d91yHXYMztrtPex54FnoKu486v9u/p81Lq2Zf"
+ "51jhDHfddaxOb5w2K+Vz0vDk2sk1UtypQ1MrplZKr5ihBYeRnmopm2RrrtaX5otLxFNSYbWvdZ/NbZmjZJPzilNoE4xMR6CJ"
+ "d7a7jO+e9pYdJctETTwtxNB89K6QJEdaZ4WsCWsUPjl8emT5qKURR0K3qIwW5tX1ZsHHwdMQ15jWMVjMH+mb7X3oUwLvA9O1"
+ "3kYF3pRUFB/LLdVcahl5s5CPHAL0nIRvkXByGM1k7dkhXhDF4TkkkgSIRNcLprRV2WM5bb1pfWxZot5TvZarNlfIr6GvQ3rb"
+ "zlrXWivbqobst32wVrW+VAurMapb3Q8Svw6RppVYXahEz5JpaIy5WGvk/8tb1fsNUEwzb0fvBPdJl+o8YGfpetqxlE7JD5OV"
+ "ZHeyJd2bylJbptLEbgkzEub8nJrUPqUa2F2T9J0Zn/RE8aytctigkHVyfmrisUKI8kW9Z+mulpSGkXGsvDnUSAi6vH9nrHYd"
+ "zNjjL8C60fFSXmm+MFxoJc6QhlpWhA4Mt0SWiwyNWBs+MnS+db9yQtjO8xjN9ViwpSFGV+2Cv5D3c0ZOT/NAV8PkB/FG8oHO"
+ "EHaJQ+W2ynO5gtiQLIQKWoUKeTeqz18YX4I5AgW110YaTyd++kpoK42RXyjvLZutO61rbKlwHWfbZntqq2UbaTmtDJDPSivE"
+ "Z+Im+Z1yXm2reuWncmu5lrxIvqx8VzR5tXwEUO99uh3FsbV6seBNX3VvVY+asTVjbUaM+45nrPuOa7Kjpb1C6viU96lbU3+H"
+ "bLAqvaj9YdqQVG9S++SMpEpJ+ZOvJfZPupU8zLFBmyuWCskRut26Rub4LkvlbmGuckC9r1SUDpJu5qLACt8Zz09XlPOKc73n"
+ "czBonsPRtBO5C7V/FD0rb7A5w/dGXc/2W9THsDO2CEsZOU24Txriv9EP/oYdMO/q6wKPvfc8m7xlghfMmmSdWFdC0kBxn9hf"
+ "6iwtkBLFPmJNcZjgpnXJYtSLbdE2Bry+rv7DOkVf6BbpqhQQZ0tHpRRptdoSLOpL6PzQyyFNbYssJRVBuihECcWFC5Ku/KME"
+ "lFFKafmlRKSOUi55plLUkmLxWH9YTXWaPFdcCRmpBA81rgU/Brr48/sEr83TMyObe2LGtYyKGdQlgVfOs/9m/9W+1RnpLOTa"
+ "6yzuLOOw2KemD087n5or7XJqVNrxlI2OzcEmwjXLGltTWz7rXsmHR6D2Qg85XGmu9FduSHVJvLbYW9Q9OKOFu6N/oLGTj0WD"
+ "+RjeEkXjz2SfOF5Ntk0NC4scEtUj8n3IA6Wl+E4whfeCIrYQPuKnrKYR0P4MouDvwWjdyk+SseIieaKsgLzaiGWl3+UcgL/t"
+ "4kmxoxCPu3HNGKiN97cEVHAv8IFtIa3EpVJuqb+0Uv6hlLXeCu0R3i78aHjZ8KuhD6wB5Z3UX2wijhFVmaiXFEWeJM2VqskN"
+ "lGfqaUtXywBLJ8tjS0OrWx0sj4DYeAQ/Rk9YUb2Xv41HdI/wxPk3BqoHznkPuG46cju+2rO7Jrlfuld5Orh7uMY6UtNcKcVT"
+ "XqRMs/d2fAFLy5WamPwlMT4h2rmcpakTbLct9eQUWhg9QOWkebarIdstneUV4lK0UkvwXM8o5U7y7AycMP38lrkkuMbPgkvM"
+ "R/ik/MV6JvRC2OKw26HlQ2pZtsrvpMUKs3yw3Fbmih5eTTvvzevt6m+vjTFGQs1o5fXYXwyjFrgHnSp2lgeotS0n1HxKfekG"
+ "nYldPC8aiUrxDuYzbV1wj57MMvA3GifIYkF5gtJC/R3QbnnrGdvvIYNCRoSsty2zrJEjxDHCNGGcmENi4haxkVhQbCkmin+K"
+ "1aQSck8lQemozlOGSSWFFqQCNnkzNkDPHsjh++p54tnofe4p7NnnphkhzucO2RHpPORIcrRycecl++r0hmkd0i6nXUvLbk+2"
+ "b007n9wv0f+z18/eSdczTqCnwEV1eSjNiYuwYby1MMYSb8WW5/IF8Q46qKV6DrivePr79wSjjFxGpDbKN80bHqhp3ECquFZ5"
+ "py5XO6uJ6lJLH6jdHljKWT+ABMrL+ehD9lgrGiyiLTT2mR+Nq3p+QJUHg80NiU/A2+lyyCo7lA9ST7G4oJFtpAytJ8wX2pN1"
+ "bKNeWauqt2Nf8HlaR9SEUmJJKb/cTj6gRFjyWX22waHZQh/aBloqKWmARLLJY+Rlsk1OETeLzaTfpUZyqNxdKg4I5Kh0XEwX"
+ "2gr5hFPUiVvxFMMZXO2zeX96Xnp+95z0rPBU8sx1j3P5HGccVR0THCcc+ZzvHbvBzkTHqfS/0lhq7rRHqS9SHiUfT56WJCVO"
+ "TinnsbM4saFcU/ydKLgl7k5LyonKCbWepaKlitKcxurEl99d2X3Jt16/ZlbVW/o2ua+5a/h6Bp+bY8k46aO62/YjZKtttGW0"
+ "ck8pad0Y2jS8avhj2yC5Iz5ohhvT9C/aJL2u3kZfpGXTbgS1wOBAC20qy0PGCNehIh1J+9PG9D3dJBQUDNwY70EneF+eyErx"
+ "bmgk/5v7UVN8nRQUZovD5EbKW6WQpT6g7t8tFdWDUGVvV+up1dRR6gGlkdJPOSvHS3OkKOmq6Befi7PEOKjLiJhIV5BsuBeP"
+ "NQO6qB/S2gUf+Gv5Zd8nTzvPM3fpjDEZbd0lM+yueq5RjvaOk/Yj6eUcOR2b06um9Ujbl/otJZAyJmVHct/k8Ylm6iNfPL8m"
+ "vBaX0p1ordnabEZqWVjotfAjEQNDk6RkZg9sDEzQn7JCZCfpx5r4H7lyu2q7b/mi9EW8HDWB1gq9hWV0jlBL2WcLhPYM/xg+"
+ "OmyRdbtUmJbDyxGF+nMiyYcKGPmCBX2LQKtj/cP10eCPV9l9VpdNNZuzs+gQHSzekcbJ/SQH7Yr38VH8Mxol7FBmWpLU29IY"
+ "KuMfqBn9JtUCpDrBgi1vlbbyWOkPaay8Us1u7R1SPjTNWly9IX2Vsit31G7WrdZfLS3Ur1I5KVaYT0fSKjSO7MLvmUNvHGwW"
+ "OOO/4nvtb+Xv7D/rO+dxZSxxDnDUdPZ3+jOKeVhGWsZOxxzHLOcNRzVHFfu+tI72nvYSzvN2nLYh+U5i/bRX3oJsjbBOGMP3"
+ "aFv9/Q2H8FvInPDVYTVsWP1NmihZAOk9JUfJCuGm+EkYgmP1OP8dL/Jv1xawW7gj+Qc/RJfZIfYnukvbyolqYVunkCe2RdZK"
+ "lpxqbzla2gtoNsz6QE0QFdzD1PQocx27z/2skDlK9wQHBI8Ex2pD9InGZvMMX49aoVb8EPOa7dkPvpjWlG+rpS3V1WxyEbCT"
+ "dKmv+tLa1bbF2tkSq4yS8ggzSXVynJwRFkh15GxSSZqEuqC9uK2wTFovj5SvSjOlN2JRsZ+whBakaaQSbUkvkTr4BDtrtDRK"
+ "GgWMMMOr/2oc02toAwMj/O39NPA60Dp4NoACjfzcN8g/33/eX9Pfz7/LPzJQIdDN/8i71PvIq/na+6f6fb7FvrK+VpDB6wXL"
+ "6T2NXUayXkq36KqxyVzBf6ApuC9ug/fg2aQY7Uo70qm0mNBHHCqFyPelUCm/+EYYLo6Ucsqq3FzaJVYRK4klxThhidBYaCa0"
+ "FiYLc+HuJq1I15NhZBcJp9VobjqHfMF/4K34LN6HS+JDaACajY4CXv0FHectuMRdzMds/CNY4ho2iDVi9Vg1VpR9M/+B6h2z"
+ "7mw2W88WsXXsFrPwxfwHb4I+o214FqlOT9FywkqhipgkXpNmyW65PlS4awFreJXcaj91rjpWbawSNZtaDjDtVSW7ckPeJJ+Q"
+ "H8lz5ZbyFSlacon7xV/FIuJrYa1QWfhEe9PDgJhHYILvAzYcjt7zXHwy1MjXzbNmZ/O2Ud9I0LkeYvyp59evaCF6V/2HVl+7"
+ "FFS1odo+bZWWR3MGfcHcWh+oD19oH7Uw3dSi9G76Dv2+Lhn9jM9GTXOYudzMxY6z3jyBt0NnUGmcgJeTNyQDNL2KZhOmCjeF"
+ "/cJzIVVIFz5BZXUCetqAVOsKOj0K8hxKB9ESdCqpSsaTg2Qy0fGvuDy+jQlZgp+hTegaKoPD8E70htfgE3gldB81Rvl5GkM8"
+ "hl/ij/g4OFNP/op3Qh3Rc76fS+hPFIeeo1j0BMWji8BREfwPfoR34qW4J/6EB0HkOIcL4J7ER6uLTQERHRMKiUfF/NI06ZM0"
+ "UE6Rdfmn7JQny4XlgDRIVpQIpZscKp0SPdJguZvwinQVeymX5FhiomJ0txAmuPAEEi3cEeNJB3bfIKiqsFFYgzqbETw77sH7"
+ "m3HGbUZxU15AfxJYbj4jt9DcQE1Pu8AEQA+GVs/XxP3I89pX3dfWc8izxVfQ9ynjJkTWFs4Qd3bPNvfbjJ0ZroyJbuQu7C7p"
+ "669PRXdISTyC1TNv80pCbmWEJcaaCnk3TGksL5AXKw3UfOohiGOfxIOCHw9jHY1nxjeWD6Ww7sbrYOFAw0CJYIhe1jzDCnCF"
+ "tTE/mJv5e9yUWoQVgiFsFpk4TmwmCDQnrSnMEE+Jd6gPcLLf+M2MZTX4HLbTKA45aoB2XCuiT9ZT9KrGZOOm0d7MzZqxsUzh"
+ "VxChX+gGmkSO0q/SHMs72y3bQ8vfag+L23Y47GB4IIyF/hXSPWSibYxtrO2sLbstzXJWraO+VLyyJNcBlBgqD5BbSNuEUPqV"
+ "nKIvwVZa0f34CLrOh/BjLM50QcyYpY/TfIFFvl7e7p47npKemu5Ql+z43V4rfaq9rn2m470jxWHY+9gD6Rn2ac69rnoZ21yf"
+ "nE8dCY7Rjp7OEMc654yMyoFpbANgg799Yd5xwSn4jFLWFmodofwqrKbJQnO1ZsjQsCahf1vbK1ukW2J1MVY4KcwFO9kudMOD"
+ "zc6Qp8ELeAymGHGXPkILaJfN3XiesEDcKRSnPch0spdeEqNkopyXndJj0SL0IrPwc2yjOv1OP+EdbIveReun7zQT2F2WYTzT"
+ "OgVZ4FZwmE7NLhA5Nppe44KBWU/+FY0kPehPuoLaqIcspZWFdWKsfMyywXbEdkBdIbeVN1h+C8uIbBDVOqJ9SJp1sG1m2KjI"
+ "6KgGkRfCZodE2wxrrDVo/cP6wTrXGmrppNjhLKOEN0J7abTUWcT0JW/DnpqLWCLfxAexNvqXwFH/BH/dAA52CTz2j/HW8XQG"
+ "lLnD293bx1PD43V/gadmnuvuhxnRbu555Z3pu+BZ7lrveuh65on3fvTMz3DZ36UfcO7z3te7Glv09to37atxlX8lqXK0Jdq6"
+ "3XLOEms9YIsIuRA6I+x0+NDwAaHRNq5slffJR2Qmq1I+YQr6aAzQl+kB46d5wLip19RcgRrB6dpdoxl7xfbwKMRRbfwb/pPs"
+ "p5XFNGmjlCB2E24SCy1KI0FTC2lu3IntN44bb4x044QxXN+rXQxUDZQIJPsbBotqHfW7ekv9oD7COGpW4xfRX+QSXSh4BK9Q"
+ "XzwjSvI4Ja/6UPkgf5RqSM2lF1DlfJcaSYOkgdI0eZTUWxorFZEHKK3VDLWL5ara1nLU8tmaIyQyJNVW0NbaehckftzaDk7K"
+ "1dNKXXmrVFBKEqPEAO1FC5ICOMh/5cO4G07iN8eZd40YyIHVjdzGMWO1EW6YelP9qH5Hf6/XNsrqY7SZmk+rb9zTYoJ3/N99"
+ "Df2T/C8Dq7SPgak+X0bLjK/uEr6R/k3+Hd5ZGcmO2/aSzrYZZXzegKwtDxjeBb6+2p/sJCkF3nxTXCMa4i35rGVZSPbQ1qGX"
+ "bLr1hWWv2lTNrf6i3lZ+in+SQzzNzM5izR1mE7OF/jTo9yf6EwOdtK96DVMzC7IE8xY7juKJKnaUvksDZIu8Vm6jvFA2qyfU"
+ "HGpRpadUV4wWooU8wgTaj1RBSWyYed/IYVY0b5g5TMmw6o81ppc3j7E/+GP+FOJ1EFUnOWgd4bQ4X5okHYT4c0s8DDX1KDmn"
+ "PA+qyGNCUaGTUFvYQJNJKGSFEXgjqoVa8OmQOynqie6iUtiNp5Ph9BJUtyOl7vJ+ZaQ6Sa1guWIRrUnWN9bxttfW65aClli1"
+ "r+pRHsjT5ZJSM/EFrUQfkglkAN6B7vETPJ2/52/5CI54bV6GV0P90Xv0GvVG1RFFQV4V18VLcF4UZAvZUraJSXwcY6YXrOpc"
+ "cF+wmjZYuwvect230fvYG+W96W3stXuXeZO9g72jfdhnerODx2ieGH/LwIGA7o13L3ZJbp/ns39y8F6wTGCd76gvEDxi1kHh"
+ "uBtksHD8lZhCWfmJMkph8g95qDJFWaeUV+Yrk2SvtFE8S+/i+ugyyG8f97L3RiftRKBioFPwnvZOf6pP174G04O59QqmzNei"
+ "vWgMesGroI54EJ0LFv6LcJdmh5PXhXiiCDPpFvIJsmsRXodnwNkqsjNmS3Oi4dSHAzZYaNSGDH/Q/N2MMFeb81lfNA5bSDw+"
+ "iC/j4WQlHSLUESPF08JZ+gQQcZTAaFPhDBVpA9IJf4As3BNvwX6UyntwkS/lW/gD/pKf5PlQTkTQRJDtZfwDHyOlSVFSjvwk"
+ "u2gh+ZY63BqrtBRvCLklXW1giwm5Z30ia/QsLS19scyw7lW3i4/xKvQNmbSJ1EJsSbsjJ3sC2cxEGvbgDngef8Pqs3GsJMqJ"
+ "LbQVOYiK8aGsNHei4kSmS/BBHg8WWYZ15dPRH3yXWc7YqjXWFL2+cc7w6D+D4wO5/B/8CwNbg9eDawNvfMu8y71nfZ/8yYGQ"
+ "YJVAuH+dL+hL9r8OSNru4NZAG8Cgyb7K/iHglaavju+NZ61nmfeQ/0bgQ4AGogNnA5u0O0ZDbgHc4uQd0QXcX2gnXZRySylC"
+ "vBAQfpME+bX0u5hBF5I5+Djglt7oGy/MT5qTjIL6ccizTfUJxndjmPGrflOL0IdB/OsAqKY72sdX8UkgwdV0hDBAuEcdZB/J"
+ "DnKaKPygfahIOuI/0G20D61Cy3gO/sP8Zo40k81TZln203SZO808LIZl4624xsuiQ+gn6g54NgeZSl4Dzi1L29OF9A96gQ6m"
+ "PWkZWp6eIevJIjKQNCTpeAh+DzY1DC1Dh9F2NBhFoIN8B//ER6FkZMWv0Snwyc+oLt6N47EXNFyG5APMlRcyZRM8F88B9DUN"
+ "VUWf+Tn0lGymi2htfBAsoh3ZQI+LE0VVmItr4MWkgrhPOif+IswhGjbwG1oBcvAq6sFVcB2chseSAnQJ4fgFmouao79RNL6B"
+ "r+LO+BmvxPvBiS5Bj4pdfAnbY3KzIH/Bz4NdTDaHGSWMQ8ZaswfrYYYZT7VnWjc9ylhotDEW6wO1O5AZLmiadlcrpcnatuCc"
+ "YKvg8uCtYB1tp7Zfq6sVB0RcWOurubRhejP9kvY4GAjm1dZoKcHdwa+B9oE431jfLX/rYDDYJZgW6BS4F6ivXTR6A25dzXez"
+ "KrwsjhS+iYa0X7oIOL28RJQNUJ8fl03psLhfKCu8A83NJs/xO/SUt2A1TQm8DvKfqZjTjRCjqNHT/MEOg9ev5PNA3m9REO8E"
+ "NFBHWAzzFtDFQmnxunhPdAoXaCnamJ6morALPH0XyLcxmoI+ITvUAU4+lecDC1vMG6NnaD9YksZrQ3XQAktkA7lOupAK5DeC"
+ "6T+0uTBCoLBCY1qf7qC1AIlFCvkA2dwFNC2CHTzG1fFKpPNlwM02fpd7uJcfBPlrrBTE0rloCrlLCN2FV+MreAf9IVSVTHGU"
+ "aNI0ekEoJFWXR0itxLpCPL0D9b5T2C10oJOIieuQaWQumUU+YahV0W9oLWIoDb1EfVB+tIB35Im8NVqCBiEVjeBNAft/56Mh"
+ "lqSDN3xjn1kDfhsqkY38LcvDyrOS7G+WDFSUXTTzmQ3NoeYnM948aYabF4zZxjJjr+ExrhlrjMZGFcOlNzfyGtkhC/cGSRcy"
+ "DF3XX+g39WqGYUjmPWORscAoYqwyJhjbjQ+Aek9BpXkCaiMXRH9Zp8ZnvYeeDlXSDn2LKfEcqCiKBT4eo5NkidBa7CEmCYOE"
+ "CUJZMZdUVfoilhJLCoOpi1yCk4aSebgfeKmfLWBlWS3WkxVgDyDmTjefm9HMyabwhXw7j+V+QNeHcQhpCxIqC1X3JFIeasZH"
+ "oOupJCdxQUSeDh6ajNvh2agMYmDzSZDVXvO2/ALgjHdmPkZ5V96Mn4PqcxeL5PGQFRag0Wge1K+FoaJ9g29BDLgD9ZJK+pGl"
+ "pDv47Rt8AE/HM3B9XBG/RVsgOiXye4ATN4D91AWPSmSPGeEvWSrLz/vw8lCZKVCpreU/uZ1f5M/5bIjLR8FXn5G+OD9+hr/R"
+ "cDFB/CKMoflJFdpPWC01kz4Jg+hkUonE0F1CmnCbRpGf6ADEj1nATUWcG5Xgw1lr9hL2ymCbWV7GjarGF+Oc2Zc1YGvNw0Zl"
+ "o7MRajrNtuyC6TdqGaVAQwUg0iWZVcwWRub/kSpnjDBaGYn6bEBWrfWaemn9ofZKOwTe30JbrH3VtukrdFnvpaUHPwYfapHG"
+ "buO23l+bERS1QfpOI8FoYVzRNgUnB4fq1c3b5gTDDk8tgh20WP2AEWkc0ioHjwRqB84ECgdzabX0aVBHm8FhwU3BNvpHcw/4"
+ "wmIWYdYyv7OLWBDaCXPJSbCNENyZVhIThLx0HqrH/+RV8ESSg0xGvVl1UzZfQ4Um8pHsF7OYEdSnGtPMOnD2juwzVO5fzSfs"
+ "B98OmX0haohKodVoEG5F/oQa+ig2UDbcEGrwAmQcXgQV8Vq+HuJFgJ/mRfmvLNlMNXuy2+wHm8/c5iPTY66ASroxj+ClOGdN"
+ "wFIqo2gUwKWon06k+0k0vSdYAH80VprLJQBhF5WvKbvUi8ouaZyYU2wAttxYGiEuojvxLaizk7CJo/FRHsZGm6/MBawo38QO"
+ "md+N341NRjtTZArbbJrGTyPJKGHOMLeaG8w+ZoaxzmhvdDfyg34GgCY362+1G1qaVhF0lK7N1eppWCukjdUua7u07oCE/9Yu"
+ "aY+04lB7RulYb6iv1f36Ez1WZxDF8xtljUHGTqODEWF81csY0fB8yzhvtATNn9bP68eMp8ZRw69P1wfoY2BORV3TdmvttSda"
+ "DtD/St2mH9WG6E0MK1TFPVgFVpltZFd5PDqJd+D7+DTW8ABikmq0CN1EOpM+pAy5jffjXTgP3gY5qAh6D9k0yA6yADvPtrAB"
+ "rB3ryiaxdNYKUGVR3gAiZHPIyHlxBdwCb8Yy+YMECKI7yQVyk1Sko2lniml7cgnk2BM8OTeJxhPAj1uDd37OnIcW8t58HQ/y"
+ "pqgGikQPOEJ7kIBDwC/forKQM7dDbGgC8fsFROcA3g94oL+gizHSXvEBDRO4sEQ+qvRRo5RYQFfHxXrKR7WKmiAFhexCTaG/"
+ "9Ctg+TNCfTIMFyHT6Sc6nwZxKJoBEaQmPoXjkIx+5QIgiWdZ/z9tOrcD6nrKPjAXa80L8sesGgsCpkgzK7LZLJrNM+1GqpHd"
+ "3GdeNqeapc32Rro+3GgMz83NP4yuoPPFRnmwv1um1exnLDGY8c58b640J5oPjUuGag4yR5uFoAYZZa6A3wwjxGxh7jYlFsZe"
+ "mH+aE0wCWPU31oodBQ4UvoddAzk35GtAxicgwiWznFAfVASMUZUfYe1ZDXYKeJ3F3piNzApmN/O8mWJeMTuayGxjPgZLvccO"
+ "sBOsMh8Lc74AbmwNES832Uzy0xi6mt6nNkDN+4UzQpywWTgEGNovHBGWC4uEacIGYYXQWsgvvIEs5qTRQlXhDh0A6GkT/Uwj"
+ "hDDhHO1LR9A9lIKMswkfICcvAmT1lHrobcjZeagVcFs8OUQWkpLkOF6J/8Br8C84ATDUTPQraomaoCoomZ+BU+3kY/gQPpoP"
+ "4Pn5a+ZmYZBn4yD6XmYzWQfWh/0JVrcSbG4Q6wTeHcdk7mGxEOcNFs3nQBwewpvwipBHdJ4TneLt+Ax+E3Lpab6cl+aJIL/T"
+ "7B82mjnN2SCjbmZuwBxTjOZGTfCmTB/abQwxphnfjJVQHeaFODLf3GN2gsxaAmTdgSUCqlzDMmP/FPan2d8caNrYNjaDOSBa"
+ "5THXmB3YWeBvBLsPntWTPWCD4BTPYN5A0GIhfoyf4934PqaZ7VhuyC4ePoEfg3eH2G98EFqBHMD9L5BNjqJeeBXuiL+gE6g5"
+ "5KjF5CHIrT5g0t+JQAfR6bQLIJVcgFcH0aX0OX0GuptBp9FdoEFF8NFXUKXsAVzzmJo0lxAuIEDK72gcdVMXzSOUFpLpXnqc"
+ "vqcBKgspNJ4mgo7O0GP0Mj0H1610Dm1NI6lB/iEXyRrItDlJCkSFvoCCnOgaZNHeKDs6C3KtDNXObfYXG8PysX/MhWZb8zez"
+ "u1nHDBiPjT+NbXANMweDV3SGqjjaXG5WAinMYb8wysLheoF9Z59YP3bHRCChC2wR42Cru83rUEHbANEkmTpg+UKAbxLN/FDn"
+ "bGI3IDdeYW1YX9DgHL4L9D6DTQdrqMj/gHqrFlSqMvjqKf6RL+CxLDfkkO6sC8g0lV0xx5onzPqgncfA7XKzgfnSfAkYys2G"
+ "slxgSRfZYO7ml3l2/gkqqFjI6REoFOLcfrivgOYDTUTd0Ep0ErBlFTwI98R9cCwOJ+1ISzIOsA0nrcAb9tBVdBlIuq1wVYgR"
+ "GgrFhYrCDuG94BO2CNWFdFpDOCDsgTc24Ss9CXrjtKTwnY6lw0GjW0CTo0GfPWgL2px2h5o9B5UgTn4mxyBG9iZNSSo+D1G4"
+ "J7ZAvmuOCiGM4gCbNOGP2E6wycxqPYaVY5/MJ6YXrLQAE1kEK8JGwpt1bDf7BtF5KoxvxkuAbxREf6HJyAOy6QxW+BdKRfkQ"
+ "Bvm9ZHY+BCLgHrbRPGyeZD7+hhfgCeZ4sybrwXsgO7/BcrLGbDHvDRK5xW+x9Swc8Noy9JaH8f3sKqvAu/OZPIT3Y7VZL5bE"
+ "7oDH5mdW0Fpb8N+hrAlzmcUga5wDPxwPmf4j+MV4sKUVIPvi/A5vC7IuDRX/Rn4B4v8OyP3loHpdwHOh8+g71HgR6AO3gh4a"
+ "44E4HY0EnRTEx7AbqqKWuDTuhr/g/qQu8eG1gPFU0gFQZyNSk+g4P0S5O+Qc5LPGgPoXkPPQJpI2gP0WgH/NIc2BOoB/7YAZ"
+ "MaQaaUbGQN5aQlqRPKQErNiF1CGYnMDH8Vf8Cf+N22IRJ0EV2BgXww4UA/KrApzfBn7qgd084gSeqwO37yDuzIOYdgEs9A6c"
+ "sy54+C98OOS3pTyGV+HR0NOfb+Vn+QNAv1P5Zs4ArRZBtVBhVAxVg6ozFs6dAtcZaCj6A71AOXADQD/zwQZi0D9QzXaAKDoD"
+ "0FFtFI/64SlYwNXQd94eEdwf94J3ZaFyqYycaDzOh7cgBSE0AOJKdvwTdUZfuJN3hrwbD/VtEcTBBzqDhb8EVDoD6qVBaCfS"
+ "kIyj8DW0FWT+DZXANjivHR0DPrzoF1wV18YI5JAT+gfgybg3rgnv2wFPeyBLL4GePhDJNuFrED+24EOABg7B3TnQzVl4vxIw"
+ "xd+AfXeCL+2E380wFmo4sPIL+B6+iY/i61B7fcXpMP4ESP0baPcFfgn19k5A6/vwZbwY/4qbAw4cj3/HkwBDExyGa+HfQEIN"
+ "sQR6aYy742kQSfNhDjh7CnjuQOBPxSWhuh6AO8HJ7qPHyAZzauMfYGFX4akYrgZzn0DN74c5Q2F9N5xVwiNhz93AcyWwtNX4"
+ "FQ7CGWbiIVBP3McZ2AOn7I1H47v4LT6Jx+GyIIVecP4FuD2OAC1UwIPh7S+YAo/FYeQ6OPkUsNhieAR+CLXINuCtLm4C1xP4"
+ "COyVDeuoAIxsB/uXwCnoOHoEVpADZP8CUNAZdAc9QXHIA56bBHyGg9YzUC7cFFaoB3G6GlBFeOoBZy8Ke/qRgq1YQ270APR4"
+ "Al1Cr9EhqHJmgkedh7sD4Ge7AGUdQgkoACgsDr1D6VmaL4Jz47xYhhq1DkgtJ1h9KPSaIJGnMOYruoXuocuQxcehsWAzM9Bc"
+ "NAZNh+sk8M3xsGLm10br0Z/oAljwKRj7Cj2E2BMLfFyD5+3ob5h9Aew4HnoWoo5gZ3HAwQPwoxhA6KPA0r6g56g9VHkR8HQQ"
+ "bHUVaoUk8KwY4Pwi6oWyoVyoDRoIz0MAL3ohducCPFEc+fg/PJVbsr7LskFzAJ7rhPqiquAPAioP/tMcVYZxAYhxGbw8zHXy"
+ "q4BAbvJX/BvEtDi+B/LzTOi5Dv47iQ/iXSDa9uUT+TTeizeCyDkK3o4E/LUavPYoP86vwHUt5KVrsO9tvgXmDOBzwdO381kw"
+ "PhQwc33o6Qy45ht7zt6yCMApeXgG5P9tkJdUHgkY4x92GCiOBSGuMvYOMtMz5oPa2M88gPzesIcQo++xF5AHr8P1NvzugAz4"
+ "AOgji4fK8SWsYGcCz8utXIV6pwjE+/K8NuxUCCJsLdi9HUScXLBvDog+9Xh96E/KmpON5wSk9Ra4OQVR28841Lqn2XZATKks"
+ "FNZKhVG3YQcJcFQYd7LPEN3DYJ98gJZdgNMMVpiXhCedpQDHCE4j8gCMT8j6gkmHmvYDcPg16ykF8lECy/wXZD9gqcx/S9Zh"
+ "fjjwLMFqHDCdwA0WAs0LY3U4T6YMMr+I4jDHBOlk7v+NMajJ3bDmOzj9VxhpByl9YjdBMq9h/ZfsFrsE0jnFjgBCPMk2sFWA"
+ "HLextWw5mwd36yB7zQe0PIdNAyy/AbLRQshQw9kU6N/H/mDLoKoZAW0zzN4I2Ws0GwLzFrAlMHoYIJe+bCqMmQH9fWHWDMjA"
+ "2wCH7oCxu2DXJ+wV6O4+aOwVcPMJatFPwNFd6HsE7Snc3QVOrwCufQTvnwLPz2HOY/ae/QSJp8GJ3kCzg4R0kIcGJwsyK+gw"
+ "G2iVQZ+Y9YWZyhFPgLVTs74ZSwRJPIP93rMvgFlT4PoeUFYCzMWcgEw1kLKPabCeAjoUuBfeuOGdBTK2BTSX+RUagvUj4UmC"
+ "0UF4p4AeEcjfAfIPQnOBTtJhxwSgL6DTz7DHBzhB5lnuw1nuAd1kf4PMTwFie5aF2U6BPG7AGd8D3YOnk5D/n8Cch9B/HGqb"
+ "83DuNzD7HNh+LEjkJTxfh/7tgFxOgA7Psr2AGdYB0jkNY87CmL9g5EUY9Qxs9Ro7A5b5AlZ4AatfgBkXofch+ETmzifg/Y0s"
+ "zu5D73XofZxlH09h/AewoR8gtUzJpcPZvf/5WVrWd3SMUZCaAXWuASdnIBkdbA+BNEx4MqE/CM0DErHDDCfc+0G6Bsz8l4ws"
+ "+8xcReaZI3WwXpYlvUSQpi9rTS9I8SM0b9a85CzNpWRpiAK+/Q7c2WFU5peCOoxxQKOgEQY7uWCcEzTmyfKLn2BdicBFpgc4"
+ "4ZoEazmybMYH751gHQ6Yk8m9BnNSss6dBL0JWfvHAb2DnTNl8SVrpWSYw4CLf79htIK1RPIoiFyleTGoggtlURmIKqXA54tA"
+ "1V8BYkwT3hjiSQ2oResDzmzD2/JWvDn8doZ4GcMH8t+zrkP5CIiM0wHrTAGaDL9zAN8tgjYPouVivgqq240QRxfyJXC/EbDR"
+ "Zoihq/kGiMKxgJNO8YOAy49CXL4FNdRtoJtQDb/g7wD3v4Xfp0AvIYa/4E/+o8fQnkM9/5rH8w8Q239Cre+CPGEHvOOG2O/M"
+ "ujqA0uDXBe8/8s8w7itP4Mk8Ba6JWTM8PIn/gJYIfZlfun6AFd/Avp8z/44aKB5mpMCoVOj5B3Z9Du/igJeHwN8d4OE1PL3L"
+ "4vMb7O3nBmA9g5tQqQazyOAUWSFXyUgEnGaDKisfygF1iIwsKArlRjmhT0SZowXokSEneoBnDZ4yv0PWss4QhDU1HgB+0+HZ"
+ "CyfL/NtqB/xqWd/oemBfjWd+s4wgQ2a+C3IF8imGJy/wYoV9MneKhL0iUQHA4uWBiqKCgDCrZH2pXAdQaUVUKeu75frQakNG"
+ "rQitMqoAWLMkUGkYWzyLMr91LoTyojyQo3PBunlh5QhYNxKFoXDYQYLz/PvVNAb+vf/x6wPOU7Iknwb3buA+Fe7c8NYP5M3i"
+ "WoNz/vsHAW4lsIqUJbd/v8KWQH4yXKX/VpeyrlAI//elNs36Jf/d/89vuDMl+b+/7/73G+/MHTL34P9jv/97/ffd/3369/d/"
+ "AYxHlHJ2PgAA"
+)
+
+
+@lru_cache(maxsize=1)
+def ready_trigger_pcm() -> bytes:
+ return gzip.decompress(base64.b64decode(READY_TRIGGER_PCM_16KHZ_MONO_GZIP_B64))
diff --git a/litellm/llms/gdc/__init__.py b/litellm/llms/gdc/__init__.py
new file mode 100644
index 00000000000..e69de29bb2d
diff --git a/litellm/llms/gdc/chat/__init__.py b/litellm/llms/gdc/chat/__init__.py
new file mode 100644
index 00000000000..e69de29bb2d
diff --git a/litellm/llms/gdc/chat/transformation.py b/litellm/llms/gdc/chat/transformation.py
new file mode 100644
index 00000000000..61631920a64
--- /dev/null
+++ b/litellm/llms/gdc/chat/transformation.py
@@ -0,0 +1,285 @@
+"""
+GDC Gemini chat completion transformation
+"""
+
+import json
+import os
+import re
+import threading
+from typing import Any, Final
+from urllib.parse import urlsplit
+
+import litellm
+from litellm.llms.openai_like.chat.transformation import OpenAILikeChatConfig
+
+
+class GDCGeminiConfig(OpenAILikeChatConfig):
+ supports_vertex_params: bool = True # Tell LiteLLM utilities not to strip vertex_ params
+ _GDCH_CREDENTIAL_TYPE: Final[str] = "gdch_service_account"
+ _PATH_ID_PATTERN: Final[re.Pattern[str]] = re.compile(r"^[a-zA-Z0-9_-]+$")
+
+ def __init__(self, **kwargs: Any) -> None:
+ super().__init__(**kwargs)
+ self._creds_lock = threading.Lock()
+ self._gdch_creds_cache: dict = {}
+
+ def get_supported_openai_params(self, model: str) -> list:
+ return [
+ "vertex_project",
+ "vertex_location",
+ ] + super().get_supported_openai_params(model)
+
+ def _resolve_project(self, optional_params: dict, litellm_params: dict) -> str | None:
+ return (
+ litellm_params.get("vertex_project")
+ or litellm_params.get("vertex_ai_project")
+ or getattr(litellm, "vertex_project", None)
+ or optional_params.get("vertex_project")
+ or optional_params.get("vertex_ai_project")
+ )
+
+ def _resolve_location(self, optional_params: dict, litellm_params: dict) -> str | None:
+ return (
+ litellm_params.get("vertex_location")
+ or litellm_params.get("vertex_ai_location")
+ or getattr(litellm, "vertex_location", None)
+ or optional_params.get("vertex_location")
+ or optional_params.get("vertex_ai_location")
+ )
+
+ def _effective_project(self, api_base: str, optional_params: dict, litellm_params: dict) -> str | None:
+ match = re.search(r"/v1/projects/([^/]+)", api_base)
+ if match:
+ return match.group(1)
+ return self._resolve_project(optional_params, litellm_params)
+
+ def _validate_path_id(self, value: str, field: str, model: str) -> str:
+ if not self._PATH_ID_PATTERN.match(value):
+ raise litellm.utils.AuthenticationError(
+ message=f"{field} must be a plain identifier of letters, digits, hyphens or underscores.",
+ llm_provider="gdc",
+ model=model,
+ )
+ return value
+
+ def get_complete_url(
+ self,
+ api_base: str | None,
+ api_key: str | None,
+ model: str,
+ optional_params: dict,
+ litellm_params: dict,
+ stream: bool | None = None,
+ ) -> str:
+ api_base = api_base or litellm.gdc_api_base or litellm.api_base
+ if not api_base:
+ raise litellm.utils.AuthenticationError(
+ message="api_base/host is required for GDC Gemini. Please set it or pass it.",
+ llm_provider="gdc",
+ model=model,
+ )
+
+ if not api_base.startswith("http"):
+ api_base = f"https://{api_base}"
+
+ api_base = api_base.rstrip("/")
+
+ if "/v1/projects/" in api_base:
+ return api_base
+
+ project = self._resolve_project(optional_params, litellm_params)
+
+ if not project:
+ raise litellm.utils.AuthenticationError(
+ message="project is required for GDC Gemini. Please pass vertex_project.",
+ llm_provider="gdc",
+ model=model,
+ )
+
+ location = self._resolve_location(optional_params, litellm_params)
+
+ if not location:
+ raise litellm.utils.AuthenticationError(
+ message="location is required for GDC Gemini. Please pass vertex_location.",
+ llm_provider="gdc",
+ model=model,
+ )
+
+ project = self._validate_path_id(project, "vertex_project", model)
+ location = self._validate_path_id(location, "vertex_location", model)
+
+ return f"{api_base}/v1/projects/{project}/locations/{location}/chat/completions"
+
+ def _read_env_bool(self, val: Any, env_var: str, default: bool = True) -> bool | str:
+ def _parse(s: str) -> bool | str:
+ cleaned = s.strip().lower()
+ if cleaned in ("false", "0", "no", "off"):
+ return False
+ if cleaned in ("true", "1", "yes", "on"):
+ return True
+ return s
+
+ if val is not None:
+ if isinstance(val, str):
+ return _parse(val)
+ return val
+
+ _env_val = os.getenv(env_var)
+ if _env_val is None:
+ return default
+ return _parse(_env_val)
+
+ def _fetch_auth(self, gdch_creds: Any, ssl_verify: bool | str) -> None:
+ import requests
+ from google.auth.transport import requests as auth_requests
+
+ auth_session = requests.Session()
+ auth_session.verify = ssl_verify
+ auth_request = auth_requests.Request(session=auth_session)
+ gdch_creds.refresh(auth_request)
+
+ def _cached_fetch_token(self, creds: Any, audience: str, ssl_verify: bool | str, api_key: str | None = None) -> str:
+ # Key cache by both audience and credential identity to prevent cross-caller contamination
+ cache_key = (audience.rstrip("/"), api_key or str(id(creds)))
+
+ with self._creds_lock:
+ if cache_key not in self._gdch_creds_cache:
+ self._gdch_creds_cache[cache_key] = creds.with_gdch_audience(audience.rstrip("/"))
+
+ gdch_creds = self._gdch_creds_cache[cache_key]
+
+ if not getattr(gdch_creds, "valid", False) or not getattr(gdch_creds, "token", None):
+ self._fetch_auth(gdch_creds, ssl_verify)
+
+ token = gdch_creds.token
+
+ return token
+
+ def _load_creds_from_key(self, api_key: str) -> tuple[Any, bool]:
+ import google.auth
+
+ try:
+ json_obj = json.loads(api_key)
+ except json.JSONDecodeError:
+ return None, False
+ if not isinstance(json_obj, dict) or json_obj.get("type") != self._GDCH_CREDENTIAL_TYPE:
+ raise ValueError(
+ "GDC only accepts a GDCH service account credential as a JSON api_key "
+ '(expected "type": "gdch_service_account"). Other Google credential types are '
+ "rejected so their token or external-account endpoints cannot drive server-side requests."
+ )
+ creds, _ = google.auth.load_credentials_from_dict(json_obj)
+ return creds, True
+
+ def validate_environment(
+ self,
+ headers: dict,
+ model: str,
+ messages: list[Any],
+ optional_params: dict,
+ litellm_params: dict,
+ api_key: str | None = None,
+ api_base: str | None = None,
+ ) -> dict:
+ import google.auth.exceptions
+
+ api_base = api_base or litellm.gdc_api_base or litellm.api_base
+ if not api_base:
+ raise litellm.utils.AuthenticationError(
+ message="api_base/host is required for GDC Gemini. Please set it or pass it.",
+ llm_provider="gdc",
+ model=model,
+ )
+
+ if not api_key:
+ raise litellm.utils.AuthenticationError(
+ message="api_key is required for GDC Gemini. Please pass your service account string or token as the api_key.",
+ llm_provider="gdc",
+ model=model,
+ )
+
+ project = self._effective_project(api_base, optional_params, litellm_params)
+ if not project:
+ raise litellm.utils.AuthenticationError(
+ message="project is required for GDC Gemini. Please pass vertex_project.",
+ llm_provider="gdc",
+ model=model,
+ )
+ project = self._validate_path_id(project, "vertex_project", model)
+
+ _audience_parts = urlsplit(api_base if api_base.startswith("http") else f"https://{api_base}")
+ audience = f"{_audience_parts.scheme}://{_audience_parts.netloc}"
+
+ try:
+ creds, is_service_account = self._load_creds_from_key(api_key)
+ except (
+ google.auth.exceptions.GoogleAuthError,
+ ValueError,
+ TypeError,
+ KeyError,
+ AttributeError,
+ ) as e:
+ raise litellm.utils.AuthenticationError(
+ message=f"Failed to load service account credentials from api_key: {str(e)}",
+ llm_provider="gdc",
+ model=model,
+ ) from e
+
+ if creds is not None:
+ ssl_verify = self._read_env_bool(litellm_params.get("ssl_verify"), "SSL_VERIFY", default=True)
+ if self._read_env_bool(litellm_params.get("gdc_token_caching"), "GDC_TOKEN_CACHING", default=False):
+ token = self._cached_fetch_token(creds, audience, ssl_verify, api_key)
+ else:
+ gdch_creds = creds.with_gdch_audience(audience)
+ self._fetch_auth(gdch_creds, ssl_verify)
+ token = gdch_creds.token
+ headers["Authorization"] = f"Bearer {token}"
+
+ if "Authorization" not in headers and not is_service_account:
+ headers["Authorization"] = f"Bearer {api_key}"
+
+ # Standardize necessary metadata headers
+ if "content-type" not in headers and "Content-Type" not in headers:
+ headers["Content-Type"] = "application/json"
+
+ stale_quota_headers = tuple(h for h in headers if h.lower() == "x-goog-user-project")
+ for stale in stale_quota_headers:
+ headers.pop(stale, None)
+ headers["x-goog-user-project"] = f"projects/{project}"
+
+ return headers
+
+ def transform_request(
+ self,
+ model: str,
+ messages: list[Any],
+ optional_params: dict,
+ litellm_params: dict,
+ headers: dict,
+ ) -> dict:
+ """
+ Transforms the request to the GDC provider
+ """
+ if model.startswith("gdc/"):
+ model = model.split("/", 1)[1]
+
+ data = super().transform_request(
+ model=model,
+ messages=messages,
+ optional_params=optional_params,
+ litellm_params=litellm_params,
+ headers=headers,
+ )
+
+ # Remove extra params used for routing/auth
+ for param in [
+ "vertex_project",
+ "vertex_ai_project",
+ "vertex_location",
+ "vertex_ai_location",
+ "ssl_verify",
+ "gdc_token_caching",
+ ]:
+ data.pop(param, None)
+
+ return data
diff --git a/litellm/llms/github_copilot/messages/__init__.py b/litellm/llms/github_copilot/messages/__init__.py
new file mode 100644
index 00000000000..e69de29bb2d
diff --git a/litellm/llms/github_copilot/messages/transformation.py b/litellm/llms/github_copilot/messages/transformation.py
new file mode 100644
index 00000000000..fb3f0a4e159
--- /dev/null
+++ b/litellm/llms/github_copilot/messages/transformation.py
@@ -0,0 +1,118 @@
+from typing import Any, Optional
+
+from litellm.exceptions import AuthenticationError
+from litellm.llms.anthropic.experimental_pass_through.messages.transformation import (
+ AnthropicMessagesConfig,
+)
+
+from ..authenticator import Authenticator
+from ..common_utils import (
+ DEFAULT_GITHUB_COPILOT_API_BASE,
+ GetAPIKeyError,
+ get_copilot_default_headers,
+)
+
+_MESSAGES_PROXY_API_VERSION = "2026-06-01"
+
+
+class GithubCopilotAnthropicMessagesConfig(AnthropicMessagesConfig):
+ """
+ GitHub Copilot implementation of Anthropic messages API.
+ Routes requests to Copilot's /v1/messages endpoint with appropriate authentication and headers.
+ """
+
+ def __init__(self) -> None:
+ super().__init__()
+ self.authenticator = Authenticator()
+
+ def handles_web_search_natively(self) -> bool:
+ """
+ Copilot's /v1/messages endpoint does not execute ``web_search`` tools, so
+ the interception handler must short-circuit web-search-only requests
+ instead of routing them here.
+ """
+ return False
+
+ def should_filter_anthropic_beta_headers(self) -> bool:
+ """
+ Copilot's /v1/messages is a native Anthropic Messages passthrough, so
+ ``anthropic-beta`` values injected by ``_update_headers_with_anthropic_beta``
+ (context_management, structured outputs, ...) must reach the upstream
+ verbatim. The default provider-scoped filter would drop them because
+ github_copilot has no entry in ``anthropic_beta_headers_config.json``.
+ """
+ return False
+
+ 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]]:
+ """
+ Validate environment for GitHub Copilot and add Copilot-specific headers.
+
+ The caller-supplied ``api_base`` is intentionally ignored. Routing this
+ request anywhere other than the authenticated Copilot endpoint would
+ leak the Copilot bearer token to a caller-controlled URL.
+ """
+ # Always use the Copilot endpoint resolved from the authenticated
+ # session, never the caller-supplied api_base. rstrip so a
+ # tenant-specific base with a trailing slash does not yield a
+ # double-slash URL once "/v1/messages" is appended downstream.
+ dynamic_api_base = (self.authenticator.get_api_base() or DEFAULT_GITHUB_COPILOT_API_BASE).rstrip("/")
+ try:
+ dynamic_api_key = self.authenticator.get_api_key()
+ except GetAPIKeyError as e:
+ raise AuthenticationError(
+ model=model,
+ llm_provider="github_copilot",
+ message=str(e),
+ )
+
+ # Merge Copilot headers with provided headers
+ copilot_headers = get_copilot_default_headers(dynamic_api_key)
+ for key, value in copilot_headers.items():
+ if key not in headers:
+ headers[key] = value
+
+ headers["openai-intent"] = "messages-proxy"
+ headers["x-interaction-type"] = "messages-proxy"
+ headers["x-github-api-version"] = _MESSAGES_PROXY_API_VERSION
+
+ if "anthropic-version" not in headers:
+ headers["anthropic-version"] = "2023-06-01"
+
+ headers = self._update_headers_with_anthropic_beta(
+ headers, optional_params, custom_llm_provider="github_copilot"
+ )
+
+ return headers, dynamic_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:
+ """
+ Return the complete URL for GitHub Copilot /v1/messages endpoint.
+
+ ``api_base`` here is the value already resolved by
+ ``validate_anthropic_messages_environment`` (the authenticated Copilot
+ host), not the raw caller-supplied base — that one is discarded there to
+ avoid leaking the Copilot bearer token to a caller-controlled URL. We
+ reuse it to avoid a second authenticator read, falling back to a fresh
+ resolution only if it was not provided.
+ """
+ resolved = (api_base or self.authenticator.get_api_base() or DEFAULT_GITHUB_COPILOT_API_BASE).rstrip("/")
+ if not resolved.endswith("/v1/messages"):
+ resolved = f"{resolved}/v1/messages"
+ return resolved
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 39503bd78dd..4bca3e8f71d 100644
--- a/litellm/llms/vertex_ai/image_generation/vertex_gemini_transformation.py
+++ b/litellm/llms/vertex_ai/image_generation/vertex_gemini_transformation.py
@@ -1,6 +1,8 @@
import os
from typing import TYPE_CHECKING, Any, Dict, List, Optional
+from litellm._logging import verbose_logger
+
import httpx
import litellm
@@ -52,6 +54,7 @@ class VertexAIGeminiImageGenerationConfig(BaseImageGenerationConfig, VertexLLM):
return [
"n",
"size",
+ "imageConfig",
"aspectRatio",
"aspect_ratio",
"imageSize",
@@ -83,7 +86,12 @@ class VertexAIGeminiImageGenerationConfig(BaseImageGenerationConfig, VertexLLM):
mapped_params["aspectRatio"] = v
elif k in ("imageSize", "image_size"):
mapped_params["imageSize"] = v
- elif k not in ("tools", "web_search_options"):
+ elif k == "imageConfig":
+ if isinstance(v, dict):
+ mapped_params["imageConfig"] = v
+ else:
+ verbose_logger.warning("imageConfig must be a dict, got %s — ignoring.", type(v).__name__)
+ elif k not in ("tools", "web_search_options", "imageConfig"):
mapped_params[k] = v
mapped_params = map_gemini_image_tools_params(non_default_params, mapped_params)
@@ -211,16 +219,14 @@ class VertexAIGeminiImageGenerationConfig(BaseImageGenerationConfig, VertexLLM):
# Prepare generation config
generation_config: Dict[str, Any] = {"responseModalities": ["IMAGE"]}
- # Handle image-specific config parameters
- image_config: Dict[str, Any] = {}
+ # Seed from user-supplied imageConfig dict; flat params are overlaid for backward compat.
+ image_config: Dict[str, Any] = dict(optional_params.get("imageConfig") or {})
- # Map aspectRatio
if "aspectRatio" in optional_params:
image_config["aspectRatio"] = optional_params["aspectRatio"]
elif "aspect_ratio" in optional_params:
image_config["aspectRatio"] = optional_params["aspect_ratio"]
- # Map imageSize (for Gemini 3 Pro)
if "imageSize" in optional_params:
image_config["imageSize"] = optional_params["imageSize"]
elif "image_size" in optional_params:
diff --git a/litellm/main.py b/litellm/main.py
index 18d2c367f8d..567930a4999 100644
--- a/litellm/main.py
+++ b/litellm/main.py
@@ -210,6 +210,7 @@ from .llms.bedrock.embed.embedding import BedrockEmbedding
from .llms.bedrock.image_edit.handler import BedrockImageEdit
from .llms.bedrock.image_generation.image_handler import BedrockImageGeneration
from .llms.bytez.chat.transformation import BytezChatConfig
+from .llms.gdc.chat.transformation import GDCGeminiConfig
from .llms.clarifai.chat.transformation import ClarifaiConfig
from .llms.codestral.completion.handler import CodestralTextCompletion
from .llms.cohere.embed import handler as cohere_embed
@@ -318,6 +319,7 @@ google_batch_embeddings = GoogleBatchEmbeddings()
vertex_partner_models_chat_completion = VertexAIPartnerModels()
vertex_gemma_chat_completion = VertexAIGemmaModels()
vertex_model_garden_chat_completion = VertexAIModelGardenModels()
+gdc_transformation = GDCGeminiConfig()
# vertex_text_to_speech is now replaced by VertexAITextToSpeechConfig
sagemaker_llm = SagemakerLLM()
watsonx_chat_completion = WatsonXChatHandler()
@@ -4336,6 +4338,45 @@ def _complete_gradient_ai(ctx: _CompletionDispatchContext) -> _CompletionDispatc
)
+def _complete_gdc(ctx: _CompletionDispatchContext) -> _CompletionDispatchResult:
+ acompletion = ctx.acompletion
+ api_base = ctx.api_base
+ api_key = ctx.api_key
+ client = ctx.client
+ custom_llm_provider = ctx.custom_llm_provider
+ headers = ctx.headers
+ litellm_params = ctx.litellm_params
+ logging = ctx.logging
+ messages = ctx.messages
+ model = ctx.model
+ model_response = ctx.model_response
+ optional_params = ctx.optional_params
+ stream = ctx.stream
+ timeout = ctx.timeout
+
+ api_key = api_key or litellm.gdc_key or get_secret_str("GDC_API_KEY") or litellm.api_key
+ api_base = api_base or litellm.gdc_api_base or get_secret_str("GDC_API_BASE") or litellm.api_base
+
+ return base_llm_http_handler.completion(
+ model=model,
+ messages=messages,
+ headers=headers,
+ model_response=model_response,
+ api_key=api_key,
+ api_base=api_base,
+ acompletion=acompletion,
+ logging_obj=logging,
+ optional_params=optional_params,
+ litellm_params=litellm_params,
+ timeout=timeout, # type: ignore
+ client=client,
+ custom_llm_provider=custom_llm_provider,
+ encoding=_get_encoding(),
+ stream=stream,
+ provider_config=gdc_transformation,
+ )
+
+
def _complete_bytez(ctx: _CompletionDispatchContext) -> _CompletionDispatchResult:
acompletion = ctx.acompletion
api_base = ctx.api_base
@@ -5533,6 +5574,8 @@ def completion( # type: ignore
elif custom_llm_provider == "gradient_ai":
response = _complete_gradient_ai(_dispatch_ctx)
+ elif custom_llm_provider == "gdc":
+ response = _complete_gdc(_dispatch_ctx)
elif custom_llm_provider == "bytez":
response = _complete_bytez(_dispatch_ctx)
elif custom_llm_provider == "lemonade":
diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index b16e1015255..bf63ef73c22 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -1154,6 +1154,7 @@
"bedrock_output_config_effort_ceiling": "max"
},
"anthropic.claude-opus-4-7": {
+ "bedrock_converse_supports_strict_tools": false,
"supports_adaptive_thinking": true,
"cache_creation_input_token_cost": 6.25e-06,
"cache_creation_input_token_cost_above_1hr": 1e-05,
@@ -1203,6 +1204,7 @@
"supports_output_config": true
},
"global.anthropic.claude-opus-4-7": {
+ "bedrock_converse_supports_strict_tools": false,
"supports_adaptive_thinking": true,
"cache_creation_input_token_cost": 6.25e-06,
"cache_creation_input_token_cost_above_1hr": 1e-05,
@@ -1237,6 +1239,7 @@
"bedrock_output_config_effort_ceiling": "xhigh"
},
"us.anthropic.claude-opus-4-7": {
+ "bedrock_converse_supports_strict_tools": false,
"supports_adaptive_thinking": true,
"cache_creation_input_token_cost": 6.875e-06,
"cache_creation_input_token_cost_above_1hr": 1.1e-05,
@@ -1271,6 +1274,7 @@
"bedrock_output_config_effort_ceiling": "xhigh"
},
"eu.anthropic.claude-opus-4-7": {
+ "bedrock_converse_supports_strict_tools": false,
"supports_adaptive_thinking": true,
"cache_creation_input_token_cost": 6.875e-06,
"cache_creation_input_token_cost_above_1hr": 1.1e-05,
@@ -1305,6 +1309,7 @@
"bedrock_output_config_effort_ceiling": "xhigh"
},
"au.anthropic.claude-opus-4-7": {
+ "bedrock_converse_supports_strict_tools": false,
"supports_adaptive_thinking": true,
"cache_creation_input_token_cost": 6.875e-06,
"cache_creation_input_token_cost_above_1hr": 1.1e-05,
@@ -1471,6 +1476,7 @@
"bedrock_output_config_effort_ceiling": "xhigh"
},
"anthropic.claude-opus-4-8": {
+ "bedrock_converse_supports_strict_tools": false,
"supports_adaptive_thinking": true,
"cache_creation_input_token_cost": 6.25e-06,
"cache_creation_input_token_cost_above_1hr": 1e-05,
@@ -1505,6 +1511,7 @@
"bedrock_output_config_effort_ceiling": "xhigh"
},
"global.anthropic.claude-opus-4-8": {
+ "bedrock_converse_supports_strict_tools": false,
"supports_adaptive_thinking": true,
"cache_creation_input_token_cost": 6.25e-06,
"cache_creation_input_token_cost_above_1hr": 1e-05,
@@ -1539,6 +1546,7 @@
"bedrock_output_config_effort_ceiling": "xhigh"
},
"us.anthropic.claude-opus-4-8": {
+ "bedrock_converse_supports_strict_tools": false,
"supports_adaptive_thinking": true,
"cache_creation_input_token_cost": 6.875e-06,
"cache_creation_input_token_cost_above_1hr": 1.1e-05,
@@ -1573,6 +1581,7 @@
"bedrock_output_config_effort_ceiling": "xhigh"
},
"eu.anthropic.claude-opus-4-8": {
+ "bedrock_converse_supports_strict_tools": false,
"supports_adaptive_thinking": true,
"cache_creation_input_token_cost": 6.875e-06,
"cache_creation_input_token_cost_above_1hr": 1.1e-05,
@@ -1607,6 +1616,7 @@
"bedrock_output_config_effort_ceiling": "xhigh"
},
"au.anthropic.claude-opus-4-8": {
+ "bedrock_converse_supports_strict_tools": false,
"supports_adaptive_thinking": true,
"cache_creation_input_token_cost": 6.875e-06,
"cache_creation_input_token_cost_above_1hr": 1.1e-05,
@@ -1641,6 +1651,7 @@
"bedrock_output_config_effort_ceiling": "xhigh"
},
"jp.anthropic.claude-opus-4-7": {
+ "bedrock_converse_supports_strict_tools": false,
"cache_creation_input_token_cost": 6.875e-06,
"cache_read_input_token_cost": 5.5e-07,
"input_cost_per_token": 5.5e-06,
@@ -1672,16 +1683,16 @@
"supports_minimal_reasoning_effort": true
},
"anthropic.claude-sonnet-5": {
- "cache_creation_input_token_cost": 3.75e-06,
- "cache_creation_input_token_cost_above_1hr": 6e-06,
- "cache_read_input_token_cost": 3e-07,
- "input_cost_per_token": 3e-06,
+ "cache_creation_input_token_cost": 2.5e-06,
+ "cache_creation_input_token_cost_above_1hr": 4e-06,
+ "cache_read_input_token_cost": 2e-07,
+ "input_cost_per_token": 2e-06,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
- "output_cost_per_token": 1.5e-05,
+ "output_cost_per_token": 1e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@@ -1705,16 +1716,16 @@
"bedrock_output_config_effort_ceiling": "xhigh"
},
"global.anthropic.claude-sonnet-5": {
- "cache_creation_input_token_cost": 3.75e-06,
- "cache_creation_input_token_cost_above_1hr": 6e-06,
- "cache_read_input_token_cost": 3e-07,
- "input_cost_per_token": 3e-06,
+ "cache_creation_input_token_cost": 2.5e-06,
+ "cache_creation_input_token_cost_above_1hr": 4e-06,
+ "cache_read_input_token_cost": 2e-07,
+ "input_cost_per_token": 2e-06,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
- "output_cost_per_token": 1.5e-05,
+ "output_cost_per_token": 1e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@@ -1738,16 +1749,16 @@
"bedrock_output_config_effort_ceiling": "xhigh"
},
"us.anthropic.claude-sonnet-5": {
- "cache_creation_input_token_cost": 4.125e-06,
- "cache_creation_input_token_cost_above_1hr": 6.6e-06,
- "cache_read_input_token_cost": 3.3e-07,
- "input_cost_per_token": 3.3e-06,
+ "cache_creation_input_token_cost": 2.75e-06,
+ "cache_creation_input_token_cost_above_1hr": 4.4e-06,
+ "cache_read_input_token_cost": 2.2e-07,
+ "input_cost_per_token": 2.2e-06,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
- "output_cost_per_token": 1.65e-05,
+ "output_cost_per_token": 1.1e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@@ -1771,16 +1782,16 @@
"bedrock_output_config_effort_ceiling": "xhigh"
},
"eu.anthropic.claude-sonnet-5": {
- "cache_creation_input_token_cost": 4.125e-06,
- "cache_creation_input_token_cost_above_1hr": 6.6e-06,
- "cache_read_input_token_cost": 3.3e-07,
- "input_cost_per_token": 3.3e-06,
+ "cache_creation_input_token_cost": 2.75e-06,
+ "cache_creation_input_token_cost_above_1hr": 4.4e-06,
+ "cache_read_input_token_cost": 2.2e-07,
+ "input_cost_per_token": 2.2e-06,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
- "output_cost_per_token": 1.65e-05,
+ "output_cost_per_token": 1.1e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@@ -1804,16 +1815,16 @@
"bedrock_output_config_effort_ceiling": "xhigh"
},
"au.anthropic.claude-sonnet-5": {
- "cache_creation_input_token_cost": 4.125e-06,
- "cache_creation_input_token_cost_above_1hr": 6.6e-06,
- "cache_read_input_token_cost": 3.3e-07,
- "input_cost_per_token": 3.3e-06,
+ "cache_creation_input_token_cost": 2.75e-06,
+ "cache_creation_input_token_cost_above_1hr": 4.4e-06,
+ "cache_read_input_token_cost": 2.2e-07,
+ "input_cost_per_token": 2.2e-06,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
- "output_cost_per_token": 1.65e-05,
+ "output_cost_per_token": 1.1e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@@ -1837,16 +1848,16 @@
"bedrock_output_config_effort_ceiling": "xhigh"
},
"jp.anthropic.claude-sonnet-5": {
- "cache_creation_input_token_cost": 4.125e-06,
- "cache_creation_input_token_cost_above_1hr": 6.6e-06,
- "cache_read_input_token_cost": 3.3e-07,
- "input_cost_per_token": 3.3e-06,
+ "cache_creation_input_token_cost": 2.75e-06,
+ "cache_creation_input_token_cost_above_1hr": 4.4e-06,
+ "cache_read_input_token_cost": 2.2e-07,
+ "input_cost_per_token": 2.2e-06,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
- "output_cost_per_token": 1.65e-05,
+ "output_cost_per_token": 1.1e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@@ -2082,7 +2093,8 @@
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
- "supports_vision": true
+ "supports_vision": true,
+ "bedrock_converse_supports_strict_tools": false
},
"anthropic.claude-sonnet-4-5-20250929-v1:0": {
"cache_creation_input_token_cost": 3.75e-06,
@@ -2409,7 +2421,8 @@
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
- "supports_vision": true
+ "supports_vision": true,
+ "bedrock_converse_supports_strict_tools": false
},
"assemblyai/best": {
"input_cost_per_second": 3.333e-05,
@@ -2710,16 +2723,16 @@
"supports_vision": true
},
"azure_ai/claude-sonnet-5": {
- "cache_creation_input_token_cost": 3.75e-06,
- "cache_creation_input_token_cost_above_1hr": 6e-06,
- "cache_read_input_token_cost": 3e-07,
- "input_cost_per_token": 3e-06,
+ "cache_creation_input_token_cost": 2.5e-06,
+ "cache_creation_input_token_cost_above_1hr": 4e-06,
+ "cache_read_input_token_cost": 2e-07,
+ "input_cost_per_token": 2e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
- "output_cost_per_token": 1.5e-05,
+ "output_cost_per_token": 1e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@@ -10474,16 +10487,16 @@
"supports_web_search": true
},
"claude-sonnet-5": {
- "cache_creation_input_token_cost": 3.75e-06,
- "cache_creation_input_token_cost_above_1hr": 6e-06,
- "cache_read_input_token_cost": 3e-07,
- "input_cost_per_token": 3e-06,
+ "cache_creation_input_token_cost": 2.5e-06,
+ "cache_creation_input_token_cost_above_1hr": 4e-06,
+ "cache_read_input_token_cost": 2e-07,
+ "input_cost_per_token": 2e-06,
"litellm_provider": "anthropic",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
- "output_cost_per_token": 1.5e-05,
+ "output_cost_per_token": 1e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@@ -14813,7 +14826,8 @@
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
- "supports_vision": true
+ "supports_vision": true,
+ "bedrock_converse_supports_strict_tools": false
},
"eu.anthropic.claude-sonnet-4-5-20250929-v1:0": {
"cache_creation_input_token_cost": 4.125e-06,
@@ -19176,7 +19190,8 @@
"max_tokens": 16000,
"mode": "chat",
"supported_endpoints": [
- "/v1/chat/completions"
+ "/v1/chat/completions",
+ "/v1/messages"
],
"supports_function_calling": true,
"supports_parallel_function_calling": true,
@@ -19189,7 +19204,8 @@
"max_tokens": 16000,
"mode": "chat",
"supported_endpoints": [
- "/v1/chat/completions"
+ "/v1/chat/completions",
+ "/v1/messages"
],
"supports_function_calling": true,
"supports_parallel_function_calling": true,
@@ -19242,7 +19258,8 @@
"max_tokens": 16000,
"mode": "chat",
"supported_endpoints": [
- "/v1/chat/completions"
+ "/v1/chat/completions",
+ "/v1/messages"
],
"supports_function_calling": true,
"supports_parallel_function_calling": true,
@@ -20071,7 +20088,8 @@
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
- "supports_vision": true
+ "supports_vision": true,
+ "bedrock_converse_supports_strict_tools": false
},
"global.anthropic.claude-haiku-4-5-20251001-v1:0": {
"cache_creation_input_token_cost": 1.25e-06,
@@ -33155,7 +33173,8 @@
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
- "supports_vision": true
+ "supports_vision": true,
+ "bedrock_converse_supports_strict_tools": false
},
"us.deepseek.r1-v1:0": {
"input_cost_per_token": 1.35e-06,
@@ -35207,16 +35226,16 @@
"supports_vision": true
},
"vertex_ai/claude-sonnet-5": {
- "cache_creation_input_token_cost": 3.75e-06,
- "cache_creation_input_token_cost_above_1hr": 6e-06,
- "cache_read_input_token_cost": 3e-07,
- "input_cost_per_token": 3e-06,
+ "cache_creation_input_token_cost": 2.5e-06,
+ "cache_creation_input_token_cost_above_1hr": 4e-06,
+ "cache_read_input_token_cost": 2e-07,
+ "input_cost_per_token": 2e-06,
"litellm_provider": "vertex_ai-anthropic_models",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
- "output_cost_per_token": 1.5e-05,
+ "output_cost_per_token": 1e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@@ -42674,16 +42693,16 @@
}
},
"vertex_ai/claude-sonnet-5@default": {
- "cache_creation_input_token_cost": 3.75e-06,
- "cache_creation_input_token_cost_above_1hr": 6e-06,
- "cache_read_input_token_cost": 3e-07,
- "input_cost_per_token": 3e-06,
+ "cache_creation_input_token_cost": 2.5e-06,
+ "cache_creation_input_token_cost_above_1hr": 4e-06,
+ "cache_read_input_token_cost": 2e-07,
+ "input_cost_per_token": 2e-06,
"litellm_provider": "vertex_ai-anthropic_models",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
- "output_cost_per_token": 1.5e-05,
+ "output_cost_per_token": 1e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@@ -42887,6 +42906,26 @@
"supports_tool_choice": true,
"supports_vision": true
},
+ "bedrock_mantle/xai.grok-4.3": {
+ "input_cost_per_token": 1.25e-06,
+ "output_cost_per_token": 2.5e-06,
+ "cache_read_input_token_cost": 2e-07,
+ "litellm_provider": "bedrock_mantle",
+ "max_input_tokens": 131072,
+ "max_output_tokens": 16384,
+ "max_tokens": 16384,
+ "mode": "chat",
+ "supported_endpoints": [
+ "/v1/chat/completions",
+ "/v1/responses"
+ ],
+ "supports_function_calling": true,
+ "supports_reasoning": true,
+ "supports_response_schema": true,
+ "supports_tool_choice": true,
+ "supports_vision": true,
+ "source": "https://aws.amazon.com/bedrock/pricing/"
+ },
"volcengine/doubao-seed-2-0-pro-260215": {
"litellm_provider": "volcengine",
"max_input_tokens": 256000,
diff --git a/litellm/proxy/_experimental/mcp_server/db.py b/litellm/proxy/_experimental/mcp_server/db.py
index a2ce3307061..1d62b325dec 100644
--- a/litellm/proxy/_experimental/mcp_server/db.py
+++ b/litellm/proxy/_experimental/mcp_server/db.py
@@ -1228,6 +1228,23 @@ def _remaining_token_seconds(expires_at: str | None) -> int | None:
return remaining if remaining > 0 else None
+async def get_active_submitted_mcp_server_ids_for_user(
+ prisma_client: PrismaClient,
+ user_id: str,
+) -> list[str]:
+ """Return active BYOM servers submitted by this user (creator visibility)."""
+ if not user_id:
+ return []
+
+ rows = await MCPServerRepository(prisma_client).table.find_many(
+ where={
+ "submitted_by": user_id,
+ "approval_status": MCPApprovalStatus.active,
+ },
+ )
+ return [row.server_id for row in rows]
+
+
async def approve_mcp_server(
prisma_client: PrismaClient,
server_id: str,
diff --git a/litellm/proxy/_experimental/mcp_server/mcp_server_manager.py b/litellm/proxy/_experimental/mcp_server/mcp_server_manager.py
index b6760e58852..95d00554034 100644
--- a/litellm/proxy/_experimental/mcp_server/mcp_server_manager.py
+++ b/litellm/proxy/_experimental/mcp_server/mcp_server_manager.py
@@ -1246,6 +1246,67 @@ class MCPServerManager:
"""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]
+ @staticmethod
+ def get_byom_submitted_servers_cache_key(user_id: str) -> str:
+ return f"byom_submitted_servers:{user_id}"
+
+ async def invalidate_byom_submitted_servers_cache(self, user_id: str | None) -> None:
+ if not user_id:
+ return
+ try:
+ from litellm.proxy.proxy_server import user_api_key_cache
+
+ await user_api_key_cache.async_delete_cache(key=self.get_byom_submitted_servers_cache_key(user_id))
+ except Exception as e: # noqa: BLE001
+ verbose_logger.warning(f"Failed to invalidate BYOM submitted MCP server cache: {str(e)}")
+
+ async def _get_active_submitted_mcp_server_ids_for_user(
+ self, user_api_key_auth: UserAPIKeyAuth | None
+ ) -> list[str]:
+ submitter_user_id = getattr(user_api_key_auth, "user_id", None) if user_api_key_auth else None
+ if not submitter_user_id:
+ return []
+
+ try:
+ from litellm.proxy._experimental.mcp_server.db import ( # noqa: PLC0415
+ get_active_submitted_mcp_server_ids_for_user,
+ )
+ from litellm.proxy.proxy_server import prisma_client, user_api_key_cache
+ except Exception as e: # noqa: BLE001
+ verbose_logger.warning(f"Failed to load BYOM submitted MCP server cache dependencies: {str(e)}")
+ return []
+
+ byom_cache_key = self.get_byom_submitted_servers_cache_key(submitter_user_id)
+ submitted_server_ids: list[str] | None = None
+ try:
+ cached_submitted_server_ids = await user_api_key_cache.async_get_cache(key=byom_cache_key)
+ if cached_submitted_server_ids is not None:
+ submitted_server_ids = cast(list[str], cached_submitted_server_ids)
+ except Exception as e: # noqa: BLE001
+ verbose_logger.warning(f"Failed to read BYOM submitted MCP server cache: {str(e)}")
+
+ if submitted_server_ids is None:
+ if prisma_client is None:
+ submitted_server_ids = []
+ else:
+ try:
+ submitted_server_ids = await get_active_submitted_mcp_server_ids_for_user(
+ prisma_client, submitter_user_id
+ )
+ except Exception as e: # noqa: BLE001
+ verbose_logger.warning(f"Failed to read BYOM submitted MCP servers from database: {str(e)}")
+ submitted_server_ids = []
+ try:
+ await user_api_key_cache.async_set_cache(
+ key=byom_cache_key,
+ value=submitted_server_ids,
+ ttl=60,
+ )
+ except Exception as e: # noqa: BLE001
+ verbose_logger.warning(f"Failed to write BYOM submitted MCP server cache: {str(e)}")
+
+ 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]:
"""
Get the allowed MCP Servers for the user.
@@ -1259,25 +1320,30 @@ class MCPServerManager:
allow_all_server_ids = self.get_allow_all_keys_server_ids()
+ # The key explicitly opted out of every MCP server. Return zero before
+ # layering on allow_all_keys or submitted servers so the opt-out is absolute.
+ key_object_permission = user_api_key_auth.object_permission if user_api_key_auth else None
+ if key_object_permission is not None and (
+ SpecialMCPServerNames.no_mcp_servers.value in (key_object_permission.mcp_servers or [])
+ ):
+ return []
+
+ # Check if object_permission.mcp_servers is explicitly set (not None, empty list is valid)
+ has_explicit_object_permission = key_object_permission is not None and (
+ key_object_permission.mcp_servers is not None
+ )
+ if has_explicit_object_permission:
+ verbose_logger.debug(f"Object permission mcp_servers explicitly set: {key_object_permission.mcp_servers}")
+
+ # BYOM creator visibility never widens a key that was explicitly scoped:
+ # only keys without their own mcp_servers list get submitted servers unioned in.
+ submitted_server_ids = (
+ []
+ if has_explicit_object_permission
+ else await self._get_active_submitted_mcp_server_ids_for_user(user_api_key_auth)
+ )
+
try:
- # The key explicitly opted out of every MCP server. Return zero before
- # layering on allow_all_keys servers so the opt-out is absolute.
- key_object_permission = user_api_key_auth.object_permission if user_api_key_auth else None
- if key_object_permission is not None and (
- SpecialMCPServerNames.no_mcp_servers.value in (key_object_permission.mcp_servers or [])
- ):
- return []
-
- # Check if object_permission.mcp_servers is explicitly set
- has_explicit_object_permission = False
- if user_api_key_auth and user_api_key_auth.object_permission:
- # Check if mcp_servers is explicitly set (not None, empty list is valid)
- if user_api_key_auth.object_permission.mcp_servers is not None:
- has_explicit_object_permission = True
- verbose_logger.debug(
- f"Object permission mcp_servers explicitly set: {user_api_key_auth.object_permission.mcp_servers}"
- )
-
# If admin but NO explicit object permission, get all servers
if user_api_key_auth and _user_has_admin_view(user_api_key_auth) and not has_explicit_object_permission:
verbose_logger.debug("Admin user without explicit object_permission - returning all servers")
@@ -1299,6 +1365,7 @@ class MCPServerManager:
in_toolset_scope = _mcp_active_toolset_id.get() is not None
if not in_toolset_scope:
combined_servers.update(allow_all_server_ids)
+ combined_servers.update(submitted_server_ids)
# For anonymous callers (no user_id, no role), also surface any
# servers the operator has opted into upstream-delegated auth.
@@ -1331,9 +1398,9 @@ class MCPServerManager:
except Exception: # noqa: BLE001
verbose_logger.exception(
"Failed to get allowed MCP servers; team-level object_permission "
- "grants may be dropped. Falling back to global servers only."
+ "grants may be dropped. Falling back to global and submitted servers."
)
- return allow_all_server_ids
+ return list(dict.fromkeys(allow_all_server_ids + submitted_server_ids))
async def resolve_toolset_tool_permissions(
self,
diff --git a/litellm/proxy/_experimental/out/404.html b/litellm/proxy/_experimental/out/404.html
new file mode 100644
index 00000000000..dd2a01991de
--- /dev/null
+++ b/litellm/proxy/_experimental/out/404.html
@@ -0,0 +1 @@
+404: This page could not be found.LiteLLM Dashboard
404
This page could not be found.
\ No newline at end of file
diff --git a/litellm/proxy/_experimental/out/404/index.html b/litellm/proxy/_experimental/out/404/index.html
new file mode 100644
index 00000000000..dd2a01991de
--- /dev/null
+++ b/litellm/proxy/_experimental/out/404/index.html
@@ -0,0 +1 @@
+404: This page could not be found.LiteLLM Dashboard