scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-08 03:08:45 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 114

fix(anthropic_wif): declare federation params as owned connection leaves and chart their metrics

Browse source 
Register the 18 Anthropic and 3 OpenAI federation params as frozen
ConnectionSettings leaves so the owned-kwarg registry, the kwargs funnel
and the request-body ban list read one declaration. Pass the deployment
api_base through to the count-tokens handler instead of a pre-suffixed
URL, which doubled the /count_tokens path on main's prompt-cache
predictor. Add the five litellm_anthropic_wif_* families to the
all-metrics Grafana dashboard.
This commit is contained in:
mateo-berri 2026-10-02 21:28:39 -07:00
parent 9e97756239
commit 54de31e46c
8 changed files with 194 additions and 76 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

127
cookbook/litellm_proxy_server/grafana_dashboard/dashboard_all_metrics/grafana_dashboard.json
View file

@ -5710,6 +5710,17 @@
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"editorMode": "code",
"expr": "histogram_quantile(0.95, sum(rate(litellm_anthropic_wif_latency_bucket[$__rate_interval])) by (le))",
"legendFormat": "anthropic_wif",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
@ -5719,7 +5730,7 @@
"expr": "histogram_quantile(0.95, sum(rate(litellm_auth_latency_bucket[$__rate_interval])) by (le))",
"legendFormat": "auth",
"range": true,
"refId": "A"
"refId": "B"
},
{
"datasource": {
@ -5730,7 +5741,7 @@
"expr": "histogram_quantile(0.95, sum(rate(litellm_batch_write_to_db_latency_bucket[$__rate_interval])) by (le))",
"legendFormat": "batch_write_to_db",
"range": true,
"refId": "B"
"refId": "C"
},
{
"datasource": {
@ -5741,7 +5752,7 @@
"expr": "histogram_quantile(0.95, sum(rate(litellm_postgres_latency_bucket[$__rate_interval])) by (le))",
"legendFormat": "postgres",
"range": true,
"refId": "C"
"refId": "D"
},
{
"datasource": {
@ -5752,7 +5763,7 @@
"expr": "histogram_quantile(0.95, sum(rate(litellm_proxy_pre_call_latency_bucket[$__rate_interval])) by (le))",
"legendFormat": "proxy_pre_call",
"range": true,
"refId": "D"
"refId": "E"
},
{
"datasource": {
@ -5763,7 +5774,7 @@
"expr": "histogram_quantile(0.95, sum(rate(litellm_redis_latency_bucket[$__rate_interval])) by (le))",
"legendFormat": "redis",
"range": true,
"refId": "E"
"refId": "F"
},
{
"datasource": {
@ -5774,7 +5785,7 @@
"expr": "histogram_quantile(0.95, sum(rate(litellm_redis_daily_org_spend_update_queue_latency_bucket[$__rate_interval])) by (le))",
"legendFormat": "redis_daily_org_spend_update_queue",
"range": true,
"refId": "F"
"refId": "G"
},
{
"datasource": {
@ -5785,7 +5796,7 @@
"expr": "histogram_quantile(0.95, sum(rate(litellm_redis_daily_tag_spend_update_queue_latency_bucket[$__rate_interval])) by (le))",
"legendFormat": "redis_daily_tag_spend_update_queue",
"range": true,
"refId": "G"
"refId": "H"
},
{
"datasource": {
@ -5796,7 +5807,7 @@
"expr": "histogram_quantile(0.95, sum(rate(litellm_redis_daily_team_spend_update_queue_latency_bucket[$__rate_interval])) by (le))",
"legendFormat": "redis_daily_team_spend_update_queue",
"range": true,
"refId": "H"
"refId": "I"
},
{
"datasource": {
@ -5807,7 +5818,7 @@
"expr": "histogram_quantile(0.95, sum(rate(litellm_redis_window_spend_update_queue_latency_bucket[$__rate_interval])) by (le))",
"legendFormat": "redis_window_spend_update_queue",
"range": true,
"refId": "I"
"refId": "J"
},
{
"datasource": {
@ -5818,7 +5829,7 @@
"expr": "histogram_quantile(0.95, sum(rate(litellm_reset_budget_job_latency_bucket[$__rate_interval])) by (le))",
"legendFormat": "reset_budget_job",
"range": true,
"refId": "J"
"refId": "K"
},
{
"datasource": {
@ -5829,7 +5840,7 @@
"expr": "histogram_quantile(0.95, sum(rate(litellm_router_latency_bucket[$__rate_interval])) by (le))",
"legendFormat": "router",
"range": true,
"refId": "K"
"refId": "L"
},
{
"datasource": {
@ -5840,7 +5851,7 @@
"expr": "histogram_quantile(0.95, sum(rate(litellm_self_latency_bucket[$__rate_interval])) by (le))",
"legendFormat": "self",
"range": true,
"refId": "L"
"refId": "M"
}
],
"title": "Service latency p95 (litellm_<service>_latency)",
@ -5888,6 +5899,28 @@
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"editorMode": "code",
"expr": "sum(rate(litellm_anthropic_wif_total_requests_total[$__rate_interval]))",
"legendFormat": "anthropic_wif",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"editorMode": "code",
"expr": "sum(rate(litellm_anthropic_wif_cache_total_requests_total[$__rate_interval]))",
"legendFormat": "anthropic_wif_cache",
"range": true,
"refId": "B"
},
{
"datasource": {
"type": "prometheus",
@ -5897,7 +5930,7 @@
"expr": "sum(rate(litellm_auth_total_requests_total[$__rate_interval]))",
"legendFormat": "auth",
"range": true,
"refId": "A"
"refId": "C"
},
{
"datasource": {
@ -5908,7 +5941,7 @@
"expr": "sum(rate(litellm_batch_write_to_db_total_requests_total[$__rate_interval]))",
"legendFormat": "batch_write_to_db",
"range": true,
"refId": "B"
"refId": "D"
},
{
"datasource": {
@ -5919,7 +5952,7 @@
"expr": "sum(rate(litellm_postgres_total_requests_total[$__rate_interval]))",
"legendFormat": "postgres",
"range": true,
"refId": "C"
"refId": "E"
},
{
"datasource": {
@ -5930,7 +5963,7 @@
"expr": "sum(rate(litellm_proxy_pre_call_total_requests_total[$__rate_interval]))",
"legendFormat": "proxy_pre_call",
"range": true,
"refId": "D"
"refId": "F"
},
{
"datasource": {
@ -5941,7 +5974,7 @@
"expr": "sum(rate(litellm_redis_total_requests_total[$__rate_interval]))",
"legendFormat": "redis",
"range": true,
"refId": "E"
"refId": "G"
},
{
"datasource": {
@ -5952,7 +5985,7 @@
"expr": "sum(rate(litellm_redis_daily_org_spend_update_queue_total_requests_total[$__rate_interval]))",
"legendFormat": "redis_daily_org_spend_update_queue",
"range": true,
"refId": "F"
"refId": "H"
},
{
"datasource": {
@ -5963,7 +5996,7 @@
"expr": "sum(rate(litellm_redis_daily_tag_spend_update_queue_total_requests_total[$__rate_interval]))",
"legendFormat": "redis_daily_tag_spend_update_queue",
"range": true,
"refId": "G"
"refId": "I"
},
{
"datasource": {
@ -5974,7 +6007,7 @@
"expr": "sum(rate(litellm_redis_daily_team_spend_update_queue_total_requests_total[$__rate_interval]))",
"legendFormat": "redis_daily_team_spend_update_queue",
"range": true,
"refId": "H"
"refId": "J"
},
{
"datasource": {
@ -5985,7 +6018,7 @@
"expr": "sum(rate(litellm_redis_window_spend_update_queue_total_requests_total[$__rate_interval]))",
"legendFormat": "redis_window_spend_update_queue",
"range": true,
"refId": "I"
"refId": "K"
},
{
"datasource": {
@ -5996,7 +6029,7 @@
"expr": "sum(rate(litellm_reset_budget_job_total_requests_total[$__rate_interval]))",
"legendFormat": "reset_budget_job",
"range": true,
"refId": "J"
"refId": "L"
},
{
"datasource": {
@ -6007,7 +6040,7 @@
"expr": "sum(rate(litellm_router_total_requests_total[$__rate_interval]))",
"legendFormat": "router",
"range": true,
"refId": "K"
"refId": "M"
},
{
"datasource": {
@ -6018,7 +6051,7 @@
"expr": "sum(rate(litellm_self_total_requests_total[$__rate_interval]))",
"legendFormat": "self",
"range": true,
"refId": "L"
"refId": "N"
}
],
"title": "Service request rate (litellm_<service>_total_requests)",
@ -6066,6 +6099,28 @@
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"editorMode": "code",
"expr": "sum(rate(litellm_anthropic_wif_failed_requests_total[$__rate_interval])) by (error_class)",
"legendFormat": "anthropic_wif / {{error_class}}",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"editorMode": "code",
"expr": "sum(rate(litellm_anthropic_wif_cache_failed_requests_total[$__rate_interval])) by (error_class)",
"legendFormat": "anthropic_wif_cache / {{error_class}}",
"range": true,
"refId": "B"
},
{
"datasource": {
"type": "prometheus",
@ -6075,7 +6130,7 @@
"expr": "sum(rate(litellm_auth_failed_requests_total[$__rate_interval])) by (error_class)",
"legendFormat": "auth / {{error_class}}",
"range": true,
"refId": "A"
"refId": "C"
},
{
"datasource": {
@ -6086,7 +6141,7 @@
"expr": "sum(rate(litellm_batch_write_to_db_failed_requests_total[$__rate_interval])) by (error_class)",
"legendFormat": "batch_write_to_db / {{error_class}}",
"range": true,
"refId": "B"
"refId": "D"
},
{
"datasource": {
@ -6097,7 +6152,7 @@
"expr": "sum(rate(litellm_postgres_failed_requests_total[$__rate_interval])) by (error_class)",
"legendFormat": "postgres / {{error_class}}",
"range": true,
"refId": "C"
"refId": "E"
},
{
"datasource": {
@ -6108,7 +6163,7 @@
"expr": "sum(rate(litellm_proxy_pre_call_failed_requests_total[$__rate_interval])) by (error_class)",
"legendFormat": "proxy_pre_call / {{error_class}}",
"range": true,
"refId": "D"
"refId": "F"
},
{
"datasource": {
@ -6119,7 +6174,7 @@
"expr": "sum(rate(litellm_redis_failed_requests_total[$__rate_interval])) by (error_class)",
"legendFormat": "redis / {{error_class}}",
"range": true,
"refId": "E"
"refId": "G"
},
{
"datasource": {
@ -6130,7 +6185,7 @@
"expr": "sum(rate(litellm_redis_daily_org_spend_update_queue_failed_requests_total[$__rate_interval])) by (error_class)",
"legendFormat": "redis_daily_org_spend_update_queue / {{error_class}}",
"range": true,
"refId": "F"
"refId": "H"
},
{
"datasource": {
@ -6141,7 +6196,7 @@
"expr": "sum(rate(litellm_redis_daily_tag_spend_update_queue_failed_requests_total[$__rate_interval])) by (error_class)",
"legendFormat": "redis_daily_tag_spend_update_queue / {{error_class}}",
"range": true,
"refId": "G"
"refId": "I"
},
{
"datasource": {
@ -6152,7 +6207,7 @@
"expr": "sum(rate(litellm_redis_daily_team_spend_update_queue_failed_requests_total[$__rate_interval])) by (error_class)",
"legendFormat": "redis_daily_team_spend_update_queue / {{error_class}}",
"range": true,
"refId": "H"
"refId": "J"
},
{
"datasource": {
@ -6163,7 +6218,7 @@
"expr": "sum(rate(litellm_redis_window_spend_update_queue_failed_requests_total[$__rate_interval])) by (error_class)",
"legendFormat": "redis_window_spend_update_queue / {{error_class}}",
"range": true,
"refId": "I"
"refId": "K"
},
{
"datasource": {
@ -6174,7 +6229,7 @@
"expr": "sum(rate(litellm_reset_budget_job_failed_requests_total[$__rate_interval])) by (error_class)",
"legendFormat": "reset_budget_job / {{error_class}}",
"range": true,
"refId": "J"
"refId": "L"
},
{
"datasource": {
@ -6185,7 +6240,7 @@
"expr": "sum(rate(litellm_router_failed_requests_total[$__rate_interval])) by (error_class)",
"legendFormat": "router / {{error_class}}",
"range": true,
"refId": "K"
"refId": "M"
},
{
"datasource": {
@ -6196,7 +6251,7 @@
"expr": "sum(rate(litellm_self_failed_requests_total[$__rate_interval])) by (error_class)",
"legendFormat": "self / {{error_class}}",
"range": true,
"refId": "L"
"refId": "N"
}
],
"title": "Service failure rate (litellm_<service>_failed_requests)",

2
cookbook/litellm_proxy_server/grafana_dashboard/dashboard_all_metrics/readme.md
View file

@ -1,6 +1,6 @@
# LiteLLM All Prometheus Metrics dashboard
Every `litellm_*` metric family the proxy can expose on `/metrics` (136 families across 97 panels), grouped into rows: proxy traffic, latency, spend and tokens, cache, LLM API deployments, key and team rate limits, budgets, guardrails, MCP, managed files and batches, users and teams, the Redis circuit breaker, the spend log cleanup job, and the `prometheus_system` service callback metrics (per-service latency, request and failure rates, spend update queue sizes). Panel titles are the metric names so you can grep the JSON for the metric you care about
Every `litellm_*` metric family the proxy can expose on `/metrics` (141 families across 97 panels), grouped into rows: proxy traffic, latency, spend and tokens, cache, LLM API deployments, key and team rate limits, budgets, guardrails, MCP, managed files and batches, users and teams, the Redis circuit breaker, the spend log cleanup job, and the `prometheus_system` service callback metrics (per-service latency, request and failure rates, spend update queue sizes). Panel titles are the metric names so you can grep the JSON for the metric you care about
Import `grafana_dashboard.json` from **Dashboards > New > Import** and pick your Prometheus data source when prompted (the `DS_PROMETHEUS` variable). Counters are plotted as `rate()` over `$__rate_interval`, histograms as p50 / p95 / p99, gauges as the raw value grouped by the most useful label. Every query names the metric exactly as the proxy emits it (counters carry the `_total` suffix the Prometheus client adds), and `tests/unit/integrations/test_prometheus_metric_name_consistency.py` fails if a metric is renamed without updating this dashboard

3
litellm/llms/anthropic/prompt_cache_prediction.py
View file

@ -526,7 +526,6 @@ async def count_prompt_tokens(
) -> int | None:
try:
native: Final = _CountBody.model_validate(body)
count_url: Final = _messages_url(model, api_key, api_base) + "/count_tokens"
result: Final = _CountResult.model_validate(
await _counter.handle_count_tokens_request(
model=model,
@ -534,7 +533,7 @@ async def count_prompt_tokens(
tools=_count_objects(native.tools) if native.tools is not None else None,
system=_JSON_OBJECT.validate_python(MappingProxyType({"system": native.system}))["system"],
api_key=api_key,
api_base=count_url,
api_base=api_base,
optional_params=_JSON_OBJECT.validate_python(
MappingProxyType({key: body[key] for key in COUNT_TOKEN_OPTION_NAMES if key in body})
),

31
litellm/types/litellm_params.py
View file

@ -104,10 +104,41 @@ class BedrockBatchConnection:
bedrock_tags: Sequence[Mapping[str, str]] | None = None
@dataclass(frozen=True, slots=True, kw_only=True)
class AnthropicFederationConnection:
anthropic_federation_rule_id: str | None = None
anthropic_organization_id: str | None = None
anthropic_service_account_id: str | None = None
anthropic_federation_workspace_id: str | None = None
anthropic_identity_token_file: str | None = None
anthropic_identity_token: str | None = None
anthropic_identity_source: str | None = None
anthropic_issuer_url: str | None = None
anthropic_issuer_subject: str | None = None
anthropic_issuer_audience: str | None = None
anthropic_issuer_ttl_seconds: int | None = None
anthropic_issuer_signing_key_ref: str | None = None
anthropic_keycloak_token_url: str | None = None
anthropic_keycloak_client_id: str | None = None
anthropic_keycloak_auth_method: str | None = None
anthropic_keycloak_client_secret_ref: str | None = None
anthropic_keycloak_scope: str | None = None
anthropic_disable_workload_identity_federation: bool | None = None
@dataclass(frozen=True, slots=True, kw_only=True)
class OpenAIFederationConnection:
openai_identity_provider_id: str | None = None
openai_service_account_id: str | None = None
openai_identity_token_file: str | None = None
@dataclass(frozen=True, slots=True, kw_only=True)
class ConnectionSettings:
provider: ProviderConnection
bedrock_batch: BedrockBatchConnection
anthropic_federation: AnthropicFederationConnection
openai_federation: OpenAIFederationConnection
@dataclass(frozen=True, slots=True, kw_only=True)

1
litellm/types/utils.py
View file

@ -3965,7 +3965,6 @@ secret_bearing_wif_litellm_params: Final = tuple(sorted(WIF_SECRET_BEARING_KEYS)
all_litellm_params = [ # rebind-ok: two star imports in litellm/__init__.py re-bind it
*OWNED_KWARG_NAMES,
*KWARG_ARTIFACTS,
*server_owned_wif_litellm_params,
*StandardCallbackDynamicParams.__annotations__,
*CustomPricingLiteLLMParams.model_fields,
]

41
litellm/types/workload_identity.py
View file

@ -1,9 +1,9 @@
"""litellm_params keys that configure workload identity federation.
The kwargs funnel (``litellm_core_utils.get_litellm_params``) and the request-body ban list
(``types.utils.all_litellm_params``) both derive from these sets, so they live in a module with
no litellm imports that either side can reach without a cycle. Every key here rides the funnel
into ``litellm_params`` and is banned from request bodies, which also covers
The key sets derive from the federation connection leaves in ``types.litellm_params``, so the
kwargs funnel (``litellm_core_utils.get_litellm_params``) and the request-body ban list
(``types.utils.all_litellm_params``) read one declaration. Every key rides the funnel into
``litellm_params`` and is banned from request bodies, which also covers
``anthropic_disable_workload_identity_federation``: the proxy sets it when a client redirects
``api_base`` so a federated deployment stops minting for a base the caller chose, and a caller
must not be able to set it in either direction.
@ -11,36 +11,11 @@ must not be able to set it in either direction.
from typing import Final
ANTHROPIC_WIF_KWARGS_KEYS: Final = frozenset(
{
"anthropic_federation_rule_id",
"anthropic_organization_id",
"anthropic_service_account_id",
"anthropic_federation_workspace_id",
"anthropic_identity_token_file",
"anthropic_identity_token",
"anthropic_identity_source",
"anthropic_issuer_url",
"anthropic_issuer_subject",
"anthropic_issuer_audience",
"anthropic_issuer_ttl_seconds",
"anthropic_issuer_signing_key_ref",
"anthropic_keycloak_token_url",
"anthropic_keycloak_client_id",
"anthropic_keycloak_auth_method",
"anthropic_keycloak_client_secret_ref",
"anthropic_keycloak_scope",
"anthropic_disable_workload_identity_federation",
}
)
from litellm.types.litellm_params import AnthropicFederationConnection, OpenAIFederationConnection, wire_names
OPENAI_WIF_KWARGS_KEYS: Final = frozenset(
{
"openai_identity_provider_id",
"openai_service_account_id",
"openai_identity_token_file",
}
)
ANTHROPIC_WIF_KWARGS_KEYS: Final = frozenset(wire_names(AnthropicFederationConnection))
OPENAI_WIF_KWARGS_KEYS: Final = frozenset(wire_names(OpenAIFederationConnection))
WIF_SECRET_BEARING_KEYS: Final = frozenset(
{

15
tests/unit/llms/anthropic/test_anthropic_prompt_cache_prediction.py
View file

@ -115,7 +115,16 @@ def test_prediction_header_eligibility(headers: Mapping[str, str], supported: bo
@pytest.mark.asyncio
async def test_provider_count_uses_same_version_and_preserves_native_input(monkeypatch: pytest.MonkeyPatch) -> None:
@pytest.mark.parametrize(
"api_base, count_url",
[
(None, "https://api.anthropic.com/v1/messages/count_tokens"),
("https://gateway.example/v1/messages", "https://gateway.example/v1/messages/count_tokens"),
],
)
async def test_provider_count_uses_same_version_and_preserves_native_input(
monkeypatch: pytest.MonkeyPatch, api_base: str | None, count_url: str
) -> None:
body: Final = _body()
requests: Final[list[httpx.Request]] = []
@ -128,12 +137,12 @@ async def test_provider_count_uses_same_version_and_preserves_native_input(monke
client.client = httpx.AsyncClient(transport=httpx.MockTransport(provider))
monkeypatch.setattr(count_handler, "get_async_httpx_client", lambda **kwargs: client)
try:
assert await count_prompt_tokens(_MODEL, _KEY, body) == 311
assert await count_prompt_tokens(_MODEL, _KEY, body, api_base=api_base) == 311
finally:
await client.client.aclose()
assert len(requests) == 1
assert requests[0].headers["anthropic-version"] == DEFAULT_ANTHROPIC_API_VERSION
assert requests[0].url == "https://api.anthropic.com/v1/messages/count_tokens"
assert requests[0].url == count_url
assert json.loads(requests[0].content) == body

50
tests/unit/types/test_litellm_params.py
View file

@ -95,6 +95,27 @@ CONNECTION_NAMES: Final = (
"s3_secret_access_key",
"s3_encryption_key_id",
"bedrock_tags",
"anthropic_federation_rule_id",
"anthropic_organization_id",
"anthropic_service_account_id",
"anthropic_federation_workspace_id",
"anthropic_identity_token_file",
"anthropic_identity_token",
"anthropic_identity_source",
"anthropic_issuer_url",
"anthropic_issuer_subject",
"anthropic_issuer_audience",
"anthropic_issuer_ttl_seconds",
"anthropic_issuer_signing_key_ref",
"anthropic_keycloak_token_url",
"anthropic_keycloak_client_id",
"anthropic_keycloak_auth_method",
"anthropic_keycloak_client_secret_ref",
"anthropic_keycloak_scope",
"anthropic_disable_workload_identity_federation",
"openai_identity_provider_id",
"openai_service_account_id",
"openai_identity_token_file",
)
OPTION_NAMES: Final = (
@ -491,6 +512,12 @@ TYPE_HINT_NAMESPACE: Final[Mapping[str, object]] = {
LEAF_SAMPLES: Final[Mapping[type, Mapping[str, object]]] = {
litellm_params.ProviderConnection: {"api_key": "k", "request_timeout": 1.5},
litellm_params.BedrockBatchConnection: {"aws_batch_role_arn": "arn", "bedrock_tags": ({"k": "v"},)},
litellm_params.AnthropicFederationConnection: {
"anthropic_federation_rule_id": "fdrl_1",
"anthropic_issuer_ttl_seconds": 300,
"anthropic_disable_workload_identity_federation": True,
},
litellm_params.OpenAIFederationConnection: {"openai_identity_provider_id": "idp_1"},
litellm_params.DispatchOptions: {"custom_llm_provider": "openai"},
litellm_params.RoutingOptions: {
"fallbacks": [{"model": "gpt-4o", "api_key": "k", "temperature": 0}],
@ -526,6 +553,8 @@ LEAF_SAMPLES: Final[Mapping[type, Mapping[str, object]]] = {
LEAF_BAD_SAMPLES: Final[Mapping[type, Mapping[str, object]]] = {
litellm_params.ProviderConnection: {"api_key": 1},
litellm_params.BedrockBatchConnection: {"aws_batch_role_arn": 1},
litellm_params.AnthropicFederationConnection: {"anthropic_issuer_ttl_seconds": "300"},
litellm_params.OpenAIFederationConnection: {"openai_identity_provider_id": 1},
litellm_params.DispatchOptions: {"custom_llm_provider": 1},
litellm_params.RoutingOptions: {"num_retries": "2"},
litellm_params.DeploymentOptions: {"rpm": "2"},
@ -620,6 +649,24 @@ def test_routing_options_accept_every_strategy_the_router_accepts(strategy: str)
NAMES_SHARED_WITH_TYPED_MODELS: Final[Mapping[str, tuple[str, ...]]] = MappingProxyType(
{
"credentials": (
"anthropic_disable_workload_identity_federation",
"anthropic_federation_rule_id",
"anthropic_federation_workspace_id",
"anthropic_identity_source",
"anthropic_identity_token",
"anthropic_identity_token_file",
"anthropic_issuer_audience",
"anthropic_issuer_signing_key_ref",
"anthropic_issuer_subject",
"anthropic_issuer_ttl_seconds",
"anthropic_issuer_url",
"anthropic_keycloak_auth_method",
"anthropic_keycloak_client_id",
"anthropic_keycloak_client_secret_ref",
"anthropic_keycloak_scope",
"anthropic_keycloak_token_url",
"anthropic_organization_id",
"anthropic_service_account_id",
"api_base",
"api_key",
"api_version",
@ -630,6 +677,9 @@ NAMES_SHARED_WITH_TYPED_MODELS: Final[Mapping[str, tuple[str, ...]]] = MappingPr
"bedrock_tags",
"client_id",
"client_secret",
"openai_identity_provider_id",
"openai_identity_token_file",
"openai_service_account_id",
"region_name",
"s3_access_key_id",
"s3_bucket_name",