scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-12 23:01:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 87
litellm/tests/test_litellm/integrations
History
Exact
Yassin Kortam 05efbc6454
fix(guardrails): run pre_call hook once for model-level guardrails (#30543) 
* fix(guardrails): run pre_call hook once for model-level guardrails

A CustomGuardrail attached to a deployment via litellm_params.guardrails
gets its async_pre_call_hook invoked twice per request: once by the proxy
pre-call loop and again by async_pre_call_deployment_hook after the router
spreads the model-level guardrails into the top-level request kwargs.

Record in request metadata that the proxy pre-call loop already ran a given
guardrail, and have the deployment hook skip it when the marker is present.
Direct-SDK usage never runs the proxy loop, so the deployment hook stays the
sole invocation there and still fires exactly once.

The marker key is stripped from untrusted caller metadata so a request body
cannot suppress a model-only guardrail by pre-seeding it.

* fix(guardrails): mark pre_call dedup on the post-hook request data

Record the exactly-once marker after async_pre_call_hook runs, on the data
object that flows downstream, rather than before it. A guardrail whose hook
returns a brand-new request dict (instead of mutating or spreading the one it
received) would otherwise discard the marker, letting the deployment hook
re-run the guardrail a second time.

(cherry picked from commit 4faeabc254)
2026-06-17 11:25:28 -07:00
..
arize Litellm oss staging 250526 (#28770) 2026-05-26 11:57:39 -07:00
azure_storage style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
bitbucket fix: block path traversal SSRF in BitBucket, Arize Phoenix, and AssemblyAI clients (#26943) 2026-05-01 11:45:12 -07:00
cloudzero style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
compression_interception Prompt Compression - add it to the proxy (#25729) 2026-04-20 15:08:00 -07:00
datadog fix(datadog): drain cost-management queue + opt-in FinOps tag allowlist (#28487) 2026-05-28 21:04:04 +02:00
dotprompt style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
focus style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
gcs_bucket fix cloud storage file guards 2026-05-01 15:34:11 -07:00
gcs_pubsub Litellm fix GitHub action testing (#11163) 2025-05-26 14:41:42 -07:00
gitlab style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
langfuse style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
levo style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
litellm_agent Agent Builder - support new experimental agent builder, to ensure agents pass compliance checks (#21817) 2026-02-21 15:32:47 -08:00
open_telemetry fix(proxy): link passthrough success spans to the SERVER root OTEL span (#29315) 2026-05-29 21:30:45 -07:00
otel feat(otel): typed semconv-aligned OpenTelemetry instrumentation (#28909) 2026-05-29 23:15:27 -07:00
SlackAlerting style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
websearch_interception Emit native web_search_tool_result blocks for Anthropic clients (Claude Desktop / Cowork citations) (#27886) 2026-05-14 12:30:47 -07:00
rubrik_test_helpers.py Litellm oss staging 04 21 2026 2 (#26569) 2026-05-20 21:25:19 -07:00
test_agentops.py Litellm fix GitHub action testing (#11163) 2025-05-26 14:41:42 -07:00
test_anthropic_cache_control_hook.py fix(tests): replace deprecated Bedrock Claude 3.7 Sonnet model ID 2026-04-28 14:24:19 -07:00
test_athina.py Litellm fix GitHub action testing (#11163) 2025-05-26 14:41:42 -07:00
test_azure_sentinel.py Add Azure Sentinel audit log support (#27280) 2026-05-06 15:50:06 -07:00
test_braintrust_logging.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_braintrust_span_name.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_custom_guardrail.py fix(guardrails): run pre_call hook once for model-level guardrails (#30543) 2026-06-17 11:25:28 -07:00
test_custom_guardrail_recursion.py fix: recursive pydantic issue (#19531) 2026-01-22 19:56:41 -08:00
test_custom_prompt_management.py [Fix] CI/CD - Fix failing proxy and core integration tests (#17926) 2025-12-13 10:11:01 -08:00
test_deepeval.py fix: use fastuuid helper (#14903) 2025-09-25 15:47:01 -07:00
test_galileo.py fix(galileo): support hosted v2 spans API and string output extraction (#28771) 2026-05-26 14:10:33 -07:00
test_langfuse.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_langfuse_otel.py fix: prevent sys.modules["langfuse"] import failures in langfuse unit tests 2026-02-18 08:22:23 -03:00
test_langsmith_init.py Remove unneeded metadata info from LangSmith 2026-05-01 15:42:12 -07:00
test_mlflow.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_openmeter.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_opentelemetry.py feat(otel): add team_metadata, http.route, and model names to inference spans (#29319) 2026-05-30 00:54:30 -07:00
test_opentelemetry_dynamic_imports.py Make grpc dependency optional (#19447) 2026-01-20 19:03:52 -08:00
test_otel_guardrail_violation_spans.py feat: add guardrail violation span attributes and fix missing spans on pre-call blocks (#28364) 2026-05-21 15:49:42 -07:00
test_otel_team_attributes_matrix.py feat: propagate team_id and team_alias to all child OTEL spans (#28273) 2026-05-19 15:31:25 -07:00
test_prometheus_api_promql_escape.py fix(prometheus): quote api_key for PromQL string literal in spend lookup 2026-05-01 21:38:19 +00:00
test_prometheus_cache_metrics.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_prometheus_client_ip_user_agent.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_prometheus_custom_metadata_label_counts.py Fix Prometheus remaining metric zero values (#27348) 2026-05-06 17:22:20 -07:00
test_prometheus_end_user_cardinality.py perf: cap Prometheus end-user metric cardinality with TTL + LRU eviction (#27272) 2026-05-06 13:35:13 -07:00
test_prometheus_invalid_key_filtering.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_prometheus_labels.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_prometheus_metric_name_consistency.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_prometheus_missing_metrics.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_prometheus_none_metadata.py fix: guard against None metadata in prometheus metrics (#21489) 2026-02-18 12:40:45 -08:00
test_prometheus_queue_guardrail_metrics.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_prometheus_remaining_tokens_router_fallback.py fix(prometheus): emit litellm_remaining_tokens_metric for Bedrock and Vertex (#27705) 2026-05-13 17:40:59 -07:00
test_prometheus_services.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_prometheus_spend_logs_metadata.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_prometheus_stream_label.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_prometheus_token_detail_metrics.py feat(prometheus): emit per-token-type detail metrics (LIT-3220) (#28372) (#28378) 2026-05-23 12:17:42 -07:00
test_prometheus_user_team_metrics.py feat(prometheus): add user_email and user_alias to user budget metrics (#28155) 2026-05-18 16:28:14 -07:00
test_prompt_manager_ssti.py fix(security): sandbox jinja2 in gitlab/arize/bitbucket prompt managers 2026-05-02 09:14:02 +00:00
test_responses_background_cost.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_rubrik.py Litellm oss staging 04 21 2026 2 (#26569) 2026-05-20 21:25:19 -07:00
test_s3_v2.py decouple S3 audit-log config via s3_audit_callback_params 2026-05-05 13:23:32 -07:00
test_weave_otel.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00