scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-31 06:56:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 245
litellm/tests/integration/_support
History
mika-lt ebf84f8649
fix(caching): read the cache key's model group from the router's metadata for the call (#48917) 
* test(caching): audit #44542 response cache model group key

* fix(caching): key the response cache by the router's metadata bucket only

* fix(caching): read the router's model group before the caller's metadata

* fix(caching): read caching groups only beside the router's model group

A caller's own metadata.caching_groups on /v1/responses and /v1/messages could
still pick the cache key, so a string group let one model group fill another's
entry. The key now reads caching_groups only from the metadata that holds the
router's model_group.

* test(caching): type the planted caching groups parameter

* fix(caching): read the model group from the metadata that carries the call's deployment

A router call can carry a litellm_metadata it did not write, from the auto router's classifier embedding or an SDK caller, while the router writes its own group into metadata. The cache now picks the metadata source whose model_info matches the call's deployment, then falls back to the previous order.

* fix(caching): keep main's model group lookup for calls outside the router

---------

Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
2026-10-29 05:35:23 -07:00
..
__init__.py
actors.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00
agentic_probe.py fix(responses): honor caller stream flag when provider forces SSE (internal copy of #34095) (#41235) 2026-10-06 03:30:47 +00:00
anthropic_refusal.py fix(anthropic): keep refusal stop_reason and stop_details on the logged response (#46104) 2026-10-14 14:42:49 -07:00
anthropic_sse.py fix(router): retry a /v1/messages stream the provider drops before the first content chunk (#44276) 2026-10-05 22:53:39 +00:00
anthropic_thinking.py test: expect the list-position index on streamed thinking blocks in the integration suite (#46618) 2026-10-15 05:52:56 +00:00
asgi.py fix(ci): isolate integration workers and repair test fixtures (#45863) 2026-10-11 01:56:02 -07:00
async_server.py fix(bedrock): forward Nova Sonic realtime tool calls with their arguments (#46214) 2026-10-16 01:10:53 +00:00
aws_control_plane.py fix(bedrock): list the account's invocable models behind bedrock/* when check_provider_endpoint is on (#43981) 2026-10-09 14:14:17 -07:00
bedrock_discovery.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00
bedrock_realtime_peer.py fix(bedrock)!: block realtime replay after an input-first start and reject malformed Nova Sonic session settings (#46936) 2026-10-17 00:29:50 +00:00
bedrock_runtime_peer.py test(ci): fix six CircleCI test regressions on main (#44429) 2026-10-03 20:55:01 -07:00
browser_state.py test: add extension and browser integration contracts 2026-09-16 13:15:53 -07:00
budget.py test(integration): give chaos and timing tests a harness API and gate raw signals (#46031) 2026-10-12 05:27:33 -07:00
claude_code.py test(anthropic): native /v1/messages reasoning integration tests built on a captured Claude Code request (#43361) 2026-10-01 09:12:53 -07:00
client.py fix(caching): read the cache key's model group from the router's metadata for the call (#48917) 2026-10-29 05:35:23 -07:00
codex_vendor.py fix(responses): honor caller stream flag when provider forces SSE (internal copy of #34095) (#41235) 2026-10-06 03:30:47 +00:00
copilot_session_prometheus_worker.py fix(prometheus): count provider-side 401s in LLM failure and deployment metrics (#46668) 2026-10-26 17:57:06 -07:00
daily_activity.py fix(proxy): look up hashed key names with two spend log rows per key (#43656) 2026-09-29 20:21:55 -07:00
daily_spend_rows.py fix(ui): group cost optimization cache leakage by model group (#43008) 2026-09-24 23:51:51 -07:00
database.py test(integration): isolate every multi-worker integration suite by default (#46027) 2026-10-12 03:46:06 -07:00
database_relay.py test(integration): hand every harness server a port from one per-worker block (#46761) 2026-10-15 16:56:40 -07:00
deepseek_tokens.py fix(token_counter): count DeepSeek V4 text with DeepSeek's own tokenizer (#47353) 2026-10-20 03:43:35 +00:00
device_login.py fix(github_copilot): treat a malformed api-key.json like a missing one (#44723) 2026-10-29 03:46:44 -07:00
forward_proxy.py feat(strands_decider): call a Strands Decider on an AgentCore runtime ARN (#45678) 2026-10-09 22:51:19 -07:00
generation.py fix(tests): resolve the integration support package without run.py's PYTHONPATH 2026-09-15 21:10:08 -07:00
hook_count_probe.py fix(logging)!: fire one CustomLogger failure hook per async call outside the async flag list (#47124) 2026-10-20 15:19:14 -07:00
hook_counts.py fix(logging)!: fire one CustomLogger failure hook per async call outside the async flag list (#47124) 2026-10-20 15:19:14 -07:00
idle_gateway.py fix(http): restore the 15s aiohttp keep-alive default in the Python and Rust clients (#46355) 2026-10-14 10:50:11 -07:00
interception_vendor.py fix(websearch_interception): drop stream_options when forcing stream=False and replay it on the final stream (#45433) 2026-10-09 22:16:02 -07:00
mail.py feat(proxy): email alerts at configured percentages of a team member budget (#42665) 2026-09-26 02:42:45 +00:00
manifest.py fix(caching): never store or serve a chat completion with no choices (#44709) 2026-10-06 20:07:30 +00:00
mcp.py fix(mcp): upgrade to MCP SDK 2.3.0 and raise the per-event SSE size cap (#47034) 2026-10-20 16:00:00 -07:00
mcp_e2e_upstream_server.py test: migrate proxy security, schema migration and MCP legacy tests (#45937) 2026-10-11 16:17:24 -07:00
mcp_grants.py fix(mcp): resolve team-granted toolsets for non-admin keys and dashboard sessions (#43908) 2026-10-01 14:15:06 -07:00
mcp_stdio_peer.py test(integration): add MCP gateway coverage wave 1 with a dedicated mcp shard and proxy coverage artifact (#42711) 2026-09-23 07:48:46 -07:00
oauth_server.py test(integration): credential canary slots for MCP and pass-through credentials (#43308) 2026-09-28 17:10:51 -07:00
openai_wire.py test: fix shared-provider discovery, Codex catalog size and generated master key mismatches in CircleCI suites (#44905) 2026-10-07 00:11:25 +00:00
ordering.py fix(ci): isolate integration workers and repair test fixtures (#45863) 2026-10-11 01:56:02 -07:00
otlp_sink.py test(integration): hand every harness server a port from one per-worker block (#46761) 2026-10-15 16:56:40 -07:00
pdf_document.py fix(token_counter): price a base64 PDF document per page instead of as one image (#45301) 2026-10-08 21:20:46 -07:00
ports.py test(integration): hand every harness server a port from one per-worker block (#46761) 2026-10-15 16:56:40 -07:00
prisma_clients.py test: migrate tests/proxy_behavior into integration and unit tiers (#45939) 2026-10-11 08:28:42 -07:00
process.py fix(proxy): keep every startup line JSON when json_logs is on (#47035) 2026-10-27 14:49:07 -07:00
prometheus_series.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00
prompt_cache_breakpoint.py fix(responses): map input_audio blocks in the chat-to-Responses bridge (#45224) 2026-10-07 22:25:35 -07:00
provider.py fix(ci): isolate integration workers and repair test fixtures (#45863) 2026-10-11 01:56:02 -07:00
proxy.py perf(ci): isolate and shard integration suites (#44146) 2026-10-10 11:15:19 -07:00
redaction_probe.py fix(logging): deliver completed batch success callbacks consistently (#47192) 2026-10-18 09:19:04 -07:00
redis_breaker_worker.py fix(caching): report Redis circuit-breaker metrics through the Prometheus services logger (#46484) 2026-10-14 14:29:54 -07:00
redis_process.py test(integration): hand every harness server a port from one per-worker block (#46761) 2026-10-15 16:56:40 -07:00
responses_replay.py fix(responses): replay the original Responses item order, phase, and boundaries on the next chat turn (#48912) 2026-10-29 00:56:02 -07:00
responses_stream.py fix(responses): keep the provider code and message on top-level stream error events (#46438) 2026-10-14 16:16:46 -07:00
responses_vendor.py fix(responses): drop bridge-minted reasoning items from OpenAI replays (#44132) 2026-10-02 19:39:48 -07:00
responses_ws_peer.py fix(responses): write one spend-log row per native WebSocket turn (#46768) 2026-10-15 19:05:22 -07:00
riva.py test(nvidia_riva): audit #41021 (#48801) 2026-10-28 05:24:08 -07:00
routing.py test(integration): isolate every multi-worker integration suite by default (#46027) 2026-10-12 03:46:06 -07:00
runtime.py test(integration): wait for every worker to report the websocket session cap instead of sleeping (#47412) 2026-10-19 15:35:29 -07:00
safeguards_rig.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00
sagemaker_embedding.py feat(sagemaker)!: inference components and OpenAI-compatible embeddings (#44985) 2026-10-12 22:25:52 +00:00
scim.py fix(scim)!: delete a group through the team delete's bulk path instead of one member at a time (#47544) 2026-10-21 00:59:23 +00:00
sdk_models.py test(integration): build OpenAI and Anthropic SDK models before tests start threads (#46797) 2026-10-15 18:28:32 -07:00
sharding.py perf(ci): use native timing splits with bounded integration concurrency (#45837) 2026-10-10 13:35:11 -07:00
sigv4.py fix(bedrock): list the account's invocable models behind bedrock/* when check_provider_endpoint is on (#43981) 2026-10-09 14:14:17 -07:00
timing.py test(integration): give chaos and timing tests a harness API and gate raw signals (#46031) 2026-10-12 05:27:33 -07:00
tls.py fix(azure_storage): name Data Lake objects without base64 padding or slashes (#43914) 2026-09-30 18:17:13 -07:00
tool_rows.py feat(tool-policies): show the user who owns the key that discovered a tool (#43892) 2026-10-01 20:34:57 +00:00
tool_search.py fix(responses bridge): round-trip tool_search_call and tool_search_output items between turns (#46444) 2026-10-14 21:40:14 -07:00
upstream.py test(integration): stop GET /__observations from draining the upstream log (#47256) 2026-10-18 09:58:05 +00:00
vertex.py fix(vertex_ai): forward system and tools to partner model count_tokens (#43900) 2026-10-03 16:36:14 -07:00
wire.py fix(ollama): forward embedding credentials, headers and timeout (#48707) 2026-10-28 09:32:47 -07:00
worker_readiness.py test(integration): cover responses endpoint contracts (#44733) 2026-10-14 06:59:15 +00:00
workers.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00