litellm/litellm/types
devin-ai-integration[bot] b1d0e45f8d
feat(policy-engine): stream detect-only post_call pipeline steps live when buffering is off (#45516)
* feat(policy-engine): stream detect-only post_call pipeline steps live when buffering is off

* fix(policy-engine): scan live pipeline streams a provider error cuts short and discard rewrites per step

A live detect-only pipeline now scans the chunks the client received when the provider fails mid-stream, then re-raises the error. Each step's rewrite is discarded right after the step, so later steps scan the text the client actually received.

* fix(proxy): keep a guardrail verdict recorded after a stream failure on the failure spend row

---------

Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
2026-10-09 15:46:51 -07:00
..
containers refactor: expose public hidden_params accessors (#44668) 2026-10-07 00:01:33 -07:00
google_genai refactor: expose public hidden_params accessors (#44668) 2026-10-07 00:01:33 -07:00
images chore(lint): remove litellm/types from the ruff lint exclusion 2026-08-05 01:10:15 -07:00
integrations feat(prometheus): expose per-project per-model rate limit allowed and used gauges (#43561) 2026-10-08 12:03:29 -05:00
interactions refactor: expose public hidden_params accessors (#44668) 2026-10-07 00:01:33 -07:00
litellm_core_utils fix(streaming): keep an explicit provider prompt_tokens=0 or completion_tokens=0 in streamed usage 2026-09-21 14:01:08 -07:00
llms refactor(sdk): separate core AWS and tokenizer dependencies (#44447) 2026-10-08 19:07:57 -07:00
management_endpoints feat(ui): add auto-router usage and savings table (#45152) 2026-10-07 15:04:07 -07:00
mcp_server feat(mcp): support upstream OAuth client metadata identities (#45231) 2026-10-08 04:10:34 -07:00
passthrough_endpoints perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
prompts perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
proxy feat(policy-engine): stream detect-only post_call pipeline steps live when buffering is off (#45516) 2026-10-09 15:46:51 -07:00
repositories refactor(repositories): daily activity repository with centralized bounded usage queries (#43398) 2026-10-01 16:02:01 -07:00
responses refactor: expose public hidden_params accessors (#44668) 2026-10-07 00:01:33 -07:00
secret_managers feat(secret_managers): support customer-managed KMS key for virtual keys stored in AWS Secrets Manager (#40475) 2026-09-11 09:54:08 -07:00
videos refactor: expose public hidden_params accessors (#44668) 2026-10-07 00:01:33 -07:00
access_group.py perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
adapter.py fix(lint): bring basedpyright rule counts back under their budget limits 2026-08-05 10:23:02 -07:00
agents.py refactor: expose public hidden_params accessors (#44668) 2026-10-07 00:01:33 -07:00
caching.py fix(caching): never store or serve a chat completion with no choices (#44709) 2026-10-06 20:07:30 +00:00
completion.py refactor: expose core private helpers under public names (#44871) 2026-10-07 00:05:27 +00:00
compression.py chore(lint): remove litellm/types from the ruff lint exclusion 2026-08-05 01:10:15 -07:00
decisions.py feat(decisions): add OpenAI as a Decisions provider behind a shared decisions format (#45214) 2026-10-08 04:57:41 +00:00
embedding.py perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
files.py fix(types): resolve the four type-discipline additions surfaced by the staging merge 2026-08-05 11:05:53 -07:00
fine_tuning.py (feat) POST /fine_tuning/jobs support passing vertex specific hyper params (#7490) 2025-01-01 07:44:48 -08:00
guardrail_base_init.py refactor(types): replace Any with real types across 54 more backend files 2026-08-29 19:00:43 +00:00
guardrails.py feat(guardrails): per-mode stream_scope with bedrock stream and pass-through fixes (#43801) 2026-10-08 13:46:53 -07:00
lar1.py perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
litellm_params.py feat(github_copilot): per-user GitHub OAuth connections for Copilot credentials (#45241) 2026-10-09 15:19:07 -07:00
mcp.py feat(mcp): translate input requests and bind continuations (#45464) 2026-10-08 20:10:10 -07:00
memory_management.py perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
model_insights.py perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
object_permission.py feat(proxy): granular key/team access control for Claude Code marketplace plugins (#40518) 2026-09-10 14:26:09 -07:00
policy_engine.py chore(lint): remove litellm/types from the ruff lint exclusion 2026-08-05 01:10:15 -07:00
rag.py perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
realtime.py perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
rerank.py refactor: expose public hidden_params accessors (#44668) 2026-10-07 00:01:33 -07:00
roi_calculator.py perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
roi_observed.py perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
router.py feat(microsoft_365_copilot): add Microsoft 365 Copilot chat provider with OAuth token exchange (#45158) 2026-10-09 15:19:07 -07:00
router_weights.py fix(router): honor team and key provider weights 2026-09-14 23:31:52 -07:00
scheduler.py Squashed commit of the following: (#9709) 2025-04-02 21:24:54 -07:00
search.py chore(lint): remove litellm/types from the ruff lint exclusion 2026-08-05 01:10:15 -07:00
services.py perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
tag_management.py perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
tool_management.py perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
utils.py feat(github_copilot): per-user GitHub OAuth connections for Copilot credentials (#45241) 2026-10-09 15:19:07 -07:00
vector_store_files.py chore(lint): remove litellm/types from the ruff lint exclusion 2026-08-05 01:10:15 -07:00
vector_stores.py perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
workload_identity.py feat(anthropic): workload identity federation and pluggable identity sources (#44448) 2026-10-03 17:08:30 -07:00