scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-17 04:34:25 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 172
litellm/litellm
History
yucheng-berri 53729cf747 fix(logging): keep replayed instructions and router usage marker under redaction 
The shared request body keeps system and instructions again, so spend logs
store them and previous_response_id follow-ups replay the real instructions.
Per-callback copies still redact them.

Provider-specific fields in metadata.hidden_params are cleared in place, so
the metadata dict keeps its identity and the router's counted-usage marker
stays visible to deployment_callback_on_success (no double tpm/rpm count).
2026-10-12 12:35:11 -07:00
..
_v2
a2a_protocol refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
anthropic_interface
assistants refactor(types): replace Any with proven types in 157 files (#44798) 2026-10-06 15:31:54 +00:00
batch_completion
batches refactor(proxy): expose public names for private proxy helpers (#45170) 2026-10-07 18:59:27 -07:00
caching fix(caching): give RedisClusterCache one async client per event loop (#45784) 2026-10-10 12:23:45 -07:00
chat_completions refactor(python-bridge): ship a signature base and read the resolved call (#45450) 2026-10-08 17:20:29 -07:00
completion_extras fix(responses): keep a flagged hosted deployment's prompt cache breakpoint on the chat bridge (#45500) 2026-10-09 04:00:39 -07:00
compression refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
containers refactor: expose core private helpers under public names (#44871) 2026-10-07 00:05:27 +00:00
decisions feat(guardrails): add decision model guardrail with Admin UI flow (#45663) 2026-10-10 16:00:27 -07:00
embeddings refactor(python-bridge): ship a signature base and read the resolved call (#45450) 2026-10-08 17:20:29 -07:00
endpoints/speech/speech_to_completion_bridge
evals
experimental_mcp_client fix(mcp): keep one upstream MCP session per gateway session across tool calls (#42741) 2026-10-10 14:49:45 -07:00
files refactor: expose core private helpers under public names (#44871) 2026-10-07 00:05:27 +00:00
fine_tuning
google_genai refactor(proxy): expose public names for private proxy helpers (#45170) 2026-10-07 18:59:27 -07:00
harness refactor(types): replace Any with proven types in 16 files (#45029) 2026-10-07 04:31:51 -07:00
images refactor: expose public hidden_params accessors (#44668) 2026-10-07 00:01:33 -07:00
integrations fix(langfuse): log Responses API token usage instead of zeros (#42212) 2026-10-10 16:42:59 -07:00
interactions refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
litellm_core_utils fix(logging): keep replayed instructions and router usage marker under redaction 2026-10-12 12:35:11 -07:00
llms fix(guardrails): scan or refuse attachments in the bedrock guardrail (#43383) 2026-10-10 16:48:37 -07:00
messages feat(rust): add the Vertex AI Anthropic Messages config (#45626) 2026-10-09 16:29:45 -07:00
models refactor(skills): move NewSkillRequest to litellm.models.skills (#45768) 2026-10-10 20:33:16 +00:00
ocr refactor(python-bridge): ship a signature base and read the resolved call (#45450) 2026-10-08 17:20:29 -07:00
passthrough refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
proxy feat(ui): streamline auto-router setup with deployed decision models (#45913) 2026-10-10 20:49:59 -07:00
proxy_auth
rag perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
realtime_api fix(vertex_ai): dial the multi-region Live API host for realtime sessions (#45166) 2026-10-07 17:39:38 -07:00
repositories feat(usage): add top users by spend and user activity views (#45310) 2026-10-10 12:21:43 -07:00
rerank_api
responses refactor(sdk): import UserAPIKeyAuth from litellm.types.proxy.auth (#45806) 2026-10-10 21:27:48 +00:00
router_strategy feat(ui): streamline auto-router setup with deployed decision models (#45913) 2026-10-10 20:49:59 -07:00
router_utils feat(ui): streamline auto-router setup with deployed decision models (#45913) 2026-10-10 20:49:59 -07:00
rust_bridge docs(agents): ban semicolons and colons in human-facing text (#45684) 2026-10-09 16:36:32 -07:00
sandbox
search refactor(types): replace Any with proven types in 157 files (#44798) 2026-10-06 15:31:54 +00:00
secret_managers refactor(types): move CommonProxyErrors into litellm/types/proxy (#45745) 2026-10-10 19:06:04 +00:00
skills
systemone feat(sdk): add litellm.systemone and trim litellm.decisions to the OpenAI shape (#45846) 2026-10-10 22:16:51 +00:00
tracing docs(agents): ban semicolons and colons in human-facing text (#45684) 2026-10-09 16:36:32 -07:00
types feat(ui): load Home page What's new launches from /public/whats_new at runtime (#45912) 2026-10-10 19:42:18 -07:00
vector_store_files
vector_stores refactor: expose core private helpers under public names (#44871) 2026-10-07 00:05:27 +00:00
videos refactor(types): replace Any with proven types in 157 files (#44798) 2026-10-06 15:31:54 +00:00
__init__.py feat(ui): load Home page What's new launches from /public/whats_new at runtime (#45912) 2026-10-10 19:42:18 -07:00
_internal_context.py
_lazy_imports.py refactor: expose core private helpers under public names (#44871) 2026-10-07 00:05:27 +00:00
_lazy_imports_registry.py feat(scaledown): add native text provider support (#44168) 2026-10-10 14:01:17 -07:00
_logging.py perf(proxy): keep stream end output and Redis cache debug strings off the event loop (#45252) 2026-10-09 14:56:16 -07:00
_redis.py refactor: expose core private helpers under public names (#44871) 2026-10-07 00:05:27 +00:00
_redis_credential_provider.py refactor: expose core private helpers under public names (#44871) 2026-10-07 00:05:27 +00:00
_service_logger.py refactor(sdk): import UserAPIKeyAuth from litellm.types.proxy.auth (#45806) 2026-10-10 21:27:48 +00:00
_uuid.py
_version.py feat(sdk): build core from an independent packaging manifest (#44340) 2026-10-08 18:40:14 -07:00
anthropic_beta_headers_config.json fix(vertex_ai): forward the inline-tools-2026-09-15 beta to Vertex and Anthropic (#45297) 2026-10-08 12:27:52 -07:00
anthropic_beta_headers_manager.py refactor(types): move SpanAttributes, SpecialHeaders and AllowedModelRegion out of proxy._types (#44717) 2026-10-05 21:40:13 -07:00
blog_posts.json
budget_manager.py
constants.py fix(mcp): keep one upstream MCP session per gateway session across tool calls (#42741) 2026-10-10 14:49:45 -07:00
cost.json
cost_calculator.py feat(sdk): add litellm.systemone and trim litellm.decisions to the OpenAI shape (#45846) 2026-10-10 22:16:51 +00:00
exceptions.py fix: support OpenAI SDK 3 while retaining SDK 2 compatibility (#44927) 2026-10-09 19:45:50 -07:00
main.py feat(decisions): accept decisions as a model mode alongside evaluation (#45474) 2026-10-10 19:18:53 -07:00
model_prices_and_context_window_backup.json fix(azure): move gpt-realtime-translate deprecation_date to the Models API date (#45849) 2026-10-10 15:00:27 -07:00
policy_templates_backup.json
provider_endpoints_support_backup.json feat(scaledown): add native text provider support (#44168) 2026-10-10 14:01:17 -07:00
py.typed
router.py feat: forward-port dd user_email span tag and model hub description from internal staging (#42749) 2026-10-10 16:48:49 -07:00
scheduler.py fix(scheduler): remove a request's queue entry once it stops waiting (#43061) 2026-10-07 17:34:38 -07:00
setup_wizard.py
timeout.py
tool_loop.py
utils.py feat(sdk): add litellm.systemone and trim litellm.decisions to the OpenAI shape (#45846) 2026-10-10 22:16:51 +00:00