litellm/litellm
mateo-berri d91bc3fb8e
Some checks are pending
Cost map pins recheck / rerun-cost-map-guard (push) Waiting to run
LiteLLM Rust DB / db-queries (push) Waiting to run
LiteLLM Rust / rust-test (push) Waiting to run
LiteLLM Rust / rust-lint (push) Waiting to run
LiteLLM Rust / rust-wheel (push) Waiting to run
Terraform Modules / fmt, validate, test (aws) (push) Waiting to run
Terraform Modules / fmt, validate, test (gcp) (push) Waiting to run
test(messages): use rstest for the new bedrock invoke thinking tests
2026-11-15 21:15:28 -08:00
..
a2a_protocol refactor(typing): clear about 1,100 basedpyright Any errors across 303 files (#49986) 2026-11-06 13:31:15 -08:00
accounting fix(proxy): alert on customer org, customer team, and customer member budgets (#51579) 2026-11-13 09:16:33 -08:00
anthropic_interface feat(anthropic): forward message threads on native /v1/messages (#50976) 2026-11-10 18:33:54 -08:00
assistants refactor(typing): clear 1141 basedpyright Any errors across 182 files (#50711) 2026-11-11 22:11:47 +00:00
batch_completion
batches refactor(s3-log): move the rust-backed s3 logger from s3_v3 to s3_v2 (#51893) 2026-11-14 22:24:23 -08:00
caching perf(caching): format dual cache debug logs lazily (#51902) 2026-11-15 06:50:04 +00:00
chat_completions fix(rust): run native async calls through python's async wrapper steps (#50423) 2026-11-10 00:24:20 +00:00
cli chore: move workspace packages under litellm (#51000) 2026-11-12 04:19:57 +00:00
completion_extras fix(openai): cap and bill web search rounds on Responses-pinned chat completions (#51802) 2026-11-14 14:36:10 -05:00
compression refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
containers feat(openai)!: honor per-deployment workload identity on non-chat routes (#39966) 2026-10-16 22:25:15 +00:00
decisions feat(gemini): support gemini-decision-1 on /v1/decisions and /v1/systemone (#51220) 2026-11-11 18:33:22 -08:00
deploy chore: move LiteLLM's configs and e2e tests off gpt-4o and gpt-4.1 before their 2027-01-14 shutdown (#51800) 2026-11-14 10:50:59 -08:00
embeddings fix(rust): run native async calls through python's async wrapper steps (#50423) 2026-11-10 00:24:20 +00:00
endpoints/speech/speech_to_completion_bridge feat(accounting): capture request usage through the durable meter (#49133) 2026-10-31 07:32:25 -07:00
enterprise bump: litellm-enterprise 0.1.85 -> 0.1.86, litellm-proxy-extras 0.4.116 -> 0.4.117 (#51876) 2026-11-14 16:42:35 -08:00
evals
experimental_mcp_client refactor(mcp): drop the experimental label from the MCP server and client paths (#48513) 2026-10-27 17:47:50 +00:00
extraction feat(extraction): add /v1/extraction with Cloudflare Clairic support (#47473) 2026-10-20 15:51:45 -07:00
files refactor(vertex_ai): remove unreachable VertexAIFilesHandler.afile_content (#51966) 2026-11-15 13:54:05 -08:00
fine_tuning fix(managed_files): send provider file ids when creating a fine-tuning job from managed files (#46552) 2026-10-19 14:40:15 -07:00
google_genai feat(custom_llm): let custom providers serve native generateContent (#51083) 2026-11-14 05:57:58 -05:00
harness refactor(typing): clear 1141 basedpyright Any errors across 182 files (#50711) 2026-11-11 22:11:47 +00:00
images feat(replicate): add video generation, image generation and text to speech through the predictions API (#51360) 2026-11-12 08:44:50 -08:00
integrations feat(dynamic_rate_limiter): customer organizations and keys borrow idle model capacity and split class shares (#51705) 2026-11-15 12:05:58 -08:00
interactions feat(vertex_ai): label Vertex requests with the caller's key, team, org, and project (#50732) 2026-11-14 00:39:01 -05:00
litellm_core_utils fix(count_tokens): return 400 for malformed Anthropic server-tool blocks (#51957) 2026-11-15 20:10:12 +00:00
llms Merge remote-tracking branch 'origin/main' into litellm_messages_drop_unsigned_thinking 2026-11-15 19:53:13 -08:00
mcp_client feat(mcp): cache upstream tool lists with an admin-set lifetime (#51160) 2026-11-12 08:48:04 -08:00
messages feat(messages): serve bedrock invoke messages on rust only (#51330) 2026-11-15 16:58:31 -08:00
models feat(proxy): support budget_limits windows on internal users (#51763) 2026-11-14 07:44:35 -05:00
ocr fix(rust): run native async calls through python's async wrapper steps (#50423) 2026-11-10 00:24:20 +00:00
packaging fix(packaging): keep the litellm-proxy package version in step with litellm (#51807) 2026-11-14 18:16:47 -08:00
passthrough refactor: remove redundant comments from fresh changes (#51163) 2026-11-11 09:18:18 -08:00
proxy feat(messages): serve bedrock invoke messages on rust only (#51330) 2026-11-15 16:58:31 -08:00
proxy-extras fix(db): index customer hierarchy filters (#51961) 2026-11-16 04:28:34 +08:00
proxy_auth
rag refactor(typing): clear 1141 basedpyright Any errors across 182 files (#50711) 2026-11-11 22:11:47 +00:00
realtime_api refactor(typing): clear 1141 basedpyright Any errors across 182 files (#50711) 2026-11-11 22:11:47 +00:00
redis feat(budgets): replace the python budget hold and settle engine with a rust engine admitted at auth (#51535) 2026-11-15 16:03:51 -08:00
repositories feat(db): classify errors and recycle poisoned pools like Prisma (#49801) 2026-11-14 15:28:11 -08:00
rerank_api refactor(typing): clear 1141 basedpyright Any errors across 182 files (#50711) 2026-11-11 22:11:47 +00:00
responses fix(openai): cap and bill web search rounds on Responses-pinned chat completions (#51802) 2026-11-14 14:36:10 -05:00
router_rust fix(router): free a failed rust router call's request without waiting for a full gc (#51963) 2026-11-15 17:04:38 -05:00
router_strategy fix(router)!: name the request size when usage-based routing refuses an over-tpm request (#51838) 2026-11-14 16:16:21 -05:00
router_utils feat(github_copilot): support GitHub App authentication with PEM upload (#51427) 2026-11-14 10:33:20 -05:00
runtime chore: move scripts and runtime sources under litellm (#51006) 2026-11-12 04:19:57 +00:00
rust test(messages): use rstest for the new bedrock invoke thinking tests 2026-11-15 21:15:28 -08:00
rust_bridge feat(messages): serve bedrock invoke messages on rust only (#51330) 2026-11-15 16:58:31 -08:00
sandbox refactor(typing): clear 1181 basedpyright Any errors across 431 files (#47789) 2026-10-24 11:31:09 -07:00
scripts chore: move LiteLLM's configs and e2e tests off gpt-4o and gpt-4.1 before their 2027-01-14 shutdown (#51800) 2026-11-14 10:50:59 -08:00
search fix(search): price Tavily advanced and Linkup deep searches at their own cost map entries (#47411) 2026-10-19 23:32:31 -07:00
secret_managers refactor(typing): clear 1141 basedpyright Any errors across 182 files (#50711) 2026-11-11 22:11:47 +00:00
skills refactor(typing): clear about 1,100 basedpyright Any errors across 303 files (#49986) 2026-11-06 13:31:15 -08:00
systemone fix(decisions): log every request field the caller sent on /v1/systemone and /v1/decisions (#47183) 2026-10-19 14:19:14 -07:00
telemetry refactor: clean up fresh tech debt in per-user Copilot auth, Ternary FOCUS export and telemetry (#45769) 2026-10-15 04:29:27 +00:00
text_completions refactor(typing): clear 1141 basedpyright Any errors across 182 files (#50711) 2026-11-11 22:11:47 +00:00
tracing chore: move scripts and runtime sources under litellm (#51006) 2026-11-12 04:19:57 +00:00
types feat(budgets): replace the python budget hold and settle engine with a rust engine admitted at auth (#51535) 2026-11-15 16:03:51 -08:00
ui feat(customers): sort organizations, teams and members by budget limit (#51924) 2026-11-16 05:22:10 +08:00
vector_store_files fix(secret_managers)!: resolve oidc/file and oidc/env refs in admin-configured api_key per request (#47341) 2026-10-20 01:43:59 +00:00
vector_stores fix(bedrock): map OpenAI vector store search filters to AWS RetrievalFilter (#51291) 2026-11-14 13:39:43 -05:00
videos refactor(typing): clear 1141 basedpyright Any errors across 182 files (#50711) 2026-11-11 22:11:47 +00:00
vscode-extension chore: move ui and vscode-extension under litellm and delete docs (#50992) 2026-11-12 04:19:57 +00:00
__init__.py fix(router)!: name the request size when usage-based routing refuses an over-tpm request (#51838) 2026-11-14 16:16:21 -05:00
_internal_context.py refactor(redis): delete the Python RedisBatch now that every request op is native (#51383) 2026-11-13 03:22:28 +00:00
_lazy_imports.py refactor: read lazy attributes with getattr instead of a TypedDict wrapper (#50543) 2026-11-07 10:56:30 -08:00
_lazy_imports_registry.py feat(decisions): support Vercel AI Gateway decision models (#50642) 2026-11-14 09:43:08 -05:00
_logging.py chore: move workspace packages under litellm (#51000) 2026-11-12 04:19:57 +00:00
_process_defaults.py perf(cli): start lite without initializing the litellm SDK (#46803) 2026-10-17 04:53:32 +00:00
_redis.py feat(redis): serve the proxy's common Redis call with Rust stores (#50170) 2026-11-06 06:01:11 +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 fix(caching): report Redis circuit-breaker metrics through the Prometheus services logger (#46484) 2026-10-14 14:29:54 -07:00
_uuid.py fix: support Python 3.15 (#48359) 2026-10-26 16:00:11 +00:00
_version.py feat(sdk): build core from an independent packaging manifest (#44340) 2026-10-08 18:40:14 -07:00
anthropic_beta_gated_fields.py fix(anthropic)!: drop beta-gated body fields under drop_params (#48793) 2026-10-29 06:25:31 -07:00
anthropic_beta_headers_config.json fix(bedrock): forward the compact-2026-09-04 compaction param on Invoke /v1/messages (#51223) 2026-11-11 15:10:32 -08:00
anthropic_beta_headers_manager.py feat(messages): serve anthropic messages on rust only (#51119) 2026-11-12 00:07:20 +00:00
blog_posts.json chore(blog): refresh the bundled blog posts backup with the latest 50 posts from the docs RSS feed (#49971) 2026-11-03 23:41:15 +00:00
budget_manager.py refactor(typing): clear 1143 basedpyright Any errors across 273 files (#46574) 2026-10-15 21:08:47 +00:00
constants.py feat(dynamic_rate_limiter): customer organizations and keys borrow idle model capacity and split class shares (#51705) 2026-11-15 12:05:58 -08:00
cost.json
cost_calculator.py fix(azure): send no api-version on Foundry project /openai/v1 Responses bases (#51767) 2026-11-14 05:24:12 -05:00
exceptions.py fix(router)!: name the request size when usage-based routing refuses an over-tpm request (#51838) 2026-11-14 16:16:21 -05:00
guardrails.py Add guardrails.apply SDK helper (#49217) (#49469) 2026-10-31 23:37:45 +00:00
main.py fix(sdk): stop global model_fallbacks from recursing on every completion call (#51817) 2026-11-14 16:28:38 -05:00
model_prices_and_context_window_backup.json chore(cost-map): add fal_ai seedream v5 pro US edit and text-to-image rows priced per image from their fal.ai pages (#51881) 2026-11-15 00:28:42 +00:00
policy_templates_backup.json fix(packaging): keep wheel paths under Windows MAX_PATH for Store Python (#43903) 2026-09-30 22:20:36 +00:00
provider_endpoints_support_backup.json chore(pricing): sync replicate model prices from replicate.com model pages (#51067) 2026-11-11 01:07:16 +00:00
py.typed
router.py refactor(typing): clear 1141 basedpyright Any errors across 182 files (#50711) 2026-11-11 22:11:47 +00:00
router_api.py feat(redis): serve the router's session pins from a native store (#50870) 2026-11-13 03:22:28 +00:00
router_attempt.py refactor(router): delete the python router core, the rust core is the only core (#50178) 2026-11-05 10:40:46 -08:00
router_config.py refactor(typing): clear about 1,100 basedpyright Any errors across 303 files (#49986) 2026-11-06 13:31:15 -08:00
router_core.py chore: move workspace packages under litellm (#51000) 2026-11-12 04:19:57 +00:00
router_deprecated.py fix(router): re-check and reserve per-model rate limits on fallback targets (#50994) 2026-11-10 16:36:10 -08:00
router_host.py refactor(router): move router callers onto the entry points and invert the proxy imports (#48847) 2026-10-29 17:26:33 +00:00
router_python_host.py fix(sdk): stop global model_fallbacks from recursing on every completion call (#51817) 2026-11-14 16:28:38 -05:00
scheduler.py fix(scheduler): read shared queue from Redis so expired dead-replica entries stop blocking waiters (#49387) 2026-10-31 11:43:46 -07:00
schema.prisma fix(db): index customer hierarchy filters (#51961) 2026-11-16 04:28:34 +08:00
setup_wizard.py fix(model_prices): correct Claude Sonnet 5.5 capabilities and provider keys (#43587) 2026-09-28 19:12:31 +00:00
timeout.py
tool_loop.py fix(tool_choice): accept the Responses API's flat allowed_tools layout on chat completions (#50467) 2026-11-10 13:04:06 -08:00
utils.py fix(cost): keep a deployment's per-second video price over the catalog row's flat price (#51688) 2026-11-15 12:04:41 -08:00