Mateo Wang 2d181e6633 fix(token_counter): count DeepSeek V4 text with DeepSeek's own tokenizer (#47353) ... Local token counts for DeepSeek V3 and V4 model names now use DeepSeek's own bundled tokenizer instead of cl100k_base, and tool definitions on V4 names count with V4's chat-template tool framing		2026-10-20 03:43:35 +00:00
..
_v2	feat(cache): select Rust caching through explicit cache objects (#43601)	2026-09-29 00:01:44 +00:00
a2a_protocol	refactor(typing): clear 1143 basedpyright Any errors across 273 files (#46574)	2026-10-15 21:08:47 +00:00
anthropic_interface	refactor(typing): clear 1143 basedpyright Any errors across 273 files (#46574)	2026-10-15 21:08:47 +00:00
assistants	feat(openai)!: honor per-deployment workload identity on non-chat routes (#39966)	2026-10-16 22:25:15 +00:00
batch_completion
batches	fix(batches): apply the Vertex regional endpoint uplift to batch cost (#47466)	2026-10-20 01:51:51 +00:00
caching	fix(otel): report cache hits at zero cost with a cache-hit flag in V1 and V2 spans (#43604)	2026-10-17 18:25:32 +00:00
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(router)!: stop a chat-mode Mantle deployment from rewriting the shared Responses routing row (#46263)	2026-10-17 21:39:14 +00:00
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	fix(decisions): log every request field the caller sent on /v1/systemone and /v1/decisions (#47183)	2026-10-19 14:19:14 -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	fix(speech)!: correctly propagate spend logging and usage for Gemini TTS bridge (#44551)	2026-10-19 23:02:11 +00:00
evals
experimental_mcp_client	fix(mcp): log upstream exchange when an MCP health check fails (#44125)	2026-10-16 20:58:26 -07:00
files	feat(openai)!: honor per-deployment workload identity on non-chat routes (#39966)	2026-10-16 22:25:15 +00:00
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	fix(vertex_ai): price streamed pass-through calls with the regional uplift (#44795)	2026-10-19 08:10:52 +00:00
harness	refactor(typing): clear 1143 basedpyright Any errors across 273 files (#46574)	2026-10-15 21:08:47 +00:00
images	feat(openai)!: honor per-deployment workload identity on non-chat routes (#39966)	2026-10-16 22:25:15 +00:00
integrations	fix(exa): return highlights, highlight scores, score and the response envelope from Exa search (#47423)	2026-10-19 15:45:56 -07:00
interactions	fix(interactions): keep background interaction bills through crashes, late restarts, and deployment keys (#45743)	2026-10-16 12:00:08 +00:00
litellm_core_utils	fix(token_counter): count DeepSeek V4 text with DeepSeek's own tokenizer (#47353)	2026-10-20 03:43:35 +00:00
llms	fix(databricks): stream Claude json_schema answers as text on every streaming path (#47424)	2026-10-20 02:41:55 +00:00
messages	fix(router)!: bound fake-streamed calls by the request timeout, not stream_timeout (#47162)	2026-10-17 22:08:02 +00:00
models	fix(proxy): allow model instances in LiteLLM_EndUserTable validation (#41677)	2026-10-15 10:57:26 -07:00
ocr	refactor(python-bridge): ship a signature base and read the resolved call (#45450)	2026-10-08 17:20:29 -07:00
passthrough	feat(router): let a deployment set a timeout per service_tier (#47406)	2026-10-19 14:27:29 -07:00
proxy	fix(proxy): price a billed failure row at the deployment's own rate like the success path (#47437)	2026-10-19 19:55:21 -07:00
proxy_auth	refactor(types): replace Any with real types across 29 more backend files	2026-09-08 10:14:07 +00:00
rag	fix(rag)!: use team provider credentials and allow viewer and JWT team access (#45497)	2026-10-17 23:51:48 +00:00
realtime_api	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
repositories	fix(proxy): reset end-user spend in committed pages so the budget cascade survives a large LiteLLM_EndUserTable (#46502)	2026-10-15 19:47:12 -07:00
rerank_api	refactor(typing): clear 1143 basedpyright Any errors across 273 files (#46574)	2026-10-15 21:08:47 +00:00
responses	fix(sdk): decide MCP gateway routing without importing the proxy handler (#45961)	2026-10-20 01:44:54 +00:00
router_strategy	perf(savings): read deployment pricing from the router's cached model info (#47400)	2026-10-19 17:07:00 -07:00
router_utils	fix(router): key prompt caching affinity on tools and the /v1/messages system prompt (#46411)	2026-10-19 19:59:09 -07:00
rust_bridge	fix(logging): keep the async request's logging payload when the sync success thread runs late (#47019)	2026-10-17 06:39:35 +00:00
sandbox	refactor(typing): clear 1143 basedpyright Any errors across 273 files (#46574)	2026-10-15 21:08:47 +00:00
search	refactor(typing): clear 1143 basedpyright Any errors across 273 files (#46574)	2026-10-15 21:08:47 +00:00
secret_managers	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
skills	refactor(typing): clear 1143 basedpyright Any errors across 273 files (#46574)	2026-10-15 21:08:47 +00:00
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
tracing	fix(proxy): cooldown errors carry 429, Sentry starts at boot without request bodies, tracing failures log at ERROR, exporter counters exported (#46344)	2026-10-16 00:53:52 +00:00
types	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_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(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
videos	feat(dashscope): add Wan 3.0, Wan 2.7 and HappyHorse video generation via /v1/videos (#43706)	2026-10-14 10:10:07 -07:00
__init__.py	fix(baseten): list current Model APIs instead of retired 2023 deployment IDs (#46945)	2026-10-19 16:40:13 +00:00
_internal_context.py	fix(responses): log and bill every round of non-stream MCP auto-execute (#43667)	2026-10-16 17:37:33 +00:00
_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: add Nace Drex decisions provider (#46523)	2026-10-16 18:07:50 -07:00
_logging.py	fix(logging): keep root logger INFO lines when json_logs is on and LITELLM_LOG is set (#47175)	2026-10-17 21:33:26 +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	refactor(typing): clear 1143 basedpyright Any errors across 273 files (#46574)	2026-10-15 21:08:47 +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
_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(databricks): use the native Anthropic route for Claude /v1/messages (#46091)	2026-10-18 02:44:38 +00:00
anthropic_beta_headers_manager.py	fix(anthropic): add the dangerous-tool-use beta when a /v1/messages request carries safeguards (#43955)	2026-10-17 16:46:25 +00:00
blog_posts.json
budget_manager.py	refactor(typing): clear 1143 basedpyright Any errors across 273 files (#46574)	2026-10-15 21:08:47 +00:00
constants.py	fix(mcp): retry upstream 429 on tools/list and error when every server fails (#46649)	2026-10-19 16:01:23 -07:00
cost.json
cost_calculator.py	fix(batches): apply the Vertex regional endpoint uplift to batch cost (#47466)	2026-10-20 01:51:51 +00:00
exceptions.py	fix(proxy)!: answer 400 for malformed tools on count_tokens instead of crashing (#46583)	2026-10-16 14:57:53 -07:00
main.py	fix(sdk): decide MCP gateway routing without importing the proxy handler (#45961)	2026-10-20 01:44:54 +00:00
model_prices_and_context_window_backup.json	chore(bedrock): add Model EOL deprecation dates for Palmyra X4, X5 and Pegasus v1.2 (#47462)	2026-10-19 18:27:38 -07:00
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	feat(openinfer): add OpenInfer as an OpenAI-compatible provider (#41034)	2026-10-17 23:22:19 +00:00
py.typed
router.py	fix(proxy): match partial wildcards against prefix-stripped model ids (#46390)	2026-10-20 02:49:42 +00:00
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	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(responses bridge): round-trip tool_search_call and tool_search_output items between turns (#46444)	2026-10-14 21:40:14 -07:00
utils.py	fix(token_counter): count DeepSeek V4 text with DeepSeek's own tokenizer (#47353)	2026-10-20 03:43:35 +00:00