Merge pull request #40262 from BerriAI/litellm_lit_7190_inline_token_counts
2026-09-15 13:38:00 -07:00
fix(anthropic_endpoints): return Anthropic type:error envelope for /v1/messages errors
2026-08-31 16:23:36 -07:00
refactor(typing): replace Any with proven types in 89 more backend files
2026-09-02 23:08:42 +00:00
refactor(vertex): move batch usage modality parsing under llms
2026-09-15 02:03:32 +00:00
Merge pull request #41171 from BerriAI/litellm_converted_stream_spend_tracking
2026-09-15 15:34:13 -07:00
style(responses_bridge): apply ruff format
2026-09-16 23:52:53 +00:00
merge: main into litellm_headroom_protect_cached_prefix
2026-09-15 04:12:28 +00:00
Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_decrease_anys_opus5_r4
2026-09-02 23:32:10 +00:00
endpoints/speech /speech_to_completion_bridge
refactor(speech): freeze httpx response header dicts (LIT002)
2026-08-31 21:12:53 -07:00
fix(mcp): reject missing upstream authentication credentials
2026-09-15 18:06:00 -07:00
merge: bring litellm_internal_staging into the Bedrock files delete and list fix
2026-09-09 19:27:40 -07:00
refactor(typing): replace Any with proven types in 89 more backend files
2026-09-02 23:08:42 +00:00
refactor(types): replace Any with precise types across 73 modules
2026-09-01 11:05:02 +00:00
refactor(typing): replace Any with proven types in 89 more backend files
2026-09-02 23:08:42 +00:00
Merge pull request #40669 from BerriAI/litellm_otel_passthrough_trace_propagation
2026-09-16 16:02:46 -07:00
refactor(typing): replace Any with proven types in 42 more backend files
2026-09-02 15:35:01 +00:00
Merge pull request #41507 from BerriAI/litellm_attribute_router_rejected_spend_provider
2026-09-16 18:21:44 -07:00
Merge pull request #41508 from BerriAI/litellm_1789600151_discover_context_limits
2026-09-16 20:29:57 -07:00
Merge pull request #41403 from BerriAI/litellm_key_total_spend
2026-09-16 14:49:02 -07:00
refactor(ocr): move file preparation from the python bridge into litellm-core
2026-09-16 21:02:30 +00:00
fix(passthrough): parse Bedrock stream spend incrementally instead of buffering the whole response ( #40724 )
2026-09-11 09:53:37 -07:00
refactor(proxy): move llm_api_check moderation dispatch to its own PR
2026-09-17 21:36:13 +00:00
Merge remote-tracking branch 'origin/main' into litellm_bedrock_rag_retrieval_filter
2026-09-15 15:21:57 -07:00
fix(realtime): send openai and xai health check keys as bearer tokens
2026-09-15 02:20:09 -07:00
fix(proxy): always decrement on spend reset and reseed counters from the DB
2026-09-15 19:52:37 +00:00
fix(rerank): adopt declared authenticating providers in arerank instead of resolving them
2026-09-01 14:47:59 -07:00
refactor(responses): drop the api_base cast and mark the header merge mutable-ok
2026-09-16 15:45:50 -07:00
fix(router): accept fenced Fuse classifier verdicts
2026-09-15 13:11:56 -07:00
Merge pull request #41379 from runjivu/fix/fallback-budget-check
2026-09-16 14:39:56 -07:00
refactor(ocr): move file preparation from the python bridge into litellm-core
2026-09-16 21:02:30 +00:00
fix(search): forward search-tool params through the router, complete Parallel AI v1 param mapping ( #37883 )
2026-09-01 21:46:46 -07:00
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
feat(skills): semantic search over the LiteLLM-hosted skill registry ( #39401 )
2026-09-07 12:28:38 -07:00
fix(router): scope discovered limits to active deployments
2026-09-16 23:37:28 +00:00
refactor(typing): replace Any with proven types in 42 more backend files
2026-09-02 15:35:01 +00:00
Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_python_version_ci
2026-09-03 00:16:19 -07:00
Merge pull request #41513 from BerriAI/litellm_internal_copy_31400
2026-09-16 17:12:35 -07:00
fix(proxy): price one cost estimate at one moment
2026-09-07 18:38:12 -07:00
fix(lazy_imports): type import_map as Mapping to stay under the LIT001 budget
2026-09-05 16:12:45 -07:00
Merge remote-tracking branch 'origin/main' into litellm_azure_ai_responses_native
2026-09-15 18:04:36 -07:00
Merge pull request #40934 from BerriAI/litellm_fix_ocr_native_multipage_pdf
2026-09-16 18:06:11 -07:00
fix(redis): accept every truthy flag and sign serverless ElastiCache caches
2026-09-10 10:13:03 -04:00
fix(redis): accept every truthy flag and sign serverless ElastiCache caches
2026-09-10 10:13:03 -04:00
chore: merge origin/litellm_internal_staging into litellm_decrease_anys_opus5_r4
2026-09-04 18:59:35 -07:00
fix(anthropic): add the per-turn-control beta when a message carries output_config
2026-09-14 22:01:47 -07:00
fix(proxy): default prompt injection heuristics executor to a single worker
2026-09-17 05:45:33 +00:00
Merge pull request #41318 from BerriAI/litellm_ws_responses_service_tier_pricing
2026-09-15 17:23:35 -07:00
fix(sdk): carry a litellm_proxy error's headers on e.response, not e.headers
2026-09-14 22:22:26 -07:00
Merge pull request #41268 from BerriAI/litellm_outbound_http2_opt_in
2026-09-16 10:05:37 -07:00
Merge pull request #41201 from BerriAI/litellm_gemini_37_38_flash_no_minimal_thinking
2026-09-16 16:52:08 -07:00
fix(ocr): send each provider a health-check document it accepts
2026-09-04 22:52:12 -07:00
fix(router): preserve discovered limits and model info fallbacks
2026-09-17 00:23:50 +00:00
feat(models): add Claude Fable 5.1 across Anthropic, Bedrock, Vertex AI, and Azure AI
2026-09-01 18:07:06 +00:00
Merge remote-tracking branch 'origin/main' into litellm_converted_stream_post_call_hook
2026-09-17 00:31:24 +00:00
b4f71df2d2