tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-07-13 09:06:18 +00:00
Code Issues Packages Projects Releases Wiki Activity
30,204 Commits 2,072 Branches 1,425 Tags
b352d0d4fd76cc5ece5daadb6871a21cd2efe7b8
Commit Graph

30204 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Alexsander Hamir b352d0d4fd [Perf] Remove premature model.dump call on the hot path (#19109) 2026-01-14 12:40:27 -08:00
Ishaan Jaff 747829dadb [Fix] Claude Code + Bedrock Converse Usage - ensure budget tokens are passed to converse api correctly (#19107) 
* test_bedrock_converse_budget_tokens_preserved

* test_openai_model_with_thinking_converts_to_reasoning_effort

* fix translate_anthropic_thinking_to_reasoning_effort

* test_bedrock_converse_budget_tokens_preserved

* test_anthropic_messages_bedrock_converse_with_thinking
 2026-01-14 12:02:27 -08:00
yuneng-jiang f0e34a46a7 Merge pull request #19045 from dominicfeliton/main 
fix: model hub client side exception
 2026-01-14 11:58:42 -08:00
Peter Dave Hello 62eee47618 Add support for OpenAI's gpt-5.2-codex (#19101) 
Reference:
- https://openai.com/index/introducing-gpt-5-2-codex/
- https://platform.openai.com/docs/models/gpt-5.2-codex
 2026-01-14 11:49:40 -08:00
Rayan Pal f880ea537f fix(vertex): add type object to tool schemas missing type field (#19103) 
Tools with no parameters (like EnterPlanMode from Anthropic Agents SDK)
send schemas with only $schema and no type field. Gemini rejects these
with "functionDeclaration parameters schema should be of type OBJECT".

Adds type: object when schema has no type and no anyOf/oneOf/allOf.
 2026-01-15 00:43:35 +05:30
Emerson Gomes 9f6fa4fb49 Fix Azure Grok prices (#19102) 2026-01-15 00:30:47 +05:30
Alexsander Hamir 45968c01bd update troubleshoot (#19099) 2026-01-14 10:01:47 -08:00
Alexsander Hamir 0959467699 docs: Update troubleshooting guide with version tracking and error logs/metrics (#19097) 2026-01-14 09:32:28 -08:00
Peter Golm c215b3a79f fix: preserve llm_provider-* headers in error responses (#19020) 
Extract and preserve provider-specific headers (llm_provider-*) when
handling error responses from LLM providers. This ensures that useful
debugging information from providers is available even when requests
fail with BadRequestError or similar exceptions.
 2026-01-14 22:49:39 +05:30
Alexsander Hamir 05ebb0a739 docs: Add troubleshooting guide (#19096) 2026-01-14 09:17:43 -08:00
Debnil Sur 84dad952a2 fix(gemini): dereference $defs/$ref in tool response content (#19062) 
Gemini API rejects JSON schemas with $defs/$ref references anywhere in
the conversation, including in function_response content. This causes
errors when tools return JSON containing schemas (e.g., toolbelt_inspect_tool
returning tool definitions).

The fix:
1. Apply unpack_defs() to all JSON tool responses before sending to Gemini
2. Recursively remove $defs sections after inlining references
3. Replace any remaining $ref (circular refs, external URLs) with placeholders

Edge cases handled:
- Circular $ref (self-referential types like TreeNode.left -> TreeNode)
- External $ref (URL-based like https://...)
- Deeply nested $ref in anyOf/oneOf/allOf

This ensures function_response content is clean before being sent to the
Gemini API.

Related issues:
- https://github.com/google-gemini/gemini-cli/issues/13326
- FastMCP #1372, #1426
 2026-01-14 22:28:28 +05:30
Sameer Kankute cd2d381dd4 Merge pull request #19042 from BerriAI/litellm_staging_01_13_2026 
Staging 01/13/2026
 2026-01-14 21:29:09 +05:30
Cesar Garcia e0da7ca918 fix(models): correct max_input_tokens for GPT-5 models (#19056) 
OpenAI's 400k context window is split between input and output:
- GPT-5/5.1/5.2 models: 272k input + 128k output = 400k context
- GPT-5-pro models: 128k input + 272k output = 400k context

Reference: https://openai.com/index/introducing-gpt-5-for-developers/
"In the API, all GPT-5 models can accept a maximum of 272,000 input
tokens and emit a maximum of 128,000 reasoning & output tokens"

Fixes incorrect 400k max_input_tokens values across 32 models.
 2026-01-14 19:01:23 +05:30
Sameer Kankute 08ac26e5b4 Fix all 130126 tests 3 2026-01-14 18:01:22 +05:30
Sameer Kankute 4aadc0d41f Merge pull request #19074 from BerriAI/litellm_19046-bug-retry-policies-are-not-applied-on-responses-calls 
Add retry policy support to responses API
 2026-01-14 17:56:11 +05:30
Sameer Kankute 26d8ef734c Merge pull request #19070 from BerriAI/litellm_19066-bug-gemini-image-generation-returns-incorrect-prompt_tokens_details 
Fix: [Bug]: Gemini Image Generation Returns Incorrect prompt_tokens_d…
 2026-01-14 17:55:09 +05:30
Sameer Kankute 49d873e894 Merge pull request #19067 from BerriAI/litellm_caching_fix 
Fix: anthropic token counter with thinking
 2026-01-14 17:52:56 +05:30
Sameer Kankute b677ea1113 Merge pull request #19064 from BerriAI/litellm_openai_content_none_fix 
Fix: Responses content can't be none
 2026-01-14 17:52:31 +05:30
Sameer Kankute c0e97410b8 Fix all 130126 tests 2026-01-14 17:49:20 +05:30
Sameer Kankute 7dbf09cb12 Fix all 130126 tests 2026-01-14 17:47:03 +05:30
Sameer Kankute d03548b064 Fix all 130126 tests 2026-01-14 17:42:52 +05:30
Sameer Kankute 8b987db26f Merge pull request #19080 from BerriAI/revert-18147-feat/gemini-response-json-schema 
Revert "feat(gemini): add opt-in support for responseJsonSchema"
 2026-01-14 17:07:23 +05:30
Sameer Kankute b4a48f7996 Revert "feat(gemini): add opt-in support for responseJsonSchema (#18147)" 
This reverts commit 4e417f9ef1.
 2026-01-14 17:06:13 +05:30
Sameer Kankute ff467c797d Merge pull request #19079 from BerriAI/main 
merge main
 2026-01-14 16:44:31 +05:30
Sameer Kankute 075d0c70be Merge pull request #19078 from rohanwinsor/fix/respect-disable-fallbacks-streaming 
fix: add handling for user-disabled mid-stream fallbacks
 2026-01-14 16:38:52 +05:30
rohan.w.charles bc88dbfbc9 fix: implement mid-stream fallback handling based on user preference 2026-01-14 16:28:51 +05:30
rohan.w.charles e70b1bbfad fix: add handling for user-disabled mid-stream fallbacks 2026-01-14 16:04:36 +05:30
Sameer Kankute 52d3c9dcfc Add retry policy support to responses API 2026-01-14 14:55:17 +05:30
Sameer Kankute b2d4f67e17 Merge pull request #19023 from eagle-p/feat/guardrail-clean-error-message 
fix(guardrails): use clean error messages for blocked requests
 2026-01-14 14:03:16 +05:30
Sameer Kankute 11cc8dc9d2 Merge pull request #19037 from Jetemple/json-log-fix 
fix: enable JSON logging via configuration and add regression test
 2026-01-14 13:51:36 +05:30
Sameer Kankute 6991342dc4 Fix: [Bug]: Gemini Image Generation Returns Incorrect prompt_tokens_details 2026-01-14 13:47:46 +05:30
Sameer Kankute 0563ce42a4 Fix: anthropic token counter with thinking 2026-01-14 12:59:23 +05:30
Sameer Kankute 1b34d17935 Fix: Responses content can't be none 2026-01-14 12:13:18 +05:30
YutaSaito 8d204f0a84 Merge pull request #19060 from BerriAI/litellm_fix_anthropic-during-call-error 
[fix] anthropic during call error
 2026-01-14 15:13:09 +09:00
YutaSaito 5de0e97539 Merge pull request #19063 from BerriAI/litellm_docs_auth_message_ui 
[docs] auth message UI
 2026-01-14 15:09:37 +09:00
Yuta Saito 16ebfb0d5c docs: add mcp faq 2026-01-14 15:08:31 +09:00
Yuta Saito 2d3c292cd8 chore: Clarify MCP OAuth token handling in UI 2026-01-14 14:31:18 +09:00
yuneng-jiang 39f56abd8d Merge pull request #18878 from BerriAI/litellm_hakhundov_contribution 
[Fix] Feature Flag for Fix SCIM GET /Users error and enforce SCIM 2.0 compliance
 2026-01-13 20:46:28 -08:00
Yuta Saito 82ed6283fa test: reorganize unified guardrail tests into nested classes 2026-01-14 13:38:43 +09:00
Yuta Saito c5ced033c9 fix: anthropic during call guardrail error 2026-01-14 13:37:01 +09:00
yuneng-jiang d5f05f6c23 Merge pull request #19055 from BerriAI/litellm_ui_usage_model_act_fix 
[Fix] UI - Usage: Model Activity Chart Y Axis
 2026-01-13 19:53:08 -08:00
Cesar Garcia 2b79d37e39 feat: Add Cerebras zai-glm-4.7 model support and deprecate zai-glm-4.6 (#18864) 
- Add cerebras/zai-glm-4.7 with same specs as 4.6 (128K context, $2.25/M input, $2.75/M output)
- Mark cerebras/zai-glm-4.6 with deprecation_date: 2026-01-20
- Both models support function calling, reasoning, and tool choice
 2026-01-13 19:45:02 -08:00
YutaSaito 95b419d65b Merge pull request #18938 from BerriAI/litellm_fix_generate_two_telemetry 
[fix] generate two telemetry in responses
 2026-01-14 12:35:23 +09:00
Ishaan Jaffer fd46140fef add call flow 2026-01-13 19:19:19 -08:00
Ishaan Jaffer cf82236176 docs fix 2026-01-13 19:18:36 -08:00
Ishaan Jaff d1acfcdb28 [Docs] Add Litellm architecture md doc (#19057) 
* v0 of this

* remove bloat

* bring back older diagram

* fix

* fix

* docs fix

* fix rate limiting

* docs fix

* fix

* doc fix

* docs fix

* add SDK level fixes

* docs fix
 2026-01-13 19:05:12 -08:00
Ishaan Jaff 1b00576711 [Feat] New Model - Azure Model Router on LiteLLM AI Gateway (#19054) 
* fix - azure model router integration

* fix:_check_provider_match

* fix:_get_response_model

* tests azure model router

* test_azure_ai_model_router_streaming_model_in_chunk

* fix LlmProviders.AZURE.value

* test_azure_ai_model_router_streaming_cost_with_stream_options

* def test_get_model_from_chunks_azure_model_router():

* _get_model_from_chunks

* docs azure model router

* azure model router
 2026-01-13 18:31:43 -08:00
yuneng-jiang 851006790c Fix model list not showing 2026-01-13 18:16:26 -08:00
Yuta Saito a1bceb8403 fix: anthropic Extra inputs are not permitted error 2026-01-14 11:15:56 +09:00
Yuta Saito 2814d3dd3d test: cover success handler sync/async logging branches 2026-01-14 10:52:14 +09:00