scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-05 08:07:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 135
30248 commits 4051 branches 1400 tags 4.1 GiB
Commit graph

30248 commits

This branch
This branch
All branches
Author SHA1 Message Date
Krrish Dholakia
011dc94467 docs(index.json): document ai coding tool tutorials 2026-01-16 01:48:01 +05:30
Krrish Dholakia
03d2bee847 docs: link to non-anthropic model tutorial for claude code 2026-01-16 00:46:42 +05:30
Krrish Dholakia
70660dab77 docs(claude_non_anthropic_models.md): add tutorial showing non anthropic model connection to claude code 2026-01-16 00:45:01 +05:30
Krrish Dholakia
08f16935f9 docs: cleanup links for ai coding tools 2026-01-16 00:30:53 +05:30
Krrish Dholakia
1e261b6570 fix: safely handle unmapped call type 2026-01-15 21:26:06 +05:30
Krrish Dholakia
04eec6c909 docs: update index.json 2026-01-15 20:54:30 +05:30
Krrish Dholakia
c7ca2dd4d8 docs(claude_mcp.md): separate claude mcp tutorial into a separate doc 
easier to surface
 2026-01-15 20:52:31 +05:30
Krrish Dholakia
37abfc6a77 fix(index.json): have a parent index.json and just link out to guides from docs 
maintain just 1 place for tutorials
 2026-01-15 19:26:40 +05:30
Krrish Dholakia
02d782f7f1 refactor: rename file for consistency 2026-01-15 16:31:06 +05:30
Krrish Dholakia
7c53bf1c2b docs: new cookbook .md for claude code 
allows rendering on models.litellm.ai
 2026-01-15 16:30:08 +05:30
Harshit Jain
8804c78cf9
docs(logging.md): add guide for mounting custom callbacks in Helm/K8s (#19136) 2026-01-15 15:58:44 +05:30
Sameer Kankute
83cdfd886a
Merge pull request #19059 from BerriAI/litellm_openrouter_image_gen 
Add openrouter support for image/generation endpoints
 2026-01-15 15:48:00 +05:30
Sameer Kankute
2023982218 Fix: code quality tests 2026-01-15 15:45:53 +05:30
Sameer Kankute
58eef291f9 Fix: code quality tests 2026-01-15 15:43:48 +05:30
YutaSaito
f541bc0261
Merge pull request #19129 from BerriAI/litellm_fix_mcp_chat_completions 
[fix] mcp chat completions
 2026-01-15 18:21:37 +09:00
Yuta Saito
9d173ba4fe fix: prevent MCP type objects from being captured in locals() 2026-01-15 17:14:58 +09:00
Yuta Saito
0db6229b63 fix: lint 2026-01-15 16:04:01 +09:00
Sameer Kankute
e5121b3654
Merge pull request #19127 from BerriAI/litellm_enterprise_version_bump 
bump litellm version to 0.1.28
 2026-01-15 12:25:14 +05:30
Yuta Saito
1c2942d808 test: add mcp completions test 2026-01-15 15:47:45 +09:00
Yuta Saito
ba43f742ab fix: event loop nesting issue in MCP chat completions with streaming 
Problem: When using MCP tools with  and , the following error occurred:

RuntimeError: Timeout context manager should be used inside a task
 2026-01-15 15:36:56 +09:00
Sameer Kankute
7fa8ef620b bump litellm version to 0.1.28 2026-01-15 11:35:49 +05:30
Sameer Kankute
dca42047b9
Merge pull request #19068 from BerriAI/litellm_responses_caching_support 
[Fix] Add support for caching for responses API
 2026-01-15 08:38:31 +05:30
Sameer Kankute
c7be5065f8 fix mypy error in caching.py 2026-01-15 08:35:08 +05:30
Ishaan Jaffer
62b4fe79b2 fix 2026-01-14 18:12:01 -08:00
yuneng-jiang
27bc5c1fca
Merge pull request #19120 from BerriAI/litellm_yj_triage_branch 
[Fix] Azure Storage Circular Reference Error
 2026-01-14 18:08:38 -08:00
Ishaan Jaff
458f773861
[Feat] Claude Code - Add support for Prompt Caching with Bedrock Converse (#19123) 
* init BaseAnthropicMessagesPromptCachingTest

* fix UsageDelta

* fix: _create_initial_usage_delta

* TestBedrockInvokePromptCaching

* translate_anthropic_messages_to_openai wiht cache control

* fix translate_anthropic_messages_to_openai
 2026-01-14 18:05:10 -08:00
yuneng-jiang
0de871b03e Fixing unused import 2026-01-14 17:45:21 -08:00
Ishaan Jaff
e67e9e7054
[Fix] Containers API - Allow routing to regional endpoints (#19118) 
* fix get_complete_url

* fix url resolution containers API

* TestContainerRegionalApiBase
 2026-01-14 17:28:18 -08:00
YutaSaito
e3e6fc2806
Merge pull request #19122 from BerriAI/litellm_docs_mcp_troubleshooting 
[doc] add MCP troubleshooting guide
 2026-01-15 09:34:35 +09:00
yuneng-jiang
93f3dd8008
Merge pull request #19119 from BerriAI/litellm_ui_key_edit_team_dropdown 
[Feature] UI - Edit Key: Add search to key edit team dropdown
 2026-01-14 16:17:14 -08:00
yuneng-jiang
97c39dbb7a Fixing circular reference for azure storage 2026-01-14 16:11:55 -08:00
yuneng-jiang
a149ff448d Fixing build 2026-01-14 15:49:31 -08:00
yuneng-jiang
a4fecc74fb Add search to key edit team dropdown 2026-01-14 15:47:50 -08:00
Alexsander Hamir
f442b57848
docs: Add structured issue reporting guides for CPU and memory issues (#19117) 2026-01-14 15:28:20 -08:00
Ishaan Jaff
62187103b4
[Fix] Containers API - Container API routes return 401 for non-admin users - routes missing from openai_routes (#19115) 
* test_containers_routes_are_llm_api_routes

* allow /containers/* API
 2026-01-14 15:14:03 -08:00
Yuta Saito
0b04145c11 doc: add MCP troubleshooting guide 2026-01-15 08:01:59 +09:00
Ishaan Jaff
06ded8750e
[Fix] Claude Code (/messages) - Litellm fix claude code Bedrock Invoke usage, request signing (#19111) 
* test_should_not_fail_with_forwarded_headers_bedrock_invoke_messages

* use common get_request_headers for BaseAWS

* fix get_request_headers

* test_should_not_fail_with_forwarded_headers_bedrock_invoke_messages
 2026-01-14 14:51:50 -08:00
yuneng-jiang
dcac090de0
Merge pull request #19053 from BerriAI/litellm_intern_user_usage 
[Fix] /team/daily/activity Show Internal Users Their Spend Only
 2026-01-14 13:47:34 -08:00
yuneng-jiang
23e954f2b4
Merge pull request #19058 from BerriAI/litellm_ui_add_model_ant 
[Feature] UI - Model: Anthropic Models QOL
 2026-01-14 13:43:57 -08:00
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