Alexsander Hamir
797f561de4
fix(gcs_bucket): use asyncio.Queue and batch_size limit to prevent unbounded queue growth
...
- Replace List with asyncio.Queue for thread-safe concurrent access
- Remove unnecessary flush_lock (asyncio.Queue handles concurrency atomically)
- Add batch_size limit to prevent processing all queued items at once
- Extract queue draining logic into _drain_queue_batch() helper function
- Remove debug print statements and unnecessary try/finally blocks
This fixes the issue where the queue grew unbounded (2000+ logs) because
async_send_batch() attempted to process all queued items in a single flush,
taking longer than the flush interval and causing continuous accumulation.
2026-01-17 17:28:00 -08:00
Sameer Kankute
8b7c36c271
Merge pull request #19135 from BerriAI/litellm_websocker_realtime_fix
...
Fix model name from query param in realtime request
2026-01-15 22:26:28 +05:30
Sameer Kankute
0ae471aba9
Merge pull request #19141 from BerriAI/litellm_stablise_mock_tests
...
Stabilise mock tests
2026-01-15 22:25:41 +05:30
Sameer Kankute
8c454eb74f
Fix: mock test tests
2026-01-15 22:02:51 +05:30
Sameer Kankute
83e33944ef
Fix: mock test tests
2026-01-15 22:02:42 +05:30
Sameer Kankute
890fa85a33
Fix: response enterprise tests
2026-01-15 21:25:22 +05:30
Harshit Jain
3ad8fa5422
fix: mount config.yaml as single file in Helm chart ( #19146 )
2026-01-15 21:21:13 +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
Sameer Kankute
b4ee1b2589
Fix: response enterprise tests
2026-01-15 19:53:04 +05:30
Sameer Kankute
4bdda9cc28
Fix: tests/test_litellm/proxy/test_proxy_server.py::test_embedding_input_array_of_tokens
2026-01-15 19:46:35 +05:30
Sameer Kankute
f28d951202
Fix: tests/test_litellm/proxy/test_litellm_pre_call_utils.py::test_embedding_header_forwarding_with_model_group
2026-01-15 19:41:16 +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
Sameer Kankute
3af994a32a
Fix: test router
2026-01-15 19:21:31 +05:30
Sameer Kankute
3ebf16e2e0
remove unused space
2026-01-15 18:59:22 +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
Sameer Kankute
7f79140ff2
Add logger to see websocket request
2026-01-15 15:07:02 +05:30
Sameer Kankute
e9a2999f61
Fix: handling of model name in query param
2026-01-15 15:06:37 +05:30
Sameer Kankute
a3cf178e24
Fix : #19089 websocket version error
2026-01-15 15:06:24 +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
