scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-09 03:18:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 109
52320 commits 3347 branches 1448 tags 5 GiB
Commit graph

52320 commits

This branch
This branch
All branches
Author SHA1 Message Date
mateo-berri
bd8df0ed8f test: keep the Qwen brand missing-key tests off the network and split the ChatGPT fields test back out 2026-09-21 12:54:23 -07:00
mateo-berri
21b5e2d8a1 fix(anthropic): add the dangerous-tool-use beta when safeguards arrive without it on Bedrock Invoke and Vertex 2026-09-21 12:52:38 -07:00
Mateo Wang
2e35ae1065
Merge pull request #42049 from BerriAI/litellm_mantle_native_anthropic_messages 
feat(bedrock_mantle): serve /v1/messages for Claude models on Mantle's native Anthropic Messages API
 2026-09-21 12:52:16 -07:00
Yujong Lee
991108cc48 refactor(rust): align cache foundation with Python backends 2026-09-21 12:50:21 -07:00
yuneng
d69eb7f095 fix(proxy): fall back to the credentials table when validating litellm_credential_name 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 19:47:27 +00:00
yassin
ee97f7327e fix(edenai): register the chat config class directly in the provider table 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 19:45:15 +00:00
tin-berri
457b01e96d
Merge pull request #42055 from BerriAI/litellm_prompt_caching_request_table 
feat(ui): show prompt caching requests and net savings
 2026-09-21 12:45:11 -07:00
Mateo Wang
e8d97d381a
Merge pull request #42080 from BerriAI/litellm_prompt_caching_affinity_lookback 
fix(router): keep prompt caching affinity when the breakpoint moves
 2026-09-21 12:44:34 -07:00
yucheng
5a63c932a4 fix(otel v2): drop the redundant _ocr_choices docstring 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 19:42:45 +00:00
yassin
594d97e7e7 fix(edenai): restore unrelated files the squashed PR commit had reverted 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 19:42:37 +00:00
kerry-berri
c3663aaac8
Merge pull request #42289 from BerriAI/litellm-providers/price-sync-openrouter 
chore(prices): sync OpenRouter prices: 1 model
 2026-09-21 12:41:02 -07:00
kerry-berri
2692a275fa
Merge pull request #42290 from BerriAI/litellm-providers/price-sync-aws-bedrock 
chore(prices): sync AWS Bedrock prices: 3 models [enrichment failed: AWS Bedrock, 18 held]
 2026-09-21 12:40:58 -07:00
yassin
889b8fb220 Merge remote-tracking branch 'origin/main' into litellm_add_edenai_provider 2026-09-21 19:40:48 +00:00
mateo-berri
057c45f23f test(e2e): send no-cache on cacheable SDK calls and accept Bedrock's 400 on the responses leg 
The deleted wrapper put cache: {"no-cache": true} on every request body, so the
gateway's response cache never answered a re-sent prompt. The SDKs send nothing
of the sort, and the mid-conversation prompt-cache priming loop re-sends an
identical body until the provider reports a warm cache, which a cached reply
never does. NO_PROXY_CACHE in sdk_clients.py restores the field as extra_body
on every messages, responses, completions, and embeddings call.

The wrapper also returned a 4xx as a value where the SDKs raise. The Bedrock
safety_identifier test judges the captured Converse body, and Claude on Bedrock
rejects the forwarded field with a 400, so the /v1/responses leg now suppresses
openai.BadRequestError the way the chat leg carries the same 400 as a Result.
 2026-09-21 12:39:16 -07:00
joshua-berri
211ff96943
Merge pull request #39189 from BerriAI/litellm_mcp_list_pagination_lit5594 
fix(mcp): paginate prompt and resource discovery
 2026-09-21 19:35:17 +00:00
Mateo Wang
0e7cf5113e
Merge pull request #42069 from BerriAI/litellm_redacted_thinking_prompt_caching_pin 
fix(token_counter): count replayed redacted_thinking blocks so prompt_caching keeps pinning
 2026-09-21 12:35:14 -07:00
yassin
3c1b1fd1ed fix(edenai): annotate the provider model set for the type-discipline gate 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 19:34:53 +00:00
yassin
7dc9609109 Merge branch 'main' into litellm_add_edenai_provider 2026-09-21 19:34:49 +00:00
berriai-litellm-provider-info-sync[bot]
f851e6ddb7
chore(prices): sync AWS Bedrock prices: 3 models [enrichment failed: AWS Bedrock, 18 held] 
us.moonshotai.kimi-k3: 
zai.glm-4.7: max_tokens, supports_vision, max_input_tokens, max_output_tokens, supports_audio_input, supports_response_schema
zai.glm-4.7-flash: max_tokens, supports_vision, max_input_tokens, max_output_tokens, supports_audio_input, supports_response_schema
 2026-09-21 19:31:34 +00:00
berriai-litellm-provider-info-sync[bot]
cbf5bb5e71
chore(prices): sync OpenRouter prices: 1 model 
openrouter/deepseek/deepseek-v4-pro: input_cost_per_token, output_cost_per_token, cache_read_input_token_cost
 2026-09-21 19:31:29 +00:00
Joshua Valluru
2da7e6dfe2 ci: trigger MCP fix checks against main 2026-09-21 12:31:18 -07:00
Yujong Lee
efcafa7f12 fix(rust): invalidate changed Redis pool settings 2026-09-21 12:30:17 -07:00
mateo-berri
deca6aea79 test(bedrock): assert safeguard_results survive message_start and check the beta by membership 2026-09-21 12:30:11 -07:00
Mateo Wang
d8267d507d
Merge pull request #41956 from BerriAI/litellm_explicit_cache_injection_points_survive_client_marks 
fix: apply configured cache_control_injection_points beside client cache_control marks
 2026-09-21 12:28:02 -07:00
Joshua Valluru
a835e75620 fix(mcp): handle split UTF-8 routing previews in place 2026-09-21 12:24:19 -07:00
yuneng
177021b2ac fix(proxy): gate explicit credential detach only on PATCH /model/{id}/update 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 19:22:57 +00:00
yuneng
10d343c3ee fix(proxy): detach stored credential when model editor selects None (LIT-7597) 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 19:22:57 +00:00
Yujong Lee
14febcc878 fix(rust): shrink cache configuration bridge 2026-09-21 12:22:18 -07:00
kerry
3429348305 fix(types): avoid mutable image serializer annotations 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 19:21:53 +00:00
mateo-berri
0e16050100 fix(anthropic): forward Claude Code safeguards and dangerous-tool-use beta to Bedrock Invoke and Vertex on /v1/messages 
Claude Code's server-side auto-mode classifier sends a `safeguards` body field
together with the `dangerous-tool-use-2026-09-03` beta. PR #42152 made the
first-party anthropic route pass them through, but the beta header mapping
left the other two Claude platforms at null, so Bedrock Invoke dropped both
(classifier silently disabled) and Vertex forwarded the body field without
the beta, which the platform rejects with "safeguards: Extra inputs are not
permitted" (a 400 Claude Code hides by retrying without them).

Map the beta for bedrock and vertex_ai in the beta headers config and add
`safeguards` to the Bedrock Invoke request allowlist so the pair reaches
both platforms unchanged. Nothing is injected: a client that sends
`safeguards` without the beta still gets the platform's 400, exactly as
api.anthropic.com answers it.
 2026-09-21 12:21:50 -07:00
Mateo Wang
e7e4df9098
Merge pull request #42041 from BerriAI/litellm_azure_ai_gpt5_tools_responses_bridge 
fix(azure_ai): bridge gpt-5.4+ function tools with reasoning to the Foundry Responses API
 2026-09-21 12:21:02 -07:00
Joshua Valluru
bf5dff8986 chore: sync MCP UTF-8 fix with main 2026-09-21 12:15:57 -07:00
mateo-berri
cf00ab1bf8 fix: rename the mainland China brand to Qianwen AI Platform 2026-09-21 12:13:43 -07:00
kerry-berri
f92ff60ebd
Merge pull request #42280 from BerriAI/litellm-providers/price-sync-openrouter 
chore(prices): sync OpenRouter prices: 3 models
 2026-09-21 12:11:43 -07:00
kerry-berri
b619cc22bd
Merge pull request #42279 from BerriAI/litellm-providers/price-sync-aws-bedrock 
chore(prices): sync AWS Bedrock prices: 4 models [enrichment failed: AWS Bedrock, 26 held]
 2026-09-21 12:11:39 -07:00
kerry
c12c20083f fix(fal_ai): keep image data serializer none safe 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 19:10:33 +00:00
kerry
9b54c4b077 refactor(fal_ai): bill flux dev per 1024x1024 megapixel and drop ImageResponse retyping 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 19:10:33 +00:00
kerry
adc4e6a132 fix(fal_ai): price images from the dimensions fal returns 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 19:10:32 +00:00
Yujong Lee
59dbbe5ce7 fix(cache): outline Python configuration extraction 2026-09-21 12:10:06 -07:00
Yujong Lee
cda8904382 fix(cache): keep native wheel within size budget 2026-09-21 12:03:13 -07:00
kerry
8d73ce756a feat(fal_ai): add MiniMax H3 text-to-video and reference-to-video 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 19:03:00 +00:00
Mateo Wang
9a90adad32
Merge pull request #42275 from BerriAI/litellm_claude_platform_messages_beta_passthrough 
fix(bedrock): forward anthropic-beta headers verbatim on the Claude platform messages path
 2026-09-21 12:01:39 -07:00
berriai-litellm-provider-info-sync[bot]
a6842da112
chore(prices): sync OpenRouter prices: 3 models 
openrouter/~deepseek/deepseek-pro-latest: max_tokens, max_output_tokens, off_peak_pricing, input_cost_per_token, output_cost_per_token, cache_read_input_token_cost
openrouter/deepseek/deepseek-v4-pro: input_cost_per_token, output_cost_per_token, cache_read_input_token_cost
openrouter/deepseek/deepseek-v4-pro-0813: max_tokens, max_output_tokens, off_peak_pricing, input_cost_per_token, output_cost_per_token, cache_read_input_token_cost
 2026-09-21 19:01:36 +00:00
berriai-litellm-provider-info-sync[bot]
ae06a6478f
chore(prices): sync AWS Bedrock prices: 4 models [enrichment failed: AWS Bedrock, 26 held] 
global.moonshotai.kimi-k3: 
qwen.qwen3-coder-next: max_tokens, supports_vision, max_input_tokens, max_output_tokens, supports_audio_input, supports_response_schema
qwen.qwen3-next-80b-a3b: max_tokens, supports_vision, max_input_tokens, max_output_tokens, supports_audio_input, supports_response_schema
qwen.qwen3-vl-235b-a22b: max_tokens, max_input_tokens, max_output_tokens, supports_audio_input, supports_response_schema
 2026-09-21 19:01:36 +00:00
Yassin Kortam
5673f67727
Merge pull request #42022 from BerriAI/litellm_redis_durable_spend_log_buffer 
fix(proxy): park requeued spend logs in Redis so they survive a pod restart during a DB outage
 2026-09-21 14:01:34 -05:00
mateo-berri
5db2a97829 chore: keep main's lazy OpenAPI snapshot 
The snapshot check runs on Python 3.12, which keeps the indentation of a route docstring that Python 3.13+ strips at compile time, so regenerating it locally on 3.14 produces a file CI rejects.
 2026-09-21 12:01:26 -07:00
mateo-berri
2fe5c8990e fix(bedrock_mantle): bill Mantle's un-versioned Claude ids from a Mantle cost row 
Mantle serves anthropic.claude-haiku-4-5 without the dated -20251001-v1:0
suffix the Bedrock row carries, so the native route billed it at 0. Add a
bedrock_mantle/anthropic.claude-haiku-4-5 row and let a
bedrock_mantle/<region>/<model> name fall back to the region-free
bedrock_mantle/<model> row before the provider-prefixed lookup. Also
satisfy the mutable-collection gate in the native messages transformation.
 2026-09-21 12:00:38 -07:00
mateo-berri
4eed951e6f Merge commit '36b8be7d81b' into litellm_mantle_native_anthropic_messages_b4dc 
# Conflicts:
#	tests/test_litellm/llms/anthropic/experimental_pass_through/messages/test_anthropic_experimental_pass_through_messages_handler.py
 2026-09-21 12:00:37 -07:00
Yujong Lee
a7bc8e373e feat(cache): project Python backend configuration 2026-09-21 11:56:04 -07:00
mateo-berri
5ea4fe620f test(router): give each prompt caching check test a fresh callback registry 2026-09-21 11:55:58 -07:00