scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-06 02:48:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103
52356 commits 3198 branches 1436 tags 4.5 GiB
Commit graph

52356 commits

This branch
This branch
All branches
Author SHA1 Message Date
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
moe-berri
a83773cfa5
Merge pull request #41886 from BerriAI/litellm_jev_autorouter_launch_1789767495 
feat(auto-router): add JEV classifier alongside LLM classifier
 2026-09-21 11:55:44 -07:00
mateo-berri
f549c87091 Merge branch 'main' into litellm_prompt_caching_affinity_lookback 2026-09-21 11:55:40 -07:00
Mateo Wang
7cb884cd31
Merge pull request #42120 from BerriAI/litellm_cadence_58065d4_google_genai_proxy_master_key 
test(google): boot the unified Google proxy fixture with a real master key
 2026-09-21 11:54:03 -07:00
kerry-berri
8ee8613b07
Merge pull request #42271 from BerriAI/litellm_bedrock_kimi_k3_us_cris 
feat(bedrock): add us.moonshotai.kimi-k3 pricing and fill the global Kimi K3 entry
 2026-09-21 11:51:54 -07:00
kerry-berri
12379aa1e3
Merge pull request #42095 from BerriAI/litellm_fal_gpt_image_25_flux_dev_edits 
feat(fal_ai): add gpt-image-2.5 flare/sunburst, flux/dev and image edits
 2026-09-21 11:45:45 -07:00
kerry-berri
24f0f373fc
Merge pull request #42270 from BerriAI/litellm-providers/price-sync-openrouter 
chore(prices): sync OpenRouter prices: 6 models
 2026-09-21 11:41:51 -07:00
kerry-berri
9b65ec206a
Merge pull request #42269 from BerriAI/litellm-providers/price-sync-aws-bedrock 
chore(prices): sync AWS Bedrock prices: 3 models [enrichment failed: AWS Bedrock, 32 held]
 2026-09-21 11:41:45 -07:00
mateo-berri
e51ccbc759 fix(bedrock): forward anthropic-beta headers verbatim on the Claude platform messages path 2026-09-21 11:39:26 -07:00
mateo-berri
f567fe230e fix: reserve cap slots for direct marks on /v1/messages when extra_body unmarks them 2026-09-21 11:39:25 -07:00
Mateo Wang
4b2e96a5f5
Merge pull request #42143 from BerriAI/litellm_e2e_changed_keep_pytest_log 
ci(e2e): fix the stage-mirror batch reds and keep a redacted pytest log
 2026-09-21 11:39:25 -07:00
Joshua Valluru
1499d84f5a fix(mcp): paginate optional discovery lists 2026-09-21 11:37:55 -07:00
mateo-berri
4c50710c02 Merge branch 'main' into claude/e2e-tests-custom-endpoints-qxoi1o 
Resolves the six conflicts main accumulated against the SDK migration.
endpoints_client.py stays deleted (main only added the safety_identifier
kwarg to it), and its two new importers move onto the SDK clients: the
Bedrock safety_identifier forwarding test in test_responses_e2e.py now
sends its /v1/responses leg through the OpenAI SDK and its chat leg
through ProxyClient.chat, and test_messages_azure_foundry_e2e.py drops
the x-litellm-rust header check together with EXPECT_RUST, which main
removed from e2e_config in a84f68b6e3. proxy_client.py keeps both the
rerank and router-settings model imports. uv.lock is main's lock plus
the anthropic e2e-dev entry, and the pricing JSONs are taken verbatim
from main since this PR never meant to change them.
 2026-09-21 11:34:21 -07:00
kerry
29837b422e feat(bedrock): add us.moonshotai.kimi-k3 pricing and fill the global Kimi K3 entry 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 18:32:55 +00:00
berriai-litellm-provider-info-sync[bot]
9f041f3ea3
chore(prices): sync OpenRouter prices: 6 models 
openrouter/~deepseek/deepseek-pro-latest: input_cost_per_token, output_cost_per_token, cache_read_input_token_cost, off_peak_pricing
openrouter/~deepseek/deepseek-v4-flash-latest: output_cost_per_token
openrouter/deepseek/deepseek-v4-flash-0731: output_cost_per_token
openrouter/deepseek/deepseek-v4-pro: input_cost_per_token, output_cost_per_token, cache_read_input_token_cost
openrouter/deepseek/deepseek-v4-pro-0813: input_cost_per_token, output_cost_per_token, cache_read_input_token_cost, off_peak_pricing
openrouter/nvidia/nemotron-3-nano-30b-a3b: supports_prompt_caching, input_cost_per_token, output_cost_per_token
 2026-09-21 18:31:34 +00:00
berriai-litellm-provider-info-sync[bot]
950f28fa63
chore(prices): sync AWS Bedrock prices: 3 models [enrichment failed: AWS Bedrock, 32 held] 
google.gemma-3-27b-it: max_tokens, max_output_tokens, supports_audio_input, supports_response_schema, supports_function_calling
mistral.ministral-3-3b-instruct: max_tokens, supports_vision, max_output_tokens, supports_audio_input, supports_response_schema
nvidia.nemotron-nano-12b-v2: max_tokens, max_output_tokens, supports_audio_input, supports_response_schema, supports_function_calling
 2026-09-21 18:31:32 +00:00
Moe Khalil
83ec5d6101 fix(auto-router): skip JEV for encrypted delegated tasks 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 18:29:21 +00:00