Sannan Nasir
0e53b1feab
Add digitalocean provider ( #12169 )
...
* Add digitalocean provider
* Add digitalocean provider
* Revert "Add digitalocean provider"
This reverts commit 96dda40f4537bd51bd5468c8a198ee
2025-08-09 16:26:33 -07:00
Ishaan Jaff
f60a9cf908
[Bug]: Fix JWTs access not working with model groups ( #13474 )
...
* fix can_team_access_model
* test_find_team_with_model_access_model_group
2025-08-09 16:14:51 -07:00
Jugal D. Bhatt
95fbe59c46
Add local storage auth ( #13473 )
2025-08-09 16:13:56 -07:00
Jugal D. Bhatt
67833590d6
[Proxy changes] Litellm add model price reload schedule for multi-pod ( #13470 )
...
* added mcp guardrails doc in mcp.md
* add button to reload models
* Added button changes
* added button for scheduling reload
* add multi pod support to reloading the model price json
* fix ruff
2025-08-09 16:12:13 -07:00
Krish Dholakia
1c8761111f
Router - reduce p99 latency w/ redis enabled by 50% + OTEL - track pre_call hook latency ( #13362 )
...
* feat(proxy/utils.py): track pre-call hooks in OTEL
some pre call hooks can cause latency in high traffic - make sure this is tracked
* fix(router.py): move redis call on deployment_callback_on_success to pipeline operation
reduces p99 latency by half when redis is enabled
* fix(parallel_request_limiter_v3.py): only run check if any item has rate limits set
Prevents unnecessary latency added by rate limit checks
* test: add unit tests
* Latency Improvements: only track tpm/rpm usage when set on deployment+ LLM Caching - use an in-memory cache to reduce redis calls + OTEL - track time spent on LLM caching (#13472 )
* fix(router.py): only track usage for deployments with tpm/rpm set
ensures additional latency avoided for non-tpm/rpm models
* fix(caching_handler.py): log time spent on request get cache to OTEL
enables easy debugging of call latency
* fix(caching_handler.py): use dual cache object for in-memory caching + trace redis call within caching handler
* fix(caching_handler.py): working in-memory cache for redis calls
ensures dual cache works when redis cache setup for llm calls
makes calls quicker by only checking redis when in-memory cache missed for llm api call
* test: remove redundant test
* test: add unit tests
2025-08-09 16:09:51 -07:00
Ishaan Jaff
60306d34a0
[Bug Fix] Allow using Swagger for /chat/completions ( #13469 )
...
* fix get_openapi_schema
* fixes for ProxyChatCompletionRequest
* TestSwaggerChatCompletions
* fix working request body
* fix - add "messages"
* fix messages
* TestSwaggerChatCompletions
* test_messages_field_has_example
* ruff check fix
2025-08-09 15:35:45 -07:00
Jugal D. Bhatt
1270df08a4
[Proxy + UI] Litellm add reload model api and button ( #13464 )
...
* added mcp guardrails doc in mcp.md
* add button to reload models
* Added button changes
* remove the model_reload
2025-08-09 13:52:56 -07:00
Jugal D. Bhatt
10a1fe21c5
[LLM Translation] Litellm azure o series drop params ( #13353 )
...
* added route check
* fix ruff
* Added support for dropping o_series params
* Added ruff fix
* fix tests
2025-08-09 13:52:45 -07:00
Ishaan Jaff
6184e898b7
Generate unique IDs for litellm_call_id and function_id using UUID ( #13468 )
...
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: ishaan <ishaan@berri.ai>
2025-08-09 12:59:09 -07:00
Ishaan Jaff
eb4bd26f24
[Bug Fix] - Get Routes ( #13466 )
...
* fixes get_routes_for_mounted_app
* fix - use _safe_get_endpoint_name
* fix code QA check
* test_get_routes_for_mounted_app_with_static_files
* test fixes
2025-08-09 12:52:23 -07:00
Ishaan Jaff
825ea65b96
[Bug Fix] Responses API - Responses API failed if input containing ResponseReasoningItem ( #13465 )
...
* add test_responses_api_multi_turn_with_reasoning_and_structured_output
* fix transform_responses_api_request
2025-08-09 11:20:34 -07:00
Ishaan Jaff
ee40db7b31
docs native litellm prompts
2025-08-09 09:46:31 -07:00
Ishaan Jaff
94c33200a4
docs - native prompt mgmt ( #13463 )
2025-08-09 09:39:16 -07:00
Ishaan Jaff
3999e65a97
docs update
2025-08-09 09:24:41 -07:00
NULL
c75e7230d2
Merge branch 'BerriAI:main' into dev
2025-08-09 13:54:14 +08:00
NULL
54e77715ca
Merge branch 'BerriAI:main' into main
2025-08-09 13:54:01 +08:00
Cole McIntosh
d874bec480
feat(models): add OpenRouter and Cerebras GPT-OSS models (20b, 120b) with pricing and context windows; update backup; refs #13428 ( #13442 )
2025-08-08 22:47:51 -07:00
Jugal D. Bhatt
035e5497e0
added mcp guardrails doc in mcp.md ( #13452 )
2025-08-08 22:47:31 -07:00
NULL
7bb1b6f6cf
Merge pull request #2 from cometapi-dev/dev
...
feat: add CometAPI provider support with chat completions and streaming
2025-08-09 11:08:53 +08:00
NULL
d9089f77e1
Merge branch 'main' into dev
...
Signed-off-by: NULL <129579691+TensorNull@users.noreply.github.com>
2025-08-09 11:06:52 +08:00
NULL
22595b69fc
Merge branch 'BerriAI:main' into dev
2025-08-09 11:00:33 +08:00
TensorNull
ea0f768122
fix: specify type for extra_body in CometAPIConfig
2025-08-09 10:59:23 +08:00
NULL
7b0d75810d
Merge branch 'BerriAI:main' into main
2025-08-09 10:48:00 +08:00
NULL
ec87f41b22
Merge pull request #1 from cometapi-dev/dev
...
feat: add CometAPI provider support with chat completions and streaming
2025-08-09 10:47:35 +08:00
TensorNull
c9b334fcd1
feat: add CometAPI support with config, error handling and tests
2025-08-09 10:42:45 +08:00
Ishaan Jaff
3905cee579
test fixes
2025-08-08 18:50:09 -07:00
Ishaan Jaff
05b48eba62
fix security issue
2025-08-08 18:32:50 -07:00
Ishaan Jaff
32db7f1508
bump: version 1.75.3 → 1.75.4
2025-08-08 18:30:27 -07:00
Ishaan Jaff
edc38b73f9
UI new build
2025-08-08 18:30:15 -07:00
Ishaan Jaff
a843e876a8
[Feat] Working e2e flow for Responses API session management with media ( #13456 )
...
* add MultimodalContent on chat UI
* add multi modal img on chat ui
* utils for responses API imgs
* add code snippet with imgs
* chat UI add imgs
* add imge upload
* chat ui allow adding images
* fix chat send button
* fix button styles
* fix clear chat
* fixes session management
* fixes for session management
* QA fix _should_check_cold_storage_for_full_payload
* test_should_check_cold_storage_for_full_payload
2025-08-08 18:28:10 -07:00
Cole McIntosh
1d514cc68b
feat(reasoning): support 'minimal' effort type for OpenAI ( #13447 )
...
* feat(reasoning): support 'minimal' effort type for OpenAI
* fix(reasoning): correctly map 'minimal' effort to Reasoning object
* chore(dependencies): update OpenAI package version to 1.99.5 in pyproject.toml and requirements.txt
* chore(dependencies): update poetry.lock for OpenAI package version 1.99.5 and Poetry version 2.1.3
2025-08-08 17:56:23 -07:00
tanjiro
4571002e19
disable logging settings for non-enterprise users ( #13431 )
2025-08-08 17:35:29 -07:00
Ishaan Jaff
840db3fe48
LiteLLM UI - Test Key Page - allow uploading images for /chat/completions and /responses ( #13445 )
...
* add MultimodalContent on chat UI
* add multi modal img on chat ui
* utils for responses API imgs
* add code snippet with imgs
* chat UI add imgs
* add imge upload
* chat ui allow adding images
* fix chat send button
* fix button styles
* fix clear chat
2025-08-08 16:57:08 -07:00
Ishaan Jaff
7e2a00c848
[Docs] Add docs on how router / cooldowns work ( #13444 )
...
* add theme-mermaid
* docs cool down
* docs cooldown
2025-08-08 15:13:37 -07:00
Ishaan Jaff
d0aa12f3bf
Enhance team member permission error message with guidance for key creation ( #13443 )
...
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: ishaan <ishaan@berri.ai>
2025-08-08 14:35:06 -07:00
Low Jian Sheng
7f55bbc296
add support for reasoning_effort minimal ( #13401 )
2025-08-08 14:34:46 -07:00
Jugal D. Bhatt
f55666bf5f
fix prices for oai gpt 5 ( #13441 )
2025-08-08 14:33:21 -07:00
Cole McIntosh
66cc88ffb4
Merge branch 'BerriAI:main' into fix/ollama-gpt-oss-thinking-field
2025-08-08 15:06:30 -06:00
Ishaan Jaff
3b65733af8
[Bug fix] - Error creating standard logging object - can't register atexit after shutdownLitellm fixes standard logging payload ( #13436 )
...
* fix: _generate_cold_storage_object_key
* _get_configured_cold_storage_custom_logger
* test_e2e_generate_cold_storage_object_key_runtime_error_handled
2025-08-08 12:38:26 -07:00
tanjiro
4fdc866fcb
Display Error from Backend on the UI - Notification ( #13427 )
...
* fix sso logout
- add a new login page with sso button
* lint fix
* lint fix
* lint fix
* fix tests
* fix test
* Revert "fix test"
This reverts commit 74eb73457172d0b2d4c6
2025-08-08 12:34:16 -07:00
Jugal D. Bhatt
51c2ff7c15
fix user membership issue ( #13433 )
2025-08-08 12:00:58 -07:00
Ishaan Jaff
3a35c82884
[Feat] Add reasoning_effort to OpenAIGPT5Config ( #13434 )
...
* add reasoning_effort toi OpenAIGPT5Config
* test_gpt5_supports_reasoning_effort
2025-08-08 11:57:12 -07:00
Davide Pugliese
81f2563338
Enhance logging for containers
2025-08-08 18:28:35 +02:00
Edward D'Amato
793e1aa7c7
fix(proxy): add missing braintrust api base to env vars ( #13412 )
2025-08-08 08:59:33 -07:00
Thiago Salvatore
c2ad858c83
fix(access group): allow access group on mcp tool retrieval ( #13425 )
...
* fix(access group): allow access group on mcp tool retrieval
* fix(test): fix broken tests and add test case for access group
* fix(mypy): fix typing issues
2025-08-08 08:55:46 -07:00
Emerson Gomes
aea5af2165
Correct GPT-5 token limits and price ( #13423 )
2025-08-08 08:55:33 -07:00
Oz Ben-Ami
58bbecffb7
Merge remote-tracking branch 'origin/main' into fix_vertex_expired_tokens
2025-08-08 02:19:17 -04:00
Ishaan Jaff
aefa71a300
bump: version 1.75.2 → 1.75.3
2025-08-07 21:32:44 -07:00
Ishaan Jaff
6b2ad4dc0f
ui new build
2025-08-07 21:20:19 -07:00
Ishaan Jaff
9bfc4f89c9
fix ui
2025-08-07 21:13:46 -07:00
