Clint Banzhaf
caddc6dd0f
fix images being dropped from tool results for bedrock ( #16492 )
...
* fix images being dropped from tool results for bedrock
* type fixes
2025-11-21 10:52:48 -08:00
Ishaan Jaff
97d9da93e0
[Feat] Prompt Management - Allow viewing version history ( #16901 )
...
* TestPromptRequest
* add prompts/test endpoint for testing prompt
* TestPromptTestEndpoint
* feat: working v1 of this ui
* workig prompt endpoints
* add chat ui for prompts
* add conversation panel
* add init chat ui
* allow clicking edit prompt
* fix use get_base_prompt_id
* add endpoints for viewing prompt versions
* TestPromptVersioning
* add getPromptVersions
* add VersionHistorySidePanel
* allow viewing version history
* add version history
2025-11-21 08:54:52 -08:00
Ishaan Jaff
3c789ac287
feat: Add vector store create and search call types ( #16859 )
...
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: ishaan <ishaan@berri.ai>
2025-11-21 08:54:41 -08:00
Ishaan Jaff
41566722af
[Feat] UI - Prompt Management - Allow testing prompts with Chat UI ( #16898 )
...
* TestPromptRequest
* add prompts/test endpoint for testing prompt
* TestPromptTestEndpoint
* feat: working v1 of this ui
* workig prompt endpoints
* add chat ui for prompts
* add conversation panel
* add init chat ui
2025-11-21 08:53:18 -08:00
superpoussin22
b96179a07a
Upgrade pydantic to version 2.11.0 ( #16909 )
...
Updated pydantic version to 2.11.0 for compatibility.
2025-11-21 08:52:44 -08:00
ツルマルツヨシ
be9f2e026c
feat(pricing): Add Gemini 3 Pro Preview for OpenRouter ( #16905 )
2025-11-21 08:52:25 -08:00
YutaSaito
041ac054b6
feat: allow custom violation message for tool-permission guardrail ( #16916 )
2025-11-21 08:52:01 -08:00
yuneng-jiang
7225fc066f
Fix key model alias ( #16896 )
2025-11-20 16:05:49 -08:00
Krrish Dholakia
e7751f0c12
docs: fix docs bug
2025-11-20 16:05:39 -08:00
YutaSaito
93affcb732
[Feat] mcp resources support ( #16800 )
...
* feat: mcp prompts support
* feat: mcp resources support
2025-11-20 14:53:44 -08:00
Ishaan Jaffer
0d812f98bc
new u build
2025-11-20 14:05:27 -08:00
Ishaan Jaff
57544f1662
[Feat] Adds IAM role assumption support for AWS Secret Manager ( #16887 )
...
* add AWS fields for KeyManagementSettings
* docs IAM roles
* use aws iam auth on secret manager v2
* fix: load_aws_secret_manager
* test_secret_manager_with_iam_role_settings
2025-11-20 12:38:48 -08:00
yuneng-jiang
9120a02474
Change favicon ( #16837 )
2025-11-19 20:38:22 -08:00
Sameer Kankute
e5948770dd
Fix audio transcription cost tracking ( #16478 )
2025-11-19 20:29:39 -08:00
Krrish Dholakia
28cadaa123
docs: fix tags
2025-11-19 20:26:48 -08:00
Krrish Dholakia
0389f2d064
docs: cleanup
2025-11-19 20:26:48 -08:00
Sameer Kankute
c3143e388e
Add thought signature support to v1/messages api ( #16812 )
...
* Add thought signature support to v1/messages api
* update the thinking level handling logic
* update the thinking level handling logic
* Add streaming support
* fix intalling litellm error
2025-11-19 20:24:31 -08:00
Krrish Dholakia
87be419559
docs(index.md): cleanup
2025-11-19 20:23:22 -08:00
Krrish Dholakia
778425f02f
docs: add initial blog post for Gemini 3 on LiteLLM
2025-11-19 20:22:24 -08:00
Krrish Dholakia
208027dc71
docs(ui.md): reorder ui page
2025-11-19 19:17:54 -08:00
Alexsander Hamir
0a13114536
[Fix] Security - Filter secret fields form Langfuse ( #16842 )
...
* fix: remove secret fields from logs
* fix: remove secret fields from otel
2025-11-19 19:15:28 -08:00
Sebastian
cb843684b8
fix(vertex_ai): add includeThoughts=True for Gemini 3 reasoning_effort ( #16838 )
...
Gemini 3 models require 'includeThoughts: True' in the thinkingConfig to return the actual thought text. Previously, using reasoning_effort set the 'thinkingLevel' but missed the boolean flag, resulting in empty reasoning_content.
This fix:
1. Updates `_map_reasoning_effort_to_thinking_level` to include `includeThoughts: True` for low/medium/high.
2. Adds unit tests to verify the config mapping.
2025-11-19 19:14:42 -08:00
Alex Huang
3b6f3e48cb
Fix optional param mapping ( #16852 )
...
* Direct string check instead of tuple string inclusion check
* Add test
2025-11-19 19:10:04 -08:00
Cesar Garcia
7d5cb8ebb2
fix(gemini): Add reasoning_content to streaming responses with tools ( #16854 )
...
Fixes #16805
When using Gemini models (2.5/3.0) with streaming + tools enabled,
the reasoning_content field was missing from stream chunks, even though
thinking_blocks were present in non-streaming responses.
Changes:
- Convert thinking_blocks to reasoning_content for streaming responses
- Extract "thinking" field from each thinking_block
- Concatenate multiple thinking parts with newlines
- Assign to reasoning_content in chat_completion_message for streaming
Testing:
- Added test_streaming_chunk_with_tool_calls_includes_reasoning_content
- Test verifies reasoning_content appears with tool calls in streaming
- All 39 existing Gemini tests pass
2025-11-19 19:09:37 -08:00
Alexsander Hamir
7a84469605
fix(perf): add missing shared_sessions to audio/transcriptions ( #16858 )
...
This took longer than expected because the fake LLM endpoint on railway was deliverying bad performance when deployed due to some issue with railway.
2025-11-19 19:08:39 -08:00
yuneng-jiang
d22ea6f15f
[Feature] UI - Model Compare ( #16855 )
...
* Temp commit for branch switching, Compare WIP
* Model Compare UI
2025-11-19 19:07:11 -08:00
Krish Dholakia
65ff1eff56
MCP Hub - publish/discover MCP Servers within a company ( #16857 )
...
* feat: initial commit adding 'public_mcp_servers' endpoint
allow admin to make mcp servers public for AI Hub
* feat: expose public endpoint for getting public mcp's
* feat: initial flow for making MCP servers public via LiteLLM proxy
* fix: fix message on make mcp public
* fix: indicate existing public mcp servers are public, when making mcp servers public
* style: have a public column indicating if mcp server has been made public
* feat: expose new MCP Hub
* feat: include usage examples for mcp hub
2025-11-19 19:06:21 -08:00
Nigel Kukard
c5c563c302
fix: fixed openai conversion from responses to completions ( #16864 )
...
- Fix blank function name in completions response when using native function calling
- Fix Enum name being used instead of Enum value for comparison in chunk conversion
- Added additional tests to cover changes
Thanks to @mcowger for the invaluable assitance with figuring this issue out!
Fixed #16863
2025-11-19 19:02:52 -08:00
Krrish Dholakia
2d7365c795
refactor: refactor ai hub for internal users to show public model page
...
more useful than just seeing models they know they have access to
2025-11-19 18:50:10 -08:00
Sameer Kankute
6fc7397dde
Add Vertex AI Image Edit Support ( #16828 )
...
* Add vertex ai image edit support
* Fix lint errors
2025-11-19 18:39:28 -08:00
Sameer Kankute
36c9fede4e
Add azure gpt-5.1 models ( #16817 )
2025-11-19 18:37:08 -08:00
Ishaan Jaffer
95caa2e3de
bump openai 2.8.0
2025-11-19 17:47:18 -08:00
idola9
e1005cb9d3
Use LiteLLM key alias as fallback Noma applicationId in NomaGuardrail ( #16832 )
...
* Use auth key name if there are no app id in in headers or in extra_data
* use key alias instead of key name
* Fix
* last priority key alias
* Fix
* Add tests
2025-11-19 17:44:23 -08:00
Ishaan Jaffer
d389b9dd66
bump litellm enterprise
2025-11-19 16:56:50 -08:00
Sameer Kankute
9622829fa1
Fix vector store create issue ( #16804 )
2025-11-19 16:53:20 -08:00
Ishaan Jaff
cd6256f64a
[Feat] Prompt Management - Add UI for editing the prompts ( #16853 )
...
* v0 for prompt management
* v0
* clean up view of prompt editor
* commit editor view
* refactor prompt editor view
* ui - refactor prompt editor
* add move message
* add prompt editor view
* fix allow viewing dotprompt file
* add dotprompt_content
* handleSave for Prompt
* ui fix build fail
* ui fix build
2025-11-19 16:26:11 -08:00
Ishaan Jaff
ffe00f4034
Revert "make all gpt-5 and reasoning models to responses by default ( #16766 )" ( #16849 )
...
This reverts commit 149f308451
2025-11-19 13:32:58 -08:00
dependabot[bot]
98d2dbd711
Bump js-yaml from 3.14.1 to 3.14.2 ( #16802 )
...
Bumps [js-yaml](https://github.com/nodeca/js-yaml ) from 3.14.1 to 3.14.2.
- [Changelog](https://github.com/nodeca/js-yaml/blob/master/CHANGELOG.md )
- [Commits](https://github.com/nodeca/js-yaml/compare/3.14.1...3.14.2 )
---
updated-dependencies:
- dependency-name: js-yaml
dependency-version: 3.14.2
dependency-type: indirect
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2025-11-19 13:23:44 -08:00
Ishaan Jaffer
6477740b8c
bump proxy extras
2025-11-19 13:23:16 -08:00
Ishaan Jaff
c7cf18cf67
[Feat] Prompt Management - Allow storing prompt version in DB ( #16848 )
...
* test_dotprompt_auto_detection_with_model_only
* fix _auto_detect_prompt_management_logger
* test_dotprompt_with_prompt_version
* add v1, v2 tests
* add _compile_prompt_helper
* fix _compile_prompt_helper
* test_dotprompt_with_prompt_version
* test_dotprompt_with_prompt_version, test_get_prompt_with_version
* add version in schema
* feat add _get_prompt_spec_for_db_prompt
* add _get_prompt_spec_for_db_prompt
* feat add _get_prompt_spec_for_db_prompt
* update prompt table
* add version in prompt DB
* test_get_prompt_spec_for_db_prompt_with_versions
2025-11-19 13:19:56 -08:00
Naki
98dd866b26
feat(github-copilot): Add Responses API support for gpt-5.1-codex model ( #16845 )
...
- Implement GithubCopilotResponsesAPIConfig for /responses endpoint
- Add support for models requiring responses API (e.g., gpt-5.1-codex)
- Auto-detect vision requests and set X-Initiator header
- Follow OpenAI Responses API compatibility pattern
- Add comprehensive unit tests (16 tests passing)
Fixes #16820
2025-11-19 13:17:19 -08:00
Ishaan Jaff
3ebe489082
[Feat] Prompt Management - Add support for versioning prompts ( #16836 )
...
* test_dotprompt_auto_detection_with_model_only
* fix _auto_detect_prompt_management_logger
* test_dotprompt_with_prompt_version
* add v1, v2 tests
* add _compile_prompt_helper
* fix _compile_prompt_helper
* test_dotprompt_with_prompt_version
* test_dotprompt_with_prompt_version, test_get_prompt_with_version
2025-11-19 13:16:03 -08:00
Ishaan Jaff
1f8fe007a1
[Feat] Prompt Management - Allow specifying just prompt_id in a request to a model ( #16834 )
...
* test_dotprompt_auto_detection_with_model_only
* fix _auto_detect_prompt_management_logger
* test_dotprompt_auto_detection_with_model_only
2025-11-19 10:20:58 -08:00
tushar8408
5f94b372f8
Migration job labels ( #16831 )
...
* Add dynamic pod labels and annotations to migrations job
* Bump chart version to 0.4.8
2025-11-19 09:53:21 -08:00
Krrish Dholakia
08246bf908
fix: fix broken doc link
2025-11-19 08:35:38 -08:00
Alan Ponnachan
b92cc2b2f9
fix(bedrock): Ensure consistent chunk IDs in Bedrock streaming responses ( #16596 )
...
* ensure consistent chunk IDs in streaming responses
* use native conversationId for consistent stream chunk IDs
2025-11-18 20:37:21 -08:00
Sameer Kankute
149f308451
make all gpt-5 and reasoning models to responses by default ( #16766 )
2025-11-18 20:31:59 -08:00
yuneng-jiang
5f463cef64
Fix edit logging settings not appearing ( #16798 )
2025-11-18 20:31:34 -08:00
Sameer Kankute
34cc532d8d
Make sure that user inherits team permissions ( #16639 )
2025-11-18 20:14:42 -08:00
yuneng-jiang
ab8704f60d
Change placeholder for Azure in Add Model ( #16597 )
2025-11-18 20:13:48 -08:00
