yuneng-jiang
0e5b56eddf
Fixing tests
2025-12-16 12:51:44 -08:00
yuneng-jiang
66306f21b1
Add litellm overhead to spend logs metadata
2025-12-15 20:56:55 -08:00
Krish Dholakia and GitHub
f58b76aee8
Revert "Revert "Litellm bedrock guardrails block precedence over masking (#17…" ( #18023 )
...
This reverts commit 0abe5cdce9 .
2025-12-16 08:42:10 +05:30
Krish Dholakia and GitHub
0abe5cdce9
Revert "Litellm bedrock guardrails block precedence over masking ( #17968 )" ( #18022 )
...
This reverts commit a0754f1c88 .
2025-12-16 08:41:36 +05:30
kothamah and GitHub
a0754f1c88
Litellm bedrock guardrails block precedence over masking ( #17968 )
...
* prioritized bedrock guardrail blocking by removing early return based on masking flags
When mask_request_content: true or mask_response_content: true, the method immediately returning False.
The Result: Even when Bedrock Guardrails returned action: "BLOCKED" for dangerous content, LiteLLM would not raise an exception and allowing the content through the response.
So removed that early condition which will return true for the blocked actions based on guardrails.
* Added test case for bedrock guardrail block content precedence
2025-12-16 08:41:13 +05:30
Yuta Saito
defea8b887
fix: mcp deepcopy error
2025-12-16 07:02:07 +09:00
Krish Dholakia and GitHub
26fd6d5362
Guardrails API - support LLM tool call response checks on /chat/completions, /v1/responses, /v1/messages on regular + streaming calls ( #17619 )
...
* fix(unified_guardrails.py): send all chunks on completion of final stream
* feat(generic_guardrail_api.py): handle tool call response on streaming LLM responses
* fix(anthropic/chat/guardrail_translation): initial commit adding anthropic tool response streaming guardrails
enables guardrail checks on tool response from llm's to work via `/v1/messages`
* feat(anthropic/): working guardrail checks on tool response from LLMs
ensures guardrail checks on anthropic /v1/messages works as expected
* feat(responses/guardrail_translation): support tool call response guardrails on streaming for /v1/responses
ensures complete coverage of tool call responses
* refactor(openai.py): refactor to use consistent pydantic model for responses api tool response on streaming
enables non-openai model tool call response to work correctly with guardrail checks on /v1/responses
* test: update tests
* fix: fix linting error
* fix: fix failing tests
* fix: fix import errors
* fix(openai/chat/guardrail_transformation): fix final chunk returned on streaming
2025-12-15 18:19:52 +05:30
Yuta Saito
73e00c1382
fix: add MCP auth header propagation
2025-12-15 07:45:35 +09:00
Ishaan Jaffer
f6c4ad92e4
async def test_update_team_guardrails_with_org_id():
2025-12-13 16:24:58 -08:00
yuneng-jiang
61767779f8
Adding tests
2025-12-13 14:44:26 -08:00
Ishaan Jaff and GitHub
d38f241032
[Feat] JWT Auth - auth allow selecting team_id from request header ( #17884 )
...
* feat: add get_team_id_from_header for JWT Auth
* fix Auth builder JWT Auth
* test_get_team_id_from_header
* test_auth_builder_uses_team_from_header_e2e
* Select Team via Request Header
2025-12-12 10:18:20 -08:00
Sameer Kankute and GitHub
da81ab6d97
Merge pull request #17758 from BerriAI/litellm_managed_files_target_storage
...
Add v0 support for target storage
2025-12-12 22:26:34 +05:30
Sameer Kankute and GitHub
abbf8be07b
Merge pull request #17864 from BerriAI/litellm_fix_x-litellm-key-spend
...
Fix x-litellm-key-spend header update
2025-12-12 22:23:42 +05:30
Sameer Kankute and GitHub
e0428388a7
Merge pull request #17860 from BerriAI/litellm_openai_files_expire_after_support
...
Add support for expires after param in Files endpoint
2025-12-12 22:23:11 +05:30
Alexsander Hamir and GitHub
d9cf53b555
fix: remove dependency on database and redis from health test ( #17880 )
2025-12-12 08:21:48 -08:00
Alexsander Hamir and GitHub
c9063d13b1
Add health endpoint tests to CI with database and Redis support ( #17877 )
...
- Add database and Redis setup to litellm_mapped_tests_proxy job in CircleCI
- Create shared test helpers in tests/test_litellm/proxy/conftest.py for proxy test setup
- Refactor health endpoint tests to use shared helpers from conftest
- Support automatic Redis cache configuration when REDIS_HOST is set
- Ensure minimal config is created when Redis/database is needed
2025-12-12 07:35:50 -08:00
Ariel and GitHub
5df701d15c
[feat]: Add opt-in evidence results for Pillar Security guardrail during monitoring ( #17812 )
...
* add evidence headers to litellm
* ensure that evidence is surface-able, even in opt-in mode
* update the docs
2025-12-12 04:09:13 -08:00
Sameer Kankute
caaf8a6784
Fix x-litellm-key-spend update
2025-12-12 11:44:51 +05:30
Sameer Kankute
49e0f8e95f
Add support for expires after param
2025-12-12 10:01:18 +05:30
Jason Roberts and GitHub
6fc39d31b4
feat(guardrails): add configurable fail-open, timeout, and app_user to PANW Prisma AIRS guardrail ( #17785 )
...
Add configurable fail-open/fail-closed behavior, timeout settings, and app_user
metadata tracking. Includes security hardening, enhanced
observability (:unscanned header), and comprehensive test coverage (44/44 passing).
No breaking changes.
2025-12-11 15:23:59 -08:00
yuneng-jiang and GitHub
cb9bae1aba
Merge pull request #16764 from BerriAI/litellm_tag_spend_dedupe
...
[Fix] Deduplicate /tag/daily/activity metadata
2025-12-11 15:20:16 -08:00
Dominic Fallows and GitHub
756c60540e
feat: add support for configurable confidence score thresholds and scope in Presidio PII masking ( #17817 )
...
* feat: add support for configurable confidence score thresholds in Presidio PII masking
* feat: enhance Presidio PII masking with configurable score thresholds and behavior documentation
* feat: add configurable output masking and filter scope for Presidio PII guardrail
2025-12-11 15:19:11 -08:00
yuneng-jiang and GitHub
2a864e25f8
Merge pull request #17668 from BerriAI/litellm_sso_config_2
...
[Fix] Remove SSO Config Values from Config Table on SSO Update
2025-12-11 15:17:33 -08:00
yuneng-jiang and GitHub
de9a195d8c
Merge pull request #17781 from BerriAI/litellm_daily_agent_table
...
[Feature] Daily Agent Usage Backend
2025-12-11 15:01:50 -08:00
mubashir1osmani and GitHub
1b2ea270b4
fix: attach team to org table ( #17832 )
...
* fix: attach team to org table
* add test
2025-12-11 14:54:50 -08:00
Alexsander Hamir and GitHub
e9baa83a0f
[Fix] CI/CD – Clean Up Performance PR Changes & others ( #17838 )
2025-12-11 12:50:03 -08:00
yuneng-jiang and GitHub
26926d5fea
Merge pull request #17804 from BerriAI/litellm_add_model_settings_fix
...
[Fix] Ensure Model Page Honors UI Settings
2025-12-11 09:20:28 -08:00
YutaSaito and GitHub
e9571ddbc4
fix: MCP OAuth callback routing and URL handling ( #17789 )
...
* fix: MCP OAuth callback routing and URL handling
* test: add test for proxy_server
2025-12-11 08:22:59 -08:00
Ashton Sidhu and GitHub
a514313540
Add Hiddenlayer Guardrail Hooks ( #17728 )
...
* Core logic working, need to add tests
* Re add removed files
* Remove mistaken files
* one more file
* Add deployment params
* Add tests
* Remove unused imports
* Update docs from feedback
* Update guardrails
2025-12-11 07:43:26 -08:00
Sameer Kankute
7b1cef86a7
Add support for target_storage param
2025-12-11 15:08:17 +05:30
yuneng-jiang
7ca2c2abfc
Adding tests
2025-12-10 21:37:38 -08:00
Sameer Kankute and GitHub
8942053c8b
Merge pull request #17700 from BerriAI/litellm_batches_passthrough_cost_tracking
...
Add anthropic retrieve batches and retreive file content support
2025-12-11 10:31:54 +05:30
yuneng-jiang
91056c1d7e
Merge remote-tracking branch 'origin' into litellm_daily_agent_table
2025-12-10 20:47:58 -08:00
Sameer Kankute
9344d29a15
fix: Preserve systemInstructions for vertex ai generate content request
2025-12-11 09:52:32 +05:30
Sameer Kankute and GitHub
2ea855d225
Merge pull request #17707 from raghav-stripe/raghav-fix-responsesapi-rl
...
fix: responses api not applying tpm rate limits on api keys
2025-12-11 08:57:16 +05:30
Ishaan Jaff and GitHub
059fedbed5
[Feat] Agent Gateway - Track agent_id in SpendLogs ( #17795 )
...
* add agent_id in metadata in spend logs
* add agent_id in SpendLogsPayload
* add agent_id in SpendLogsPayload
* add _set_agent_id_on_logging_obj
* add agent id tracking in SpendLogs
* add agent id in spend logs
* fix create_a2a_client
* test_asend_message_passes_agent_id_to_callback
* test_get_logging_payload_includes_agent_id_from_kwargs
* test_asend_message_streaming_triggers_callbacks
* fix asend_message_streaming
* asend_message_streaming
* A2AStreamingIterator
* _handle_stream_message
* test_asend_message_streaming_propagates_metadata
2025-12-10 16:09:56 -08:00
Ishaan Jaff and GitHub
5d456bcdc3
[Feat] UI SSO - allow fetching role from generic SSO provider (Keycloak) ( #17787 )
...
* fix ui SSO
* TestGenericResponseConvertorUserRole
* Assigning User Roles via SSO
2025-12-10 13:09:28 -08:00
yuneng-jiang
1cad479297
Daily Agent Usage Table WIP
2025-12-10 11:50:52 -08:00
saisurya237 and GitHub
f3ead2c153
add a new feature fix to expose the team alias when authenticating th… ( #17725 )
...
* CLI SSO: show team aliases in team selection
* temp poetry lock fix
* add poetry.lock to gitignore
* Revert proxy_server background job refactor
* Revert proxy_server background job refactor
* rever gitignore and poetry lock file
2025-12-10 10:10:28 -08:00
yuneng-jiang and GitHub
ba554a86b9
Merge pull request #16843 from BerriAI/litellm_allow_custom_mount_paths
...
[Feature] Allow Root Path to Redirect when Docs not on Root Path
2025-12-10 09:52:30 -08:00
Sameer Kankute
9e3a04a725
Add batch passthrough endpoint cost tracking for anthropic
2025-12-10 18:24:31 +05:30
Lucas Sugi and GitHub
c7fd8fabdb
fix: Avoid error when we have just the tool_calls in input ( #17753 )
...
* fix: Avoid error when we have just the tool_calls in input
* fix: Remove the tool call validation
* feat: Add unit test
2025-12-09 22:59:59 -08:00
Ishaan Jaff and GitHub
e546f0e021
[Fix] UI SSO - allow up-serting user role when SSO provider role changes ( #17754 )
...
* use _build_sso_user_update_data
* test_build_sso_user_update_data_with_valid_role
2025-12-09 19:16:10 -08:00
Peter Chanthamynavong and GitHub
539ce89d4e
fix(guardrails): mask all regex pattern matches, not just first ( #17727 )
...
Before: search() + replace() only replaced first match
After: sub() replaces all matches of each pattern
Closes #17687
2025-12-09 18:51:28 -08:00
yuneng-jiang
d99cf81386
Fixing test
2025-12-09 16:11:17 -08:00
ephrimstanley and GitHub
a91dda1194
Return 403 instead of 503 for unauthorized routes ( #17723 )
2025-12-09 15:16:11 -08:00
yuneng-jiang
879ae45421
Change credential encryption to only affect db credentials
2025-12-09 13:36:40 -08:00
yuneng-jiang
68419cfe4e
Merge remote-tracking branch 'origin' into litellm_tag_spend_dedupe
2025-12-09 11:59:47 -08:00
yuneng-jiang
39bf7a9f7c
Merge remote-tracking branch 'origin' into litellm_allow_custom_mount_paths
2025-12-09 11:58:05 -08:00
yuneng-jiang
4bffbe0bff
Merge remote-tracking branch 'origin' into litellm_sso_config_2
2025-12-09 11:56:30 -08:00