scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-10 03:28:53 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 85
34325 commits 3393 branches 1449 tags 5.1 GiB
Commit graph

34325 commits

This branch
This branch
All branches
Author SHA1 Message Date
Julio Quinteros Pro
0dc8b08987 fix: remove unused top-level EncryptedContentAffinityCheck import 
The class is already imported locally where it's used (line 1261).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-04 11:36:08 -03:00
Julio Quinteros Pro
317c162dfe
Merge pull request #22785 from BerriAI/fix/azure-batches-test-tenacity-import 
Guard tenacity import in e2e Azure batch tests
 2026-03-04 11:34:57 -03:00
Julio Quinteros Pro
a7e2bc3a92
Merge pull request #22784 from BerriAI/fix/responses-id-security-test 
Fix responses ID security test for new request_cache parameter
 2026-03-04 11:34:23 -03:00
Julio Quinteros Pro
fac622b5e6
Merge pull request #22783 from BerriAI/fix/schema-migration-check 
Add missing migration for LiteLLM_ToolTable policy changes
 2026-03-04 11:34:16 -03:00
Julio Quinteros Pro
f4e8c02ba2
Merge pull request #22781 from BerriAI/fix/tool-management-endpoint-tests 
Fix tool management tests using wrong field name call_policy
 2026-03-04 11:34:04 -03:00
Julio Quinteros Pro
d3b210fdd0
Merge pull request #22780 from BerriAI/fix/a2a-cost-calculator-test 
Fix A2A message context_id access when message is a dict
 2026-03-04 11:33:53 -03:00
Julio Quinteros Pro
f0c80d2a86
Merge pull request #22778 from BerriAI/fix/azure-test-exclude-aresponses-websocket 
Exclude aresponses_websocket from Azure SDK client init test
 2026-03-04 11:33:23 -03:00
Julio Quinteros Pro
570e8861bd
Merge pull request #22777 from BerriAI/fix/mcp-streaming-test-and-iterator 
Fix flaky MCP streaming test and iterator silent failure
 2026-03-04 11:33:11 -03:00
Julio Quinteros Pro
8495e05221 Guard tenacity import in e2e Azure batch tests 
tenacity is not in pyproject.toml dependencies, causing ImportError
during test collection. Use pytest.importorskip to gracefully skip
when tenacity is not available.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-04 11:32:20 -03:00
Julio Quinteros Pro
c0ac788709 Fix responses ID security test for new request_cache parameter 
The _encrypt_response_id method now receives request_cache=None as a
keyword argument from async_post_call_success_hook. Updated the mock
assertion to expect this parameter.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-04 11:29:51 -03:00
Julio Quinteros Pro
d8d3375a3c Add missing migration for LiteLLM_ToolTable policy changes 
PR #22732 changed the ToolTable schema (renamed call_policy to
input_policy, added output_policy/user_agent/last_used_at columns,
updated indexes) but didn't include a migration for these changes.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-04 11:27:51 -03:00
Julio Quinteros Pro
1ec6502f88 Fix tool management tests using wrong field name call_policy 
Tests used call_policy throughout but the actual API model uses
input_policy and output_policy. Updated _make_tool_row helper,
list filter query param, and policy update request/response assertions.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-04 11:20:17 -03:00
Julio Quinteros Pro
d6949e5323 Fix A2A message context_id access when message is a dict 
The asend_message function accessed request.params.message.context_id
using attribute syntax, but message can be either a dict or an object.
Handle both cases using isinstance check, matching the existing pattern
in litellm/a2a_protocol/utils.py.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-04 11:16:48 -03:00
Julio Quinteros Pro
d22996ee87 Exclude aresponses_websocket from Azure SDK client init test 
The aresponses_websocket CallType was recently added but not included
in the test exclusion list. It uses WebSocket passthrough (not Azure SDK
client initialization), so it correctly doesn't call
initialize_azure_sdk_client.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-04 11:13:57 -03:00
Julio Quinteros Pro
e8301829cd Fix flaky MCP streaming test by properly mocking inner aresponses call 
The test_streaming_mcp_events_validation test was flaky because:
1. It didn't mock the nested aresponses() call inside the iterator's
   _create_initial_response_iterator(), causing real API calls that fail
   without credentials
2. The iterator silently swallowed exceptions and set phase="finished",
   discarding pre-generated MCP discovery events
3. The _execute_tool_calls mock had wrong signature (missing tool_server_map)

Production fix: MCPEnhancedStreamingIterator no longer sets phase="finished"
on LLM call failure — it falls through to emit MCP discovery events first.

Test fix: Added mock for litellm.responses.main.aresponses returning a fake
async streaming iterator, fixed mock signatures, removed try/except that
masked failures.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-04 11:09:24 -03:00
Sameer Kankute
51552eafe7
Merge pull request #22751 from BerriAI/litellm_fix_mcp_edit_tools 
Fix MCP server URL and tools management
 2026-03-04 18:30:28 +05:30
Sameer Kankute
db0d5588fa
Merge pull request #22740 from BerriAI/litellm_fix_file_wild_card 
Add support for wildcards models for files api
 2026-03-04 18:30:00 +05:30
Sameer Kankute
ece7fdb213
Merge pull request #22744 from BerriAI/litellm_mcp_streaming_fix 
Add mcp streaming events Fix and consistent response ID
 2026-03-04 18:29:48 +05:30
Sameer Kankute
b5183e9f3b
Merge pull request #22752 from BerriAI/litellm_search_api_add 
[Feat] Add Google Search API Integration
 2026-03-04 18:29:10 +05:30
Sameer Kankute
213bf11ede
Merge pull request #22763 from BerriAI/litellm_test_e2e_batches_test 
feat(tests): add proxy e2e azure batches test
 2026-03-04 18:28:52 +05:30
Sameer Kankute
8764e5da8c
Merge pull request #22559 from BerriAI/litellm_responses_websocket 
[Feat] Add support for Responses Websocket
 2026-03-04 17:57:34 +05:30
github-actions[bot]
09ee2d54b8
chore: regenerate poetry.lock to match pyproject.toml (#22769) 
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
 2026-03-04 12:24:44 +00:00
Sameer Kankute
a6b5197ddc
Merge pull request #22689 from BerriAI/litellm_oss_staging_03_03_2026 
Litellm oss staging 03 03 2026
 2026-03-04 17:53:57 +05:30
Sameer Kankute
95c6a7e183
Merge pull request #22768 from BerriAI/revert-21491-fix/20998-remove-hardcoded-reasoning-summary 
Revert "fix(anthropic): remove hardcoded reasoning summary in adapter"
 2026-03-04 17:53:02 +05:30
Sameer Kankute
4e229b7b21
Revert "fix(anthropic): remove hardcoded reasoning summary in adapter" 2026-03-04 17:52:49 +05:30
Sameer Kankute
7d790b39be
Merge pull request #22765 from BerriAI/main 
merge main for 030326
 2026-03-04 17:40:42 +05:30
Sameer Kankute
d14420b8f2 Add tenacity in dependencies 2026-03-04 17:28:22 +05:30
Sameer Kankute
ef7aa6c8ad Add this test in cicd 2026-03-04 17:24:48 +05:30
Sameer Kankute
7b6a972fed Add this test in cicd 2026-03-04 17:21:00 +05:30
Sameer Kankute
49738bb3e3 ci: add proxy e2e azure batches workflow 
- Run test_e2e_managed_batch with -vv -s for terminal output on failure
- PostgreSQL, Poetry, Prisma setup
- Upload logs as artifact on failure

Made-with: Cursor
 2026-03-04 17:15:33 +05:30
Sameer Kankute
812e455cbc feat(tests): add proxy e2e azure batches test cases 
- test_proxy_e2e_azure_batches: e2e managed batch test with delete retry for batch_processed
- test_fixtures_smoke: smoke test for fixtures
- validate_e2e_setup: setup validation script

Made-with: Cursor
 2026-03-04 17:15:30 +05:30
Sameer Kankute
52693a65ed feat(tests): add proxy e2e azure batches test infrastructure 
- conftest: mock server + proxy server fixtures, log capture, health check fix
- base_integration_test: fix key_alias format (replace @ and . for API validation)
- test_managed_files_base: S3 callback wait with early exit, delete retry logic

Made-with: Cursor
 2026-03-04 17:15:24 +05:30
Sameer Kankute
e3a93b9597 feat(tests): add proxy e2e azure batches test fixtures 
- Mock Azure Batch server (FastAPI) with batch, file, chat, embeddings, S3 callback routes
- Config for mock models and batch polling
- Fix mock_responses: use 'model' instead of undefined 'request_model'

Made-with: Cursor
 2026-03-04 17:15:15 +05:30
Harshit Jain
41b149ee93
Merge pull request #22678 from Harshit28j/litellm_custom_auth_opt_in 
fix(proxy): make common_checks opt-in for custom auth
 2026-03-04 14:53:44 +05:30
Harshit28j
a6b57f9301 doc: fix typo 2026-03-04 14:52:27 +05:30
Sameer Kankute
43db8f1f1e Add doc and tests for google search api 2026-03-04 13:55:43 +05:30
Sameer Kankute
0275e23601 Add routing for google search 2026-03-04 13:54:43 +05:30
Sameer Kankute
65eba6b70e Add search api config 2026-03-04 13:54:25 +05:30
Sameer Kankute
0983e4f2a0 Fix MCP server URL and tools management 2026-03-04 13:34:05 +05:30
yuneng-jiang
d0e30842e5
Merge pull request #21958 from atapia27/feat/virtual-keys-team-table 
virtual-keys-team-table
 2026-03-03 23:01:34 -08:00
Sameer Kankute
9907c635ef Fix: Removed the process-level _encrypted_response_id_cache from __init__ 2026-03-04 12:30:49 +05:30
yuneng-jiang
e331d86f26
Merge pull request #22316 from atapia27/reusable-credential-change 
reusable-credentials
 2026-03-03 22:59:54 -08:00
Sameer Kankute
f878923d26 Add test for correct streaming chunks and responses id consistency 2026-03-04 12:19:54 +05:30
Sameer Kankute
e0880c3dee Fix order of streaming for mcp responses 2026-03-04 12:11:16 +05:30
yuneng-jiang
2f192e8d97
Merge pull request #22739 from BerriAI/litellm_ui_build_fix_march3 
[Fix] UI - Tool Policies: Add missing ToolRow properties
 2026-03-03 22:19:17 -08:00
Sameer Kankute
dc2d465c7e Add support for wildcards models for files api 2026-03-04 11:48:42 +05:30
yuneng-jiang
baca1937aa fixing build 2026-03-03 22:15:56 -08:00
Peter Dave Hello
007bea10b8
Add Support for OpenAI's Chat-GPT 5.3 Chat model (#22693) 
Reference:
- https://openai.com/index/gpt-5-3-instant/
- https://developers.openai.com/api/docs/models/gpt-5.3-chat-latest
 2026-03-03 20:27:05 -08:00
Ishaan Jaff
7befe3c78f
feat(proxy): add key_alias, key_hash, requested_model DD APM span tags (#22710) 
* feat(proxy): add key_alias, key_hash, requested_model tags to DD APM spans

* refactor(proxy): consolidate DD APM tag helpers into DDSpanTagger class

* refactor(proxy): move DDSpanTagger to its own file litellm/proxy/dd_span_tagger.py
 2026-03-03 20:22:59 -08:00
Ishaan Jaff
1f412bc6d8
[Feat] Add Tool Policies for AI Gateway (#22732) 
* fix: fix ui render

* fix: fix minor bugs

* refactor: use prisma functions instead of raw sql (safer)

* fix(add-new-tiles-to-tool-policies): allow developer to see what's available

* feat: ensure tool allowlist runs correctly for tool names + mcp's

* refactor: more ui improvements

* feat: working key tool blocking

* feat(tools): show tool logs

* refactor: backend code improvements

* refactor: improve log viewer for tools

* fix: address PR review feedback for tool access control

- Add missing blocked_tools column to root schema.prisma (schema drift)
- Invalidate ToolPolicyRegistry after policy mutations so changes take effect immediately
- Remove dead code: unused get_effective_policies, get_tool_policies_cached, and helpers

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: race condition in permission resolution and remove duplicate allowlist check

- Use atomic update_many with object_permission_id=None to prevent concurrent
  requests from creating orphaned permission rows and losing tool blocks
- Remove duplicate allowed_tools enforcement from guardrail (already enforced
  in auth layer via check_tools_allowlist)
- Move inline uuid import to module level

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* update to account for  userAgent

* UI - Add ToolDetails

* input/output policy

* LiteLLM_PolicyAttachmentTable

* LiteLLM_PolicyAttachmentTable

* fix: add _enqueue_tool_registry_upsert

* fix: tool mgmt endpoints

* tool mgmt endpoints

* Update tests/test_litellm/proxy/db/test_tool_registry_writer.py

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* Update tests/test_litellm/proxy/db/test_tool_registry_writer.py

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* Update tests/test_litellm/proxy/db/test_tool_registry_writer.py

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* fix: sync root schema.prisma and fix test_tool_registry_writer for input/output policy

- Migrate root schema.prisma LiteLLM_ToolTable from call_policy to
  input_policy/output_policy, add missing user_agent and last_used_at columns
  (now consistent with litellm/proxy/schema.prisma and litellm-proxy-extras)
- Fix SpendLogToolIndex comment across all three schema files
- Fix all call_policy references in test_tool_registry_writer.py:
  swapped update_tool_policy arguments, wrong get_tools_by_names return type
  assertions, _mock_tool_row setting call_policy instead of input_policy

Addresses Greptile review feedback on PR #22732.

Made-with: Cursor

---------

Co-authored-by: Krrish Dholakia <krrishdholakia@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
 2026-03-03 20:22:20 -08:00