scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-24 00:52:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 91
52270 commits 2663 branches 1420 tags 3.4 GiB
Commit graph

1042 commits

Author SHA1 Message Date
Yujong Lee
3f11d9787d build(ci): raise native extension size limit to 30 MB for cluster support 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:06:12 +00:00
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
mateo-berri
c8e42c2ac3 ci(e2e): give string_leaves a single trailing return 2026-09-21 11:02:28 -07:00
Devin AI
0317903a44 ci(e2e-changed): surface failed test ids from the pytest log 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 07:16:02 +00:00
Devin AI
7e0fa40fe3 test(e2e): gate the Bedrock edge capture behind a provider_edge_host opt-in 
The Buildkite ephemeral stack runs the gateway in another pod, so it cannot reach the pytest host's provider edge. The GitHub changed-e2e lane runs gateways on the runner and sets E2E_PROVIDER_EDGE_HOST_REACHABLE

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 06:17:03 +00:00
Yujong Lee
82bc67b122 feat(rust): add typed secret managers and shared auth adapters 2026-09-20 16:09:20 -07:00
Yujong Lee
661da87c91 fix(rust): validate tokenizer ranks and cover backend features 2026-09-20 15:13:59 -07:00
Joshua Valluru
671b51c959 chore: merge main for MCP OAuth CI compatibility 2026-09-20 09:18:25 -07:00
Joshua Valluru
d93cc8defd test(mcp): run public client regressions in the MCP shard 2026-09-20 08:39:51 -07:00
yuneng-jiang
6ef7b86748
Merge pull request #42103 from BerriAI/litellm_test_unit_ci_wiring 
ci(tests): wire tests/unit into CircleCI and keep draining GHA shards green
 2026-09-20 00:50:00 -07:00
yuneng
adadeac245 Revert "ci(tests): temporarily point one shard at an empty directory" 
This reverts commit 3c094dbaaa.
 2026-09-20 07:10:43 +00:00
yuneng
3c094dbaaa ci(tests): temporarily point one shard at an empty directory 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-20 07:08:09 +00:00
yuneng
446bd1b250 ci(tests): wire tests/unit into CircleCI and drain legacy unit shards green 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-20 07:05:42 +00:00
Yuneng Jiang
e34fd201b3
Merge remote-tracking branch 'origin/main' into litellm_v2_migration_startup 2026-09-19 23:59:26 -07:00
mateo-berri
468f74c628 ci(e2e): fix the stage-mirror batch reds and keep a redacted pytest log 
The changed-test gate booted its stage-mirror stack without files_settings
or finetune_settings, so every raw upload with a custom_llm_provider hit a
500, and it exported the whole provider env into the gateways, so the
AWS_ROLE_NAME the assume-role test needs made the GovCloud deployment run
an AssumeRole with its static keys. The gate also deleted its pytest output,
so a red run left nothing to read. The mirror config now carries the
openai, azure, and vertex_ai file settings, gateways start without
AWS_ROLE_NAME, and the workflow uploads the pass logs and junit files with
every secret value, every field of a JSON-valued secret, and their
XML-escaped forms replaced before the raw files are removed.
 2026-09-19 22:37:07 -07:00
Mateo Wang
58065d46fd
Merge pull request #42071 from BerriAI/litellm_remove_dead_telemetry_flag 2026-09-19 21:48:02 -07:00
mateo
b2e123da43 fix(proxy): drop legacy telemetry key from persisted WORKER_CONFIG before initialize 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-20 03:14:11 +00:00
Joshua Valluru
368401e85c test(e2e): complete OAuth triggers and preserve failure diagnostics 2026-09-19 17:03:38 -07:00
Joshua Valluru
64452f76c2 test(e2e): restore LIT-3467 implementation for rework 2026-09-19 16:21:53 -07:00
Mateo Wang
af6a1798e2
Revert "test(e2e): cover MCP OAuth SSO and cold restart persistence" 2026-09-19 16:15:43 -07:00
Joshua Valluru
742a3ad93d ci(e2e): trigger OAuth acceptance on relevant pull requests 2026-09-19 13:30:36 -07:00
Joshua Valluru
b7bab56d4d test(e2e): report safe OAuth failure locations 2026-09-19 12:52:28 -07:00
Joshua Valluru
4e8a4d4b61 test(e2e): restore existing OAuth chat test to baseline 2026-09-19 12:17:51 -07:00
Devin AI
8f8c2e2fda ci(e2e): keep the Linear OAuth chat test out of the stage-mirror selector 
Co-Authored-By: bot_apk <apk@cognition.ai>
 2026-09-19 19:13:44 +00:00
Joshua Valluru
09a2e5b6ec test(e2e): adapt OAuth acceptance to merged SDK2 2026-09-19 11:59:29 -07:00
joshua-berri
eda1faba14
Merge pull request #41718 from BerriAI/litellm_mcp_dependency_gate_7737 
refactor(mcp): upgrade SDK2 while preserving legacy gateway behavior
 2026-09-19 18:53:19 +00:00
kerry
987af6c66c ci: remove auto-merge-price-sync workflow, the Devin sync automation merges price PRs 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-19 18:33:06 +00:00
Joshua Valluru
78e1103bb8 fix(ci): preserve shared runner setup time allowance 2026-09-19 10:46:38 -07:00
Joshua Valluru
8f3562ed9c ci(mcp): consolidate integration tests into shared workflow 2026-09-19 10:41:36 -07:00
Joshua Valluru
fb56a14cd4 chore(mcp): merge main with unit test timeout safeguards 2026-09-19 09:42:08 -07:00
Joshua Valluru
166a05f810 chore: merge main into MCP OAuth E2E branch 2026-09-19 09:40:42 -07:00
Joshua Valluru
2ce972b992 test(e2e): report OAuth results without raw assertion logs 2026-09-19 07:54:49 -07:00
mateo-berri
343e1eeac8 ci(unit): fail a hung test in 120s with a traceback instead of idling the shard to its step timeout 2026-09-19 02:53:36 -07:00
Devin AI
fdb0fb648e fix(e2e): bind MCP OAuth acceptance to the owned gateway and snapshot the stored token once per phase 
Co-Authored-By: bot_apk <apk@cognition.ai>
 2026-09-19 08:12:35 +00:00
Joshua Valluru
f5ab563499 fix(mcp): preserve session expiry signals and scope dependency CI 2026-09-18 22:52:10 -07:00
Joshua Valluru
aea13ee03b fix(mcp): preserve legacy behavior on SDK2 and streamline verification 2026-09-18 22:28:31 -07:00
Joshua Valluru
7f4dd4eabc test(e2e): cover MCP OAuth SSO and cold restart acceptance 2026-09-18 22:02:09 -07:00
Yuneng Jiang
62f6ee9a16
Merge remote-tracking branch 'origin/main' into litellm_v2_migration_startup 2026-09-18 20:55:05 -07:00
joshua
77cf6c2fbd ci(mcp): keep dependency-resolution matrix to resolve and import smoke 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-19 00:50:53 +00:00
ryan-crabbe-berri
a20698f802 ci(issues): comment which release carries the fix when a pull request closes an issue 2026-09-18 17:37:02 -07:00
joshua
4a7d8bbffa fix(mcp): resolve SDK2 wire-shape regressions in guardrail, arize, and benchmark paths 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-19 00:36:03 +00:00
joshua
7410d00d2e merge(main): resolve mcp server.py import conflict and relock 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-19 00:08:33 +00:00
joshua
8d8a2c3742 ci(mcp): add dependency-resolution workflow for the SDK 2 floor 
New matrix job across Python 3.10-3.14 verifies uv.lock against the
declared floors, installs the locked mcp+proxy extras and runs the MCP
unit suites, then resolves the same extras with uv's lowest-direct
strategy into a clean venv and runs scripts/check_mcp_sdk_install.py to
prove the floor still imports the SDK 2 API surface.

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-18 23:49:19 +00:00
ryan
139445179a ci: remove the dead Agent Shin triage workflows and scripts 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-18 22:59:32 +00:00
joshua
4bc3f1d0fc build(deps): migrate MCP integration to MCP SDK 2.2.0 
Replace the bespoke dependency-install CI gate with a real migration:
require mcp>=2.2.0,<3 alongside httpx2>=2.5.0,<3 and pydantic>=2.12.0,<3
in the proxy and mcp extras, drop langchain-mcp-adapters (pins mcp<2)
from the dev group, and remove the dependency-install workflow and
tests/mcp_dependency_tests that only exercised the old pins.

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-18 22:12:40 +00:00
ryan-crabbe-berri
1e8b8f7c33 ci(duplicate-check): describe the workspace-write sandbox accurately 2026-09-18 14:21:22 -07:00
ryan-crabbe-berri
1f27c442b4 ci(duplicate-check): let Codex reach GitHub from its sandbox 
Every gh search in the first real runs failed with "error connecting to
api.github.com", so the verdict was always null. The legacy
sandbox_permissions key no longer grants network in read-only mode; the
workspace-write sandbox has a network_access switch that does. Pin the CLI
to the version the prompt was proven on
 2026-09-18 14:17:00 -07:00
Mateo Wang
194e647e64
Merge pull request #41865 from BerriAI/litellm_vscode_extension 
feat(vscode): add LiteLLM language model provider extension
 2026-09-18 13:40:35 -07:00
mateo-berri
d16d17d2d2 ci(osv-scan): scan the VS Code extension lockfile 2026-09-18 13:15:17 -07:00
mateo-berri
12b7268ae9 feat(vscode): add LiteLLM language model provider extension 2026-09-18 12:29:55 -07:00