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
52407 commits 2663 branches 1420 tags 3.4 GiB
Commit graph

52407 commits

This branch
This branch
All branches
Author SHA1 Message Date
yucheng
dfc5ef70b4 test(e2e): retry a leaked video job until the guardrail sync deadline 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 22:47:14 +00:00
yucheng
a44befa8c5 test: skip avideo_generation in azure sdk client exhaustive check 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 22:47:14 +00:00
yucheng
8ffca3bd19 chore(ui): regenerate api types for video call types 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 22:47:14 +00:00
yucheng
9ae2fe2ea4 fix(guardrails): scan video prompts for key-attached guardrails on /v1/videos 
/v1/videos dispatches call_type avideo_generation, which CallTypes did not
know and no guardrail translation handler covered, so the unified guardrail
hook returned the request unscanned. Add the video call types and an OpenAI
video guardrail translation package that scans the prompt for create, remix,
edit and extension requests

Resolves LIT-6685

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 22:47:14 +00:00
yujonglee
403b4be40e
Merge pull request #42311 from BerriAI/litellm_native_disk_cache 2026-09-21 15:43:58 -07:00
ryan-crabbe-berri
a776d0d722
Merge pull request #41561 from chopratejas/fix-responses-guardrail-custom-tool-output-writeback 
fix(responses): patch custom_tool_call_output in place on guardrail write-back
 2026-09-21 15:40:34 -07:00
kerry-berri
5c2c1766a4
Merge pull request #42349 from BerriAI/litellm-providers/price-sync-openrouter 
chore(prices): sync OpenRouter prices: 3 models
 2026-09-21 15:40:29 -07:00
yuneng-jiang
17f9f5c3e6
Merge pull request #42339 from BerriAI/litellm_stale_test_fix_budget_status_and_bad_db_url 
test: fix stale budget-status and bad-database-url assertions
 2026-09-21 15:38:55 -07:00
joshua-berri
3353c57e76
Merge pull request #42292 from BerriAI/litellm_extract_mcp_operation_context_7741 
refactor(mcp): extract explicit operation context and dispatch
 2026-09-21 22:38:07 +00:00
berriai-litellm-provider-info-sync[bot]
cf7988a2df
chore(prices): sync OpenRouter prices: 3 models 
openrouter/~z-ai/glm-flash-latest: max_tokens, max_output_tokens, input_cost_per_token, output_cost_per_token, cache_read_input_token_cost
openrouter/deepseek/deepseek-v4-pro: input_cost_per_token, output_cost_per_token, cache_read_input_token_cost
openrouter/z-ai/glm-5.3-flash: max_tokens, max_output_tokens, input_cost_per_token, output_cost_per_token, cache_read_input_token_cost
 2026-09-21 22:31:01 +00:00
Yujong Lee
2a3ae253d4 refactor(rust): fold disk arms into shared match patterns 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 22:14:22 +00:00
Mateo Wang
3d26a29a1a
Merge pull request #42283 from BerriAI/litellm_mid_stream_fallback_walks_full_list 
fix(router): walk every entry of a fallback list after a mid-stream failure
 2026-09-21 15:14:04 -07:00
Mateo Wang
7ae61b62ed
Merge pull request #42323 from BerriAI/litellm_stream_usage_keep_explicit_zero 
fix(streaming): keep an explicit provider prompt_tokens=0 or completion_tokens=0 in streamed usage
 2026-09-21 15:13:21 -07:00
Yujong Lee
f7b96c9ced Merge origin/main into litellm_native_disk_cache 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 22:13:09 +00:00
ryan-crabbe-berri
f200d68309
Merge pull request #41560 from chopratejas/fix-responses-agentic-followup-duplicate-kwargs 
fix(responses): stop agentic follow-up from passing request params twice
 2026-09-21 15:12:18 -07:00
Mateo Wang
055b7314e0
Merge pull request #40121 from Atharva-Kanherkar/fix/mcp-responses-stream-single-lifecycle 
fix(responses): stream one lifecycle across MCP auto-execute rounds
 2026-09-21 15:11:57 -07:00
Mateo Wang
e7bff277a6
Merge pull request #40251 from BerriAI/litellm_decrease_anys_opus5_r5 
refactor(types): remove 1,173 Any errors across 169 backend files
 2026-09-21 15:11:44 -07:00
kerry-berri
0f47056d70
Merge pull request #42337 from BerriAI/litellm-providers/price-sync-openrouter 
chore(prices): sync OpenRouter prices: 3 models
 2026-09-21 15:10:09 -07:00
kerry-berri
39fd437013
Merge pull request #42338 from BerriAI/litellm-providers/price-sync-aws-bedrock 
chore(prices): sync AWS Bedrock prices: 6 models [enrichment failed: AWS Bedrock, 4 held]
 2026-09-21 15:10:04 -07:00
Yujong Lee
1827be1302 fix(cache-disk): absolutize store directory and stamp async expiry at write time 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 22:06:55 +00:00
yujonglee
844d24b095
Merge pull request #42321 from BerriAI/litellm_native_azure_blob_cache 
feat(rust): native Azure Blob response cache backend
 2026-09-21 15:06:55 -07:00
ryan-crabbe-berri
ddb236b7e2 Merge remote-tracking branch 'origin/main' into pr-41560 
# Conflicts:
#	tests/test_litellm/llms/custom_httpx/test_llm_http_handler.py
 2026-09-21 15:04:57 -07:00
yujonglee
41adbdaa05
Merge pull request #42309 from BerriAI/litellm_rust_secrets_azure_key_vault 
feat(rust): add Azure Key Vault secret manager backend
 2026-09-21 15:04:10 -07:00
yuneng-jiang
29e9245024
Merge pull request #42294 from BerriAI/litellm_/litellm-db-migration-scope-98b60d 
test(migrations): cover the release-to-release upgrade path
 2026-09-21 15:03:55 -07:00
berriai-litellm-provider-info-sync[bot]
b305928422
chore(prices): sync AWS Bedrock prices: 6 models [enrichment failed: AWS Bedrock, 4 held] 
minimax.minimax-m2: max_tokens, supports_vision, max_input_tokens, max_output_tokens, supports_audio_input, supports_response_schema, supports_function_calling
minimax.minimax-m2.1: max_tokens, supports_vision, max_output_tokens, supports_audio_input, supports_response_schema
minimax.minimax-m2.5: max_tokens, supports_vision, max_input_tokens, max_output_tokens, supports_audio_input, supports_response_schema
moonshot.kimi-k2-thinking: max_tokens, supports_vision, max_input_tokens, max_output_tokens, supports_audio_input, supports_response_schema, supports_function_calling
openai.gpt-oss-safeguard-120b: max_tokens, supports_vision, max_output_tokens, supports_audio_input, supports_response_schema, supports_function_calling
openai.gpt-oss-safeguard-20b: max_tokens, supports_vision, max_output_tokens, supports_audio_input, supports_response_schema, supports_function_calling
 2026-09-21 22:01:14 +00:00
berriai-litellm-provider-info-sync[bot]
0eea01427d
chore(prices): sync OpenRouter prices: 3 models 
openrouter/~deepseek/deepseek-v4-flash-latest: output_cost_per_token
openrouter/deepseek/deepseek-v4-flash-0731: output_cost_per_token
openrouter/deepseek/deepseek-v4-pro: input_cost_per_token, output_cost_per_token, cache_read_input_token_cost
 2026-09-21 22:01:13 +00:00
Yuneng Jiang
5c68545104
test: fix stale budget-status and bad-database-url assertions 
Two CI checks were asserting behaviour the proxy no longer has. Neither
was catching anything; both now fail for the right reason.

budget_exceeded (tests/otel_tests/test_e2e_budgeting.py)

bf804f5188 made 422 the default for budget refusals and added
budget_exceeded_status_code to restore 429 for callers that need it. The
e2e budget tests still asserted 429, so all six have been failing on a
status change that was deliberate. Assert 422, the documented default,
rather than reading litellm.budget_exceeded_status_code back — a test
that asks the code what it does would have passed straight through this
change and through the next one.

The helpers also caught bare Exception, so a connection error reached
`e.body` and surfaced as an AttributeError instead of a failed
assertion. Narrow both to openai.APIStatusError, which is what a refusal
actually raises (UnprocessableEntityError for 422, RateLimitError for
429), and let anything else propagate as itself.

test_bad_database_url (.circleci/config.yml)

The check required "Database setup failed after multiple retries", which
only the v1 resolver emits, OR uvicorn's "Application startup failed.
Exiting.". With v2 the default, the first branch is dead and the whole
assertion rests on an incidental uvicorn line that HEAD's run did not
emit at all.

Assert the behaviour instead of the wording: the container exits
non-zero, the log names the unreachable server (P1001), it never reaches
"Application startup complete", and it is not left running. The exit
code was previously discarded by `|| true`, so the one thing the job
most needed to check was never checked.

Verified by running the bad-DATABASE_URL container: exit 3, P1001
present, no startup-complete line, container stopped — the new check
passes and the old one passed only by the uvicorn line's accident.
 2026-09-21 15:00:54 -07:00
Mateo Wang
7b8bc54237
Merge pull request #42036 from BerriAI/litellm_team_membership_lookup_fail_closed 
fix(auth): fail closed when the team membership lookup hits a db outage
 2026-09-21 14:58:46 -07:00
mateo-berri
e7557ada57 fix(responses): list executed MCP calls as completed mcp_call items in the final output 2026-09-21 14:56:02 -07:00
Mateo Wang
4b54897b36
Merge pull request #42315 from BerriAI/litellm_scim_delete_evict_user_cache 
fix(proxy): evict the cached user row when SCIM or /user/delete removes a user
 2026-09-21 14:51:53 -07:00
yucheng-berri
e0e5b7924a
Merge pull request #42312 from BerriAI/litellm_bedrock_batch_s3_creds_leak 
Register s3_access_key_id, s3_secret_access_key and s3_encryption_key_id as
LiteLLM-owned batch params so they are no longer forwarded to Bedrock as
additionalModelRequestFields (which 400s ordinary chat on a batch-configured
deployment), keep them on CredentialLiteLLMParams so the batch/file paths
still receive them, and redact the S3 credential key names in debug logs.

Resolves LIT-8290

Co-authored-by: yucheng <yucheng@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 14:50:54 -07:00
Mateo Wang
10d0d5acb2
Merge pull request #42314 from BerriAI/litellm_alerting_batch_keeps_distinct_alerts 
fix(alerting): deliver every distinct alert queued in one flush window
 2026-09-21 14:49:54 -07:00
mateo-berri
b0305d0a31 test(router): call both mid-stream fallback attempt functions directly 
The router coverage gate wants every router.py function reached by name from
a router test. The two per-endpoint attempt functions were only reached through
their callers, so each now has a direct test proving the per-request controls
carrier never reaches the provider call and every hop's stream comes back wrapped.
 2026-09-21 14:48:42 -07:00
Yujong Lee
63c16fe5ac Merge origin/main into litellm_native_disk_cache 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:47:35 +00:00
Yujong Lee
b926cf998a chore: merge main into litellm_rust_secrets_azure_key_vault 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:47:21 +00:00
Yujong Lee
bc641f01ae Merge remote-tracking branch 'origin/main' into litellm_native_azure_blob_cache 2026-09-21 21:47:19 +00:00
yujonglee
ebb4d230f8
Merge pull request #42300 from BerriAI/litellm_python_interop_foundation 
fix(rust): preserve Python settings semantics at the native boundary
 2026-09-21 14:46:37 -07:00
yujonglee
162e5c4338
Merge pull request #42303 from BerriAI/litellm_rust_secrets_cyberark 
feat(rust): add CyberArk Conjur secret manager backend
 2026-09-21 14:45:39 -07:00
Yujong Lee
4845beddc0 ci(rust): raise native wheel size gate to 40 MB 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:44:26 +00:00
Yujong Lee
f43f9012f1 fix(rust): handle disk cache topology 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:44:24 +00:00
Yassin Kortam
17b56cc4ca
Merge pull request #41505 from BerriAI/litellm_keep_config_models_on_empty_config_read 
fix(proxy): keep config-defined deployments when a config read returns no model_list
 2026-09-21 16:43:15 -05:00
Yujong Lee
2f54f6078d chore: merge main into litellm_native_azure_blob_cache 
Combines the Redis cluster bridge changes with the Azure Blob variant and
keeps account URL query parameters when building the container URL

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:43:08 +00:00
kerry-berri
75dc9082df
Merge pull request #42066 from BerriAI/litellm_cost_shard_batches_realtime 
test(integration): batch and realtime cost cases
 2026-09-21 14:43:01 -07:00
mateo-berri
51eaad657b fix(proxy): look the entity spend table up lazily so only the selected batcher table is touched 2026-09-21 14:42:23 -07:00
Yujong Lee
98e9e8c602 Merge origin/main into litellm_native_disk_cache 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:42:10 +00:00
kerry-berri
5e746d95dc
Merge pull request #42333 from BerriAI/litellm-providers/price-sync-openrouter 
chore(prices): sync OpenRouter prices: 1 model
 2026-09-21 14:41:07 -07:00
kerry
ebad623079 Merge remote-tracking branch 'origin/main' into litellm_cost_shard_batches_realtime 2026-09-21 21:34:05 +00:00
kerry-berri
29792c45a9
Merge pull request #42060 from BerriAI/litellm_cost_shard_proxy_behaviour 
test(integration): proxy behaviour cost cases
 2026-09-21 14:33:47 -07:00
Yujong Lee
c7c0afb1f0 ci(rust): raise the native wheel size gate to 40 MB 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:33:06 +00:00
yucheng-berri
506cecfb0b
Merge pull request #42267 from BerriAI/litellm_otel_v2_langfuse_ocr_output 
fix(otel v2): map OCR page markdown onto the generation output
 2026-09-21 14:33:02 -07:00