scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-05 02:41:56 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 49
53270 commits 3118 branches 1436 tags 4.4 GiB
Commit graph

53270 commits

This branch
This branch
All branches
Author SHA1 Message Date
ryan
28f70c75d1 fix(auth): reject unchanged password on /user/password/change 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 22:02:05 +00:00
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
Yujong Lee
847f732f5d fix(cache): await valkey semantic embeddings inline on the caller loop 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 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
Yuneng Jiang
1cc38f05f4
test(proxy): type the router settings source test parameters 2026-09-21 15:00:24 -07:00
Yujong Lee
58ffa8e4ce refactor(rust): drop variable rebinding in s3 cache and bridge config 
Also adds the startup_nodes parameter to the _CacheTestHandle.redis stub to match the merged runtime signature

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 22:00:09 +00:00
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
ryan
7c8aed072f chore: merge main into litellm_cherry_pick_password_breach_reset 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:54:35 +00:00
Yujong Lee
220b981ab4 test(rust): deduplicate the merged os import 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:53:18 +00:00
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
cf7234c6f4 chore(rust): refresh workspace lockfile 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:48:40 +00:00
Yujong Lee
c3c8c35cb2 Merge origin/main into litellm_valkey_semantic_native_cache 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:48:32 +00:00
Yujong Lee
b0c1b86382 refactor(cache-qdrant-semantic): reuse qdrant-client serde payload conversion in tests 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:48:27 +00:00
Yujong Lee
a4fda8f0d8 refactor(cache-qdrant-semantic): reuse immutable indexing params 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:48:24 +00:00
Yujong Lee
e0e4850ec1 merge(main): integrate upstream secret manager changes 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:48:18 +00:00
mateo-berri
073260ce5b test(e2e): retry the hang-up when the model answers inside the window 2026-09-21 14:48:04 -07:00
Yujong Lee
b71e64446c fix(cache-qdrant-semantic): annotate indexing wait payloads 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:47:56 +00:00
Yujong Lee
6a06f69972 fix(python-bridge): restore Qdrant dispatch after rebase 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:47:56 +00:00
Yujong Lee
ff2ca804b5 fix(python-bridge): preserve Qdrant facade dispatch after rebase 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:47:56 +00:00
Yujong Lee
acbec828db fix(python-bridge): fall back to Python when qdrant_api_key changes after binding 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:47:56 +00:00
Yujong Lee
632c95f87e fix(python-bridge): make the Qdrant config tests tolerate an unset OPENAI_API_KEY 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:47:56 +00:00
Yujong Lee
877d5da419 fix(cache-qdrant-semantic): wait for Qdrant upserts to be indexed 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:47:56 +00:00
Yujong Lee
fbaa535657 fix(python-bridge): ignore class data defaults in the facade guard 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:47:56 +00:00
Yujong Lee
93e9836524 feat(python-bridge): serve QdrantSemanticCache natively 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:47:56 +00:00
Yujong Lee
8d41336a1e test(cache-qdrant-semantic): cover backend contract against an in-process Qdrant 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:47:56 +00:00
Yujong Lee
80c0ceb5e6 feat(cache-qdrant-semantic): add native Qdrant semantic cache backend 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:47:56 +00:00
Yujong Lee
fc3844e991 refactor(cache-response): generalize ResponseCache over the backend context 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:47:56 +00:00
Yujong Lee
0c72a94a84 feat(cache): add SemanticCacheContext and semantic error variants 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:47:56 +00:00
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
1509afe77e Merge remote-tracking branch 'origin/main' into litellm_gcs_native_cache 2026-09-21 21:47:29 +00:00
Yujong Lee
9f4448f42f chore(rust): merge main into litellm_gcs_native_cache 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:47:29 +00:00
Yujong Lee
95c1ba5e1d Merge remote-tracking branch 'origin/main' into litellm_native_redis_semantic_cache 2026-09-21 21:47:22 +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
Yujong Lee
f24244a1a4 Merge remote-tracking branch 'origin/main' into litellm_native_redis_semantic_cache 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

# Conflicts:
#	litellm-rust/crates/cache-redis/src/cache.rs
#	litellm-rust/crates/cache-redis/src/cache/operations.rs
#	litellm-rust/crates/python-bridge/src/cache/config.rs
#	litellm-rust/crates/python-bridge/src/cache/facade.rs
#	litellm-rust/crates/python-bridge/src/cache/handle.rs
#	litellm-rust/crates/python-bridge/src/cache/native.rs
#	tests/test_litellm_rust/test_cache.py
 2026-09-21 21:47:12 +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
Yujong Lee
3ebbb2af5b Merge remote-tracking branch 'origin/main' into litellm_rust_cache_s3 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

# Conflicts:
#	litellm-rust/Cargo.lock
#	litellm-rust/crates/python-bridge/src/cache/config.rs
#	litellm-rust/crates/python-bridge/src/cache/facade.rs
#	litellm-rust/crates/python-bridge/src/cache/handle.rs
#	tests/test_litellm_rust/test_cache.py
 2026-09-21 21:46:22 +00:00
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