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
51644 commits 2663 branches 1420 tags 3.4 GiB
Commit graph

51644 commits

This branch
This branch
All branches
Author SHA1 Message Date
mateo-berri
92ff54f134 fix(mcp): list a never-listed server before its first tools/call 
The startup tool-name fill skips servers whose upstream wants the caller's
own token (true_passthrough, OAuth discovery), and mcp 2 no longer runs the
list handler before an uncached tools/call, so every uvicorn worker that had
not served tools/list answered 404 "Tool not found" for prefixed tools/call
and the REST server_id route on those servers.

On a resolution miss, execute_mcp_tool now lists the prefix-matched (or
server_id-requested) server once, with the caller's credentials, through the
existing tools/list path, then resolves as before. Listing failures fall
through to the existing 404, a worker that already listed the server never
re-lists it, and a server outside the caller's allowed set is never listed.
 2026-09-19 18:49:26 -07:00
yucheng-berri
82ddab2405
Merge pull request #41840 from BerriAI/litellm_team_audit_lifecycle 
fix(team): emit audit events for member_delete and role changes and carry the final roster on team create
 2026-09-19 17:37:16 -07:00
yuneng-jiang
1f28813c4d
Merge pull request #42053 from BerriAI/litellm_nova_sonic_v2_e2e_model 
test(e2e): point the Nova Sonic realtime test at nova-2-sonic
 2026-09-19 17:31:07 -07:00
yucheng-berri
2ec5c2c7cd
Merge pull request #41740 from BerriAI/litellm_otel_v2_langfuse_llm_spans_only 
feat(otel v2): opt-in llm_only span scope for Langfuse destinations and the operator Langfuse exporter
 2026-09-19 17:24:50 -07:00
Yuneng Jiang
9f84382a24
test(e2e): cite the source and date for the pinned Nova Sonic model id 
AGENTS.md allows a vendor-owned literal only when its source and date are cited
next to it. A live realtime test cannot avoid naming a model, so record how the
id was checked, and record that a retired id fails as a hang rather than an
error so the next reader does not start by suspecting litellm.
 2026-09-19 17:20:00 -07:00
kerry-berri
75f4c11444
Merge pull request #42006 from BerriAI/litellm-providers/price-sync-openrouter 
chore(prices): sync OpenRouter prices: 2 models
 2026-09-19 17:11:50 -07:00
yucheng
de70cf842a fix(team): run the role update and budget upsert in one transaction under the team lock
Some checks failed
LiteLLM Rust / rust-lint (push) Has been cancelled
Details
LiteLLM Rust / rust-test (push) Has been cancelled
Details
LiteLLM Rust / rust-wheel (push) Has been cancelled
Details
Terraform Provider / gofmt, vet, build, test (push) Has been cancelled
Details
Terraform Provider / Provider endpoints vs proxy OpenAPI schema (push) Has been cancelled
Details 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-20 00:04:32 +00:00
berriai-litellm-provider-info-sync[bot]
aa8bbdbae4
chore(prices): sync OpenRouter prices: 2 models
Some checks failed
LiteLLM Rust / rust-lint (push) Has been cancelled
Details
LiteLLM Rust / rust-test (push) Has been cancelled
Details
LiteLLM Rust / rust-wheel (push) Has been cancelled
Details
Terraform Provider / gofmt, vet, build, test (push) Has been cancelled
Details
Terraform Provider / Provider endpoints vs proxy OpenAPI schema (push) Has been cancelled
Details 
openrouter/deepseek/deepseek-v4-flash: input_cost_per_token, output_cost_per_token, cache_read_input_token_cost
openrouter/z-ai/glm-5.2: input_cost_per_token, output_cost_per_token, cache_read_input_token_cost
 2026-09-20 00:00:50 +00:00
yucheng
b7db48c7c1 fix(team): 404 a role update whose target left the roster before the locked read 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-19 23:57:38 +00:00
Yuneng Jiang
ca18755b64
test(e2e): point the Nova Sonic realtime test at nova-2-sonic 
AWS retired amazon.nova-sonic-v1:0. GetFoundationModel now answers
ResourceNotFoundException "This model version has reached the end of its life",
and opening a bidirectional stream against it fails with ValidationException
"The provided model identifier is invalid". amazon.nova-2-sonic-v1:0 is the
active replacement.

The test passed on builds 219 (2026-09-16) and 246 (2026-09-17) and has failed
every run since, three attempts per build, with no litellm change to the
realtime path in between. The symptom was a clean websocket close: Bedrock ends
the stream rather than erroring, the forwarder treats a None receive as a normal
stream end and closes the client socket, so the client sees ConnectionClosedOK
and the test fails waiting for response.done.

litellm already carries both models in the cost map, with
"deprecation_date": "2026-09-14" on the old one, and the promptStart
transformation already sends the audioOutputConfiguration that nova-2-sonic
requires; only the test constant was left behind.

Verified against live Bedrock with the promptStart shape the transformation
builds: amazon.nova-sonic-v1:0 raises "The provided model identifier is
invalid", amazon.nova-2-sonic-v1:0 opens a session and returns a usageEvent.

The mocked handler and provider-cache tests keep the old id: it is only a label
there, no call reaches AWS.
 2026-09-19 16:55:00 -07:00
yucheng
f6e5ef0d26 refactor(otel v2): drop the docstring from conflicting_span_scope_error 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-19 23:48:52 +00:00
kerry-berri
1fcef68ab7
Merge pull request #42048 from BerriAI/litellm_fix_circleci_cost_and_bedrock_beta
Some checks failed
Unit Tests: Proxy DB Operations / auth-checks (push) Blocked by required conditions
Details
Unit Tests: Proxy DB Operations / budgets (push) Blocked by required conditions
Details
Unit Tests: Proxy DB Operations / custom-logging (push) Blocked by required conditions
Details
Unit Tests: Proxy DB Operations / db-and-spend (push) Blocked by required conditions
Details
Unit Tests: Proxy DB Operations / endpoints-and-responses (push) Blocked by required conditions
Details
Unit Tests: Proxy DB Operations / proxy-server-core (push) Blocked by required conditions
Details
Unit Tests: Proxy DB Operations / guardrails-hooks (push) Blocked by required conditions
Details
Unit Tests: Proxy DB Operations / jwt-and-keys (push) Blocked by required conditions
Details
Unit Tests: Proxy DB Operations / key-generation (push) Blocked by required conditions
Details
Unit Tests: Proxy DB Operations / logging-misc (push) Blocked by required conditions
Details
Unit Tests: Proxy DB Operations / proxy-runtime (push) Blocked by required conditions
Details
Unit Tests: Proxy DB Operations / proxy-utils (push) Blocked by required conditions
Details
Unit Tests / caching-local (push) Waiting to run
Details
Unit Tests / core-utils (push) Waiting to run
Details
Unit Tests / enterprise-package (push) Waiting to run
Details
Unit Tests / enterprise-routing (push) Waiting to run
Details
Unit Tests / integrations (push) Waiting to run
Details
Unit Tests / All Other Providers (push) Waiting to run
Details
Unit Tests / Vertex AI (push) Waiting to run
Details
Unit Tests / mcp-integration (push) Waiting to run
Details
Unit Tests / misc (push) Waiting to run
Details
Unit Tests / proxy-auth (push) Waiting to run
Details
Unit Tests / proxy-endpoints (push) Waiting to run
Details
Unit Tests / proxy-extras (push) Waiting to run
Details
Unit Tests / proxy-infra (push) Waiting to run
Details
Unit Tests / proxy-server (push) Waiting to run
Details
Unit Tests / responses-caching-types (push) Waiting to run
Details
GitHub Actions Security Analysis / zizmor (push) Waiting to run
Details
Terraform Provider / gofmt, vet, build, test (push) Has been cancelled
Details
Terraform Provider / Provider endpoints vs proxy OpenAPI schema (push) Has been cancelled
Details 
fix(test): unbreak the integration-cost and proxy_e2e_anthropic_messages CircleCI jobs on main
 2026-09-19 16:45:31 -07:00
yuneng-jiang
3df159308d
Merge pull request #42042 from BerriAI/litellm_websearch_activation_status 
feat(ui): report whether the serving proxy has applied web search interception
 2026-09-19 16:42:05 -07:00
kerry
7966f50c34 fix(test): run the all-beta-headers bedrock cases on Claude Fable 5.1 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-19 23:33:29 +00:00
kerry
02736e20cc fix(test): repin fireworks fallback cache-read case to the 50% default 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-19 23:33:29 +00:00
joshua-berri
f49fd22875
Merge pull request #42033 from BerriAI/litellm_mcp_redirect_regressions_7738 
test(mcp): cover SDK redirect compatibility
 2026-09-19 23:31:33 +00:00
joshua-berri
841193aab2
Merge pull request #42040 from BerriAI/revert-41909-litellm_mcp_oauth_happy_path_e2e 
Revert "test(e2e): cover MCP OAuth SSO and cold restart persistence"
 2026-09-19 23:25:20 +00:00
joshua-berri
93ebc1e281
Merge pull request #42039 from BerriAI/revert-41731-litellm_mcp_integration_regressions_4506 
Revert "test(mcp): verify scoped execution and OAuth credential isolation"
 2026-09-19 23:24:00 +00:00
yujonglee
271fe58ff0
Merge pull request #42037 from BerriAI/litellm_callbacks_legacy_python 
refactor(rust): rename legacy callback adapter crate
 2026-09-19 16:21:28 -07:00
tin-berri
252a0f1eac
Merge pull request #41617 from BerriAI/litellm_fuse_model_profile_presets 
feat(router): add maintained Fuse model and harness presets
 2026-09-19 16:17:19 -07:00
yucheng
431ddbdd22 test(team): exercise the member-add audit helper directly and drop its dead user_id None guard 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-19 23:17:18 +00:00
tin-berri
cc2c0d0f66
Merge pull request #42001 from BerriAI/litellm_heuristic_v2_scores 
fix(auto-router): show heuristic v2 score estimates in routing details
 2026-09-19 16:16:59 -07:00
yucheng
f63782f678 fix(otel v2): reject a langfuse_span_scope that conflicts with another callback entry on the same team or key 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-19 23:16:54 +00:00
tin-berri
1944d40097
Merge pull request #41177 from BerriAI/litellm_autorouter_baseline_cache 
fix(proxy): estimate auto-router baseline costs from durable cache history
 2026-09-19 16:16:29 -07:00
Yuneng Jiang
dd6a3558d5
Merge remote-tracking branch 'origin/main' into litellm_websearch_activation_status 2026-09-19 16:16:25 -07:00
Yuneng Jiang
c0bc45224c
feat(ui): report whether the serving proxy has applied the interception setting 
The stored flag is the cluster's desired state and is what the form saves, so it
cannot also stand as proof that this process activated the callback: a pod that
lagged or failed to apply it would still read as on. Report the process's own
registration as a separate read-only field and warn on the page when the two
disagree, so a failed activation is visible instead of only logged.
 2026-09-19 16:16:17 -07:00
Mateo Wang
af6a1798e2
Revert "test(e2e): cover MCP OAuth SSO and cold restart persistence" 2026-09-19 16:15:43 -07:00
Mateo Wang
57c757e9d7
Revert "test(mcp): verify scoped execution and OAuth credential isolation" 2026-09-19 16:10:47 -07:00
Mateo Wang
0058e1554b
Merge pull request #41909 from BerriAI/litellm_mcp_oauth_happy_path_e2e 
test(e2e): cover MCP OAuth SSO and cold restart persistence
 2026-09-19 16:08:51 -07:00
Yujong Lee
ad8ac449fc style(rust): format renamed callback adapter 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-19 23:08:37 +00:00
Yujong Lee
df84fef96e refactor(rust): rename legacy callback adapter crate 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-19 23:06:26 +00:00
Mateo Wang
43c0a267d5
Merge pull request #41731 from BerriAI/litellm_mcp_integration_regressions_4506 
test(mcp): verify scoped execution and OAuth credential isolation
 2026-09-19 16:05:56 -07:00
Mateo Wang
56408b3915
Merge pull request #42031 from BerriAI/litellm_internal_copy_41781 
fix(azure): drop tool_choice when the request has no tools (internal copy of #41781)
 2026-09-19 16:03:32 -07:00
Joshua Valluru
7cd96e9c2d test(mcp): assert redirect rejection without SDK wording 2026-09-19 16:01:42 -07:00
yuneng-jiang
5fc5afd595
Merge pull request #42007 from BerriAI/litellm_/web-search-autoship-scope-01a237 
feat(ui): configure web search interception from the Admin UI
 2026-09-19 15:54:03 -07:00
Joshua Valluru
064b7d10df docs(mcp): clarify method-preserving redirect scope 2026-09-19 15:52:07 -07:00
Joshua Valluru
3fdc13ccef test(mcp): cover SDK redirect compatibility 2026-09-19 15:51:01 -07:00
yucheng-berri
6afc807ae3
Merge pull request #42027 from BerriAI/litellm_stream_boundary_attr_forwarding 
Co-authored-by: yucheng <yucheng@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-19 15:47:54 -07:00
yucheng
cc41b80770 test(team): patch the scheduled member-add audit helper in the cache eviction test 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-19 22:46:37 +00:00
Mateo Wang
7651d6b550
Merge pull request #41942 from BerriAI/litellm_vllm_batch_runner 
feat(batches): run hosted_vllm batches inside LiteLLM
 2026-09-19 15:44:26 -07:00
Yuneng Jiang
4ea21cb75c
fix(ui): answer the interception panel from the stored flag, not the local pod 
Deriving enabled from whether this process has the callback registered makes a
pod that has not polled yet report off while the cluster runs it, and the next
save writes that off back for every pod. The stored flag is the cluster's own
answer, so prefer it and fall back to local registration only when none is
stored, which is the config-activated case that has no flag to read.
 2026-09-19 15:42:16 -07:00
yucheng
2ade97f80e Merge remote-tracking branch 'origin/main' into litellm_team_audit_lifecycle 2026-09-19 22:41:02 +00:00
yucheng
181406e05f fix(team): schedule membership audit writes after commit and lock the roster on role updates 
The member add, delete and role-change audit rows were awaited on the
request path, so a slow audit sink held the response, and the roster was
serialized before checking whether audit logging is enabled at all.
Membership audit work is now scheduled after the transaction commits and
skipped outright when auditing is off.

member_update read the roster outside the team advisory lock and wrote
it back, so a concurrent add or delete could be lost. It now takes the
lock, rereads the roster, and builds the before and after snapshots from
that read.

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-19 22:33:22 +00:00
ryan-crabbe-berri
bdbb4e4610
Merge pull request #41681 from BerriAI/litellm_org_alias_from_team 
fix(auth): inherit org alias, budget and rate limits for JWT and team-linked keys
 2026-09-19 15:25:14 -07:00
ryan-crabbe-berri
370eacce12
Merge pull request #41997 from BerriAI/litellm_project_zero_budget_blocks 
fix(proxy): block project requests when max_budget is 0
 2026-09-19 15:24:18 -07:00
yuneng-jiang
b6dbf145cb
Merge pull request #42009 from BerriAI/litellm_config_store_qa_fixes 
fix(proxy): close the config-ownership gaps QA found in the settings store
 2026-09-19 15:20:13 -07:00
Joshua Valluru
d5ac850feb test(e2e): isolate diagnostic reporter subprocess 2026-09-19 15:13:27 -07:00
Joshua Valluru
31b4405435 chore: merge main with shared E2E lockout fix 2026-09-19 15:10:55 -07:00
Joshua Valluru
5b9f3d4cdb chore: merge latest main for MCP regression verification 2026-09-19 15:04:07 -07:00
yucheng
358e4ea27a fix(otel v2): stop langfuse_span_scope tripping the family guard, normalize its spelling, and keep tenant routes on the full scope 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-19 22:00:02 +00:00