Commit graph

17728 commits

Author SHA1 Message Date
yassin
ce48a3fbcc test(mcp): give the new cache and tombstone patches TQ008 reasons and match the keyword eviction call
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-18 02:49:41 +00:00
yassin
e6349d00f3 Merge remote-tracking branch 'origin/main' into litellm_mcp_admin_terminate_sessions_revoke_credentials 2026-09-18 02:10:58 +00:00
yassin
fd834f6f8b fix(mcp): broadcast BYOK and OAuth credential eviction to peer workers and expire admin session tombstones
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-18 02:10:50 +00:00
yuneng-jiang
34718f0da6
Merge pull request #41723 from BerriAI/litellm_/circleci-specific-sha-0cf414
fix(proxy): forward every method on the typesafe pass-through route
2026-09-17 18:57:06 -07:00
Yuneng Jiang
471eff8421
test(logging): add azure_spillover to the GCS pub/sub spend-log golden
#41569 made SpendLogsMetadata always carry azure_spillover, null unless
Azure reported a spillover, and updated the unit tests that run on the PR
gate. The GCS pub/sub golden only runs on CircleCI's logging lane, so it
kept the old key set and test_async_gcs_pub_sub_v1 has failed on every
run since that merge with an extra metadata.azure_spillover key
2026-09-17 18:33:42 -07:00
Yuneng Jiang
349e8b9358
test(proxy): forward each method through the typesafe route to a mocked upstream
The route test only resolved route names. It now sends every method through
the proxy with a virtual key and asserts the upstream receives that method,
the proxy's TypeSafe key and the caller's body
2026-09-17 18:19:42 -07:00
Yuneng Jiang
e8c1fe884e
Merge remote-tracking branch 'origin/main' into litellm_/circleci-specific-sha-0cf414 2026-09-17 18:05:39 -07:00
Yuneng Jiang
acc375a2a9
fix(proxy): forward every method on the typesafe pass-through route
#41607 registered the typesafe pass-through with a route that only accepted
GET and POST, so a PUT, DELETE or PATCH to /typesafe/... came back 405
before reaching the upstream. CircleCI's pass-through method test caught it,
but that lane does not run on the PR gate, so the mapped unit test now
covers the same invariant for typesafe

The same CircleCI run also failed test_models_by_provider because typesafe
is not a key of models_by_provider. Registering it there would satisfy the
assertion without changing behaviour: typesafe has no LlmProviders member,
so a typesafe/* deployment never loads and get_valid_models returns nothing,
and its spend is priced straight from model_cost. The test already skips
search-mode providers for that reason, so it now skips evaluation mode too
2026-09-17 18:04:58 -07:00
Mateo Wang
c25c098bc1
Merge pull request #41469 from BerriAI/litellm_bedrock_mantle_responses_drop_top_p
fix(responses): drop top_p for gpt-5 reasoning models when drop_params is set
2026-09-17 18:04:19 -07:00
Mateo Wang
3424390101
Merge pull request #41448 from BerriAI/litellm_fix_passthrough_empty_query_params_drop_url_query
fix(passthrough): keep target URL query when client sends no query params
2026-09-17 18:02:48 -07:00
yassin
ea37596b88 feat(mcp): let proxy admins force-close live MCP sessions and revoke stored user credentials
Adds an admin-only DELETE /v1/mcp/sessions that terminates stateful MCP gateway sessions on the current worker by session id prefix and/or by the LiteLLM user that opened them, tombstones the terminated ids so a client reusing one gets 404 instead of a silently recreated stateless session, and lets PROXY_ADMIN name a user_id on the BYOK and OAuth credential delete routes. Full and view-only admins can list every user's stored credential metadata for a server (never the secret). The dashboard gains Disconnect controls on the Live Connections tab and a User Credentials tab with Revoke controls, both hidden from read-only admins.

Resolves LIT-8001

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-18 01:01:26 +00:00
Mateo Wang
706f69af50
Merge pull request #41665 from BerriAI/litellm_remove_dead_vertex_v1beta1_stub
refactor(vertex_ai): remove constant-False is_using_v1beta1_features stub and its dead call sites
2026-09-17 17:56:22 -07:00
Mateo Wang
151a92a230
Merge pull request #41662 from BerriAI/litellm_remove_retired_provider_streaming_handlers
chore(streaming): remove retired ai21/maritalk/baseten/azure raw-bytes handlers and dead palm completion code
2026-09-17 17:56:15 -07:00
Mateo Wang
98b3564a5b
Merge pull request #41660 from BerriAI/litellm_remove_commented_out_proxy_tests
chore(tests): remove fully commented-out proxy test files and their CI entries
2026-09-17 17:56:02 -07:00
Mateo Wang
2e195c5f70
Merge pull request #41654 from BerriAI/litellm_remove_commented_out_test_files
test: remove 15 fully commented-out test files that collect no tests
2026-09-17 17:55:55 -07:00
Mateo Wang
9966d9d1a8
Merge pull request #41652 from BerriAI/litellm_remove_dead_langfuse_v1_path
refactor(langfuse): remove unreachable langfuse v1 logging path
2026-09-17 17:55:47 -07:00
Mateo Wang
cb14dee357
Merge pull request #41648 from BerriAI/litellm_remove_commented_streaming_tests
test(streaming): remove commented-out retired-provider streaming tests
2026-09-17 17:55:40 -07:00
Mateo Wang
a7dc6551c0
Merge pull request #41640 from BerriAI/litellm_remove_dead_provider_config_test_blocks
chore(tests): remove commented-out hf, petals and vertex ai completion blocks
2026-09-17 17:55:12 -07:00
kerry-berri
f51f01fb54
Merge pull request #41443 from BerriAI/litellm_remove_brittle_price_pinning_tests
test: delete unit-test assertions that pin cost-map prices, limits and deprecation dates
2026-09-17 17:52:42 -07:00
ryan-crabbe-berri
85fe646776
Merge pull request #41694 from BerriAI/litellm_rename_model_sync_allowlists
fix(proxy): propagate db model renames to key, team, org, project and user model allowlists
2026-09-17 17:42:06 -07:00
kerry
8504c51f6c Revert "test: keep prompt cache prediction logic tests and drop only their price pins"
This reverts commit 810df257d8.
2026-09-18 00:40:38 +00:00
Mateo Wang
2fb502a556
Merge pull request #41702 from BerriAI/litellm_bedrock_invoke_tool_search_opus48_gen5
fix(bedrock): gate Invoke tool search on the model map for Opus 4.8 and gen 5 Claude
2026-09-17 17:39:34 -07:00
kerry
810df257d8 test: keep prompt cache prediction logic tests and drop only their price pins
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-18 00:39:34 +00:00
ryan-crabbe-berri
03ba5634a2
Merge pull request #40632 from BerriAI/litellm_fix_ui_disable_cache_control_injection_points
fix(ui): persist disabling cache control injection points on model update
2026-09-17 17:35:07 -07:00
kerry-berri
2842a2fb05
Merge pull request #41678 from BerriAI/litellm_auto-merge-drop-bot-gates
ci(auto-merge): stop requiring Greptile and Bugbot on price sync pull requests
2026-09-17 17:32:35 -07:00
kerry
b97c2d6307 test: drop pinned bedrock invoke cost literals
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-18 00:31:11 +00:00
Mateo Wang
cf42b607c3
Merge pull request #41615 from BerriAI/litellm_jev_complexity_classifier
feat(router): add TypeSafe Jev as a complexity router classifier
2026-09-17 17:31:08 -07:00
kerry
84d4d17bf8 Merge remote-tracking branch 'origin/main' into litellm_remove_brittle_price_pinning_tests
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

# Conflicts:
#	tests/test_litellm/llms/bedrock/chat/test_converse_transformation.py
2026-09-18 00:29:52 +00:00
kerry
c4620170ca test: delete assertions that pin vendor cost map facts
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-18 00:28:49 +00:00
yucheng-berri
a9bea4f64d
Merge pull request #41571 from BerriAI/litellm_policy_attachment_priority
feat(policy_engine): explicit priority for policy attachment execution order
2026-09-17 17:27:55 -07:00
mateo-berri
9ae5bde829 fix(bedrock_mantle): resolve gpt-5 sampling rules from the OpenAI catalogue entry 2026-09-17 17:25:59 -07:00
kerry
5d5f191a9c Merge remote-tracking branch 'origin/main' into litellm_auto-merge-drop-bot-gates 2026-09-18 00:20:29 +00:00
ryan
696587c4ab fix(ui): persist disabling cache control injection points on model update
Turning Cache Control off on the model edit screen omitted the field from the
PATCH body, which the backend reads as leave unchanged, so the stored
cache_control_injection_points list survived the save. The dashboard now sends
an explicit null when a stored list is being disabled, and update_db_model
clears that field on null the same way it already clears the mirrored pricing
fields. Omitted keys keep the stored value

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-18 00:20:22 +00:00
mateo-berri
853fd04bd5 test(router): price the unpriced Jev cost test off a model the registry never ships 2026-09-17 17:18:03 -07:00
Mateo Wang
02a20fe264
Merge pull request #41699 from BerriAI/litellm_fireworks_minimax_m3_supports_vision
fix(fireworks_ai): restore supports_vision on minimax-m3 in the cost map
2026-09-17 17:15:56 -07:00
kerry
68f2c64114 test: drop the cost map mutation gate script, its tests and the price relationship invariants
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-18 00:13:48 +00:00
yucheng-berri
e99902c4dd
Merge pull request #41569 from BerriAI/litellm_azure_ptu_spillover_cost
fix(cost): price Azure PTU spillover requests at standard token rates
2026-09-17 17:09:40 -07:00
yucheng-berri
4c70cb4815
Merge pull request #41578 from BerriAI/litellm_grafana_all_prometheus_metrics_dashboard
feat(grafana): add all-metrics dashboard and fix stale dashboard_v2 gauges
2026-09-17 16:57:32 -07:00
kerry-berri
9e651c8fe3
Merge pull request #41536 from BerriAI/litellm_aws_govcloud_partition_gate
test(e2e): cover bedrock batch file upload and create in the us-gov-west-1 partition
2026-09-17 16:55:53 -07:00
mateo-berri
064e49810a fix(bedrock): keep the tool search rule off azure_ai and pin dotted ids and Vertex fills 2026-09-17 16:48:15 -07:00
ryan
1d50d1ad3b fix(proxy): rewrite every model allowlist in one statement on rename
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 23:40:59 +00:00
mateo-berri
99b83a2d52 fix(fireworks_ai): restore supports_vision on minimax-m3 in the cost map 2026-09-17 16:39:31 -07:00
mateo-berri
42f2978061 Merge remote-tracking branch 'origin/main' into HEAD 2026-09-17 16:38:54 -07:00
mateo-berri
1e7e5b695f fix(router): reject a blank Jev api_key so it cannot pair with a caller-chosen api_base 2026-09-17 16:38:54 -07:00
Mateo Wang
deb9d8aedd
Merge pull request #41607 from BerriAI/litellm_typesafe_passthrough
Some checks are pending
LiteLLM Rust / rust-test (push) Waiting to run
Unit Tests: Documentation Validation / documentation (push) Waiting to run
Unit Tests: Proxy DB Operations / assert-shard-coverage (push) Waiting to run
Unit Tests: Proxy DB Operations / endpoints-and-responses (push) Blocked by required conditions
Unit Tests / caching-local (push) Waiting to run
Unit Tests / core-utils (push) Waiting to run
Unit Tests / enterprise-package (push) Waiting to run
Unit Tests / enterprise-routing (push) Waiting to run
Unit Tests / integrations (push) Waiting to run
Unit Tests: Proxy DB Operations / auth-checks (push) Blocked by required conditions
Unit Tests: Proxy DB Operations / budgets (push) Blocked by required conditions
Unit Tests: Proxy DB Operations / custom-logging (push) Blocked by required conditions
Unit Tests: Proxy DB Operations / db-and-spend (push) Blocked by required conditions
Unit Tests: Proxy DB Operations / guardrails-hooks (push) Blocked by required conditions
Unit Tests: Proxy DB Operations / jwt-and-keys (push) Blocked by required conditions
Unit Tests: Proxy DB Operations / key-generation (push) Blocked by required conditions
Unit Tests: Proxy DB Operations / logging-misc (push) Blocked by required conditions
Unit Tests: Proxy DB Operations / proxy-runtime (push) Blocked by required conditions
Unit Tests: Proxy DB Operations / proxy-server-core (push) Blocked by required conditions
Unit Tests: Proxy DB Operations / proxy-utils (push) Blocked by required conditions
Unit Tests / Vertex AI (push) Waiting to run
Unit Tests / All Other Providers (push) Waiting to run
Unit Tests / misc (push) Waiting to run
Unit Tests / proxy-auth (push) Waiting to run
Unit Tests / proxy-endpoints (push) Waiting to run
Unit Tests / proxy-extras (push) Waiting to run
Unit Tests / proxy-infra (push) Waiting to run
Unit Tests / proxy-server (push) Waiting to run
Unit Tests / responses-caching-types (push) Waiting to run
GitHub Actions Security Analysis / zizmor (push) Waiting to run
feat(proxy): add TypeSafe AI Jev evaluate passthrough with registry-priced spend tracking
2026-09-17 16:37:33 -07:00
ryan-crabbe-berri
e5aa10a1ea
Merge pull request #41686 from BerriAI/litellm_member_budget_clone_reset_and_audit
fix(team): keep a forked member budget's reset window and audit bulk member budget writes
2026-09-17 16:32:31 -07:00
ryan
de0047c802 fix(proxy): skip allowlist rewrite when the model name is unchanged
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 23:24:26 +00:00
yassin
33531649c3 perf(mcp): count gateway session groups with Counter and pin the oversized initialize peek invariant
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 23:20:47 +00:00
ryan
d3f5cde530 fix(proxy): propagate db model renames to key, team, org, project and user model allowlists
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 23:11:52 +00:00
Mateo Wang
57d41bda29
Merge pull request #41684 from BerriAI/litellm_wildcard_license_auto_router
fix(license): let a wildcard allowed_features license grant the auto_router feature
2026-09-17 16:11:40 -07:00