Commit graph

5458 commits

Author SHA1 Message Date
moe-berri
4450bfdf79 chore: merge latest main into gateway memory 2026-09-15 00:02:37 -07:00
Tin Chi Lo
398300c4e7 fix(router): honor team and key provider weights 2026-09-14 23:31:52 -07:00
yucheng
9acdebf563 chore: merge origin/main into litellm_lit6314_guardrail_metadata_transfer
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-15 05:03:31 +00:00
kerry-berri
03a4c806c4
Merge pull request #41157 from BerriAI/litellm_gemini_embedding_2_per_token_billing
fix(cost): bill gemini-embedding-2 per token and stop double charging audio
2026-09-14 19:49:11 -07:00
kerry
c0c5044c45 fix(batches): keep modality token details in raw vertex batch usage
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-15 01:57:50 +00:00
moe-berri
f2026051a3 fix(memory): clarify account activation status 2026-09-14 18:26:18 -07:00
moe-berri
866071af6f refactor(memory): align management routes and dashboard controls 2026-09-14 18:20:55 -07:00
moe-berri
5f61a5110b fix(memory): preserve stream errors and gateway navigation 2026-09-14 18:04:31 -07:00
yucheng-berri
8481bc27f9
Merge pull request #41132 from BerriAI/litellm_bedrock_grounding_from_plain_messages
fix(bedrock guardrails): derive contextual grounding source and query from plain messages
2026-09-14 17:56:58 -07:00
moe-berri
8b53d48e34 fix(memory): show enrolled users and verify live team recall 2026-09-14 17:30:11 -07:00
moe-berri
49d0e9da59 Merge remote-tracking branch 'origin/main' into litellm_memory_active_tools 2026-09-14 17:16:55 -07:00
moe-berri
5439a2acb7 feat(memory): simplify admin activation and reuse team record permissions 2026-09-14 17:16:23 -07:00
yucheng
0d0b96ed06 Revert "refactor(guardrails): rename scoped-out evaluation status from not_run to skipped"
This reverts commit b37ce94075.
2026-09-14 23:46:09 +00:00
yucheng
bd9a87ea76 Revert "fix(guardrails): keep legacy not_run neutral and stop labelling image-only input as skipped"
This reverts commit f78dd921c9.
2026-09-14 23:46:09 +00:00
tin-berri
c626ff098b
Merge pull request #40877 from BerriAI/litellm_lit7658_cache_cost_v0_fresh
feat(proxy): predict prompt-cache costs across deployments
2026-09-14 16:25:41 -07:00
yucheng
f78dd921c9 fix(guardrails): keep legacy not_run neutral and stop labelling image-only input as skipped
Some checks failed
ai-gateway image / ai-gateway release image (push) Has been cancelled
LiteLLM Rust / rust-lint (push) Has been cancelled
LiteLLM Rust / rust-test (push) Has been cancelled
Terraform Modules / fmt, validate, test (aws) (push) Has been cancelled
Terraform Modules / fmt, validate, test (gcp) (push) Has been cancelled
Terraform Provider / gofmt, vet, build, test (push) Has been cancelled
Terraform Provider / Provider endpoints vs proxy OpenAPI schema (push) Has been cancelled
Usage tracking, compliance and the dashboard now treat both not_run (older spend logs) and skipped as unevaluated through a shared UNEVALUATED_GUARDRAIL_STATUSES set, so old records stop counting as passed. The skipped record is no longer written when the request carried images, since images without text were never dispatched to guardrails before this change and that gap is not a message-scoping skip

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-14 22:34:33 +00:00
yucheng
b37ce94075 refactor(guardrails): rename scoped-out evaluation status from not_run to skipped
The per-guardrail status a scoped-out evaluation records is now skipped, matching the
skip_*_in_guardrail settings that cause it. Request-level rollup still maps it to not_run
so the StandardLoggingPayload status contract is unchanged

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-14 22:15:53 +00:00
ryan-crabbe-berri
7b6d223105
Merge pull request #40196 from BerriAI/litellm_team_admin_all_proxy_models
fix(ui): let team admins grant a team all proxy models
2026-09-14 15:05:01 -07:00
yucheng
442af3aab6 fix(bedrock guardrails): gate plain-message grounding behind contextual_grounding_from_messages
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-14 22:04:42 +00:00
ryan-crabbe-berri
51926c2e79
Merge pull request #41023 from BerriAI/litellm_ui_move_metadata_tags_to_tags_field
fix(ui): move tags typed into key metadata JSON into the Tags field
2026-09-14 15:03:54 -07:00
ryan
52a3b0ede7 fix(ui): trim and drop blank tags moved out of key metadata JSON
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-14 21:50:25 +00:00
ryan
df87a49f8b fix(ui): offer no models when an org team's ceiling never arrives
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-14 21:35:55 +00:00
moe-berri
57b6496a1e chore(memory): merge current gateway main 2026-09-14 13:28:03 -07:00
moe-berri
f4fc27f2e2 feat(memory): add user activation and contributor table 2026-09-14 13:23:31 -07:00
yassin
39f6ac4788 perf(proxy): serialize /model/info listing once with orjson
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-14 19:47:51 +00:00
Yassin Kortam
687cb6cb7a
Merge pull request #40992 from BerriAI/litellm_model_info_team_alias
fix(ui): show the team alias on the model info page and in its raw JSON
2026-09-14 12:40:02 -07:00
ryan
5ddb0fe691 fix(ui): keep the team model select loading until /team/info reports the org ceiling
useTeam seeds its cache from the team list, which has no organization_models, so the select briefly rendered unfiltered. Also drop the Prisma include assertion from the backend test.

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-14 19:38:05 +00:00
ryan-crabbe-berri
b6a5563d05 fix(ui): let team admins grant a team all proxy models
The team edit form only offered "All Proxy Models" when the dashboard could
read the parent organization, and /organization/info 403s for anyone who is
not a proxy admin or an admin of that org. A team admin with the internal_user
proxy role therefore saw only "No Default Models", which is the opposite of
what they wanted, and had no way to grant their team everything on the proxy.

/team/info now reports the parent org's model ceiling as organization_models,
which the same authorization already admits, and ModelSelect reads the ceiling
from the team it is editing before falling back to the organization. That also
makes the individual model list respect the org's allow-list instead of
listing every proxy model to a caller whose save would be rejected.

useTeam was typed as Team while returning the /team/info envelope, so its one
other caller unwrapped it behind a cast. It now returns the team itself.

Claude-Session: https://claude.ai/code/session_011Tn3657NkV6ojLqewL64Kb
2026-09-14 19:30:44 +00:00
yucheng
b1a006ea66 test(ui): hoist not_run guardrail fixtures out of inline call args
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-14 18:54:24 +00:00
yassin
82ef6ea6ab feat(proxy): add general_settings.allowed_file_extensions for /v1/files
Opt-in allowlist for upload filename extensions, checked before the existing blocked_file_extensions blocklist and mapped through the same upload validation failure path. None keeps today's behaviour, [] rejects every upload, matching is case-insensitive on both sides, and a filename with no extension is rejected when the allowlist is set.

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-14 18:53:29 +00:00
yucheng
e41faf54a8 fix(ui): anchor guardrail lifecycle on timed entries and show not_run skip reason
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-14 18:39:10 +00:00
yucheng
4be84a859d Merge remote-tracking branch 'origin/main' into litellm_lit6314_guardrail_metadata_transfer 2026-09-14 18:01:01 +00:00
yucheng
b4e3d7c533 chore: merge main into litellm_lit6314_guardrail_metadata_transfer
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-14 17:33:04 +00:00
ryan
0201ca60e7 fix(ui): move tags typed into key metadata JSON into the Tags field
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-13 23:09:27 +00:00
yassin
330ba7cbf9 fix(ui): show the team alias on the model info page and in its raw JSON
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-13 09:21:09 +00:00
mateo-berri
76ae35dfcd fix(types): break the CachedTokensDetails import cycle
CodeQL flagged two module-level cyclic imports introduced by defining
CachedTokensDetails in litellm.types.llms.openai and importing it from
litellm.types.utils and litellm.cost_calculator. The class now lives in
litellm.types.llms.base, which imports nothing from litellm, and every
user imports it from there.

Also pins that combining realtime usages where only one response.done
carries cached_tokens_details keeps the earlier modality split in both
orders, and commits the regenerated dashboard API types.
2026-09-13 01:14:35 -07:00
devin-ai-integration[bot]
8851148330
fix(router): preserve Azure Entra ID params in reusable credentials (#40889)
CredentialLiteLLMParams omitted tenant_id, client_id, client_secret,
azure_scope, azure_username and azure_password, so the strict dump used
by credential reuse and Azure client init dropped them and the reused
credential ended with no auth at all

Co-authored-by: yassin <yassin@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-12 21:13:45 -07:00
Mateo Wang
386d29ee67
Merge pull request #38867 from BerriAI/litellm_hide_admin_tabs_view_only
fix(ui): hide admin write-form tabs on the models page from view-only admins
2026-09-12 21:13:34 -07:00
moe-berri
72f9f3cc63 fix(memory): preserve paging boundaries and select only accessible keys 2026-09-12 21:12:49 -07:00
mateo-berri
8608a03bd8 Merge origin/litellm_internal_staging into litellm_spend_log_request_id_call_id
Keeps the base's rule that a non-admin id lookup matching no spend-log row answers 403, so the detail route never consults cold storage without an owner row
2026-09-12 21:04:25 -07:00
moe-berri
3bba16c6a6 feat(memory): show a recent memory feed and key-aware opt-in toggle 2026-09-12 21:00:50 -07:00
ryan
8ccde3879d Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_key_alias_substring_non_admin 2026-09-12 23:06:23 +00:00
devin-ai-integration[bot]
b1360efc2f
fix(proxy): attribute gate-rejected requests to their endpoint in cache analytics (#40824)
* fix(proxy): attribute gate-rejected requests to their endpoint in cache analytics

Requests rejected before dispatch (bad key, blocked key, budget, rate limit, malformed body) were spend-logged with an empty call_type because the synthesized logging object never reached the failure lifter. The caching dashboard rolled all of them, plus failed calls on info routes such as /model/info, into one Unknown group.

Resolve call_type from the matched route first, falling back to body shape, and keep the synthesized logging object on request_data so the lifter sees it. Log bare auth exceptions with the 401 ProxyException the client gets so error_code is never empty. Exclude info routes from the cache analytics groups and error breakdown. The dashboard explains the Unknown group when older rows still produce one.

Resolves LIT-5884

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(proxy): keep the raw auth exception for failure callbacks

Record the client-facing status in the spend log through a separate client_exception argument so custom failure callbacks still receive the exception auth raised.

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(proxy): keep the route for multi-operation endpoints and exclude info routes from cache filter options

Routes such as /v1/files map to several operations (create, list) and the
method is not available in the failure hook, so a rejected request there is
filed under its route instead of the first mapped call type. The key alias and
model filter-option queries now apply the same info-route exclusion as the
groups and error breakdown, so every offered filter value returns data. The
info-route exclusion and Unknown grouping are now covered against a real
Postgres in tests/proxy_behavior/spend/test_cache_activity.py

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(proxy): drop client_exception, the spend log row never used it

The DB spend row for a gate rejection is written by _ProxyDBLogger from the
original exception, so the status-bearing copy only reached the in-memory
logging payload. Live runs at the tip still recorded bare auth exceptions as
Unknown/Exception, the same as the base branch. Removing the plumbing keeps
this PR to endpoint attribution and the info-route exclusion

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

---------

Co-authored-by: yucheng <yucheng@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-12 16:03:38 -07:00
Mateo Wang
fc053dae3e
Merge pull request #40770 from BerriAI/litellm_lit6996_agent_skills_wellknown
feat(proxy): serve registered skills as an Agent Skills well-known index
2026-09-12 15:20:20 -07:00
moe-berri
bbbb0e1592 chore: sync current staging changes for memory integration 2026-09-12 15:09:40 -07:00
ryan-crabbe-berri
ba6a0c9fc6
Merge pull request #40652 from BerriAI/litellm_key_activity_search
feat(ui): search Key Activity by key alias, key hash, user id, or email
2026-09-12 15:05:53 -07:00
ryan
a3ebeae28b chore(ui): regenerate schema.d.ts for /key/list substring_matching descriptions
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-12 22:05:20 +00:00
ryan-crabbe-berri
9a3f752724
Merge pull request #40656 from BerriAI/litellm_ui_table_search_pending_state
fix(ui): show loading state instead of stale rows while a table search is pending
2026-09-12 14:49:24 -07:00
Tin Chi Lo
cba843cc16 feat(proxy): predict prompt-cache costs across deployments 2026-09-12 14:02:45 -07:00
Yuneng Jiang
b24480941b
fix(ui): retain cleared user budget values after save 2026-09-12 13:43:55 -07:00