scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-04 02:31:27 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 70
50675 commits 3112 branches 1436 tags 4.4 GiB
Commit graph

50675 commits

This branch
This branch
All branches
Author SHA1 Message Date
yassin
cf22e4b171 fix(proxy): make SettingsStore.clear terminate when the config file owns a key 
MutableMapping.clear pops items until the mapping is empty, but __delitem__
keeps config-owned keys, so clear spun forever on any store that had loaded a
config file. unittest.mock.patch.dict calls clear on exit, which is why the
proxy-infra and proxy-endpoints shards hung at 99 percent until the 20 minute
job timeout on every run since the store started refusing config-owned writes

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-18 19:51:15 +00:00
yassin
307df09792 test(mcp): assert the self-revoke response instead of echoing the delete mock 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-18 18:51:43 +00:00
yassin
048aaad627 Merge remote-tracking branch 'origin/main' into litellm_mcp_admin_terminate_sessions_revoke_credentials 2026-09-18 18:39:16 +00:00
Yassin Kortam
0594dd7caf
Merge pull request #41539 from BerriAI/litellm_vault_login_secret_namespace 
feat(vault): add separate login and secret namespaces for HashiCorp Vault
 2026-09-18 11:38:49 -07:00
Yassin Kortam
84ae0805ba
Merge pull request #41620 from BerriAI/litellm_team_member_temp_budget_increase 
feat(proxy): temporary budget increase for team members
 2026-09-18 11:38:34 -07:00
ryan-crabbe-berri
30035f817b
Merge pull request #40935 from BerriAI/litellm_codex_duplicate_issue_check 
ci: replace the title-similarity duplicate bot with a Codex semantic check
 2026-09-18 11:37:51 -07:00
Yassin Kortam
f6d9b2552f
Merge pull request #41692 from BerriAI/litellm_mcp_gateway_sessions_by_client_user 
feat(mcp): show live gateway sessions by AI client and user
 2026-09-18 11:37:16 -07:00
Yassin Kortam
ca79c393d5
Merge pull request #41636 from BerriAI/litellm_per_key_end_user_default_budget 
feat(proxy): per-key default budget for dynamically created customers
 2026-09-18 11:36:59 -07:00
Yassin Kortam
f129e7e2d0
Merge pull request #41515 from BerriAI/litellm_transcribe_passthrough 
feat(proxy): add Amazon Transcribe pass-through with completion-time job pricing
 2026-09-18 11:35:06 -07:00
yassin
3b8f887686 ci: rerun proxy-infra after main timeout 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-18 18:19:32 +00:00
Yassin Kortam
d42f448e41
Merge pull request #41585 from BerriAI/litellm_lazy_fastapi_bpe_imports 
perf: defer fastapi and tiktoken BPE imports out of import litellm
 2026-09-18 11:19:13 -07:00
Yassin Kortam
660f3dfdd3
Merge pull request #41555 from BerriAI/litellm_max_parallel_requests_queue_size 
feat(router): reject with 429 when a deployment's max_parallel_requests slots are all in use
 2026-09-18 11:18:08 -07:00
Mateo Wang
db756b9393
Merge pull request #40730 from BerriAI/litellm_responses_nested_additional_drop_params 
fix(responses): honor nested additional_drop_params paths
 2026-09-18 11:04:38 -07:00
kerry-berri
fd58c31cc7
Merge pull request #41832 from BerriAI/litellm_lit_8111_cache_read_missing_rate 
fix(cost): bill cache-read tokens at the input rate when the map has no cache-read rate
 2026-09-18 10:56:25 -07:00
yassin
fa70e49b81 chore: merge main into litellm_transcribe_passthrough 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-18 17:54:59 +00:00
ryan-crabbe-berri
a9ee15372f
Merge pull request #39308 from BerriAI/litellm_ui_per_second_video_pricing 
fix(ui): show per-second pricing for video models instead of $0.00 token costs
 2026-09-18 10:05:26 -07:00
ryan-crabbe-berri
4e2117832a
Merge pull request #40700 from BerriAI/litellm_ui_editable_model_team_id 
fix(ui): let admins change a model's team from the model edit page
 2026-09-18 09:53:34 -07:00
yuneng-jiang
c4ab1d98e9
Merge pull request #41779 from BerriAI/litellm_settings_store_precedence 
refactor(proxy): make the config file win over the database
 2026-09-18 09:52:09 -07:00
kerry
af61d9247c test(cost_tracking): expect cache reads without a map rate to estimate at the input rate 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-18 16:33:17 +00:00
kerry
88d1eb3b35 fix(cost): bill cache-read tokens at the input rate when the map has no cache-read rate 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-18 16:22:14 +00:00
ryan
4f86035a79 style(ui): format pricing test fixtures with prettier 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-18 16:16:28 +00:00
ryan
d197ca20fa fix(ui): type transformModelData output as ModelData so the dashboard build typechecks 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-18 16:13:28 +00:00
kerry-berri
0bd8b7fe02
Merge pull request #41772 from BerriAI/litellm-providers/price-sync-openrouter 
chore(prices): sync OpenRouter prices: 15 models, 6 deprecated
 2026-09-18 09:12:05 -07:00
berriai-litellm-provider-info-sync[bot]
cc0342ac56
chore(prices): sync OpenRouter prices: 15 models, 6 deprecated 
openrouter/~deepseek/deepseek-pro-latest: input_cost_per_token, output_cost_per_token, cache_read_input_token_cost
openrouter/~deepseek/deepseek-v4-flash-latest: input_cost_per_token, output_cost_per_token, cache_read_input_token_cost
openrouter/~z-ai/glm-latest: input_cost_per_token, output_cost_per_token, cache_read_input_token_cost
openrouter/deepseek/deepseek-v4-flash: 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/deepseek/deepseek-v4-pro-0813: input_cost_per_token, output_cost_per_token, cache_read_input_token_cost
openrouter/google/gemini-2.5-flash: deprecation_date
openrouter/google/gemini-2.5-flash-image: deprecation_date
openrouter/google/gemini-2.5-flash-lite: deprecation_date
openrouter/google/gemini-2.5-flash:batch: deprecation_date
openrouter/google/gemini-2.5-pro: deprecation_date
openrouter/google/gemini-2.5-pro:batch: deprecation_date
openrouter/meta/muse-glimmer-30b: input_cost_per_token, output_cost_per_token
openrouter/qwen/qwen-plus-2025-07-28: supports_prompt_caching
openrouter/z-ai/glm-5.2: input_cost_per_token, output_cost_per_token, cache_read_input_token_cost
 2026-09-18 16:01:00 +00:00
yujonglee
799673d5ba
Merge pull request #41829 from BerriAI/litellm_rust_crate_layering 
refactor(rust): align crates with Python package layering
 2026-09-18 08:55:10 -07:00
ryan
b5070408e7 refactor(ui): move per-second cost formatter to dataUtils and type transformModelData input 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-18 15:48:56 +00:00
Mateo Wang
861f79797f
Merge pull request #41663 from BerriAI/litellm_remove_legacy_interactions_schema_flag 
refactor(interactions): remove expired use_legacy_interactions_schema shim
 2026-09-18 08:48:30 -07:00
Mateo Wang
48c4204b43
Merge pull request #41658 from BerriAI/litellm_remove_orphaned_use_delete_project_hook 
chore(ui): remove orphaned useDeleteProject hook and its test
 2026-09-18 08:48:05 -07:00
Mateo Wang
444d345d69
Merge pull request #41657 from BerriAI/litellm_remove_dead_use_key_list_hook 
refactor(ui): remove dead useKeyList hook from key_list.tsx
 2026-09-18 08:47:56 -07:00
Mateo Wang
8ff4991583
Merge pull request #41656 from BerriAI/litellm_remove_dead_networking_and_marketplace_helpers 
refactor(ui): remove dead networking exports and orphaned Claude Code marketplace helpers
 2026-09-18 08:47:46 -07:00
Mateo Wang
e9823c6063
Merge pull request #41655 from BerriAI/litellm_remove_unused_access_group_types 
chore(ui): remove unused access-groups type interfaces
 2026-09-18 08:47:34 -07:00
Mateo Wang
c51bd68ef4
Merge pull request #41653 from BerriAI/litellm_remove_dead_role_exports 
refactor(ui): drop unused rolesAllowedToSeeUsage, viewOnlyRoles and isViewOnlyRole exports
 2026-09-18 08:47:25 -07:00
Mateo Wang
57a273b087
Merge pull request #41651 from BerriAI/litellm_cost_tracking_dead_barrel_exports 
refactor(ui): drop unused cost-tracking barrel re-exports and response types
 2026-09-18 08:47:16 -07:00
Mateo Wang
1f0554c80d
Merge pull request #41650 from BerriAI/litellm_remove_dead_create_credential_from_model 
refactor(ui): remove unused createCredentialFromModel helper and CredentialValues interface
 2026-09-18 08:47:08 -07:00
Mateo Wang
1f50923211
Merge pull request #41649 from BerriAI/litellm_remove_dead_compareui_modelselector 
chore(ui): remove dead compareUI ModelSelector and its test
 2026-09-18 08:46:57 -07:00
Mateo Wang
aa9a08959a
Merge pull request #41647 from BerriAI/litellm_remove_unused_newbadge 
chore(ui): remove unused NewBadge component and its test
 2026-09-18 08:46:45 -07:00
Mateo Wang
8183199992
Merge pull request #41646 from BerriAI/litellm_remove_dead_guardrail_config 
chore(ui): remove never-rendered GuardrailConfig mock component and its test
 2026-09-18 08:46:25 -07:00
Mateo Wang
cbfabbd8ab
Merge pull request #41645 from BerriAI/litellm_remove_orphaned_role_styles 
chore(ui): remove orphaned ROLE_STYLES and RoleStyle from pretty messages view
 2026-09-18 08:46:16 -07:00
Mateo Wang
57a59889ac
Merge pull request #41644 from BerriAI/litellm_remove_dead_helplink_helpicon 
refactor(ui): remove unused HelpLink and HelpIcon components
 2026-09-18 08:46:08 -07:00
ryan
0beb2ffb81 Merge remote-tracking branch 'origin/main' into litellm_ui_per_second_video_pricing 2026-09-18 15:45:18 +00:00
ryan-crabbe-berri
4f70b88a1f
Merge pull request #41707 from BerriAI/litellm_jwt_mapping_cache_evict_on_bulk_key_delete 
fix(proxy): evict jwt key mapping cache on user, team, org, and bulk key deletion
 2026-09-18 08:41:31 -07:00
Yuneng Jiang
0d9c5159df
test(e2e): assert config ownership instead of absence from the stored row 
/config/field/info used to answer from the LiteLLM_Config row, so "the field
400s" proved the row did not carry it. It now answers from the resolved
settings, and the CI stack config declares general_settings.max_parallel_requests,
so the endpoint returns that value and the old assertion could never hold.

The check that /add/allowed_ip writes only what the caller changed moves to
/config/list, which still reports stored_in_db off the row, and the field/info
call now asserts the ownership the endpoint reports: the config file owns the
key, so it reads back as source=config and editable=false.

Verified against a live proxy on an isolated Postgres rather than in CI, where
this check has never run: it waits on protected-environment approval.
 2026-09-18 02:53:37 -07:00
yassin
efd2b8a3cd refactor(vault): type the KV read body walk as Mapping[str, object] 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-18 09:28:20 +00:00
Yuneng Jiang
2f3e4fa724
test(proxy): pass the new pass-through argument to the side-effect dispatcher 
_apply_general_settings_side_effects grew a fourth argument when the reload
started comparing the resolved pass-through list, and this dispatch test calls
it positionally, so it failed with a TypeError.
 2026-09-18 02:17:52 -07:00
Yuneng Jiang
460f336d8a
fix(proxy): rebuild pass-through routes whenever the resolved list changes 
The reload only re-registered pass-through endpoints when the stored row
still carried the key, so deleting the row left the deleted routes serving
traffic until the process restarted.

It now compares the resolved list before and after the row is applied and
rebuilds on any difference, including a deletion that resolves back to the
config file's list or to nothing.

This matches what _apply_retention_settings already does with the retention
values, so the two reload effects no longer disagree about what counts as a
change.

The tests assert the proxy's registry of live pass-through routes, which is
what decides whether a request is routed upstream or falls through to the
auth error, rather than that the registration helper was called.
 2026-09-18 02:05:09 -07:00
yassin
61ce1b46d9 Merge remote-tracking branch 'origin/main' into litellm_max_parallel_requests_queue_size 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

# Conflicts:
#	tests/test_litellm/test_utils.py
 2026-09-18 08:57:53 +00:00
yassin
bc636bc5ff Merge remote-tracking branch 'origin/main' into litellm_vault_login_secret_namespace 2026-09-18 08:57:50 +00:00
yassin
b10944ef1d Merge remote-tracking branch 'origin/main' into litellm_lazy_fastapi_bpe_imports 2026-09-18 08:56:21 +00:00
Yuneng Jiang
23ee8ad1c3
fix(proxy): close the last three surfaces that bypassed config ownership 
The two dashboard toggles under litellm_settings wrote through save_config,
so the refusal applied, but they mutated the litellm module global first: a
refused write still took effect in the running process until the next reload.
Both now check before they mutate.

/config/field/delete drops the stored key without touching the store, so a
deleted key kept reading back from the process. It now refreshes the store
like the other write paths.

/config/list reported source and editable for the general_settings rows but
not for the litellm_settings ones, so the dashboard would have shown a
config-declared toggle as editable.
 2026-09-18 01:53:54 -07:00
Yuneng Jiang
8e67a33fc3
fix(proxy): refuse config-owned writes at one choke point and refresh the store 
Both write paths now go through the same refusal, so /config/field/update and
/config/update answer identically instead of each phrasing its own rule.

A successful write now applies to the SettingsStore, so the next read sees it.
Without this, /config/field/info reported a key the dashboard had just stored
as "not set" until the process reloaded from the database.

resolve() no longer takes a KeyRule it never reads; the store picks the row.
The matrix tests resolve through SettingsStore instead of calling resolve
directly, so the section and key in each case actually route a lookup.

ConfigFieldInfo and ConfigList type `source` as the FieldSource literal, and
the dashboard API types are regenerated for the two new fields.
 2026-09-18 01:49:30 -07:00