scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-16 23:41:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 102
49147 commits 2457 branches 1410 tags 2.9 GiB
Commit graph

49147 commits

This branch
This branch
All branches
Author SHA1 Message Date
Tin Chi Lo
398300c4e7 fix(router): honor team and key provider weights 2026-09-14 23:31:52 -07:00
Mateo Wang
c93708b2a5
Merge pull request #40228 from AaronHowell/litellm_fix_responses_credentials_affinity 
fix(responses): preserve provider affinity
 2026-09-14 23:09:55 -07:00
yucheng-berri
91588221cd
Merge pull request #39050 from BerriAI/litellm_lit6314_guardrail_metadata_transfer 
fix(guardrails): record not_run evaluation when scoping leaves nothing to scan
 2026-09-14 22:31:16 -07:00
Mateo Wang
a78b24c195
Merge pull request #41172 from BerriAI/litellm_azure_spend_log_zero_cost 
fix(proxy): log the provider usage on deferred /v1/messages calls and price cache writes without a creation rate
 2026-09-14 22:26:22 -07:00
yucheng
fe0fb97fd2 fix(guardrails): record not_run when a skipped role mixes text and images 
Only image-only unscoped content stays unrecorded; text or tool content
removed by scoping is recorded as not_run even when an image sits beside it.
Also keeps the type-discipline budget flat by returning the reason from the
helper and annotating the accumulator lists _extract_inputs requires.

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-15 05:20:56 +00:00
yucheng
714b113c5f fix(guardrails): leave scoped-out image-only input unrecorded and split the not_run helper 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-15 05:10:32 +00:00
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
Mateo Wang
c16c172a65
Merge pull request #40939 from BerriAI/litellm_responses_per_message_guardrail_rewrite 
fix(guardrails): write per-message guardrail rewrites back onto Responses input items
 2026-09-14 21:57:29 -07:00
mateo-berri
d7a2bdd441 test(cost): type the cache rate cases of the base cost test 2026-09-14 21:56:23 -07:00
mateo-berri
8573241c49 fix(cost): resolve a missing 1h cache write rate after off-peak pricing 
The one-hour cache write fallback now takes the applied cache write rate, so an off-peak write price carries into it instead of the input rate

The cost estimate test for a cost-map model without cache prices now expects writes at the input rate, which is what the proxy bills

The recording logger in the deferred guardrail test types its callback parameters
 2026-09-14 21:46:33 -07:00
mateo-berri
f8c2539ba7 Merge remote-tracking branch 'origin/main' into litellm_azure_spend_log_zero_cost 2026-09-14 21:37:19 -07:00
yuneng-jiang
b4cff58be7
Merge pull request #41181 from BerriAI/litellm_pin_ci_pricing 
fix(ci): test checked-out model pricing in unit jobs
 2026-09-14 21:31:34 -07:00
yuneng-jiang
26a13132f8
Merge pull request #41149 from BerriAI/litellm_strict_provider_identity 
test: add strict stateless provider replay identity
 2026-09-14 21:31:25 -07:00
mateo-berri
e01d97ea08 fix(guardrails): read Prompt Security modified rows with the slot count's own predicate 
A chat row whose content carried an empty text part counted two slots in the
chat completions handler while Prompt Security read one text out of the
modified row, so the structured rewrite was dropped and the request got the
named rejection. One shared helper now lists a row's slot texts and both the
slot count and the modified-row reader use it.
 2026-09-14 21:31:22 -07:00
Yuneng Jiang
6969bd9c54
ci: run replay harness on every admitted CircleCI pipeline 2026-09-14 21:12:16 -07:00
Yuneng Jiang
16fb44f23a
ci: run provider replay harness in CircleCI 2026-09-14 21:03:58 -07:00
Mateo Wang
94f08636c7
Merge pull request #40315 from rad-p44/fix/headroom-protect-cache-control-rows 
fix(headroom): protect cache_control-marked rows anywhere in history
 2026-09-14 21:03:16 -07:00
Yuneng Jiang
a1d216b7d7
fix(ci): test checked-out model pricing in unit jobs 2026-09-14 21:00:00 -07:00
Mateo Wang
2bdafa1206
Merge branch 'main' into fix/headroom-protect-cache-control-rows 2026-09-14 20:53:07 -07:00
yuneng-jiang
9d7f2aad04
Merge branch 'main' into litellm_strict_provider_identity 2026-09-14 20:43:55 -07:00
yuneng-jiang
15bd8b0e4a
Merge pull request #40892 from BerriAI/litellm_jwt_management_callers 
test: bind management E2E callers and isolate JWT actors
 2026-09-14 20:30:52 -07:00
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
954dfa6ba7 test(utils): allow modality batch cost fields in cost map schema test 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-15 02:38:53 +00:00
kerry
7761d04450 test(vertex): cover malformed batch usage details 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-15 02:37:51 +00:00
kerry
168d0d3d99 fix(cost): drop remaining unnecessary cast in batch cost calculator 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-15 02:26:19 +00:00
mateo-berri
22b377fe2a fix(proxy): log the provider usage on deferred /v1/messages calls and price cache writes without a creation rate 
With a post-call guardrail the proxy defers async success logging, and every nested wrapper on a
/v1/messages call bridged to the Responses API overwrote the stored closure, so the spend log was
built from the outermost Anthropic-shaped reply under Responses semantics and recorded the prompt
tokens without the cache hit. The first wrapper to exit now keeps the slot, which is the innermost
provider response, the same one the non-deferred path logs.

The flat cost path also billed cache-creation tokens at 0 when the model had no
cache_creation_input_token_cost. It now falls back to the input rate, and the 1h rate to the
creation rate, matching the tiered path and the custom pricing helper.
 2026-09-14 19:21:03 -07:00
kerry
a5f00b9189 fix(cost): drop unnecessary cast in batch rate lookup 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-15 02:15:22 +00:00
kerry
bf1bdb3045 fix(ci): keep cost map schema generated by the base branch generator 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-15 02:07:44 +00:00
kerry
a5fc880c90 refactor(vertex): move batch usage modality parsing under llms 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-15 02:03:32 +00:00
kerry
ca7364fb05 fix(batches): avoid strict lint violation in usage parser 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-15 02:00:48 +00:00
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
kerry
2b32f586c0 refactor(cost): extract batch modality rate lookup 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-15 01:51:41 +00:00
kerry
ce83fac351 fix(cost): bill batch embeddings per modality token rate 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-15 01:50:21 +00:00
mateo-berri
16c326537f fix(guardrails): define UnappliableRequestRewrite in the shared guardrail translation utils 
The three guardrail translation handlers imported the exception from the proxy policy engine through a function-local import, which CodeQL flagged as a cyclic import. The exception and its helper now live next to the handlers in the shared guardrail translation utils, and the tests import it from there.

The Prompt Security modify-mode helper is also restructured into early-return TypedDict displays so the LIT002 budget stays at its limit
 2026-09-14 18:39:54 -07:00
Mateo Wang
d2859e18d7
Merge pull request #40988 from BerriAI/litellm_responses_stream_error_exception_mapping 
fix(responses): route mid-stream error events through exception_type so content_policy_fallbacks fire
 2026-09-14 18:36:20 -07:00
kerry
a28ea22ec1 fix(cost): move gemini-embedding-2-preview to per-token rates 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-15 01:34:22 +00:00
kerry
27a486e4d3 test(cost): cover modality guards and image detection fallbacks 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-15 01:34:17 +00:00
Mateo Wang
1ba97665b2
Merge pull request #41046 from BerriAI/devin/1789368982-cli-strenum-py310 
fix(cli): drop enum.StrEnum so the CLI imports on Python 3.10
 2026-09-14 18:32:30 -07:00
mateo-berri
931bdb8c0b fix(compression): protect part-level cache_control rows in compress() too 
compress() scores text-only copies of the rows, so a content-part cache_control marker was gone by the time get_protected_indices ran and the pinned row could still be stubbed. Read protection from the original rows, which are index-aligned with the normalized copies, and add a regression test that fails without the change.
 2026-09-14 18:19:51 -07:00
mateo-berri
6574d83eae Merge remote-tracking branch 'origin/main' into HEAD 
# Conflicts:
#	litellm/proxy/guardrails/guardrail_hooks/prompt_security/prompt_security.py
 2026-09-14 18:19:38 -07:00
kerry
4a8ec7b9d8 fix(cost): bill gemini-embedding-2-preview per token like the GA entries 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-15 01:18:50 +00:00
kerry
6a18105275 fix(vertex): only bill image rate without modality details when every input is an image 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-15 01:16:00 +00:00
kerry
6cbed7b4c0 fix(vertex): drop Final image_tokens redeclaration flagged by basedpyright 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-15 01:10:27 +00:00
kerry
ac8e1a355c test(vertex): load local pricing in embedding billing tests 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-15 01:00:32 +00:00
Mateo Wang
dad6e9be4a
Merge branch 'main' into fix/headroom-protect-cache-control-rows 2026-09-14 17:58:17 -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
kerry
e31c64d2e0 fix(schema): sync model price schema with cost map 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-15 00:54:58 +00:00
kerry
e5845c17ff fix(vertex): bill image inputs at the image rate when usage lacks modality details 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-15 00:51:49 +00:00
kerry
6c9fe65608 style(cost): apply ruff formatting to modality guards 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-15 00:47:30 +00:00
kerry
0c91d9157c refactor(vertex): drop unused resolved_files from embed response parsing 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-15 00:45:08 +00:00