scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-30 01:52:18 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 70
53300 commits 2968 branches 1429 tags 3.9 GiB
Commit graph

53300 commits

This branch
This branch
All branches
Author SHA1 Message Date
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
Joshua Valluru
daff22a884 test(mcp): grant the guardrail control team its server 2026-09-17 17:50:01 -07:00
Yuneng Jiang
726dbf0d0d
fix(ocr): keep a downloaded document inlined when callbacks intercept the request 
Providers that cannot fetch a public document URL themselves (Azure AI
mistral document AI, Azure cohere parse, Vertex AI) download it and
inline it as a data URI. When a pre-call callback or debug logging
intercepts the request, the Python host hands the caller's original
document back into the body, so the provider request carried the URL
again and Azure's inline-only check rejected it with "invalid OCR
document data URI". The core now keeps the prepared document when a
hook returns the untouched caller document, while a hook that edits or
replaces the document still wins
 2026-09-17 17:48:52 -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
Joshua Valluru
6aa921c1bc fix(ci): run dependency tests in an isolated Python environment 2026-09-17 17:42:01 -07:00
Joshua Valluru
640b0e5fa9 test(mcp): discover concrete tools through a catalog key 2026-09-17 17:41:57 -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
Joshua Valluru
15b45839e1 test(mcp): enforce security regression contracts through live gateway 2026-09-17 17:37:40 -07:00
Joshua Valluru
b42e2827a5 ci(mcp): document pinned workflow action versions 2026-09-17 17:36:58 -07:00
Joshua Valluru
c19b5c5847 ci(deps): document pinned action versions 2026-09-17 17:36:46 -07:00
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
Joshua Valluru
1dbcf31fe8 ci(mcp): run isolated dependency gates in GitHub Actions 2026-09-17 17:29:03 -07:00
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
Joshua Valluru
0a87dc6cb1 ci(deps): run wheel installation gates in GitHub Actions 2026-09-17 17:25:20 -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
82d252210e fix(proxy): word the token exchange's 503 by whether the database fault can clear 
A permanent database fault (a missing or version-skewed query engine)
in the subject_token check was answered with the same "retry" wording
as a transient outage. The status stays 503 temporarily_unavailable,
the only OAuth error a client reads as the server's fault and what the
mint path already answers to the same fault, but the description now
says retrying will not help until the deployment is repaired, using
PrismaDBExceptionHandler.is_permanent_database_fault the way the mint
path does.
 2026-09-17 17:20:17 -07:00
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
yassin
4f8a5b5e12 Merge remote-tracking branch 'origin/main' into litellm_transcribe_passthrough 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

# Conflicts:
#	litellm/proxy/_lazy_features.py
#	litellm/proxy/_lazy_openapi_snapshot.json
#	litellm/proxy/pass_through_endpoints/success_handler.py
#	ui/litellm-dashboard/src/lib/http/schema.d.ts
 2026-09-18 00:17:47 +00:00
ryan
761e0775b9 test(proxy): share the jwt key mapping test doubles across the deletion endpoint tests 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-18 00:17:45 +00:00
mateo-berri
d4b5f05f97 chore: merge main into litellm_foundry_a2a_entra_agents 2026-09-17 17:17:21 -07:00
mateo-berri
44fff9297d fix(a2a): narrow discovery status codes through a structural protocol 
basedpyright cannot narrow the probe error through
isinstance(error, AgentCardResolutionError) while that class is imported
inside try/except ImportError, which left three reportAttributeAccessIssue
errors over the budget main now carries. A runtime-checkable Protocol with
the same status_code contract carries the narrowing instead, so the check
no longer depends on the possibly unbound SDK name and the import goes.
 2026-09-17 17:17:21 -07:00
Joshua Valluru
3519d01549 test(mcp): add isolated SDK2 dependency compatibility gate 2026-09-17 17:16:47 -07:00
yassin
ea1fd5f288 fix(proxy): price deleted Transcribe jobs from their start response and read media length without loading it 
Restrict signed media fetches to https URLs, treat a job AWS no longer knows as
priceable from the media named in its StartTranscriptionJob response instead of
polling to the eight hour maximum, and read the media length with libsndfile
headers instead of decoding the whole file into memory

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-18 00:16:18 +00:00
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
kerry-berri
19aa9da7a7
Merge pull request #41703 from BerriAI/litellm_bump_soupsieve_osv 
build(deps): bump soupsieve to 2.9.2 to clear the osv-scan advisories
 2026-09-17 17:10:42 -07:00
mateo
b989e3bd0a test(ui): stub fetch without a type suppression in interactions playground test 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-18 00:10:03 +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
ryan-crabbe-berri
5156dbc67f fix(ui): show the saved team in read mode before the model query refetches 
Read mode built the Team display from the react-query snapshot while save only wrote localModelData, so the old team flashed until the parent's invalidation refetched. Read the team from localModelData like the neighbouring fields and look up its alias from the local team id. The regression test also waits for the Select trigger to report expanded before clicking an option, because Base UI opens the popup asynchronously and keeps the closed popup mounted, which made back-to-back option clicks flaky.
 2026-09-17 17:04:14 -07:00
Joshua Valluru
eebc76cf2c fix(deps): correct minimum versions for supported Python releases 2026-09-17 17:03:19 -07:00
ryan
e79d03e604 fix(proxy): evict jwt key mapping cache on bulk user and team member deletion 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-18 00:00:17 +00:00
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
76ae1bfa2f build(deps): bump soupsieve to 2.9.2 to clear the osv-scan advisories 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-17 23:56:05 +00:00
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
kerry
d1b9360e5e test: drop the cost map independence workflow, keep the gate as a local script 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-17 23:55:04 +00:00
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
38586e9684 refactor(proxy): drop redundant docstring from organization key cleanup helper 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-17 23:46:32 +00:00
mateo-berri
c29d1c2813 chore: merge main into litellm_foundry_a2a_entra_agents 2026-09-17 16:45:07 -07:00
mateo
d09ccc4b0e fix(ui): parse current interaction stream events in playground 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-17 23:45:04 +00:00
yassin
d0591665b5 Merge remote-tracking branch 'origin/main' into HEAD 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

# Conflicts:
#	litellm/proxy/pass_through_endpoints/success_handler.py
#	tests/test_litellm/proxy/pass_through_endpoints/test_llm_pass_through_endpoints.py
 2026-09-17 23:44:13 +00:00
Devin AI
569ef3ea25 merge: resolve conflict with main in member budget seeding 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-17 23:42:41 +00:00