Commit graph

447 commits

Author SHA1 Message Date
devin-ai-integration[bot]
fc87a06f00
fix(proxy): stop leaking periodic tasks on every DB config reload (#42784)
Co-authored-by: yassin <yassin@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-24 15:42:36 -05:00
devin-ai-integration[bot]
d17c0d7724
refactor: daily fresh tech debt cleanup, rolling PR (#42710)
* refactor: clear fresh tech debt from the last 24 hours (2026-09-05, 2026-09-06)

Drop the TID251 cast import and both cast-ok casts from the refusal
message_delta rebuild by narrowing the TypedDict union on its type literal,
drop the redundant Mapping cast after the isinstance check in
_mapping_field, and type the Lyria predict read-only helpers as
Mapping[str, object] instead of a bare dict with mutable-ok.

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

* refactor: clear fresh tech debt from the last 24 hours (2026-09-09)

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

* refactor: clear fresh tech debt from the last 24 hours (2026-09-10)

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

* refactor: keep the pre-existing cost-estimate comment and usage cost read out of the cleanup

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

* refactor: clear fresh tech debt from the last 24 hours (2026-09-13)

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

* refactor: keep the model info pricing helper out of the cleanup

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

* refactor: drop suppressions that no longer suppress anything (2026-09-16)

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

* refactor: keep the rebind-ok reason inside the line limit

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

* fix(anthropic): rebuild the refusal message_delta by spreading the chunk

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

* refactor: clear fresh tech debt from the last 24 hours (2026-09-17)

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

* refactor: clear fresh tech debt from the last 24 hours (2026-09-18)

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

* refactor: clear fresh tech debt from the last 24 hours (2026-09-19)

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

* refactor: keep the pre-existing protected-resource return type out of the cleanup

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

* refactor: clear fresh tech debt from the last 24 hours (2026-09-20)

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

* refactor: type fresh getattr, Any, and bare dict debt from 2026-09-22

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

* fix(mcp): keep the string guard on tools/list next_cursor

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

* refactor(vercel_ai_gateway): type the embedding error headers dict

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

* chore(techdebt): fix inert suppressions and missing Final in 2026-09-22 changes

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

* chore(techdebt): shorten suppression reason to fit line length

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

* chore(techdebt): format provider spread so its suppression sits on the literal

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

* chore(techdebt): drop the logger extras suppression that LIT013 now flags as inert

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

* chore(techdebt): clear fresh suppressions, Any aliases and slop from the 24h window

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

* refactor(vercel): take a read-only headers mapping in get_error_class

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

---------

Co-authored-by: mateo <mateo@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-24 04:17:23 -07:00
devin-ai-integration[bot]
1175559c39
feat(lint): add LIT013 flagging *-ok suppressions that suppress nothing and remove the 240 stale ones (#42793) 2026-09-23 17:50:09 -07:00
moe-berri
2157351004
feat(ui): simplify auto-router setup and clarify feature limits (#42625)
* feat(ui): simplify auto-router setup and clarify feature limits

* fix(ui): validate auto-router drafts before saving

* fix: keep auto-router allowances consistent after deletes and refreshes
2026-09-22 18:03:32 -07:00
tin-berri
5a8c4f48e4
feat(router): native compact-to-fit across conversation APIs (#42074)
* feat(router): native compact-to-fit across conversation APIs

* fix(router): preserve compaction admission and shared client boundaries

* fix(router): honor compaction fit fallbacks and router-scoped access

* fix(router): charge compaction usage to caller token limits

* test(http): keep FastAPI inside proxy tests

* fix(router): check compactor capacity before skipping escalation
2026-09-21 22:52:29 -07:00
devin-ai-integration[bot]
1106b16745
feat(openrouter): price typesafe/jev-1.13 and add an openrouter decisions pass-through (#42301) 2026-09-22 02:44:15 +00:00
tin-berri
275c0c4d96
Merge pull request #42057 from BerriAI/litellm_classifier_forecast_cards
feat(ui): show Capability and FUSE v2 routing forecasts
2026-09-21 17:55:25 -07:00
Tin Chi Lo
9221109d18 chore(router): resolve merge conflict with main 2026-09-21 16:52:47 -07:00
Tin Chi Lo
1b9fb34679 refactor(router): simplify optional forecast retention
Some checks failed
LiteLLM Rust / rust-lint (push) Has been cancelled
Terraform Provider / gofmt, vet, build, test (push) Has been cancelled
LiteLLM Rust / rust-test (push) Has been cancelled
LiteLLM Rust / rust-wheel (push) Has been cancelled
Terraform Provider / Provider endpoints vs proxy OpenAPI schema (push) Has been cancelled
2026-09-21 16:47:21 -07:00
Tin Chi Lo
21fb652586 chore: merge main to restore lint checker 2026-09-21 16:44:08 -07:00
Tin Chi Lo
7980a8f65f fix(router): freeze retained forecast fields for lint 2026-09-21 16:40:55 -07:00
Tin Chi Lo
7f997a420d chore(ui): resolve routing forecast merge conflict 2026-09-21 12:57:57 -07:00
mateo-berri
c62c187054 Merge remote-tracking branch 'origin/main' into litellm_decrease_anys_opus5_r5
# Conflicts:
#	litellm/integrations/otel/model/metadata.py
#	litellm/litellm_core_utils/coroutine_checker.py
#	litellm/litellm_core_utils/exception_mapping_utils.py
#	litellm/litellm_core_utils/llm_response_utils/response_metadata.py
#	litellm/llms/bedrock_mantle/responses/transformation.py
#	litellm/llms/openai/chat/guardrail_translation/handler.py
#	litellm/proxy/common_utils/reset_budget_job.py
#	litellm/proxy/db/db_spend_update_writer.py
#	litellm/proxy/guardrails/guardrail_hooks/llm_as_a_judge/__init__.py
#	litellm/proxy/openai_files_endpoints/storage_backend_service.py
#	litellm/proxy/pass_through_endpoints/llm_provider_handlers/vertex_passthrough_logging_handler.py
#	litellm/realtime_api/main.py
2026-09-21 12:57:38 -07:00
Tin Chi Lo
71465fc2f7 chore(router): resolve merge conflict with main 2026-09-21 11:29:48 -07:00
Moe Khalil
83ec5d6101 fix(auto-router): skip JEV for encrypted delegated tasks
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-21 18:29:21 +00:00
Moe Khalil
bb46e8b774 chore(auto-router): merge main and preserve JEV configuration
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-21 17:16:18 +00:00
Tin Chi Lo
a233ba910d feat(auto-router): configure heuristic v2 success threshold 2026-09-21 08:53:13 -07:00
Moe Khalil
f9dc57a844 fix(auto-router): isolate JEV verdicts from logging failures
Some checks failed
LiteLLM Rust / rust-lint (push) Has been cancelled
LiteLLM Rust / rust-test (push) Has been cancelled
LiteLLM Rust / rust-wheel (push) Has been cancelled
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-20 17:46:15 +00:00
Moe Khalil
bda1bd89ae chore(auto-router): document mutable logging API boundaries
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-20 15:04:33 +00:00
Moe Khalil
8505d10017 chore(auto-router): merge main into JEV launch branch
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-20 14:53:05 +00:00
Devin AI
ccd8997b08 refactor(types): replace Any with proven types in 34 files
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-20 10:16:48 +00:00
Mateo Wang
93e39d5042
Merge pull request #42062 from BerriAI/litellm_pr38499_batch_retrieve_model_group
fix(router): stamp model_group when retrieving a batch, so batch tokens are attributable (internal copy of #38499)
2026-09-19 18:23:06 -07:00
Tin Chi Lo
7c79c7efad feat(ui): show Capability and FUSE v2 routing forecasts 2026-09-19 17:04:14 -07:00
Moe Khalil
e77c154c36 chore(auto-router): merge main into JEV launch branch
Some checks failed
LiteLLM Rust / rust-lint (push) Waiting to run
LiteLLM Rust / rust-test (push) Waiting to run
LiteLLM Rust / rust-wheel (push) Waiting to run
Terraform Provider / gofmt, vet, build, test (push) Has been cancelled
Terraform Provider / Provider endpoints vs proxy OpenAPI schema (push) Has been cancelled
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-19 23:28:15 +00:00
tin-berri
252a0f1eac
Merge pull request #41617 from BerriAI/litellm_fuse_model_profile_presets
feat(router): add maintained Fuse model and harness presets
2026-09-19 16:17:19 -07:00
Moe Khalil
afde938a67 docs(auto-router): disclose shared JEV context defaults
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-19 19:46:46 +00:00
Tin Chi Lo
dde73968cf fix(auto-router): show heuristic v2 score estimates in routing details 2026-09-19 12:19:43 -07:00
Tin Chi Lo
4d659135b6 fix(router): preserve unavailable Fuse presets 2026-09-19 11:48:40 -07:00
Moe Khalil
52aa20d138 refactor(auto-router): freeze JEV logging input mappings
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-19 17:49:55 +00:00
Tin
5f722bc195 chore(router): remove in-repo escalation docs
Some checks failed
LiteLLM Rust / rust-lint (push) Has been cancelled
LiteLLM Rust / rust-test (push) Has been cancelled
LiteLLM Rust / rust-wheel (push) Has been cancelled
Terraform Modules / fmt, validate, test (aws) (push) Has been cancelled
Terraform Modules / fmt, validate, test (gcp) (push) Has been cancelled
2026-09-19 10:26:42 -07:00
Tin Chi Lo
e9109ddf4a fix(router): make context-window escalation opt-in 2026-09-19 10:01:43 -07:00
mateo-berri
12bc9ad7b4 Merge remote-tracking branch 'origin/main' into litellm_pr38499_batch_retrieve_model_group 2026-09-19 02:12:25 -07:00
Moe Khalil
e0b2c51144 fix(auto-router): validate JEV usage and clear stale context
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-18 23:41:20 +00:00
Moe Khalil
8e5f43f458 fix(auto-router): preserve JEV accounting and context bounds
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-18 22:09:27 +00:00
Moe Khalil
86e079d7a8 feat(auto-router): integrate JEV context and usage accounting
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-18 21:38:15 +00:00
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-berri
7f581f6bc7 fix(router): keep the TypeSafe key off caller-chosen Jev endpoints 2026-09-17 16:09:31 -07:00
mateo
0a66328663 fix(router): validate Jev classifier probabilities
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 17:31:08 +00:00
mateo
d7b281ce8f refactor(router): build the Jev client without rebinding the constructor argument
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 17:06:58 +00:00
mateo
9b7fcd0480 feat(router): add TypeSafe Jev as a complexity router classifier
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 17:05:07 +00:00
Tin Chi Lo
2fa115db2b feat(router): add maintained Fuse model and harness presets 2026-09-17 12:53:15 -04:00
Tin Chi Lo
9352d24863 fix(router): accept fenced Fuse classifier verdicts 2026-09-15 13:11:56 -07:00
Tin Chi Lo
56b20525f5 fix(router): honor Fuse task context and fallback policy 2026-09-15 13:11:56 -07:00
Tin Chi Lo
92bece2baa fix(router): expose exact Fuse v2 forecast metadata 2026-09-15 13:11:56 -07:00
Tin Chi Lo
902b2e7ef8 feat(router): add experimental joint LLM V2 classifier 2026-09-15 13:11:55 -07:00
Tin Chi Lo
55fc0deabc style(router): format encrypted task selection 2026-09-15 12:09:05 -07:00
Tin Chi Lo
cadb7ee44d fix(router): preserve native encrypted capability tasks 2026-09-15 12:05:30 -07:00
Tin Chi Lo
896f35c751 fix(router): extract capability tasks with request scoped markers 2026-09-15 11:52:20 -07:00
Tin Chi Lo
e62f0d0376 fix(router): reject unknown capability policy fields 2026-09-15 11:43:04 -07:00
Tin Chi Lo
2da9bbfc0f chore: merge main into capability classifier copy 2026-09-15 11:24:01 -07:00