The merged TestTeamMemberAutoRouterWrites class dropped the parametrize
decorator on test_admin_router_changes_release_member_scope, leaving the
test with an unsatisfiable endpoint fixture; this restores main's
patch/legacy x config/strategy/unrelated matrix. _full_team now sets
tpd_limit so the every-team-field grant coverage assertion sees the new
LiteLLM_VerificationTokenView field populated.
Bugbot on #42668 flagged that the backport's picks left the member
auto-router management path unwired on this line. This ports the pieces
that make it work, mirroring main: the member write slot in
model_management_endpoints (FOR UPDATE lock, team reload with the model
table include, identity and name-collision checks, post-commit config
publish), StoredAutoRouterIdentity wiring, the license feature helpers,
team tpd_limit, Router.config_deployments, the member_auto_router
ModelInfo flag, the _TEAM_GRANT_RELATIONS include on team lookups, and
the UserAPIKeyAuth fields the team_grants unpack needs. Test files were
rebuilt as line content plus the picks' own additions, and
ui_sso/test_team_grants carry the pick's grant assertions.
Gate-clearing edits stay local to what the picks added: prisma TypedDict
arguments replace mutable dict literals, remaining dict/mapping
arguments carry reasoned mutable-ok comments, test-quality-ok comments
mark the picks' internal-seam patches, and the regenerated dashboard api
types are staged. The only remaining make check failure is pre-existing
staging drift in untouched tests/test_litellm/test_router.py:2969.
The type check gate flagged six new reportArgumentType errors and one reportGeneralTypeIssues error over base: an outcome Final rebinding in the fallback path, a Mapping handed to the dict-typed request_kwargs parameter, optional message sequences passed to a non-optional parameter, DatabaseClient where PrismaClient is expected on two access-group lookups, the effective-config helper object return passed to the Mapping-typed validator, the project row passed to can_project_access_model, and the Response or None from AsyncHTTPHandler.post. The flagged sites now pass the right shape or carry a rule-scoped pyright ignore with the reason.
Merge debris cleanup and 1.102.x-only imports fixed; usesClassifierContext re-exported, JEV custom-tier emission, and preset test adapted to the static preset registry.
The #41615 and #41757 picks brought litellm/proxy/_lazy_openapi_snapshot.json and ui/litellm-dashboard/src/lib/http/schema.d.ts verbatim from main. Both files were regenerated under Python 3.12.
Backport of #41607 to stable/1.100.x.
Cherry-picked from deb9d8aedd (main).
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Backport of #42048 to stable/1.100.x.
Cherry-picked from 7966f50c34 (main). The safeguards backport maps the dangerous-tool-use-2026-09-03 beta for Bedrock, which Claude Opus 4.5 on Bedrock Invoke rejects as an invalid beta flag, so the all-beta-headers Bedrock cases run on Claude Fable 5.1 as they do on main.
The picked TypedDict fields use read-only Sequence[Mapping[str, object]] annotations and the picked Vertex test carries a test-quality-ok marker, so stable/1.100.x's LIT001, LIT012 and TQ008 budgets hold. Static typing only, no runtime change.
Hand-ported to stable/1.100.x from 47b2479c94 on main (fix(bedrock): gate Invoke tool search on the model map's supports_tool_search flag), the one prerequisite the #42288 handler tests need; the rest of that commit stays on main.
Backport of #42288 to stable/1.100.x.
Cherry-picked from merge commit fc82f6e8fa (litellm_safeguards_bedrock_vertex_messages).
The line has no bedrock_mantle beta-header mapping and no Mantle /v1/messages route, so the Mantle mapping, its test file, and the bedrock_mantle test parameter are left out.
Backports the Converse part of fbc6fb56ae from main (PR #31884). The gate only matched
openai.gpt-5, so a GPT-6 model fell through to Anthropic's thinking block and Bedrock
rejected the first real turn after a Claude Code /model switch with 400 Unknown
parameter: 'thinking'. The Nova 2 tool_choice registry keys and the invoke json_mode
forwarding in that commit stay on main
Backport of #41870 to stable/1.100.x. Cherry-picked from a6e3a72ed8 (main) with -m 1.
converse_transformation.py conflicted because this line has no `import re` and no
_is_openai_gpt_reasoning_model helper next to the insertion point. The resolution adds
exactly the four hunks #41870 merged: the import, the 16-token constant,
_requires_min_max_tokens, and the clamped maxTokens assignment. The test file applied clean.
Move the BaseLLMException import into _map_error_event_exception so the
module no longer imports it at load time, clearing the module-level cyclic
import CodeQL flagged. The class is used only on the cold error path.
Replace the mutable list-append test collector with aiter/anext so the
regression tests read the stream immutably.
(cherry picked from commit c246372859)
Mid-stream error events on the streaming Responses API were all raised as
APIError, so a content_policy_violation event never matched the router's
content-policy fallback dispatch and the client got the raw error instead
of the fallback model's answer. Map each error event's code and status
through the existing exception_type mapping, matching the non-streaming
path, and unwrap the typed ContentPolicyViolationError and
ContextWindowExceededError so the router routes them to the configured
content_policy_fallbacks and context_window_fallbacks.
(cherry picked from commit 073d4fe2b0)
