The backported Hugging Face download test sends HEAD to the wire peer, which the line only answered for POST, PUT, GET and DELETE.
Hand-ported from the wire.py part of 2c3866ebb4 (#43914, main), leaving out its keep-alive and connection counting.
Backport of #47353 to stable/1.104.x.
Cherry-picked from 2d181e6633 (main).
Adapted to the stable compatibility rule: the bundled DeepSeek tokenizer is selected only on the proxy count routes, through select_count_route_tokenizer, so token_counter, encode and decode, budget reservation, ITPM, context-management triggers and failed-request spend rows keep the line's tokenizer and a request admitted on v1.104.4 is still admitted. A DeepSeek tokenizer that fails to load falls back to tiktoken on the count routes, the way every other bundled tokenizer does. The wire tests read the line's proxy_config.yaml, which has no general_settings or router_settings, and use azure_ai/grok-4 as the control model, since the line's azure_ai/grok-4-1 entry rejects tool_choice. The failed-dispatch spend test is left out, and the wire tests that asserted the DeepSeek tokenizer on those paths now assert the line's count is kept.
Backport of #47173 to stable/1.104.x.
Cherry-picked from c82e8244a5 (main), applied through the line's earlier resolution c3d07e70d6.
Adapted to the line: the default tool count keeps the line's formatter, since #43417 is not on the line, and only the chat-template path gets the function-definition helpers.
Adapted to the stable compatibility rule: the chat-template tool count is opt-in through token_counter(chat_template_tools=True), which only the proxy count routes pass, so ITPM, budget reservation and context-management estimates keep the line's OpenAI tool framing and a request they admitted on v1.104.4 is still admitted. The tests that asserted the new framing on those paths now assert the line's framing is kept.
Defer the breaking error policy from #46121. Adapt the #46777 count settings flow to attempt a labelled local estimate for provider failures across providers and configured count models.
Keep provider errors when local counting is disabled or cannot estimate the request, and test the shared behavior across HTTP error statuses.
Keep #43900, #45301, #46121, #46784, #46759, #46767, #46772, #46815, #47057 and #46777. Port only the Gemini prerequisites from #46430.
Remove the deferred Bedrock Mantle behavior and unrelated picks from the final tree. Restore the PDF test provider fixture and deployment, and retain required test imports.
Hand-ported to stable/1.104.x from main (bedrock_runtime_peer, provider, _cache_control_marks_support verbatim, graceful_stop_seconds at the line's 30s stop wait).
Backport of #47064 to stable/1.104.x.
Cherry-picked from ae6f7f6613 (main).
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Backport of #46430 to stable/1.104.x.
Cherry-picked from 08a24d391a (main).
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Backport of #46121 to stable/1.104.x.
Cherry-picked from 719c44db3f (main).
Co-authored-by: Krrish Dholakia <krrishdholakia@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: yuneng-jiang <yuneng@berri.ai>
Backport of #45463 to stable/1.104.x.
Cherry-picked from d34ad35281 (main).
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
Backport of #45301 to stable/1.104.x.
Cherry-picked from 50ab9a3211 (main).
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
Backport of #43900 to stable/1.104.x.
Cherry-picked from 6d73fa6b49 (main).
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: jesus <jesus@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
Backport of #43417 to stable/1.104.x.
Cherry-picked from 8e6d99d74a (main).
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
The tests picked from #47067 annotate module constants with Final, which main's copy imports and this line's did not, so the module failed to import on Python 3.12.
Backport of #47067 to stable/1.104.x.
Cherry-picked from e979bd0ecf (main).
Conflict: main renamed the model access helper to check_model_access_helper, while stable/1.104.x still names it _check_model_access_helper, so the new owning-team check calls it by the line's name.
Line adaptation: the line's test_auth_utils.py had no module-level Router import, which main's copy has and the picked helper uses, so it is added.
The decision model guardrail backport (#45900) added supported_decisions_providers to
litellm.decisions.main and imported it from there in get_guardrail_ui_settings. The
decisions backport (#45906) then picked #45130, which rewrites litellm.decisions.main
and moves the provider list into litellm.decisions.call as _supported_providers, so the
import broke and GET /guardrails/ui/add_guardrail_settings raises ImportError. The Admin
UI's Add Provider Guardrail wizard gets no providers as a result
Match main by naming it supported_decisions_providers in litellm.decisions.call and
pointing the endpoint and its test there, the same fix rc/1.105.0 got in fcbb02231b
