߲jdZddlmZddlmZddlmZmZddlm Z ddl m Z ddl m Z ded zd efd ZGd d e ZeddddZe ey )uCustom / Ollama (local) provider profile: any endpoint registered as provider="custom" (Ollama, vLLM, llama.cpp, GLM-5.2 on ARK, …).)Any)urlparse)OPENAI_COMPAT_WIRE_EFFORTS clamp_effort)register_provider)ProviderProfile)base_url_host_matchesbase_urlNreturnch|xsdj}|sytd|vr|nd|} |jdk(ry |jxsdj j d}t|xr-|dk(xs&|jd xsd |jdvS#t$rYywxYw) zTrue only for explicit Ollama signatures (port 11434 or an ``ollama`` host label). ``think`` is Ollama-native; strict hosts (Mistral, Groq) 422 on it, and arbitrary localhost may be llama.cpp / vLLM / LM Studio.Fz://z//i,T.z ollama.comz .ollama.comollama) striprport ValueErrorhostnamelowerrstripboolendswithsplit)r rawparsedhosts L/home/ubuntu/.hermes/hermes-agent/plugins/model-providers/custom/__init__.py_looks_like_ollama_endpointr s >r "C  Uc\cC5z :F ;;%   OO !r ( ( * 1 1# 6D : o4</n4==3OnS[_c_i_ijm_nSno sB%% B10B1c eZdZdZdedzdeedffdZddedzdedzfdZdddd edzd e dzd e deeee feee fffd Z ddd ddedzdedzde de edzffdZxZS) CustomProfileuACustom/Ollama local provider — think=false and num_ctx support.modelNr .ctS)uThe OpenAI-compat wire set, mirroring this profile's own chat-completions clamp. Without this declaration the Responses transport clamps onto the OpenAI per-model ladder (``codex_supported_efforts``), where ``max`` is gpt-5.6-only — so a custom relay's model had a configured ``max`` silently demoted to ``xhigh`` while the same provider over chat-completions forwarded ``max`` unchanged (#114249). A custom endpoint's vocabulary is undiscoverable, so the widest OpenAI-compat set is the honest ceiling; ``ultra`` still clamps to ``max`` via the shared ``clamp_effort`` policy. )rselfr s rsupported_reasoning_effortsz)CustomProfile.supported_reasoning_efforts!s *)c dddS)uUnset ``agent.reasoning_effort`` → ``medium``, as on the Nous / OpenRouter profiles. Leaving the field off lets the endpoint's own default apply, and for a hosted reasoning model that default can be its ceiling: kimi-k3 behind an OpenAI-compatible relay defaults to ``max`` — 3x the reasoning tokens and ~3x the latency of medium. The agent skips this default for models the catalog marks non-reasoning (``agent.reasoning_params``). Tmedium)enabledeffortr"s rdefault_reasoning_configz&CustomProfile.default_reasoning_config.s 844r%)reasoning_configollama_num_ctxr,r-ctxc i}i}|rd|i|d<|rt|tr|jdxsdjj }|dk(s|jdddur(d|d <t |jd rd|d <||fS|r1t t|jd xsdd r d |d <||fS|rt|t|d <||fS)Nnum_ctxoptionsr)r noner(TFreasoning_effortr thinkz api.groq.comdefault) isinstancedictgetrrrr strrr)r#r,r-r. extra_body top_levelr)s rbuild_api_kwargs_extrasz%CustomProfile.build_api_kwargs_extras8s&( $& %.$?Jy !  +;T B&**84:AACIIKF#3#7#7 4#HE#Q06 ,-.swwz/BC*/Jw'9$$ 1#cggj6I6OR2PR`a1: ,-9$$0r r?cF|s |jsyt| |||S)z/base_url is user-configured; fetch only if set.Nr=)r super fetch_models)r#r>r r? __class__s rrBzCustomProfile.fetch_modelsVs)DMMw#GhPW#XXr%)N)__name__ __module__ __qualname____doc__r9tupler$r7r+intrr<floatlistrB __classcell__)rCs@rrrsK *t *c3h *5cDj5D4K526TX%#'$;%GJTz%ad% tCH~tCH~- .%>(,D[^Y*Y7:TzYSXY cT YYr%rcustom)rlocalvllmllamacppz llama.cppz llama-cppr*r )namealiasesenv_varsr )rGtypingr urllib.parseragent.reasoning_effortrr providersrproviders.baserutilsr r9rrrrMr*r%rrZsjE!K'*'p#*pp">YO>YB  \   &r%