+ kHjRt^RIHt^RIHt^RIHtHt^RIH t ^RI H t ^RI H t RRlt!R R ] 4t]!R RRR R 7t] !]4R#)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_matchesc>V^8dQhR\R,R\/#)base_urlNreturn)strbool)formats"L/home/ubuntu/.hermes/hermes-agent/plugins/model-providers/custom/__init__.py __annotate__r s"pp#*ppcT;'gRP4pV'gR#\RV9dTMRV 24pVPR8XdR#TP;'gRP 4P R4p\T4;'d;TR8H;'g.TPR 4;'gR TPR49# \dR#i;i) 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 ValueErrorhostnamelowerrstriprendswithsplit)r rawparsedhosts& r_looks_like_ollama_endpointr" s >>r "C  Uc\cC5z :F ;;%   OO ! !r ( ( * 1 1# 6D : o o4</nn4==3OnnS[_c_i_ijm_nSno sC C C caa]tRt^toRtV3RlRltRV3RlRlltRRRR/V3R lR lltR RR RR R/V3RlV3RllltRt Vt V;t #) CustomProfileuACustom/Ollama local provider — think=false and num_ctx support.cH<V^8dQhRS[R,RS[S[R3,/#)r modelNr .)r tuple)r __classdict__s"rrCustomProfile.__annotate__!s' * *t *c3h *rc \#)uEThe 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_efforts)CustomProfile.supported_reasoning_efforts!s *)rNcB<V^8dQhRS[R,RS[R,/#)r r&Nr )r dict)rr(s"rrr).s#55cDj5D4K5rc RRRR/#)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``). enabledTeffortmediumr+s&&rdefault_reasoning_config&CustomProfile.default_reasoning_config.s4844rreasoning_configollama_num_ctxc <V^8dQhRS[R,RS[R,RS[RS[S[S[S[3,S[S[S[3,3,/#)r r8Nr9ctxr )r0intrr'r )rr(s"rrr)8sO%%#'$;%GJTz%ad% tCH~tCH~- .%rc */p/pV'dRV/VR&V'd\V\4'dVPR4;'gRP4P 4pVR8XgVPRR4RJd.RVR&\ VPR 44'dRVR &WE3#V'd=\ \VPR 4;'gR4R 4'd R VR&WE3#V'd\V\4VR&WE3#) num_ctxoptionsr3rnoner2TFreasoning_effortr thinkz api.groq.comdefault) isinstancer0getrrr"rr rr)r,r8r9r; extra_body top_levelr3s&$$, rbuild_api_kwargs_extras%CustomProfile.build_api_kwargs_extras8s&( $& %.$?Jy !  +;T B B&**84::AACIIKF#3#7#7 4#HE#Q06 ,-.swwz/BCC*/Jw'$$ 1#cggj6I6O6OR2PR`aa1: ,-$$0risVE!K'*'p">YO>YB  \   &r