i$ UdZddlZddlZddlZddlZddlZddlmZddlm Z m Z m Z m Z ddl mZddlZddlZddlmZmZddlmZejeZdeezfd Zehd Zeeed <ejd ej Z!ej"d Z#dedefdZ$ia%e ee ee ffed<da&e'ed<dZ(iZ)e ee ee ee fffed<iZ*e ee'fed<dZ+gdZ,e,dZ-dZ.idddddddddddddd d!d"d#d$d%d$d&d"d'd(d)d$d*d+d,d(d-d.d/d0id1d0d2d0d3d4d5d6d7dd8dd9dd:dd;d(dd?d@d4dAdBdCdDdEd0dFdGidHd6dIdGdJdGdKd0dLd4dMd4dNd4dOd?dPd0dQd4dRd?dSd?dTd4dUd4dVdWdXd?dYd?d?dBd?d.d.d.d?d?dDdZ Z/d[Z0d\Z1d]Z2d^Z3d_edefd`Z4ddbede eeffdcZ5d_edefddZ6d_edefdeZ7idfdgdhdgdidjdkdldmdldndodpdqdrdodsdtdudtdvdwdxdAdydzd{dzd|d}d~ddd-dd;dddddddddddd Z8e eefed<d_ede efdZ9d_edefdZ:d_edefdZ;dd_edbede efdZde>de e>fdZ?de ee fde@edfde e>fdZAde ee fde e>fdZBde ee fde e>fdZCde ee fde ee ffdZDde ee ee ffdede ee fddfdZEddede ee ee fffdZF dd_edbedede ee ee fffdZG dded_edbede e>fdZHdefdZIde ee>ffdZJded_ede>ddfdZKded_ede e>fdZLded_eddfdZMde>de e>fdZNdede e>fdZOdede e>fdZPdededefdZQdded_edbede e>fdZRdded_edbede e>fdZSdedefdZTded_edbede e>fdZUdddddddddd ZVe ee>fed<iaWe ee>fed<daXe'ed<dZYdede ee>ffdZZ ddedede e>fd„Z[dede e>fdÄZ\ dded_edbede>dzdede]dzde>fdDŽZ^dede>fdɄZ_de e ee fde>fd˄Z`dadd̜de e ee fdede e e ee fde>fdτZadS)zModel metadata, context lengths, and token estimation utilities. Pure utility functions with no AIAgent dependency. Used by ContextCompressor and run_agent.py for pre-flight context checks. N)Path)AnyDictListOptional)urlparse)base_url_host_matchesbase_url_hostname)OPENROUTER_MODELS_URLreturncdD];}tj|}|r#tj|r|cS>#&& JJJ 4>Hx-aix.aiz-aiz.aikimi-cnarcee-ai deep-seek gmi-cloud ai-gateway minimax-cn nvidia-nim moonshot-cn qwen-portal xiaomi-mimo opencode-zen github-models google-gemini minimax-oauth tencent-cloudgoogle-ai-studiogoglmgminimxaizaizengrokkilokimimimonousqwenarceelocalzhipualiyunclaudecustomgeminigithubgooglenvidiaollamavercelxiaomialibabaarceeaicopilotminimaxstepfuntencentdeepseekgmicloudkilocodemoonshotnemotronopencodetokenhub anthropic dashscope openrouter tencentmaas qwen-oauth copilot-acp kimi-coding opencode-go ollama-cloud openai-codexgithub-copilotkimi-coding-cntencent-tokenhub_PROVIDER_PREFIXESzE^(\d+\.?\d*b|latest|stable|q\d|fp?\d|instruct|chat|coder|vision|text)z 100.64.0.0/10modelc,d|vs|dr|S|dd\}}|}|tvr0t |r|S|S|S)uaStrip a recognised provider prefix from a model string. ``"local:my-model"`` → ``"my-model"`` ``"qwen3.5:27b"`` → ``"qwen3.5:27b"`` (unchanged — not a provider prefix) ``"qwen:0.5b"`` → ``"qwen:0.5b"`` (unchanged — Ollama model:tag) ``"deepseek:latest"``→ ``"deepseek:latest"``(unchanged — Ollama model:tag) :http) startswithsplitstriplowerrb_OLLAMA_TAG_PATTERNmatch)rcprefixsuffix prefix_lowers r_strip_provider_prefixrqVs %5++F33 [[a((NFF<<>>''))L)))  $ $V\\^^ 4 4 L Lr_model_metadata_cache_model_metadata_cache_timei_endpoint_model_metadata_cache#_endpoint_model_metadata_cache_timei,)i}i>i@rxzclaude-opus-4-7i@Bzclaude-opus-4.7zclaude-opus-4-6zclaude-sonnet-4-6zclaude-opus-4.6zclaude-sonnet-4.6r?i@ gpt-5.5iz gpt-5.4-nano gpt-5.4-minigpt-5.4z gpt-5.1-chatrwgpt-5zgpt-4.1izgpt-4rAizgemma-4rvgemma4z gemma-4-31bzgemma-3igemmai zdeepseek-v4-prozdeepseek-v4-flashz deepseek-chatzdeepseek-reasonerrNllamazqwen3-coder-plusz qwen3-coderir:rKi r/izgrok-code-fastz grok-4-1-fastiz grok-2-visionz grok-4-fastz grok-4.20zgrok-4zgrok-3zgrok-2r5r7z hy3-previewrRtrinityelephantzQwen/Qwen3.5-397B-A17BzQwen/Qwen3.5-35B-A3Bzdeepseek-ai/DeepSeek-V3.2izmoonshotai/Kimi-K2.5zmoonshotai/Kimi-K2.6) zmoonshotai/Kimi-K2-ThinkingzMiniMaxAI/MiniMax-M2.5zXiaomiMiMo/MiMo-V2-Flashz mimo-v2-proz mimo-v2.5-proz mimo-v2.5z mimo-v2-omniz mimo-v2-flashz zai-org/GLM-5) context_lengthcontext_windowmax_context_lengthmax_position_embeddings max_model_lenmax_input_tokensmax_sequence_length max_seq_len n_ctx_trainn_ctxctx_size)max_completion_tokensmax_output_tokens max_tokens) localhostz 127.0.0.1z::1z0.0.0.0)z.docker.internalz.containers.internalz.lima.internalbase_urlcT|pddS)N/)rjrstriprs r_normalize_base_urlr s& N ! ! # # * *3 / //rrapi_keyc^t|pd}|siSdd|iS)Nr AuthorizationBearer )strrj)rtokens r _auth_headersrs@  2   $ $ & &E  .u.. //rc"t|dS)N openrouter.ai)r rs r_is_openrouter_base_urlrs ? ; ;;rc^t|}t|ot| SN)rboolr)r normalizeds r_is_custom_endpointrs.$X..J    G$;J$G$G GGrzapi.openai.comopenaiz chatgpt.comapi.anthropic.comrUzapi.z.air3zopen.bigmodel.cnzapi.moonshot.air[zapi.moonshot.cnr`z api.kimi.comzapi.stepfun.airLzapi.stepfun.comz api.arcee.air;z api.minimaxzdashscope.aliyuncs.comrHzdashscope-intl.aliyuncs.comzportal.qwen.airYrrWz!generativelanguage.googleapis.comr9rJ fireworksr\r2rDrGr0rar]) zinference-api.nousresearch.comzapi.deepseek.comzapi.githubcopilot.comzmodels.github.aizapi.fireworks.aiz opencode.aizapi.x.aizintegrate.api.nvidia.comzapi.xiaomimimo.comzxiaomimimo.comzapi.gmi-serving.comztokenhub.tencentmaas.comz ollama.com_URL_TO_PROVIDERct|}|sdStd|vr|nd|}|jp|j}t D] \}}||vr|cSdS)aInfer the models.dev provider name from a base URL. This allows context length resolution via models.dev for custom endpoints like DashScope (Alibaba), Z.AI, Kimi, etc. without requiring the user to explicitly set the provider name in config. N://zhttps://)rrnetlocrkrritems)rrparsedhosturl_partproviders r_infer_provider_from_urlrBs%X..J t EZ$7$7jj=T =T=T U UF =   7FK$5$5$7$7D.4466( t  OOO  4rc$t|duSr)rrs r_is_known_provider_base_urlrTs #H - -T 99rc t|}|sdSd|vr|nd|} t|}|jpdn#t$rYdSwxYwtvrdSt fdt DrdS tj}|j s|j s|j rdSt|tj r |tvrdSn#t$rYnwxYwd}t#|dkr t%|d t%|d }}|d krdS|d krd |cxkrdkrnndS|dkr|dkrdS|dkrd|cxkrdkrnndSn#t$rYnwxYwdS)aReturn True if base_url points to a local machine. Recognises loopback (``localhost``, ``127.0.0.0/8``, ``::1``), container-internal DNS names (``host.docker.internal`` et al.), RFC-1918 private ranges (``10/8``, ``172.16/12``, ``192.168/16``), link-local, and Tailscale CGNAT (``100.64.0.0/10``). Tailscale CGNAT is included so remote-but-trusted Ollama boxes reached over a Tailscale mesh get the same timeout auto-bumps as localhost Ollama. Frzhttp://rTc3BK|]}|VdSr)endswith).0rors r z$is_local_endpoint..ns/ I IV4== I I I I I Ir.rrg d@)rrhostname Exception _LOCAL_HOSTSany_CONTAINER_LOCAL_SUFFIXES ipaddress ip_address is_private is_loopback is_link_local isinstance IPv4Address_TAILSCALE_CGNAT ValueErrorrilenint) rrurlraddrpartsfirstsecondrs @ris_local_endpointrXs%X..J u++**1G:1G1GC#$" uu |t I I I I/H I I IIIt #D)) ? d. $2D 4 dI1 2 2 t?O7O7O4       JJsOOE 5zzQ aMM3uQx==6E{{t||f 2 2 2 2 2 2 2 2 2t||# t||f 3 3 3 3 3 3 3 3 3t    D  5sK: AA9)C $#C CC0E45E4 E4E44 FFcddl}t|}|}|dr |dd}t|} |d|5} ||d}|jdkr dddd Sn#t$rYnwxYw ||d }|jdkr8 |}d |vr dddd Sn#t$rYnwxYwn#t$rYnwxYw ||d }|jdkr||d}|jdkrd|j vr ddddSn#t$rYnwxYw ||d}|jdkr&|}d|vr ddddSn#t$rYnwxYwdddn #1swxYwYn#t$rYnwxYwdS)zDetect which local server is running at base_url by probing known endpoints. Returns one of: "ollama", "lm-studio", "vllm", "llamacpp", or None. rN/v1g@timeoutheaders/api/v1/models lm-studioz /api/tagsmodelsrE /v1/props/propsdefault_generation_settingsllamacppz/versionversionvllm) httpxrrrClientget status_coderjsontext) rrrr server_urlrclientrdatas rdetect_local_server_typers` LLL$X..JJ5!!%_ G$$G* \\#w\ 7 7' 6 JJ*<<<===C''& ' ' ' ' ' ' ' ' (     JJ*77788=C'' vvxx#t++#+#' ' ' ' ' ' ' '  ,$     JJ*77788=C'' j#8#8#899A=C'',IQV,S,S%9' ' ' ' ' ' ' ' :     JJ*66677=C''6688D D((%K' ' ' ' ' ' ' ' L    M' ' ' ' ' ' ' ' ' ' ' ' ' ' ' P       4sG/G##B G/G# BG#BG#!#C=C, G/+C=, C96C=8C99C=<G#= D G# D  G#AE, G/+G#, E96G#8E99G#=;G9 G/G# GG#GG# G/#G''G/*G'+G// G<;G<valuec#Kt|tr2|V|D]}t|Ed{VdSt|tr|D]}t|Ed{VdSdSr)rdictvalues_iter_nested_dictslist)rnesteditems rrrs%0 llnn 2 2F)&11 1 1 1 1 1 1 1 1 2 2 E4 0 0 0D)$// / / / / / / / /00 0 0r逖minimummaximumc$ t|trdSt|tr(|dd}t |}n#t tf$rYdSwxYw||cxkr|krnn|SdS)N,r)rrrrjreplacer TypeErrorr)rrrresults r_coerce_reasonable_intr s eT " " 4 eS ! ! 3KKMM))#r22EU z "tt&####G##### 4sA&A A&&A;:A;payloadkeys.cd|D}t|D]W}|D]@\}}t||vr)t |}||ccSAXdS)Nc6h|]}|S)rk)rkeys r z%_extract_first_int..s * * *cciikk * * *r)rrrrkr )r r keysetmappingrrcoerceds r_extract_first_intrs * *T * * *F%g..!--//  JC3xx~~v--,U33G"#   4rc,t|tSr)r_CONTEXT_LENGTH_KEYSr s r_extract_context_lengthr g'; < <z$_extract_pricing..s.PPP*#uc#hhnn&&PPPrc3NK|]}tfd|DV dS)c3 K|]}|vV dSrr)raliasrs rrz-_extract_pricing...s(@@uu *@@@@@@rN)r)raliasesrs rrz#_extract_pricing..s@ccW3@@@@@@@@@ccccccr)Nr)rrrr)r  alias_maprpricingtargetr5r4rs @r_extract_pricingr9sR`.fk I&g..  PP PPP ccccPYP`P`PbPbccccc  "$(00  OFG   J&&:e+2)F)F)J)JKbdh)i)i &(33 99Y33 E uh 6 6 6 "2B77I .sVJq$4G4Gj!!Z/rrrrrr model_aliasz1Failed to fetch model metadata from %s/models: %s)rrrtrrurH_ENDPOINT_MODEL_CACHE_TTLrrappendrrrJrrKrrrrrr9r@rrrrrokrLrM)#rrrArcached cached_at candidates alternater last_errorrrPr r:rcr;r<rinstcfgctxrr7alt_idexc candidater is_llamacppbase_verify props_respprops gen_settingsrr]s# rfetch_endpoint_model_metadatarr7s#%X..J 0<< /33J??7;;JJJ  49;;#:>W"W"WMJ5!!'ssO**3// & %Yj00)$$$8?G 3' 3 344RG&*J$$21 ' GDDD SS>>"YYt__F!&#..A6Af>P>P*5&%@@@=B.z:BF)++3J? ]T^   JJJJJJ  44 s##i/2 |C"MeMgMghhhH  % % ' ' 'mmooG/1E VR00 ; ;!%.. 99T??)/681L1L(M!8!?!?!-.Bikk / ;LLL   JJJJJJ b H*V`aaa13":.6:ikk' 3 IsW1I%M M."M))M.D/W?C#V#"W# V0-W/V00)W W3&W..W3ct||}||}|sht|dkr/tt |}n&|D]\}}||vs||vr|}n|r,|d}t|tr|SdS)zDResolve context length from an endpoint's live ``/models`` metadata.rUrgrN) rrrrnextiterrrrr)rcrrendpoint_metadatamatchedrr<rs r _resolve_endpoint_context_lengthrxs 6hPPP##E**G   ! !Q & &4 1 8 8 : :;;< context_length cache from disk.Ncontext_lengthsz'Failed to load context length cache: %s) r}existsopenyaml safe_loadrrrLrM)rfrrRs r_load_context_cachers " $ $D ;;==  $ZZ +1>!$$*D + + + + + + + + + + + + + + +xx)2...  >BBB s@A9A A9AA9A A99 B*B%B*%B*lengthc|d|}t}|||krdS|||<t} |jddt |d5}t jd|i|ddddn #1swxYwYt d ||d dS#t$r&}t d |Yd}~dSd}~wwxYw) zPersist a discovered context length for a model+provider combo. Cache key is ``model@base_url`` so the same model name served from different providers can have different limits. @NTparentsexist_okwrFdefault_flow_stylez%Cached context length %s -> %s tokensrz'Failed to save context length cache: %s) rrr}parentmkdirrrdumprLinforrM)rcrrrr:rrrRs rsave_context_lengthrsi   X  C  ! !E yy~~E#J " $ $DC $666 $__ O I(%0! N N N N O O O O O O O O O O O O O O O ;SV--PPPPP CCC >BBBBBBBBBCs<,C1B CBCB!C C2 C--C2cV|d|}t}||S)zBLook up a previously discovered context length for model+provider.r)rr)rcrrr:s rget_cached_context_lengthrs0   X  C  ! !E 99S>>rc|d|}t}||vrdS||=t} |jddt |d5}t jd|i|dddddS#1swxYwYdS#t$r'}t d ||Yd}~dSd}~wwxYw) zCDrop a stale cache entry so it gets re-resolved on the next lookup.rNTrrrFrz6Failed to invalidate context length cache entry %s: %s) rr}rrrrrrrLrM)rcrrr:rrrRs r!_invalidate_cached_context_lengthrsO   X  C  ! !E % c " $ $DW $666 $__ O I(%0! N N N N O O O O O O O O O O O O O O O O O O WWW MsTUVVVVVVVVVWs;,BB4 BBBB B B?B::B?current_lengthc.tD] }||kr|cS dS)z@Return the next lower probe tier, or None if already at minimum.N)CONTEXT_PROBE_TIERS)rtiers rget_next_probe_tierrs/# . KKK ! 4r error_msgc|}gd}|D]O}tj||}|r6t|d}d|cxkrdkrnK|cSPdS)a?Try to extract the actual context limit from an API error message. Many providers include the limit in their error text, e.g.: - "maximum context length is 32768 tokens" - "context_length_exceeded: 131072" - "Maximum context size 32768 exceeded" - "model's max context length is 65536" )zY(?:max(?:imum)?|limit)\s*(?:context\s*)?(?:length|size|window)?\s*(?:is|of|:)?\s*(\d{4,})z:context\s*(?:length|size|window)\s*(?:is|of|:)?\s*(\d{4,})z)(\d{4,})\s*(?:token)?\s*(?:context|limit)z">\s*(\d{4,})\s*(?:max|limit|token)z(\d{4,})\s*(?:max(?:imum)?)\brgrrNrkresearchrgroup)r error_lowerpatternspatternrmlimits rparse_context_limit_from_errorr&s//##KH ';//   A''Eu**** ***** 4rc|}d|vod|vpd|v}|sdSgd}|D]E}tj||}|r,t|d}|dkr|cSFdS)u#Detect an "output cap too large" error and return how many output tokens are available. Background — two distinct context errors exist: 1. "Prompt too long" — the INPUT itself exceeds the context window. Fix: compress history and/or halve context_length. 2. "max_tokens too large" — input is fine, but input + requested_output > window. Fix: reduce max_tokens (the output cap) for this call. Do NOT touch context_length — the window hasn't shrunk. Anthropic's API returns errors like: "max_tokens: 32768 > context_window: 200000 - input_tokens: 190000 = available_tokens: 10000" Returns the number of output tokens that would fit (e.g. 10000 above), or None if the error does not look like a max_tokens-too-large error. ravailable_tokenszavailable tokensN)zavailable_tokens[:\s]+(\d+)zavailable\s+tokens[:\s]+(\d+)z =\s*(\d+)\s*$rgr)rris_output_cap_errorrrrmtokenss r(parse_available_output_tokens_from_errorrBs //##K  # U ; . S2D 2S tH  ';//  Q((F{{ 4r candidate_id lookup_modelcb||krdSd|vr"|ddd|krdSdS)aReturn True if *candidate_id* (from server) matches *lookup_model* (configured). Supports two forms: - Exact match: "nvidia-nemotron-super-49b-v1" == "nvidia-nemotron-super-49b-v1" - Slug match: "nvidia/nvidia-nemotron-super-49b-v1" matches "nvidia-nemotron-super-49b-v1" (the part after the last "/" equals lookup_model) This covers LM Studio's native API which stores models as "publisher/slug" while users typically configure only the slug after the "local:" prefix. TrrgF)rsplit)rrs r_model_id_matchesrmsH|##t l|223::1=MMt 5rc@ddl}t|}|d}|dr |dd} t ||}n#t $rYdSwxYw|dkrdSt |} |d| 5}||d d |i } | j d kr ddddS| } | dd} d| vr| dD]s} d| vrm| } t| dkr4 t| dccdddS#t $rYowxYwt| di}|D]B\}}d|vr9t%|tt&frt|ccdddSC dddn #1swxYwYn#t $rYnwxYwdS)ayQuery an Ollama server for the model's context length. Returns the model's maximum context from GGUF metadata via ``/api/show``, or the explicit ``num_ctx`` from the Modelfile if set. Returns None if the server is unreachable or not Ollama. This is the value that should be passed as ``num_ctx`` in Ollama chat requests to override the default 2048. rNrrrrUrE@r /api/showrFrr parametersrnum_ctx  model_infor)rrqrrrrrrpostrrrrirjrrrrrfloat)rcrrrr?r server_typerrresprparamslinerrrrs rquery_ollama_num_ctxrsLLL'..J%%J5!!%_ .xIII tthtG$$G \\#w\ 7 7 &6;;*777vz>R;SSD3&& & & & & & & & &99;;DXXlB//FF"""LL..%%D D(( $ 2 2 4 4u::??%'*59~~ 5 5 & & & & & & & &$.%%% $%,33J(..00 & & U#s**z%#u/N/N*u::%%- & & & & & & & &( &) & & & & & & & & & & & & & & &.      4s A A)(A)H)H HBHE7(H* H7 FHFA#H' H4H6 HHH H H HHc ddl}t|}|d}|dr |dd}t |} t ||}n#t $rd}YnwxYw |d|5}|d krL||d d |i }|j d kr$| } | dd} d| vr| dD]s} d| vrm| } t| dkr4 t| dccdddS#t $rYowxYwt| di} | D]B\}}d|vr9t%|tt&frt|ccdddSC|dkr| |d}|j d kr| } | dgD]}t)| dd|s$t)| dd|r| dgD]j}| di}| d}|r;t%|tt&frt|cccdddSkn| |d|}|j d kr| } | dp)| dp| d}|r7t%|tt&frt|cdddS| |d }|j d kr| } | d!g}|D]}t)| dd|rz| dp)| dp| d}|r9t%|tt&frt|ccdddSdddn #1swxYwYn#t $rYnwxYwdS)"z4Query a local server for the model's context length.rNrrrrUrrrErrFrrrrrrrrrrrrrrrDrWrXz /v1/models/rrz /v1/modelsr)rrqrrrrrrrrrrrirjrrrrrrr)rcrrrrrrrrrrrrrrrr[rfrgrh models_lists r_query_local_context_lengthrs#LLL #5 ) )E%%J5!!%_ G$$G.xIII  E \\#w\ 7 7B ,6h&&{{j#;#;#;65/{RR#s**99;;D"XXlB77F F**$*LL$6$6--D(D00(, (:(:(<(<#&u::??%-/259~~(=(='B ,B ,B ,B ,B ,B ,B ,B ,(,6%-%-%-(,%-"&,!;!;J&0&6&6&8&8.. U+s22z%#u7V7V2#&u::--5B ,B ,B ,B ,B ,B ,B ,B ,Bk))zzZ"?"?"?@@#s**99;;D!XXh33"",QUU5"-=-=uEE"IZ[\[`[`aegi[j[jlqIrIr"().@"(E(E44&*hhx&<&<&)gg.>&?&?#&!4:cC<+H+H!4+.s88OOOOYB ,B ,B ,B ,B ,B ,B ,B ,Z"E"::????@@D3&&yy{{hh//g488N8O8OfSTSXSXYeSfSf,:cC<#@#@,#&s88OOEB ,B ,B ,B ,B ,B ,B ,B ,B ,B ,B ,B ,B ,B ,B ,B ,B ,B ,B ,B ,B ,B ,B ,F       4sA** A98A9=SB2R7E*R7 S* E74R76E77A#R7 S'DR79 SB(R7. S;C"R7 S*R7+ S7R;;S>R;?S SSc.|ddS)zNormalize version separators for matching. Nous uses dashes: claude-opus-4-6, claude-sonnet-4-5 OpenRouter uses dots: claude-opus-4.6, claude-sonnet-4.5 Normalize both to dashes for comparison. r-)r)rcs r_normalize_model_versionrs ==c " ""rcr|r|drdS |d}|dr |dd}|d}|dd}tj||d t }|jd krdS|}|d gD]O}|d |kr4|d} t| tr | dkr| cSPn2#t$r%} t d| Yd} ~ nd} ~ wwxYwdS)zQuery Anthropic's /v1/models endpoint for context length. Only works with regular ANTHROPIC_API_KEY (sk-ant-api*). OAuth tokens (sk-ant-oat*) from Claude Code return 401. z sk-ant-oatNrrrz/v1/models?limit=1000z 2023-06-01)z x-api-keyzanthropic-versionrrVrrrDrrz%Anthropic /v1/models query failed: %s) rhrrrJrrrrrrrrLrM) rcrrrmrrrrr[rhrRs r_query_anthropic_context_lengthrsz g((66tAs## ==   9D,,, !-  |C"E]E_E_```  s " "4yy{{&"%%  AuuT{{e##ee.//c3''C!GGJJJ   AAA  &>&>?+--      s " " LLZ    Iyy{{  5s;;; )34(>(>Fdhhx$$$BGF''$%%  xxhh'(( dC  'ZS%9%9 'cAgg#&F4::<<  .%+"*-' Ms$AB! B!! C+C C Cct|}|sdS|ret|}||vr||S|}|D]!\}}||kr|cS"|}t t ddD] \}}||vr|cSdS)zResolve a Codex OAuth model's real context window. Prefers a live probe of chatgpt.com/backend-api/codex/models (when we have a bearer token), then falls back to ``_CODEX_OAUTH_CONTEXT_FALLBACK``. Nc,t|dSNrrxs rz5_resolve_codex_oauth_context_length..sS1YYrTrreverse)rqrjrrkrsortedr)rcr model_barelive model_lowerrrhs r#_resolve_codex_oauth_context_lengthrs(..4466J t1,??    # # &&((   ID#zz||{** +""$$K%++--3F3FPT c ;  JJJ  4rct}||vr||dSt|}|D]\}}d|vr|dddn|}||ks%t||kr|dcS|}|D]\}}d|vr|dddn|}||ft||ffD]j\}}||rPt|t|ks|t|dvr|dccSkdS)uResolve Nous Portal model context length via OpenRouter metadata. Nous model IDs are bare (e.g. 'claude-opus-4-6') while OpenRouter uses prefixed IDs (e.g. 'anthropic/claude-opus-4.6'). Try suffix matching with version normalization (dot↔dash). rrrgz-:.N)rSrrrkrrirhr) rcmetadataror_idr<barerrkquerys r_resolve_nous_context_lengthrs$%%H ""#3444)%006688J ((// u),u{{3""1%%5 ::<<5;;== ( (,DT,J,J,P,P,R,RV`,`,`99-.. . . .-a ++--K ((33 u),u{{3""1%%5"&**,, !r s 3 3 Iu##E** 3I#e**,, #e**0E0N0Nyy!12222222  3 4rconfig_context_lengthrcustom_providersc|t|tr|dkr|S|r.|r,|r* ddlm}||||}|r|Sn#t$rYnwxYwt |}|rV|dkrPt ||}|>|dkr6|dkr0td|||d t||n|S|d ks4|rTt| d r2t|d r" dd l m} | |S#t$rYnwxYwt!|rt#|st%|||} | | St#|smt'|r3t)|||} | r| dkr|dkrt+||| | Std||t,d t,S|dks|r*t|dkrt/||pd|} | r| S|} | r| dvr|rt1|}|r|} | dvr) ddlm}|||} | r| Sn#t$rYnwxYw| dkrt7|} | r| S| dkr*t9||pd}|r|rt+||||S| dkr|rt%|||} | | S| rddlm}|| |} | r| St?}||vr!|| dt,S|!}tEtF$ddD] \}}||vr|cS|rBt'|r3t)|||} | r| dkr|dkrt+||| | St,S)aGet the context length for a model. Resolution order: 0. Explicit config override (model.context_length or custom_providers per-model) 1. Persistent cache (previously discovered via probing) 1b. AWS Bedrock static table (must precede custom-endpoint probe) 2. Active endpoint metadata (/models for explicit custom endpoints) 3. Local server query (for local endpoints) 4. Anthropic /v1/models API (API-key users only, not OAuth) 5. OpenRouter live API metadata 6. Nous suffix-match via OpenRouter cache 7. models.dev registry lookup (provider-aware) 8. Thin hardcoded defaults (broad family patterns) 9. Default fallback (256K) Nr)"get_custom_provider_context_length)rcrrlmstudior^rzzaDropping stale Codex cache entry %s@%s -> %s (pre-fix value); re-resolving via live /models proberbedrockzbedrock-runtime.z amazonaws.com)get_bedrock_context_lengthrUuCould not detect context length for model %r at %s — defaulting to %s tokens (probe-down). Set model.context_length in config.yaml to override.rUrzhttps://api.anthropic.com)rWr@)rJrZr_)get_copilot_model_contextr9r)rr0)lookup_models_dev_contextrc,t|dSrrrs rrz*get_model_context_length..ss1Q4yyrTr)%rrhermes_cli.configrrrqrrLrrr rhr agent.bedrock_adapterr ImportErrorrrrxrrrDEFAULT_FALLBACK_CONTEXTrrhermes_cli.modelsrrragent.models_devrrSrrkrDEFAULT_CONTEXT_LENGTHSr)rcrrrrrrcp_ctxrarr local_ctxrheffective_providerinferredr codex_ctxrrr default_modelrs rget_model_context_lengthrs0(Z8Ms-S-S(XmpqXqXq$$  H    L L L L L L77!!1F        D  #5 ) )E H ***5(;;  >))f.?.? :8]] 2%BBBB 9 h ' ' 2 23E F F "(O < <   H H H H H H--e44 4    D 8$$,-H-R-R,9%SZ[[[  %! !*844 , ** %7xQXYYY %Q:--+E8YGGG$$ KK.x$>>>>>''(:EBB  J$%%H ""#35MNNN ++--K!'%%''-@-@$""" v K ' 'MMM (%h///xQQQ  Q:%%#E8Y???  $#s5A A  A 2D DDH// H<;H<rc4|sdSt|dzdzS)aRough token estimate (~4 chars/token) for pre-flight checks. Uses ceiling division so short texts (1-3 chars) never estimate as 0 tokens, which would cause the compressor and pre-flight checks to systematically undercount when many short tool results are present. rrr)rs restimate_tokens_roughrs& q IIMa rmessagescDtd|D}|dzdzS)z:Rough token estimate for a message list (pre-flight only).c3NK|] }tt|V!dSrrrrmsgs rrz1estimate_messages_tokens_rough..s.88c#c((mm888888rrr)sum)r total_charss restimate_messages_tokens_roughr s-88x88888K !O !!r) system_prompttoolsr rcd}|r|t|z }|r|td|Dz }|r|tt|z }|dzdzS)u<Rough token estimate for a full chat-completions request. Includes the major payload buckets Hermes sends to providers: system prompt, conversation messages, and tool schemas. With 50+ tools enabled, schemas alone can add 20-30K tokens — a significant blind spot when only counting messages. rc3NK|] }tt|V!dSrrrs rrz0estimate_request_tokens_rough..s.==S3s3xx========rrr)rr r)rr rr s restimate_request_tokens_roughrsyK*s=))) >s==H======  's3u::& !O !!r)r)rr)F)rF)rrNrN)b__doc__rrNrrrHpathlibrtypingrrrr urllib.parserrJrutilsr r r|r getLogger__name__rLrrr frozensetrb__annotations__compile IGNORECASErl IPv4NetworkrrqrrrsrrIrtrur^rrMINIMUM_CONTEXT_LENGTHrrrrrrrrrrrrrrrrr tuplerrrr9r@rSrrrxr}rrrrrrrrrrrrrrrrrrrrrrr rrrrr s  ,,,,,,,,,,,,!!!!!! ::::::::222222  8 $ $$**&/Y000&&IcN4!bjLM)9(99##&46tCc3h/0555$%E%%%GIS$sDcN/B*C%C DIII8:#T#u*%5::: /q1   c w c w cwccwcc fc&w'c(F)c*F+c,w-c.F/c0 V1c2w3c4 V5c8 g9c<v=cc> f?c@6AcBvCcD TEcTyUcVWcXYYcZ[c\]c` Vacfgch6icj Fkcpvqct 6ucBfCcDWEcccFTGcH7IcJKcL fMcN fOcP fQcR FScV FWcZ6[c^_cbvccfgcjfkclFmcn ocpFqcrFscct$*$ &EcccJ < 0#0#00000030S#X0000>Q9R!+!+!+!+LMMM MM #tCH~  MMMMf c] .;;;;; T#s(^    CsCcC3C4CCCC*SCHSM WS WC WD W W W W  chsm8(( ((((VCst&444s4S4(SV-4444n[[s[c[C[QYZ]Q^[[[[|#C#C####3#PXY\P]P!!  1 1tCH~   .0DcN///),,,,!%0S0T#s(^0000h%' ! c]B F(,$( J$J$ J$J$J$: J$  J$ Tk J$ J$J$J$J$Z         "T$sCx.-A"c"""",0 """4S>""" Dc3h( ) "  """"""r