UNPKG

@bitkyc08/opencodex

Version:

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM with Codex CLI/App/SDK and Claude Code

214 lines (202 loc) • 9.93 kB
/** * Add registry models to a saved roster that is still the previous registry seed. * * `enrichProviderFromRegistry` copies the registry's `models` only when a row has none, so * every config saved while an older roster was current keeps that roster forever. That is * the right posture for a hand-edited list and the wrong one for an untouched seed: a model * the vendor added never reaches the install, and when the vendor's live `/models` roster * does not list it either, nothing else can surface it. * * This rewrites one thing: a saved `models` list that is still byte-for-byte the roster * this file names as `from`, on a provider that still carries the registry adapter, and * only while the registry currently seeds `to`. A list the user changed does not match and * is left alone. For each added id it also fills a per-model context window, output limit * and default effort, but only inside a container the row already has: enrichment fills * those records all-or-nothing, so creating one here would hide the rest of the registry seed. * Same shape and restraint as `stale-context-window-migration`. */ import { ALIBABA_INTL_TOKEN_PLAN_BASE_URL, MOONSHOT_CN_BASE_URL, MOONSHOT_INTL_BASE_URL } from "./base-url-choices"; import { PROVIDER_REGISTRY, normalizedProviderEndpoint } from "./registry"; import { ALIBABA_TOKEN_PLAN_MODELS, ALIBABA_INTL_TOKEN_PLAN_MODELS, ALIBABA_TOKEN_PLAN_CONTEXT_WINDOWS, ALIBABA_TOKEN_PLAN_MAX_OUTPUT_TOKENS, KIMI_API_DEFAULT_REASONING_EFFORTS, KIMI_API_MODEL_CONTEXT_WINDOWS, KIMI_API_MODELS, KIMI_API_MODELS_BEFORE_K31, META_MODEL_API_MODELS, META_MUSE_CONTEXT_WINDOW, META_MUSE_MODELS, META_MUSE_WONDER_MODEL, MINIMAX_M31_DEFAULT_REASONING_EFFORT, MINIMAX_M31_FLASH, MINIMAX_M31_FLASH_MAX_OUTPUT_TOKENS, MINIMAX_MODELS, MINIMAX_MODELS_BEFORE_M31, MINIMAX_MODEL_CONTEXT_WINDOWS, } from "./registry/model-seeds"; import type { OcxConfig } from "../types"; import { modelRecordValue } from "../reasoning-effort"; export interface StaleModelRoster { /** Registry provider id whose saved rows may carry the old roster. */ provider: string; /** The exact saved roster this migration may replace, and nothing else. */ from: readonly string[]; /** Exact old roster after id renames; metadata additions still compare against `from`. */ afterModelRenames?: readonly string[]; to: readonly string[]; /** Per-model seed values for the added ids, written only into containers that exist. */ contextWindows?: Readonly<Record<string, number>>; /** * Custom catalog rows read the saved map directly, so an added id missing from a * partial map would publish without the registry output limit. */ maxOutputTokens?: Readonly<Record<string, number>>; defaultReasoningEfforts?: Readonly<Record<string, string>>; /** * For a provider whose saved URL may point elsewhere (pay-as-you-go or Custom), the * destinations whose roster `to` describes. A row on any other URL keeps its list; a row * with no saved URL uses the registry default and is refreshed. */ destinationBaseUrls?: readonly string[]; } export interface StaleModelRosterProjection { config: OcxConfig; changed: boolean; warnings: string[]; } const ALIBABA_TOKEN_PLAN_MODELS_BEFORE_1017 = [ "qwen3.8-max", "qwen3.8-flash", "qwen3.7-max", "qwen3.7-plus", "qwen3.6-flash", "deepseek-v4-pro", "deepseek-v4-flash-0731", "deepseek-v4.1-flash", "glm-5.2", "glm-5.3", ]; const ALIBABA_INTL_TOKEN_PLAN_MODELS_BEFORE_1017 = [ "qwen3.8-max", "qwen3.8-flash", "qwen3.7-max", "qwen3.7-plus", "qwen3.6-plus", "qwen3.6-flash", "deepseek-v4-pro", "deepseek-v4-pro-0813", "deepseek-v4-flash", "deepseek-v4-flash-0731", "deepseek-v4.1-flash", "deepseek-v3.2", "kimi-k2.7-code", "kimi-k2.6", "kimi-k2.5", "glm-5.2", "glm-5.3", "glm-5.1", "glm-5", "MiniMax-M2.5", ]; /** * MiniMax-M3.1-Flash (2026-10-21). MiniMax's /v1/models roster does not list the * Flash, so live discovery cannot add it; the catalog keeps it only when it is configured. */ export const STALE_MODEL_ROSTERS: readonly StaleModelRoster[] = [ { provider: "meta-model", from: META_MUSE_MODELS, to: META_MODEL_API_MODELS, contextWindows: { [META_MUSE_WONDER_MODEL]: META_MUSE_CONTEXT_WINDOW }, // A Custom row may keep this id pointed at another gateway // (preserveCustomDestination); only api.meta.ai publishes the roster `to` describes. destinationBaseUrls: ["https://api.meta.ai/v1"], }, { provider: "deepseek", from: ["deepseek-chat", "deepseek-reasoner", "deepseek-flash", "deepseek-v4-flash", "deepseek-v4-flash-vision-exp"], to: ["deepseek-chat", "deepseek-reasoner", "deepseek-flash", "deepseek-v4-flash", "deepseek-v4-pro", "deepseek-v4-flash-vision-exp"], contextWindows: { "deepseek-v4-pro": 1_048_576 }, destinationBaseUrls: ["https://api.deepseek.com", "https://api.deepseek.com/v1"], }, ...["minimax", "minimax-cn"].map(provider => ({ provider, from: MINIMAX_MODELS_BEFORE_M31, to: MINIMAX_MODELS, contextWindows: { [MINIMAX_M31_FLASH]: MINIMAX_MODEL_CONTEXT_WINDOWS[MINIMAX_M31_FLASH]! }, maxOutputTokens: { [MINIMAX_M31_FLASH]: MINIMAX_M31_FLASH_MAX_OUTPUT_TOKENS }, defaultReasoningEfforts: { [MINIMAX_M31_FLASH]: MINIMAX_M31_DEFAULT_REASONING_EFFORT }, // #7807: Custom destinations keep their roster and partial metadata maps. destinationBaseUrls: ["https://api.minimax.io/v1", "https://api.minimaxi.com/v1", "https://api.minimax.cn/v1"] .flatMap(url => [url, `${url}/chat/completions`]), })), ...[ { provider: "alibaba-token-plan", from: ALIBABA_TOKEN_PLAN_MODELS_BEFORE_1017, to: ALIBABA_TOKEN_PLAN_MODELS }, // International honors pay-as-you-go and Custom URLs, which may still serve the retired ids. // Beijing needs no guard: the router pins it to the registry Token Plan host. { provider: "alibaba-token-plan-intl", from: ALIBABA_INTL_TOKEN_PLAN_MODELS_BEFORE_1017, to: ALIBABA_INTL_TOKEN_PLAN_MODELS, destinationBaseUrls: [ALIBABA_INTL_TOKEN_PLAN_BASE_URL], }, ].map(entry => ({ ...entry, contextWindows: ALIBABA_TOKEN_PLAN_CONTEXT_WINDOWS, maxOutputTokens: ALIBABA_TOKEN_PLAN_MAX_OUTPUT_TOKENS, defaultReasoningEfforts: { "deepseek-v4.1-flash-1017": "high" }, })), // Kimi K3.1 Pro (#7653). Both the International and China platforms list kimi-k3.1-pro and // -highspeed; a Custom URL may be another gateway, so it keeps its saved list. { provider: "moonshot", from: KIMI_API_MODELS_BEFORE_K31, afterModelRenames: KIMI_API_MODELS_BEFORE_K31.map(id => id === "kimi-k2.5" ? "kimi-k3.1-pro" : id), to: KIMI_API_MODELS, contextWindows: KIMI_API_MODEL_CONTEXT_WINDOWS, defaultReasoningEfforts: KIMI_API_DEFAULT_REASONING_EFFORTS, destinationBaseUrls: [MOONSHOT_INTL_BASE_URL, MOONSHOT_CN_BASE_URL], }, ]; function sameList(value: unknown, expected: readonly string[]): boolean { return Array.isArray(value) && value.length === expected.length && value.every((item, index) => item === expected[index]); } function registrySeeds(provider: string, adapter: unknown, roster: readonly string[]): boolean { const entry = PROVIDER_REGISTRY.find(row => row.id === provider); return entry !== undefined && entry.adapter === adapter && sameList(entry.models, roster); } function servesRoster(baseUrl: unknown, destinations: readonly string[] | undefined): boolean { if (!destinations || baseUrl === undefined || baseUrl === "") return true; if (typeof baseUrl !== "string") return false; const saved = normalizedProviderEndpoint(baseUrl); return destinations.some(url => normalizedProviderEndpoint(url) === saved); } function fillExisting<T>(container: Record<string, T> | undefined, values: Readonly<Record<string, T>> | undefined, ids: readonly string[]): boolean { if (!container || !values) return false; let filled = false; for (const id of ids) { const value = values[id]; if (value !== undefined && modelRecordValue(container, id) === undefined) { container[id] = value; filled = true; } } return filled; } /** Pure projection. The caller decides whether to persist. */ export function projectStaleModelRosters( config: OcxConfig, entries: readonly StaleModelRoster[] = STALE_MODEL_ROSTERS, ): StaleModelRosterProjection { const warnings: string[] = []; let changed = false; for (const entry of entries) { const prov = config.providers?.[entry.provider]; if (!prov) continue; if (!registrySeeds(entry.provider, prov.adapter, entry.to)) continue; if (!servesRoster(prov.baseUrl, entry.destinationBaseUrls)) continue; const added = entry.to.filter(id => !entry.from.includes(id)); if (sameList(prov.models, entry.to)) { // A row refreshed before output limits joined the refresh still has a partial map. // Only that record is revisited: the earlier pass already filled windows and efforts, // so refilling them could restore a key the operator has since removed. if (fillExisting(prov.modelMaxOutputTokens, entry.maxOutputTokens, added)) { changed = true; warnings.push(`filled output limits for ${added.join(", ")} on the saved "${entry.provider}" row.`); } continue; } if (!sameList(prov.models, entry.from) && !(entry.afterModelRenames && sameList(prov.models, entry.afterModelRenames))) continue; prov.models = [...entry.to]; fillExisting(prov.modelContextWindows, entry.contextWindows, added); fillExisting(prov.modelMaxOutputTokens, entry.maxOutputTokens, added); fillExisting(prov.modelDefaultReasoningEfforts, entry.defaultReasoningEfforts, added); changed = true; warnings.push( `added ${added.join(", ")} to the saved "${entry.provider}" model list, which was still ` + "the previous registry seed.", ); } return { config, changed, warnings }; }