@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
text/typescript
/**
* 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 };
}