fix(custom-model): core review fixes for context-length discovery and injection

- share one context-length resolution (discovered figure, endpoint default fallback) across the routes and boot recovery, with a recovery test
- record listed per-slot context figures with a slot count of 1 and force the slot-count fallback once per rediscovery
- open up the codex model launch token for qwen3-style ids (model-plain-colon), pinned by a spawn-golden case
- pass the full discovered window to opencode as limit.context
- translate the picker search strings and document the discovery precedence
This commit is contained in:
Devvyn committed 2026-11-01 21:26:54 +08:00
1 parent dbd1b6e587
commit 1b8ac40baf
16 files changed
+256 -47

No files matched your search

+11
View File
@@ -102,6 +102,17 @@ export interface CustomModelHost {
defaultContextLength?: number;
}
/**
* The context window to apply for `modelId` on `host`: the discovered per-model figure when
* discovery has one, else the endpoint's user-set `defaultContextLength`, else undefined
* (no override applied, never a guess). ONE helper for every read site — the swap route,
* the quickstart route and boot recovery each re-write the CLI's config files, and a site
* that forgot the fallback silently loses the endpoint default on the next respawn.
*/
export function resolveCustomModelContextLength(host: CustomModelHost, modelId: string): number | undefined {
return host.modelContextLengths?.[modelId] ?? host.defaultContextLength;
}
export function customModelHostsPath(configDir: string): string {
return join(configDir, CUSTOM_MODEL_HOSTS_FILE);
}