Files
OmniRoute/open-sse/executors/codex/reasoningSuffix.ts
Praveen K Palaniswamy 65e81158ab fix(ollama): route models by advertised capability (#11088)
Landed with the design call resolved per the owner's pick — **option 1**: the synced store is now endpoint-agnostic (persistDiscoveredModels and managedModelImport no longer drop non-chat models at write time), and chat selectability moved to read time (auto-pool expansion in autoStrategy applies filterChatSelectableModels; the models-route projection already had its chatOnly filter). Your discovery test now passes end-to-end (3/3): /api/show capabilities persist per connection and image/embedding requests route through the advertising host.

Reconciliation notes: conflicted areas merged onto the current tip (adobe discovery import, requestedModel preflight signature, resolvedProvider fast-path coexists with the synced-route override — explicit resolution wins); carried base-red drains (#10055 memoization, #11071 test variants) dropped as already-landed; the managed-model-import exclusion test was propagated to the new contract (image/video models persist; the read filter still hides them from chat pickers — pinned by a new assertion). Full battery: 205/206 focused (the one red is a confirmed periodic-timer timing flake on the loaded devbox — 20/20 isolated), autoCombo vitest 30/30, combo suites 46/46, gates + typecheck clean.

Thank you @yourspraveen — the capability probe + routing design was right; it just needed the store contract opened up. Fixes #11087.
2026-08-23 11:45:01 -03:00

42 lines
1.3 KiB
TypeScript

export const CODEX_EFFORT_ORDER = [
"none",
"low",
"medium",
"high",
"xhigh",
"max",
"ultra",
] as const;
export type CodexEffortLevel = (typeof CODEX_EFFORT_ORDER)[number];
export const GPT_5_6_MAX_ALIAS_MODELS = new Set(["gpt-5.6-sol", "gpt-5.6-terra", "gpt-5.6-luna"]);
export const GPT_5_6_ULTRA_ALIAS_MODELS = new Set(["gpt-5.6-sol", "gpt-5.6-terra"]);
export function splitCodexReasoningSuffix(model: unknown): {
baseModel: string;
effort: CodexEffortLevel | null;
} {
const modelId = typeof model === "string" ? model : "";
const gpt56Match = /^(gpt-5\.6-(?:sol|terra|luna))(?:-(max|ultra)|\((max|ultra)\))$/.exec(
modelId
);
if (gpt56Match) {
const [, baseModel, hyphenEffort, parenthesizedEffort] = gpt56Match;
const effort = hyphenEffort ?? parenthesizedEffort;
const supportedModels = parenthesizedEffort
? GPT_5_6_MAX_ALIAS_MODELS
: effort === "ultra"
? GPT_5_6_ULTRA_ALIAS_MODELS
: GPT_5_6_MAX_ALIAS_MODELS;
if (supportedModels.has(baseModel)) {
return { baseModel, effort: effort as CodexEffortLevel };
}
}
for (const effort of ["none", "low", "medium", "high", "xhigh"] as const) {
if (modelId.endsWith(`-${effort}`)) {
return { baseModel: modelId.slice(0, -`-${effort}`.length), effort };
}
}
return { baseModel: modelId, effort: null };
}