luulam/9router
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(codex): support GPT-5.6 Max and Ultra overrides

Browse Source 
Add "ultra" reasoning level for Codex GPT-5.6 Sol and Terra, and expose
Max for Luna (Luna falls back Ultra to Max since it is not supported
upstream). Scoped to cx/ routes only; Kiro and generic OpenAI routing
unchanged.
This commit is contained in:
seakleang.nhak
2026-08-05 11:39:07 +07:00
parent 651df2f0e2
commit 86131b9ca4
10 changed files with 675 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
open-sse/translator/concerns/thinkingUnified.js
View File

@@ -3,6 +3,7 @@
// never hardcoded per-model here. See .docs/thinking/plan.md MATRIX VI-A.
import { getCapabilitiesForModel } from "../../providers/capabilities.js";
import { getThinkingLevels } from "../../providers/thinkingLevels.js";
import { PROVIDERS } from "../../providers/index.js";
import { LEVEL_TO_BUDGET, budgetToLevel, effortToBudget, effortToThinkingLevel } from "./thinking.js";
@@ -37,6 +38,7 @@ export function parseSuffix(model) {
const raw = m[2].trim().toLowerCase();
if (raw === "none" || raw === "off") return { cleanModel, override: { mode: "none" } };
if (raw === "auto") return { cleanModel, override: { mode: "auto" } };
if (raw === "ultra") return { cleanModel, override: { mode: "level", level: raw } };
if (/^\d+$/.test(raw)) return { cleanModel, override: { mode: "budget", budget: Number(raw) } };
if (LEVEL_TO_BUDGET[raw] !== undefined) return { cleanModel, override: { mode: "level", level: raw } };
return { cleanModel, override: null };
@@ -134,6 +136,13 @@ function toLevel(cfg) {
return null;
}
function normalizeOpenAILevel(level, supportedLevels) {
if (level !== "max" && level !== "ultra") return level;
if (supportedLevels?.includes(level)) return level;
if (level === "ultra" && supportedLevels?.includes("max")) return "max";
return "xhigh";
}
function toGeminiThinkingLevel(cfg) {
const raw = cfg.mode === "auto" ? "high" : (toLevel(cfg) || "high");
return effortToThinkingLevel(raw);
@@ -213,7 +222,7 @@ function stripAll(body) {
}
// Apply unified thinking config to body in the resolved provider-native format.
function applyFormat(fmt, body, cfg, caps) {
function applyFormat(fmt, body, cfg, caps, supportedLevels) {
const none = cfg.mode === "none";
const canDisable = caps.thinkingCanDisable !== false;
// Model cannot disable thinking → clamp "none" to minimal effort instead.
@@ -223,8 +232,7 @@ function applyFormat(fmt, body, cfg, caps) {
case "openai": {
if (none && canDisable) { body.reasoning_effort = "none"; break; }
const level = toLevel(eff);
// OpenAI reasoning_effort enum caps at "xhigh" (no "max"); clamp Claude Code's "max".
if (level) body.reasoning_effort = level === "max" ? "xhigh" : level;
if (level) body.reasoning_effort = normalizeOpenAILevel(level, supportedLevels);
break;
}
case "claude-adaptive": {
@@ -329,7 +337,8 @@ export function applyThinking(targetFormat, model, body, provider = null, intent
if (!cfg) return body;
const fmt = resolveFormat(targetFormat, cleanModel, provider);
const supportedLevels = getThinkingLevels(provider, cleanModel);
stripAll(body);
applyFormat(fmt, body, cfg, caps);
applyFormat(fmt, body, cfg, caps, supportedLevels);
return body;
}