@oh-my-pi/pi-catalog 16.3.14 → 16.4.0

package/src/provider-models/descriptors.ts

@@ -29,6 +29,7 @@ import {
 	mistralModelManagerOptions,
 	moonshotModelManagerOptions,
 	nanoGptModelManagerOptions,
+	novitaModelManagerOptions,
 	nvidiaModelManagerOptions,
 	ollamaModelManagerOptions,
 	openaiModelManagerOptions,
@@ -271,6 +272,14 @@ export const CATALOG_PROVIDERS = [
 		createModelManagerOptions: (config: ModelManagerConfig) => nvidiaModelManagerOptions(config),
 		catalogDiscovery: { label: "NVIDIA" },
 	},
+	{
+		id: "novita",
+		defaultModel: "moonshotai/kimi-k2.7-code",
+		envVars: ["NOVITA_API_KEY"],
+		createModelManagerOptions: (config: ModelManagerConfig) => novitaModelManagerOptions(config),
+		dynamicModelsAuthoritative: true,
+		catalogDiscovery: { label: "Novita", allowUnauthenticated: true },
+	},
 	{
 		id: "ollama",
 		defaultModel: "gpt-oss:20b",

package/src/provider-models/ollama.ts

@@ -25,8 +25,7 @@ type OllamaShowResponse = {
 const OLLAMA_RETRY_DELAYS_MS = [2_000, 5_000, 10_000];
 const OLLAMA_CLOUD_GLM_52_THINKING: ThinkingConfig = {
 	mode: "effort",
-	efforts: [Effort.High, Effort.XHigh],
-	effortMap: { [Effort.XHigh]: "max" },
+	efforts: [Effort.High, Effort.Max],
 };
 
 function trimTrailingSlash(value: string): string {

package/src/provider-models/openai-compat.ts

@@ -622,9 +622,8 @@ const UMANS_REASONING_EFFORT_BY_LEVEL: Record<string, Effort> = {
 	medium: Effort.Medium,
 	high: Effort.High,
 	xhigh: Effort.XHigh,
-	max: Effort.XHigh,
+	max: Effort.Max,
 };
-const UMANS_MAX_REASONING_EFFORT_MAP = { [Effort.XHigh]: "max" } as const;
 const UMANS_DEFAULT_REASONING_EFFORTS = [Effort.Minimal, Effort.Low, Effort.Medium, Effort.High, Effort.XHigh] as const;
 const UMANS_VIA_HANDOFF_MODEL_IDS = ["umans-glm-5.1", "umans-glm-5.2"] as const;
 
@@ -689,9 +688,6 @@ function mapUmansThinkingConfig(value: unknown): ThinkingConfig | undefined {
 		mode: umansHasMaxReasoningLevel(value) ? "anthropic-budget-effort" : "budget",
 		efforts,
 	};
-	if (thinking.mode === "anthropic-budget-effort") {
-		thinking.effortMap = UMANS_MAX_REASONING_EFFORT_MAP;
-	}
 	if (isRecord(value)) {
 		if (value.can_disable === false) {
 			thinking.requiresEffort = true;
@@ -821,6 +817,62 @@ export function openaiModelManagerOptions(config?: OpenAIModelManagerConfig): Mo
 	};
 }
 
+/** First-party gpt-5.6 SKUs that accept `reasoning: { mode: "pro" }` on the Responses APIs. */
+const OPENAI_PRO_REASONING_BASE_IDS: Record<string, true> = {
+	"gpt-5.6-luna": true,
+	"gpt-5.6-sol": true,
+	"gpt-5.6-terra": true,
+};
+const OPENAI_PRO_REASONING_PROVIDERS: Record<string, true> = { openai: true, "openai-codex": true };
+
+/**
+ * A row this generator pass owns: one of the derived `gpt-5.6-*-pro` alias ids
+ * on `openai`/`openai-codex` that carries the generated `reasoningMode` marker.
+ * A real upstream model occupying the same id has no `reasoningMode` and is
+ * never touched.
+ */
+function isGeneratedOpenAIProReasoningAlias(model: ModelSpec<Api>): boolean {
+	return (
+		OPENAI_PRO_REASONING_PROVIDERS[model.provider] === true &&
+		model.reasoningMode !== undefined &&
+		model.id.endsWith("-pro") &&
+		OPENAI_PRO_REASONING_BASE_IDS[model.id.slice(0, -"-pro".length)] === true
+	);
+}
+
+/**
+ * Re-derive the generated pro-reasoning aliases (`gpt-5.6-*-pro`) for the
+ * first-party `openai`/`openai-codex` gpt-5.6 rows. Each alias inherits the
+ * base row's metadata, requests the base wire id via `requestModelId`, and
+ * sets `reasoningMode: "pro"` so Responses-family request builders emit
+ * `reasoning: { mode: "pro" }`. Called by the models.json generator after all
+ * sources merge: stale copies of the owned aliases (previous snapshot) are
+ * dropped and re-projected from the current base rows so alias metadata always
+ * tracks the base, while a real upstream model that occupies an alias id wins
+ * and suppresses the projection.
+ */
+export function projectOpenAIProReasoningAliases(models: readonly ModelSpec<Api>[]): ModelSpec<Api>[] {
+	const kept = models.filter(model => !isGeneratedOpenAIProReasoningAlias(model));
+	const ids = new Set(kept.map(model => `${model.provider}/${model.id}`));
+	const out = [...kept];
+	for (const model of kept) {
+		if (!OPENAI_PRO_REASONING_PROVIDERS[model.provider]) continue;
+		if (!OPENAI_PRO_REASONING_BASE_IDS[model.id]) continue;
+		const aliasId = `${model.id}-pro`;
+		const aliasKey = `${model.provider}/${aliasId}`;
+		if (ids.has(aliasKey)) continue;
+		ids.add(aliasKey);
+		out.push({
+			...model,
+			id: aliasId,
+			name: `${model.name} Pro`,
+			requestModelId: model.id,
+			reasoningMode: "pro",
+		});
+	}
+	return out;
+}
+
 // ---------------------------------------------------------------------------
 // 2. Groq
 // ---------------------------------------------------------------------------
@@ -915,6 +967,102 @@ export function nvidiaModelManagerOptions(
 	return createSimpleOpenAICompletionsOptions("nvidia", "https://integrate.api.nvidia.com/v1", config);
 }
 
+// ---------------------------------------------------------------------------
+// 5.5 Novita
+// ---------------------------------------------------------------------------
+
+/** Novita OpenAI-compatible discovery configuration. */
+export interface NovitaModelManagerConfig {
+	apiKey?: string;
+	baseUrl?: string;
+	fetch?: FetchImpl;
+}
+
+function novitaArrayIncludes(value: unknown, expected: string): boolean {
+	return Array.isArray(value) && value.some(item => item === expected);
+}
+
+function isPublicNovitaModelId(id: string): boolean {
+	return !id.toLowerCase().startsWith("ai_infer_test");
+}
+
+// Novita reports token prices in 1/10,000 USD per million tokens.
+function toNovitaCostPerMillion(value: unknown): number {
+	return toPositiveNumber(value, 0) / 10_000;
+}
+
+function getNovitaCacheReadPricePerMillion(entry: OpenAICompatibleModelRecord): number {
+	const pricing = entry.pricing;
+	if (!isRecord(pricing)) {
+		return 0;
+	}
+	const cacheRead = pricing.input_cache_read;
+	if (!isRecord(cacheRead)) {
+		return 0;
+	}
+	return toNovitaCostPerMillion(cacheRead.price_per_m);
+}
+
+function mapNovitaModel(
+	entry: OpenAICompatibleModelRecord,
+	defaults: ModelSpec<"openai-completions">,
+	reference: ModelSpec<"openai-completions"> | undefined,
+): ModelSpec<"openai-completions"> {
+	const model = mapWithBundledReference(
+		{
+			...entry,
+			name: entry.display_name ?? entry.title ?? entry.name,
+		},
+		defaults,
+		reference,
+	);
+	return {
+		...model,
+		reasoning: novitaArrayIncludes(entry.features, "reasoning"),
+		supportsTools: novitaArrayIncludes(entry.features, "function-calling"),
+		input: toInputCapabilities(entry.input_modalities),
+		cost: {
+			input: toNovitaCostPerMillion(entry.input_token_price_per_m),
+			output: toNovitaCostPerMillion(entry.output_token_price_per_m),
+			cacheRead: getNovitaCacheReadPricePerMillion(entry),
+			cacheWrite: 0,
+		},
+		contextWindow: toPositiveNumber(entry.context_size, model.contextWindow),
+		maxTokens: toPositiveNumber(entry.max_output_tokens, model.maxTokens),
+	};
+}
+
+/** Builds Novita's public model-discovery manager. */
+export function novitaModelManagerOptions(
+	config?: NovitaModelManagerConfig,
+): ModelManagerOptions<"openai-completions"> {
+	const apiKey = config?.apiKey;
+	const baseUrl = config?.baseUrl ?? "https://api.novita.ai/openai/v1";
+	const references = createBundledReferenceMap<"openai-completions">("novita");
+	return {
+		providerId: "novita",
+		dynamicModelsAuthoritative: true,
+		fetchDynamicModels: async () =>
+			fetchOpenAICompatibleModels({
+				api: "openai-completions",
+				provider: "novita",
+				baseUrl,
+				apiKey,
+				mapModel: (entry, defaults) => mapNovitaModel(entry, defaults, references.get(defaults.id)),
+				filterModel: (entry, model) => {
+					const active = typeof entry.status !== "number" || entry.status === 1;
+					return (
+						active &&
+						isPublicNovitaModelId(model.id) &&
+						novitaArrayIncludes(entry.endpoints, "chat/completions") &&
+						toPositiveNumber(entry.max_output_tokens, 0) > 0
+					);
+				},
+				fetch: config?.fetch,
+			}),
+	};
+}
+
 // ---------------------------------------------------------------------------
 // 6. xAI
 // ---------------------------------------------------------------------------
@@ -983,6 +1131,7 @@ export const XAI_OAUTH_CURATED_MODELS: readonly XAICuratedModel[] = [
 		input: ["text", "image"],
 	},
 	{ id: "grok-4.3", contextWindow: 1_000_000, name: "Grok 4.3", input: ["text", "image"] },
+	{ id: "grok-4.5", contextWindow: 500_000, name: "Grok 4.5", input: ["text", "image"] },
 	// grok-4.20-multi-agent-0309 is text-only per the bundled catalog; omit `input` for the default.
 	{ id: "grok-4.20-multi-agent-0309", contextWindow: 2_000_000, name: "Grok 4.20 (Multi-Agent)" },
 	{
@@ -1050,18 +1199,21 @@ const XAI_REASONING_EFFORT_MAP = { minimal: "low" } as const;
 // The `minimal -> low` effort clamp (XAI_REASONING_EFFORT_MAP) is always
 // merged in so dynamic-fetched models — which arrive without curated
 // compat keys — still get the clamp applyResponsesReasoningParams expects.
+// The effort-dial pair (`supportsReasoningEffort`/`omitReasoningEffort`) is
+// authoritative: a stale flag on `base` (previous snapshot or dynamic fetch)
+// must not outlive an allowlist change in identity/family.ts.
 function mergeCuratedIntoModel(
 	base: ModelSpec<"openai-responses">,
 	curated: XAICuratedModel,
 ): ModelSpec<"openai-responses"> {
-	const effort = curated.supportsReasoningEffort;
+	const effortCapable = curated.supportsReasoningEffort ?? isGrokReasoningEffortCapable(curated.id);
 	const compat = {
 		...(base.compat ?? {}),
 		reasoningEffortMap: { ...XAI_REASONING_EFFORT_MAP, ...(base.compat?.reasoningEffortMap ?? {}) },
 		includeEncryptedReasoning: base.compat?.includeEncryptedReasoning ?? false,
 		filterReasoningHistory: base.compat?.filterReasoningHistory ?? true,
-		omitReasoningEffort: base.compat?.omitReasoningEffort ?? !isGrokReasoningEffortCapable(base.id),
-		...(effort === undefined ? {} : { supportsReasoningEffort: effort }),
+		omitReasoningEffort: !effortCapable,
+		supportsReasoningEffort: effortCapable,
 	};
 	return {
 		...base,
@@ -2649,18 +2801,13 @@ export function basetenModelManagerOptions(
 
 						const baseModel = mapWithBundledReference(entry, defaults, reference);
 
+						// Baseten's reasoning router accepts only the high/max
+						// effort tiers for its GLM-5.2 and gpt-oss routes.
 						const isEffortReasoning = defaults.id === "openai/gpt-oss-120b" || defaults.id === "zai-org/GLM-5.2";
 						const thinking = isEffortReasoning
 							? {
 									mode: "effort" as const,
-									efforts: [Effort.Minimal, Effort.Low, Effort.Medium, Effort.High, Effort.XHigh],
-									effortMap: {
-										minimal: "high",
-										low: "high",
-										medium: "high",
-										high: "high",
-										xhigh: "max",
-									},
+									efforts: [Effort.High, Effort.Max],
 								}
 							: undefined;
 
@@ -2783,8 +2930,7 @@ const SAKANA_FUGU_ULTRA_COST = { input: 5, output: 30, cacheRead: 0.5, cacheWrit
 const SAKANA_FUGU_ULTRA_CONTEXT_WINDOW = 1_000_000;
 const SAKANA_FUGU_THINKING: ThinkingConfig = {
 	mode: "effort",
-	efforts: [Effort.High, Effort.XHigh],
-	effortMap: { [Effort.XHigh]: "max" },
+	efforts: [Effort.High, Effort.Max],
 };
 const SAKANA_RESPONSES_COMPAT: ModelSpec<"openai-responses">["compat"] = {
 	includeEncryptedReasoning: false,

package/src/types.ts

@@ -691,6 +691,13 @@ export interface Model<TApi extends Api = Api> {
 	 * everything local (selection, caching, usage attribution) keys on `id`.
 	 */
 	requestModelId?: string;
+	/**
+	 * `reasoning.mode` to send on OpenAI Responses-family requests. Set on
+	 * generated pro aliases (`gpt-5.6-*-pro` on `openai`/`openai-codex`) that
+	 * pair a base wire id (`requestModelId`) with OpenAI's pro reasoning
+	 * serving path. Absent everywhere else; providers omit the wire field.
+	 */
+	reasoningMode?: "pro";
 	name: string;
 	api: TApi;
 	provider: Provider;
@@ -751,6 +758,8 @@ export interface Model<TApi extends Api = Api> {
 	transport?: "pi-native";
 	/** Hint that websocket transport should be preferred when supported by the provider implementation. */
 	preferWebsockets?: boolean;
+	/** Codex Responses Lite transport: send the lite marker and carry instructions/tools as input items (mirrors codex-rs `use_responses_lite`). */
+	useResponsesLite?: boolean;
 	/** Preferred model to switch to when context promotion is triggered (model id or provider/id). */
 	contextPromotionTarget?: string;
 	/** Preferred model to use only for compaction (model id or provider/id); the active session model is unchanged. */

package/src/variant-collapse.ts

@@ -111,15 +111,12 @@ function thinkingPair(baseId: string, name: string): EffortVariantFamily {
 	};
 }
 
-type DevinTierRoutes = Partial<Record<"off" | "minimal" | "low" | "medium" | "high" | "xhigh", string>>;
+type DevinTierRoutes = Partial<Record<"off" | "minimal" | "low" | "medium" | "high" | "xhigh" | "max", string>>;
 
-const DEVIN_FIVE_TIER_EFFORTS: readonly Effort[] = [
-	Effort.Minimal,
-	Effort.Low,
-	Effort.Medium,
-	Effort.High,
-	Effort.XHigh,
-];
+/** Devin families with a `-max` sibling: five wire tiers, `low` floor. */
+const DEVIN_FIVE_TIER_EFFORTS: readonly Effort[] = [Effort.Low, Effort.Medium, Effort.High, Effort.XHigh, Effort.Max];
+/** Devin families topping out at `-xhigh` (pre-5.6 GPT, 5.6 fast lanes). */
+const DEVIN_FOUR_TIER_EFFORTS: readonly Effort[] = [Effort.Low, Effort.Medium, Effort.High, Effort.XHigh];
 
 function devinTierFamily(
 	id: string,
@@ -132,11 +129,7 @@ function devinTierFamily(
 	for (const effort of efforts) {
 		switch (effort) {
 			case Effort.Minimal:
-				if (routes.minimal) {
-					routing[effort] = routes.minimal;
-				} else if (routes.low) {
-					routing[effort] = routes.low;
-				}
+				if (routes.minimal) routing[effort] = routes.minimal;
 				break;
 			case Effort.Low:
 				if (routes.low) routing[effort] = routes.low;
@@ -150,11 +143,20 @@ function devinTierFamily(
 			case Effort.XHigh:
 				if (routes.xhigh) routing[effort] = routes.xhigh;
 				break;
+			case Effort.Max:
+				if (routes.max) routing[effort] = routes.max;
+				break;
 		}
 	}
-	const members = [routes.off, routes.minimal, routes.low, routes.medium, routes.high, routes.xhigh].filter(
-		(member, index, items): member is string => typeof member === "string" && items.indexOf(member) === index,
-	);
+	const members = [
+		routes.off,
+		routes.minimal,
+		routes.low,
+		routes.medium,
+		routes.high,
+		routes.xhigh,
+		routes.max,
+	].filter((member, index, items): member is string => typeof member === "string" && items.indexOf(member) === index);
 	return {
 		id,
 		name,
@@ -169,11 +171,9 @@ function devinTierFamily(
 }
 
 /**
- * GPT-5.6 (Luna/Sol/Terra) adds a genuine `max` tier above `xhigh`, so the
- * standard family shifts every user effort up one notch (`minimal` → `-low`
- * … `xhigh` → `-max`), mirroring the Opus 4.7+ five-tier mapping. Devin
- * serves no `-max-priority` sibling, so the fast family keeps the direct
- * `low..xhigh` `-priority` scale.
+ * GPT-5.6 (Luna/Sol/Terra) serves per-tier siblings for the full five-tier
+ * `low..max` wire scale; user efforts route 1:1 onto them. Devin serves no
+ * `-max-priority` sibling, so the fast family tops out at `xhigh`.
  */
 function devinGpt56Families(variant: "luna" | "sol" | "terra", name: string): readonly EffortVariantFamily[] {
 	const base = `gpt-5-6-${variant}`;
@@ -183,11 +183,11 @@ function devinGpt56Families(variant: "luna" | "sol" | "terra", name: string): re
 			name,
 			{
 				off: `${base}-none`,
-				minimal: `${base}-low`,
-				low: `${base}-medium`,
-				medium: `${base}-high`,
-				high: `${base}-xhigh`,
-				xhigh: `${base}-max`,
+				low: `${base}-low`,
+				medium: `${base}-medium`,
+				high: `${base}-high`,
+				xhigh: `${base}-xhigh`,
+				max: `${base}-max`,
 			},
 			DEVIN_FIVE_TIER_EFFORTS,
 		),
@@ -201,7 +201,7 @@ function devinGpt56Families(variant: "luna" | "sol" | "terra", name: string): re
 				high: `${base}-high-priority`,
 				xhigh: `${base}-xhigh-priority`,
 			},
-			DEVIN_FIVE_TIER_EFFORTS,
+			DEVIN_FOUR_TIER_EFFORTS,
 		),
 	];
 }
@@ -357,98 +357,54 @@ export const GEMINI_CLI_VARIANT_COLLAPSE_TABLE: VariantCollapseTable = {
 };
 export const DEVIN_VARIANT_COLLAPSE_TABLE: VariantCollapseTable = {
 	families: [
-		{
-			id: "claude-opus-4-7",
-			name: "Claude Opus 4.7",
-			members: [
-				"claude-opus-4-7-low",
-				"claude-opus-4-7-medium",
-				"claude-opus-4-7-high",
-				"claude-opus-4-7-xhigh",
-				"claude-opus-4-7-max",
-			],
-			routing: {
-				[Effort.Minimal]: "claude-opus-4-7-low",
-				[Effort.Low]: "claude-opus-4-7-medium",
-				[Effort.Medium]: "claude-opus-4-7-high",
-				[Effort.High]: "claude-opus-4-7-xhigh",
-				[Effort.XHigh]: "claude-opus-4-7-max",
-			},
-			thinking: {
-				mode: "effort",
-				efforts: DEVIN_FIVE_TIER_EFFORTS,
-				requiresEffort: true,
-			},
-		},
-		{
-			id: "claude-opus-4-7-fast",
-			name: "Claude Opus 4.7 Fast",
-			members: [
-				"claude-opus-4-7-low-fast",
-				"claude-opus-4-7-medium-fast",
-				"claude-opus-4-7-high-fast",
-				"claude-opus-4-7-xhigh-fast",
-				"claude-opus-4-7-max-fast",
-			],
-			routing: {
-				[Effort.Minimal]: "claude-opus-4-7-low-fast",
-				[Effort.Low]: "claude-opus-4-7-medium-fast",
-				[Effort.Medium]: "claude-opus-4-7-high-fast",
-				[Effort.High]: "claude-opus-4-7-xhigh-fast",
-				[Effort.XHigh]: "claude-opus-4-7-max-fast",
-			},
-			thinking: {
-				mode: "effort",
-				efforts: DEVIN_FIVE_TIER_EFFORTS,
-				requiresEffort: true,
-			},
-		},
-		{
-			id: "claude-opus-4-8",
-			name: "Claude Opus 4.8",
-			members: [
-				"claude-opus-4-8-low",
-				"claude-opus-4-8-medium",
-				"claude-opus-4-8-high",
-				"claude-opus-4-8-xhigh",
-				"claude-opus-4-8-max",
-			],
-			routing: {
-				[Effort.Minimal]: "claude-opus-4-8-low",
-				[Effort.Low]: "claude-opus-4-8-medium",
-				[Effort.Medium]: "claude-opus-4-8-high",
-				[Effort.High]: "claude-opus-4-8-xhigh",
-				[Effort.XHigh]: "claude-opus-4-8-max",
+		devinTierFamily(
+			"claude-opus-4-7",
+			"Claude Opus 4.7",
+			{
+				low: "claude-opus-4-7-low",
+				medium: "claude-opus-4-7-medium",
+				high: "claude-opus-4-7-high",
+				xhigh: "claude-opus-4-7-xhigh",
+				max: "claude-opus-4-7-max",
 			},
-			thinking: {
-				mode: "effort",
-				efforts: DEVIN_FIVE_TIER_EFFORTS,
-				requiresEffort: true,
+			DEVIN_FIVE_TIER_EFFORTS,
+		),
+		devinTierFamily(
+			"claude-opus-4-7-fast",
+			"Claude Opus 4.7 Fast",
+			{
+				low: "claude-opus-4-7-low-fast",
+				medium: "claude-opus-4-7-medium-fast",
+				high: "claude-opus-4-7-high-fast",
+				xhigh: "claude-opus-4-7-xhigh-fast",
+				max: "claude-opus-4-7-max-fast",
 			},
-		},
-		{
-			id: "claude-opus-4-8-fast",
-			name: "Claude Opus 4.8 Fast",
-			members: [
-				"claude-opus-4-8-low-fast",
-				"claude-opus-4-8-medium-fast",
-				"claude-opus-4-8-high-fast",
-				"claude-opus-4-8-xhigh-fast",
-				"claude-opus-4-8-max-fast",
-			],
-			routing: {
-				[Effort.Minimal]: "claude-opus-4-8-low-fast",
-				[Effort.Low]: "claude-opus-4-8-medium-fast",
-				[Effort.Medium]: "claude-opus-4-8-high-fast",
-				[Effort.High]: "claude-opus-4-8-xhigh-fast",
-				[Effort.XHigh]: "claude-opus-4-8-max-fast",
+			DEVIN_FIVE_TIER_EFFORTS,
+		),
+		devinTierFamily(
+			"claude-opus-4-8",
+			"Claude Opus 4.8",
+			{
+				low: "claude-opus-4-8-low",
+				medium: "claude-opus-4-8-medium",
+				high: "claude-opus-4-8-high",
+				xhigh: "claude-opus-4-8-xhigh",
+				max: "claude-opus-4-8-max",
 			},
-			thinking: {
-				mode: "effort",
-				efforts: DEVIN_FIVE_TIER_EFFORTS,
-				requiresEffort: true,
+			DEVIN_FIVE_TIER_EFFORTS,
+		),
+		devinTierFamily(
+			"claude-opus-4-8-fast",
+			"Claude Opus 4.8 Fast",
+			{
+				low: "claude-opus-4-8-low-fast",
+				medium: "claude-opus-4-8-medium-fast",
+				high: "claude-opus-4-8-high-fast",
+				xhigh: "claude-opus-4-8-xhigh-fast",
+				max: "claude-opus-4-8-max-fast",
 			},
-		},
+			DEVIN_FIVE_TIER_EFFORTS,
+		),
 		devinTierFamily(
 			"gpt-5-2",
 			"GPT-5.2",
@@ -459,7 +415,7 @@ export const DEVIN_VARIANT_COLLAPSE_TABLE: VariantCollapseTable = {
 				high: "MODEL_GPT_5_2_HIGH",
 				xhigh: "MODEL_GPT_5_2_XHIGH",
 			},
-			DEVIN_FIVE_TIER_EFFORTS,
+			DEVIN_FOUR_TIER_EFFORTS,
 		),
 		devinTierFamily(
 			"gpt-5-3-codex",
@@ -470,7 +426,7 @@ export const DEVIN_VARIANT_COLLAPSE_TABLE: VariantCollapseTable = {
 				high: "gpt-5-3-codex-high",
 				xhigh: "gpt-5-3-codex-xhigh",
 			},
-			DEVIN_FIVE_TIER_EFFORTS,
+			DEVIN_FOUR_TIER_EFFORTS,
 		),
 		devinTierFamily(
 			"gpt-5-3-codex-fast",
@@ -481,7 +437,7 @@ export const DEVIN_VARIANT_COLLAPSE_TABLE: VariantCollapseTable = {
 				high: "gpt-5-3-codex-high-priority",
 				xhigh: "gpt-5-3-codex-xhigh-priority",
 			},
-			DEVIN_FIVE_TIER_EFFORTS,
+			DEVIN_FOUR_TIER_EFFORTS,
 		),
 		devinTierFamily(
 			"gpt-5-4",
@@ -493,7 +449,7 @@ export const DEVIN_VARIANT_COLLAPSE_TABLE: VariantCollapseTable = {
 				high: "gpt-5-4-high",
 				xhigh: "gpt-5-4-xhigh",
 			},
-			DEVIN_FIVE_TIER_EFFORTS,
+			DEVIN_FOUR_TIER_EFFORTS,
 		),
 		devinTierFamily(
 			"gpt-5-4-fast",
@@ -505,7 +461,7 @@ export const DEVIN_VARIANT_COLLAPSE_TABLE: VariantCollapseTable = {
 				high: "gpt-5-4-high-priority",
 				xhigh: "gpt-5-4-xhigh-priority",
 			},
-			DEVIN_FIVE_TIER_EFFORTS,
+			DEVIN_FOUR_TIER_EFFORTS,
 		),
 		devinTierFamily(
 			"gpt-5-4-mini",
@@ -516,7 +472,7 @@ export const DEVIN_VARIANT_COLLAPSE_TABLE: VariantCollapseTable = {
 				high: "gpt-5-4-mini-high",
 				xhigh: "gpt-5-4-mini-xhigh",
 			},
-			DEVIN_FIVE_TIER_EFFORTS,
+			DEVIN_FOUR_TIER_EFFORTS,
 		),
 		devinTierFamily(
 			"gpt-5-5",
@@ -528,7 +484,7 @@ export const DEVIN_VARIANT_COLLAPSE_TABLE: VariantCollapseTable = {
 				high: "gpt-5-5-high",
 				xhigh: "gpt-5-5-xhigh",
 			},
-			DEVIN_FIVE_TIER_EFFORTS,
+			DEVIN_FOUR_TIER_EFFORTS,
 		),
 		devinTierFamily(
 			"gpt-5-5-fast",
@@ -540,7 +496,7 @@ export const DEVIN_VARIANT_COLLAPSE_TABLE: VariantCollapseTable = {
 				high: "gpt-5-5-high-priority",
 				xhigh: "gpt-5-5-xhigh-priority",
 			},
-			DEVIN_FIVE_TIER_EFFORTS,
+			DEVIN_FOUR_TIER_EFFORTS,
 		),
 		...devinGpt56Families("luna", "GPT-5.6 Luna"),
 		...devinGpt56Families("sol", "GPT-5.6 Sol"),

package/src/wire/codex.ts

@@ -10,6 +10,15 @@ export const OPENAI_HEADERS = {
 	ORIGINATOR: "originator",
 	SESSION_ID: "session_id",
 	CONVERSATION_ID: "conversation_id",
+	SCOPED_SESSION_ID: "session-id",
+	THREAD_ID: "thread-id",
+	INSTALLATION_ID: "x-codex-installation-id",
+	WINDOW_ID: "x-codex-window-id",
+	TURN_METADATA: "x-codex-turn-metadata",
+	PARENT_THREAD_ID: "x-codex-parent-thread-id",
+	SUBAGENT: "x-openai-subagent",
+	/** Responses Lite transport marker (codex-rs `add_responses_lite_header`); value is always `"true"`. */
+	RESPONSES_LITE: "x-openai-internal-codex-responses-lite",
 } as const;
 
 export const OPENAI_HEADER_VALUES = {