@oh-my-pi/pi-catalog 18.2.8 → 18.2.10

package/CHANGELOG.md

@@ -2,6 +2,24 @@
 
 ## [Unreleased]
 
+## [18.2.10] - 2026-09-22
+
+### Changed
+
+- Updated default models for anthropic, amazon-bedrock, cloudflare-ai-gateway, kilo, litellm, opencode-zen, vercel-ai-gateway, and zenmux to claude-opus-5-5
+- Updated default model for commandcode to claude-sonnet-5
+
+## [18.2.9] - 2026-09-22
+
+### Fixed
+
+- Local OpenAI-compatible backends—including llama.cpp, LM Studio, vLLM, Ollama, and custom loopback or LAN hosts—now support maxTokens values above 64k without incorrectly applying the hosted OpenAI limit.
+- Fixed Union Alpha requests on OpenCode Go and Zen by using the correct Messages API.
+- Updated SuperGrok’s Grok 4.7 metadata to expose its documented 500K context window and low, medium, high, and xhigh thinking levels.
+- Fixed GPT-OSS tool interactions on Google Antigravity and Gemini CLI so function-call history is preserved correctly.
+- Fixed Devin model discovery for Enterprise credentials by falling back to the legacy Windsurf catalog when native discovery does not return the full model list.
+- Curated Xiaomi Token Plan (China) MiMo V2.6 metadata: context/output limits, reasoning, and image input ([#12841](https://github.com/can1357/oh-my-pi/pull/12841) by [@roboomp](https://github.com/roboomp)).
+
 ## [18.2.8] - 2026-09-21
 
 ### Added

package/dist/types/compat/auth-ids.d.ts

@@ -1,4 +1,4 @@
 /** Every provider with an `auth/<id>.kdl` policy. */
-export type AuthProviderId = "abliteration" | "aiand" | "aimlapi" | "alibaba-coding-plan" | "alibaba-token-plan" | "amazon-bedrock" | "anthropic" | "azure" | "baseten" | "bedrock-mantle" | "cerebras" | "charm-hyper" | "cline-pass" | "cloudflare-ai-gateway" | "commandcode" | "coreweave" | "cursor" | "deepinfra" | "deepseek" | "devin" | "exa" | "firepass" | "fireworks" | "github-copilot" | "gitlab-duo" | "gitlab-duo-agent" | "gmi-cloud" | "google" | "google-antigravity" | "google-gemini-cli" | "google-vertex" | "groq" | "huggingface" | "kagi" | "kilo" | "kimi-code" | "litellm" | "llama.cpp" | "lm-studio" | "local" | "meta" | "minimax" | "minimax-code" | "minimax-code-cn" | "mistral" | "moonshot" | "muse-code" | "nanogpt" | "novita" | "nvidia" | "ollama" | "ollama-cloud" | "openai" | "openai-codex" | "openai-codex-device" | "opencode-go" | "opencode-zen" | "openrouter" | "parallel" | "perplexity" | "qianfan" | "qwen-portal" | "sakana" | "siliconflow" | "siliconflow-cn" | "stencil" | "synthetic" | "tavily" | "together" | "typesafe" | "umans" | "venice" | "vercel-ai-gateway" | "vllm" | "wafer-serverless" | "web" | "xai" | "xai-oauth" | "xiaomi" | "xiaomi-token-plan-ams" | "xiaomi-token-plan-cn" | "xiaomi-token-plan-sgp" | "yolo-auto" | "zai" | "zai-coding-plan" | "zenmux" | "zhipu-coding-plan";
+export type AuthProviderId = "abliteration" | "aiand" | "aimlapi" | "alibaba-coding-plan" | "alibaba-token-plan" | "amazon-bedrock" | "anthropic" | "azure" | "baseten" | "bedrock-mantle" | "cerebras" | "charm-hyper" | "cline-pass" | "cloudflare-ai-gateway" | "commandcode" | "coreweave" | "cursor" | "deepinfra" | "deepseek" | "devin" | "exa" | "firepass" | "fireworks" | "github-copilot" | "gitlab-duo" | "gitlab-duo-agent" | "gmi-cloud" | "google" | "google-antigravity" | "google-gemini-cli" | "google-vertex" | "groq" | "huggingface" | "kagi" | "kilo" | "kimi-code" | "litellm" | "llama.cpp" | "lm-studio" | "local" | "meta" | "minimax" | "minimax-code" | "minimax-code-cn" | "mistral" | "moonshot" | "muse-code" | "nanogpt" | "novita" | "nvidia" | "ollama" | "ollama-cloud" | "openai" | "openai-codex" | "openai-codex-device" | "opencode-go" | "opencode-zen" | "openrouter" | "parallel" | "perplexity" | "qianfan" | "qwen-portal" | "sakana" | "siliconflow" | "siliconflow-cn" | "singularityapi-dev" | "singularityapi-tech" | "stencil" | "synthetic" | "tavily" | "together" | "typesafe" | "umans" | "venice" | "vercel-ai-gateway" | "vllm" | "wafer-serverless" | "web" | "xai" | "xai-oauth" | "xiaomi" | "xiaomi-token-plan-ams" | "xiaomi-token-plan-cn" | "xiaomi-token-plan-sgp" | "yolo-auto" | "zai" | "zai-coding-plan" | "zenmux" | "zhipu-coding-plan";
 /** Providers whose policy declares a `login` flow (the `/login` roster). */
-export type LoginProviderId = "abliteration" | "aiand" | "alibaba-coding-plan" | "alibaba-token-plan" | "anthropic" | "baseten" | "cerebras" | "charm-hyper" | "cline-pass" | "cloudflare-ai-gateway" | "commandcode" | "coreweave" | "cursor" | "deepinfra" | "deepseek" | "devin" | "exa" | "firepass" | "fireworks" | "github-copilot" | "gitlab-duo" | "gitlab-duo-agent" | "gmi-cloud" | "google-antigravity" | "google-gemini-cli" | "huggingface" | "kagi" | "kilo" | "kimi-code" | "litellm" | "llama.cpp" | "lm-studio" | "meta" | "minimax-code" | "minimax-code-cn" | "moonshot" | "muse-code" | "nanogpt" | "novita" | "nvidia" | "ollama" | "ollama-cloud" | "openai-codex" | "openai-codex-device" | "opencode-go" | "opencode-zen" | "openrouter" | "parallel" | "perplexity" | "qianfan" | "qwen-portal" | "sakana" | "siliconflow" | "siliconflow-cn" | "stencil" | "synthetic" | "tavily" | "together" | "typesafe" | "umans" | "venice" | "vercel-ai-gateway" | "vllm" | "wafer-serverless" | "xai" | "xai-oauth" | "xiaomi" | "xiaomi-token-plan-ams" | "xiaomi-token-plan-cn" | "xiaomi-token-plan-sgp" | "yolo-auto" | "zai" | "zai-coding-plan" | "zenmux" | "zhipu-coding-plan";
+export type LoginProviderId = "abliteration" | "aiand" | "alibaba-coding-plan" | "alibaba-token-plan" | "anthropic" | "baseten" | "cerebras" | "charm-hyper" | "cline-pass" | "cloudflare-ai-gateway" | "commandcode" | "coreweave" | "cursor" | "deepinfra" | "deepseek" | "devin" | "exa" | "firepass" | "fireworks" | "github-copilot" | "gitlab-duo" | "gitlab-duo-agent" | "gmi-cloud" | "google-antigravity" | "google-gemini-cli" | "huggingface" | "kagi" | "kilo" | "kimi-code" | "litellm" | "llama.cpp" | "lm-studio" | "meta" | "minimax-code" | "minimax-code-cn" | "moonshot" | "muse-code" | "nanogpt" | "novita" | "nvidia" | "ollama" | "ollama-cloud" | "openai-codex" | "openai-codex-device" | "opencode-go" | "opencode-zen" | "openrouter" | "parallel" | "perplexity" | "qianfan" | "qwen-portal" | "sakana" | "siliconflow" | "siliconflow-cn" | "singularityapi-dev" | "singularityapi-tech" | "stencil" | "synthetic" | "tavily" | "together" | "typesafe" | "umans" | "venice" | "vercel-ai-gateway" | "vllm" | "wafer-serverless" | "xai" | "xai-oauth" | "xiaomi" | "xiaomi-token-plan-ams" | "xiaomi-token-plan-cn" | "xiaomi-token-plan-sgp" | "yolo-auto" | "zai" | "zai-coding-plan" | "zenmux" | "zhipu-coding-plan";

package/dist/types/compat/axes.d.ts

@@ -25,8 +25,8 @@ export interface AxisDef {
     shape: AxisShape;
     /** Wire axes only: records this key exists on. */
     records?: readonly CompatRecordName[];
-    /** Closed value vocabulary for string scalars / string arrays. */
-    values?: readonly string[];
+    /** Closed value vocabulary for scalars / arrays (strings, and booleans on flag axes). */
+    values?: readonly (string | boolean)[];
     /**
      * Object axes only: payload child names are literal wire JSON keys copied
      * verbatim (`extra-body`). Default object payloads author kebab-case names

package/dist/types/compat/catalog-policy.d.ts

@@ -0,0 +1,7 @@
+import type { Model } from "../types.js";
+/**
+ * The `catalog` axis bag authored in the KDL cascade rules for a model,
+ * memoized per distinct model. Frozen: the bag is shared across callers, so it
+ * must stay read-only — extract the value you need rather than handing it on.
+ */
+export declare function resolveCatalogPolicy(model: Model): Readonly<Record<string, unknown>>;

package/dist/types/compat/output-limits.d.ts

@@ -0,0 +1,3 @@
+import type { Model } from "../types.js";
+/** Whether discovery and transport policy allow preserving a caller's output cap. */
+export declare function supportsOutputTokenLimit(model: Model): boolean;

package/dist/types/compat/provider-ids.d.ts

@@ -1,2 +1,2 @@
 /** Every chat-model provider with a catalog entry (`default-model` in its provider rules). */
-export type KnownProvider = "abliteration" | "aiand" | "aimlapi" | "alibaba-coding-plan" | "alibaba-token-plan" | "amazon-bedrock" | "anthropic" | "azure" | "baseten" | "bedrock-mantle" | "cerebras" | "charm-hyper" | "cline-pass" | "cloudflare-ai-gateway" | "commandcode" | "coreweave" | "cursor" | "deepinfra" | "deepseek" | "devin" | "firepass" | "fireworks" | "github-copilot" | "gitlab-duo" | "gitlab-duo-agent" | "gmi-cloud" | "google" | "google-antigravity" | "google-gemini-cli" | "google-vertex" | "groq" | "huggingface" | "kilo" | "kimi-code" | "litellm" | "lm-studio" | "local" | "meta" | "minimax" | "minimax-code" | "minimax-code-cn" | "mistral" | "moonshot" | "muse-code" | "nanogpt" | "novita" | "nvidia" | "ollama" | "ollama-cloud" | "openai" | "openai-codex" | "opencode-go" | "opencode-zen" | "openrouter" | "qianfan" | "qwen-portal" | "sakana" | "siliconflow" | "siliconflow-cn" | "synthetic" | "together" | "typesafe" | "umans" | "venice" | "vercel-ai-gateway" | "vllm" | "wafer-serverless" | "web" | "xai" | "xai-oauth" | "xiaomi" | "xiaomi-token-plan-ams" | "xiaomi-token-plan-cn" | "xiaomi-token-plan-sgp" | "yolo-auto" | "zai" | "zenmux" | "zhipu-coding-plan";
+export type KnownProvider = "abliteration" | "aiand" | "aimlapi" | "alibaba-coding-plan" | "alibaba-token-plan" | "amazon-bedrock" | "anthropic" | "azure" | "baseten" | "bedrock-mantle" | "cerebras" | "charm-hyper" | "cline-pass" | "cloudflare-ai-gateway" | "commandcode" | "coreweave" | "cursor" | "deepinfra" | "deepseek" | "devin" | "firepass" | "fireworks" | "github-copilot" | "gitlab-duo" | "gitlab-duo-agent" | "gmi-cloud" | "google" | "google-antigravity" | "google-gemini-cli" | "google-vertex" | "groq" | "huggingface" | "kilo" | "kimi-code" | "litellm" | "lm-studio" | "local" | "meta" | "minimax" | "minimax-code" | "minimax-code-cn" | "mistral" | "moonshot" | "muse-code" | "nanogpt" | "novita" | "nvidia" | "ollama" | "ollama-cloud" | "openai" | "openai-codex" | "opencode-go" | "opencode-zen" | "openrouter" | "qianfan" | "qwen-portal" | "sakana" | "siliconflow" | "siliconflow-cn" | "singularityapi-dev" | "singularityapi-tech" | "synthetic" | "together" | "typesafe" | "umans" | "venice" | "vercel-ai-gateway" | "vllm" | "wafer-serverless" | "web" | "xai" | "xai-oauth" | "xiaomi" | "xiaomi-token-plan-ams" | "xiaomi-token-plan-cn" | "xiaomi-token-plan-sgp" | "yolo-auto" | "zai" | "zenmux" | "zhipu-coding-plan";

package/dist/types/compat/tools.d.ts

@@ -0,0 +1,5 @@
+import type { Model } from "../types.js";
+/** Whether the transport exposes native tools that an empty caller catalog cannot disable. */
+export declare function requiresNativeTools(model: Model): boolean;
+/** Whether disabling tools requires a history without prior tool calls or results. */
+export declare function requiresToolFreeHistoryForToolOptOut(model: Model): boolean;

package/dist/types/provider-models/openai-compat.d.ts

@@ -661,3 +661,29 @@ export interface CharmHyperModelManagerConfig {
  * alive by a stale bundled row.
  */
 export declare function charmHyperModelManagerOptions(config?: CharmHyperModelManagerConfig): ModelManagerOptions<"openai-completions">;
+export interface SingularityApiModelManagerConfig {
+    apiKey?: string;
+    baseUrl?: string;
+    fetch?: FetchImpl;
+}
+/**
+ * `singularityapi-dev` — SingularityAPI's pay-as-you-go universal gateway
+ * (`api.singularityapi.dev`): chat completions over a 300+ model catalog,
+ * plus image generation for the rows that advertise it.
+ * `GET /v1/models` publishes each row's per-endpoint capabilities — context
+ * window, max output tokens, and per-million pricing as 12-decimal strings —
+ * with `cache-control: no-store`, so discovery reads limits and tariffs
+ * straight off the wire and the endpoint list picks each row's transport.
+ * Rows without a reasoning vocabulary stay non-reasoning; reviewed KDL rules
+ * own the ladders the gateway leaves implicit (DeepSeek Flash/Pro, GPT-5.6
+ * flagships), because a model discovered as non-reasoning never sends a
+ * `reasoning_effort` and the gateway requires one alongside tools.
+ */
+export declare function singularityApiDevModelManagerOptions(config?: SingularityApiModelManagerConfig): ModelManagerOptions<Api>;
+/**
+ * `singularityapi-tech` — SingularityAPI's slot-reserved DeepSeek lanes
+ * (`api.singularityapi.tech`). `/v1/models` answers with bare `{id}` rows and
+ * no capability metadata, so rows keep the discovery defaults and the
+ * reviewed KDL rules own the wire shape, limits patch, and effort ladder.
+ */
+export declare function singularityApiTechModelManagerOptions(config?: SingularityApiModelManagerConfig): ModelManagerOptions<Api>;

package/dist/types/wire/codex.d.ts

@@ -4,12 +4,13 @@
 export declare const CODEX_BASE_URL = "https://chatgpt.com/backend-api";
 /**
  * Pinned OpenAI Codex client version (corresponds to @openai/codex package version).
+ * Updated from npm by `bun run check-spoofed-versions --update`.
  *
  * The backend version-gates model availability against this value on both
- * `/models?client_version=` and `/responses` (`gpt-6-astra` requires ≥ 0.153.0);
- * an older pin silently hides newer SKUs from discovery.
+ * `/models?client_version=` and `/responses`; 0.155.1 exposes GPT-6 Sol and Luna.
+ * An older pin silently hides newer SKUs from discovery.
  */
-export declare const CODEX_CLIENT_VERSION = "0.153.0";
+export declare const CODEX_CLIENT_VERSION = "0.155.1";
 export declare const OPENAI_HEADERS: {
     readonly BETA: "OpenAI-Beta";
     /** Codex feature-negotiation header; values identify opt-in wire protocols. */

package/dist/types/wire/singularityapi.d.ts

@@ -0,0 +1,29 @@
+/**
+ * SingularityAPI gateways, shared so a host migration — or a self-hosted
+ * proxy override — touches a single module.
+ *
+ * SingularityAPI ships two unrelated products behind one brand: the
+ * pay-as-you-go universal gateway (`singularityapi-dev`) and the
+ * slot-reserved DeepSeek lanes (`singularityapi-tech`). They accept disjoint
+ * keys, so each provider resolves its own canonical endpoint from here.
+ */
+export declare const SINGULARITYAPI_DEV_API_BASE_URL = "https://api.singularityapi.dev/v1";
+export declare const SINGULARITYAPI_TECH_API_BASE_URL = "https://api.singularityapi.tech/v1";
+/**
+ * Resolve a configured SingularityAPI base URL onto its gateway's `/v1`
+ * surface.
+ *
+ * Every consumer must agree on this, because they key different things off the
+ * result: discovery and inference target it, and the model-cache namespace is
+ * hashed from it. `ModelRegistry` hashes the raw configured value while the
+ * model-manager options hash a `/v1`-suffixed one, so a disagreement would
+ * split the namespace discovery writes from the one the registry reads and the
+ * authoritative roster would never come back.
+ *
+ * `canonical` names the product the caller belongs to: a blank or
+ * whitespace-only value means "not configured" and resolves to that canonical
+ * host, while anything else keeps its host and gains the `/v1` segment if it
+ * omits one. Passing the wrong product's canonical URL would silently point a
+ * provider at the other gateway, so there is no default.
+ */
+export declare function normalizeSingularityApiBaseUrl(baseUrl: string | undefined, canonical: string): string;

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@oh-my-pi/pi-catalog",
-	"version": "18.2.8",
+	"version": "18.2.10",
 	"description": "Model catalog for omp: bundled model database, provider discovery descriptors, model identity, classification, and equivalence",
 	"keywords": [
 		"ai",
@@ -90,12 +90,12 @@
 		"gen:proto": "bun scripts/generate-protocols.ts"
 	},
 	"dependencies": {
-		"@oh-my-pi/omptype": "18.2.8",
-		"@oh-my-pi/pi-utils": "18.2.8"
+		"@oh-my-pi/omptype": "18.2.10",
+		"@oh-my-pi/pi-utils": "18.2.10"
 	},
 	"devDependencies": {
 		"@bgotink/kdl": "0.4.0",
-		"@oh-my-pi/pi-ai": "18.2.8",
+		"@oh-my-pi/pi-ai": "18.2.10",
 		"@types/bun": "^1.3.14"
 	},
 	"engines": {

package/src/compat/auth-ids.ts

@@ -67,6 +67,8 @@ export type AuthProviderId =
 	| "sakana"
 	| "siliconflow"
 	| "siliconflow-cn"
+	| "singularityapi-dev"
+	| "singularityapi-tech"
 	| "stencil"
 	| "synthetic"
 	| "tavily"
@@ -146,6 +148,8 @@ export type LoginProviderId =
 	| "sakana"
 	| "siliconflow"
 	| "siliconflow-cn"
+	| "singularityapi-dev"
+	| "singularityapi-tech"
 	| "stencil"
 	| "synthetic"
 	| "tavily"

package/src/compat/axes.ts

@@ -29,8 +29,8 @@ export interface AxisDef {
 	shape: AxisShape;
 	/** Wire axes only: records this key exists on. */
 	records?: readonly CompatRecordName[];
-	/** Closed value vocabulary for string scalars / string arrays. */
-	values?: readonly string[];
+	/** Closed value vocabulary for scalars / arrays (strings, and booleans on flag axes). */
+	values?: readonly (string | boolean)[];
 	/**
 	 * Object axes only: payload child names are literal wire JSON keys copied
 	 * verbatim (`extra-body`). Default object payloads author kebab-case names
@@ -284,6 +284,25 @@ export const AXES: Readonly<Record<string, AxisDef>> = {
 		shape: "scalar",
 		values: ["freeform", "function"],
 	},
+	"requires-native-tools": { key: "requiresNativeTools", set: "catalog", shape: "scalar", values: [true, false] },
+	"requires-tool-free-history-for-tool-opt-out": {
+		key: "requiresToolFreeHistoryForToolOptOut",
+		set: "catalog",
+		shape: "scalar",
+		values: [true, false],
+	},
+	"preserves-max-output-tokens": {
+		key: "preservesMaxOutputTokens",
+		set: "catalog",
+		shape: "scalar",
+		values: [true, false],
+	},
+	"omit-max-output-tokens": {
+		key: "omitMaxOutputTokens",
+		set: "catalog",
+		shape: "scalar",
+		values: [true, false],
+	},
 	"clamp-context-override": { key: "clampContextOverride", set: "catalog", shape: "scalar" },
 	"context-promotion-target": { key: "contextPromotionTarget", set: "catalog", shape: "scalar" },
 	"context-window-floor": { key: "contextWindowFloor", set: "catalog", shape: "scalar" },

package/src/compat/catalog-policy.ts

@@ -0,0 +1,28 @@
+import { toModelSpec } from "../provider-models/bundled-references";
+import type { Model } from "../types";
+import { resolveModelPolicy } from "./resolve";
+
+/**
+ * Rule-owned catalog-axis policy by model. Resolve once per process rather
+ * than walking the static policy cascade on every accessor call. The key
+ * mirrors the cascade target inputs — `providerType ?? provider`, api, model
+ * id, and the reasoning flag; identity-derived class/family/revision facts are
+ * a pure function of provider + id. Bounded: one entry per distinct model.
+ */
+const catalogPolicyCache = new Map<string, Readonly<Record<string, unknown>>>();
+const CATALOG_POLICY_CACHE_MAX = 8192;
+
+/**
+ * The `catalog` axis bag authored in the KDL cascade rules for a model,
+ * memoized per distinct model. Frozen: the bag is shared across callers, so it
+ * must stay read-only — extract the value you need rather than handing it on.
+ */
+export function resolveCatalogPolicy(model: Model): Readonly<Record<string, unknown>> {
+	const key = `${model.provider}\u0000${model.providerType ?? ""}\u0000${model.api}\u0000${model.id}\u0000${model.reasoning ? 1 : 0}`;
+	const cached = catalogPolicyCache.get(key);
+	if (cached !== undefined) return cached;
+	const policy = Object.freeze({ ...resolveModelPolicy(toModelSpec(model)).catalog });
+	if (catalogPolicyCache.size >= CATALOG_POLICY_CACHE_MAX) catalogPolicyCache.clear();
+	catalogPolicyCache.set(key, policy);
+	return policy;
+}

package/src/compat/output-limits.ts

@@ -0,0 +1,12 @@
+import type { Model } from "../types";
+import { resolveCatalogPolicy } from "./catalog-policy";
+
+/** Whether discovery and transport policy allow preserving a caller's output cap. */
+export function supportsOutputTokenLimit(model: Model): boolean {
+	const policy = resolveCatalogPolicy(model);
+	return (
+		model.omitMaxOutputTokens !== true &&
+		policy.omitMaxOutputTokens !== true &&
+		policy.preservesMaxOutputTokens !== false
+	);
+}

package/src/compat/provider-ids.ts

@@ -61,6 +61,8 @@ export type KnownProvider =
 	| "sakana"
 	| "siliconflow"
 	| "siliconflow-cn"
+	| "singularityapi-dev"
+	| "singularityapi-tech"
 	| "synthetic"
 	| "together"
 	| "typesafe"

package/src/compat/resolve.ts

@@ -562,7 +562,7 @@ function detectOpenAICompat(
 		dropThinkingWhenReasoningEffort: false,
 		nativeKimiK3Reasoning: false,
 		zaiReasoningEffortDialect: false,
-		clampOutputToModelMax: false,
+		clampOutputToModelMax: d.isLocalOpenAICompatBackend,
 		stripImageInput: false,
 		thinkingLoopGuard: undefined,
 		rejectRootObjectUnion: false,
@@ -765,7 +765,9 @@ function resolveOpenAIResponsesPolicy(
 		wireModelIdMode: isOpenRouter ? "openrouter" : "raw",
 		toolSchemaFlavor: facts.is("kimi") ? "moonshot-mfjs" : undefined,
 		alwaysSendMaxTokens: facts.is("kimi"),
-		clampOutputToModelMax: false,
+		clampOutputToModelMax:
+			PROXY_OPENAI_COMPAT_PROVIDERS[backendProvider] !== true &&
+			(LOCAL_OPENAI_COMPAT_PROVIDERS[backendProvider] === true || hasLocalLoopbackBaseUrl(baseUrl)),
 		supportsObfuscationOptOut: isOpenAIUrl || provider === "openai",
 		officialEndpoint: isOfficialOpenAIEndpoint(provider, baseUrl),
 		harmonyLeakMitigation: false,

package/src/compat/rules/README.md

@@ -152,7 +152,7 @@ discovery {
 
 ## Cascade grammar
 
-A cascade document starts with `class` or `provider`. Every selector adds a conjunct to the current rule. `on` scopes by deployment provider; `on-api` scopes by request adapter, including custom provider names. Axis directives may appear directly in any permitted scope, and nested selector blocks may appear alongside them.
+A cascade document starts with `class`, `provider`, or `on-api`. Root `on-api` declares a transport contract independent of model identity and provider name. Every selector adds a conjunct to the current rule. `on` scopes by deployment provider; `on-api` scopes by request adapter, including custom provider names. Axis directives may appear directly in any permitted scope, and nested selector blocks may appear alongside them.
 
 ```kdl
 class "gemini" {
@@ -179,15 +179,15 @@ provider "openrouter" {
 
 ### Selectors and nesting
 
-| Selector   | Form                                     | Matching semantics                                                                                                                                                      |
-| ---------- | ---------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `class`    | `class "id" { ... }`                     | Exact class ID. At document root it may contain `on`, `on-api`, `family`, `revision`, and `models`. Under `provider` it may contain `family`, `revision`, and `models`. |
-| `provider` | `provider "id" { ... }`                  | Exact provider ID. It is root-only and may contain `class` and `models`.                                                                                                |
-| `on`       | `on "provider-a" "provider-b" { ... }`   | One or more provider IDs, combined as OR. It is allowed only under a root `class`, and may contain `family`, `revision`, and `models`.                                  |
-| `on-api`   | `on-api "adapter-a" "adapter-b" { ... }` | One or more request adapter IDs, combined as OR. It is allowed only under a root `class`, and may contain `family`, `revision`, and `models`.                           |
-| `family`   | `family "id" { ... }`                    | Exact classified family ID. It may contain `revision` and `models`. A target with no family does not match.                                                             |
-| `revision` | `revision ">=2.5 <4" { ... }`            | A non-empty, whitespace-separated conjunction of comparisons. It may contain `models`. A target with no revision does not match.                                        |
-| `models`   | `models "id" "vendor/*" { ... }`         | One or more alternatives, combined as OR. It cannot contain another selector. `token="name"` matches an ASCII-case-insensitive token bounded by non-alphanumerics.      |
+| Selector   | Form                                     | Matching semantics                                                                                                                                                             |
+| ---------- | ---------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| `class`    | `class "id" { ... }`                     | Exact class ID. At document root it may contain `on`, `on-api`, `family`, `revision`, and `models`. Under `provider` it may contain `family`, `revision`, and `models`.        |
+| `provider` | `provider "id" { ... }`                  | Exact provider ID. It is root-only and may contain `class` and `models`.                                                                                                       |
+| `on`       | `on "provider-a" "provider-b" { ... }`   | One or more provider IDs, combined as OR. It is allowed only under a root `class`, and may contain `family`, `revision`, and `models`.                                         |
+| `on-api`   | `on-api "adapter-a" "adapter-b" { ... }` | One or more request adapter IDs, combined as OR. At document root it may contain `class` and `models`; under a root `class` it may contain `family`, `revision`, and `models`. |
+| `family`   | `family "id" { ... }`                    | Exact classified family ID. It may contain `revision` and `models`. A target with no family does not match.                                                                    |
+| `revision` | `revision ">=2.5 <4" { ... }`            | A non-empty, whitespace-separated conjunction of comparisons. It may contain `models`. A target with no revision does not match.                                               |
+| `models`   | `models "id" "vendor/*" { ... }`         | One or more alternatives, combined as OR. It cannot contain another selector. `token="name"` matches an ASCII-case-insensitive token bounded by non-alphanumerics.             |
 
 Class, provider/`on`, `on-api`, and family selector values are compared exactly and case-sensitively to the structured resolve target. Revision operators are `>=`, `>`, `<=`, `<`, and `=`; operands have one to three dot-separated unsigned 8-bit components, omitted components zero.
 

package/src/compat/rules/auth/_order.kdl

@@ -10,4 +10,4 @@ login-order "openai-codex" "anthropic" "zai" "zai-coding-plan" "kimi-code" "open
 	"qianfan" "venice" "siliconflow" "siliconflow-cn" "synthetic" "nanogpt" "wafer-serverless" "coreweave" \
 	"vercel-ai-gateway" "cloudflare-ai-gateway" "litellm" "kilo" "zenmux" "opencode-zen" "opencode-go" \
 	"yolo-auto" "tavily" "kagi" "exa" "parallel" "typesafe" "ollama" "ollama-cloud" "lm-studio" "llama.cpp" "vllm" \
-	"gmi-cloud" "stencil"
+	"gmi-cloud" "stencil" "singularityapi-dev" "singularityapi-tech"

package/src/compat/rules/auth/singularityapi-dev.kdl

@@ -0,0 +1,22 @@
+// SingularityAPI universal inference gateway (api.singularityapi.dev): 300+
+// models behind one OpenAI-compatible endpoint, pay-as-you-go `sk-sapi-...`
+// bearer keys, per-million-token tariffs published per model. SingularityAPI
+// ships two unrelated products behind one brand — this gateway and the
+// slot-reserved DeepSeek lanes on api.singularityapi.tech — with disjoint
+// keys, dashboards, effort ladders, and billing, so each owns its own
+// provider id, env var, and login flow (neither key works on the other host,
+// verified 2026-09-22).
+// Key validation probes the non-billable `GET /v1/models`: it answers 401
+// `invalid_api_key` for a missing, malformed, or unknown key (verified
+// 2026-09-22), so a bad key is rejected without spending.
+auth "singularityapi-dev" {
+	name "SingularityAPI"
+	env "SINGULARITYAPI_DEV_API_KEY"
+	login "api-key" {
+		auth-url "https://app.singularityapi.dev"
+		instructions "Create an API key from the SingularityAPI dashboard, then paste it here"
+		prompt "Paste your SingularityAPI API key" placeholder="sk-sapi-..."
+		normalize "strip-bearer"
+		validate "models-endpoint" label="SingularityAPI" url="https://api.singularityapi.dev/v1/models"
+	}
+}

package/src/compat/rules/auth/singularityapi-tech.kdl

@@ -0,0 +1,23 @@
+// SingularityAPI reserved DeepSeek lanes (api.singularityapi.tech, a LiteLLM
+// front end in front of slot-reserved lanes) — the vendor's other product,
+// separated from api.singularityapi.dev because the two share no key, no
+// billing model, and no effort ladder. Usage here is charged against a booked
+// reservation slot rather than prepaid credit: a valid key with no active
+// slot answers 403 `permission_error` ("No active lane reservation for this
+// key", verified 2026-09-22), so login succeeds while a slot is idle and
+// inference needs one. Keys are lane-scoped `sk-...` bearer tokens issued
+// from the dashboard.
+// Key validation probes the non-billable `GET /v1/models`: it answers 401
+// for a missing, malformed, or unknown key (verified 2026-09-21), so a bad
+// key is rejected without spending.
+auth "singularityapi-tech" {
+	name "SingularityAPI Reserved Lanes"
+	env "SINGULARITYAPI_TECH_API_KEY"
+	login "api-key" {
+		auth-url "https://app.singularityapi.tech/compute/billing"
+		instructions "Create a key from the SingularityAPI lanes dashboard, then paste it here"
+		prompt "Paste your SingularityAPI lanes key" placeholder="sk-..."
+		normalize "strip-bearer"
+		validate "models-endpoint" label="SingularityAPI Reserved Lanes" url="https://api.singularityapi.tech/v1/models"
+	}
+}

package/src/compat/rules/classes/gpt-oss.kdl

@@ -13,4 +13,7 @@ class "gpt-oss" {
 	on "venice" "vercel-ai-gateway" {
 		thinking-efforts "minimal" "low" "medium" "high" "xhigh"
 	}
+	on "google-antigravity" "google-gemini-cli" {
+		supports-function-part-id #true
+	}
 }

package/src/compat/rules/classes/xai.kdl

@@ -5,7 +5,7 @@ class "xai" {
 	// on both the API and OAuth surfaces; the multiplier form tracks
 	// stencil.so price updates. Zero-cost subscription rows carry no tier.
 	on "xai" "xai-oauth" {
-		models "grok-4.3" "grok-4.5" "grok-4.6" "grok-build-0.1" "grok-4.20*" {
+		models "grok-4.3" "grok-4.5" "grok-4.6" "grok-4.7" "grok-build-0.1" "grok-4.20*" {
 			long-context-cost {
 				input-threshold 200000
 				input-threshold-inclusive #true
@@ -26,10 +26,10 @@ class "xai" {
 			}
 		}
 	}
-	// First-party xhigh-capable SKUs (grok-4.6, multi-agent) advertise xhigh.
+	// First-party xhigh-capable SKUs (grok-4.6, grok-4.7, multi-agent) advertise xhigh.
 	on "xai" "xai-oauth" {
 		family "grok" {
-			models "grok-4.6*" "grok-4.20-multi-agent*" {
+			models "grok-4.6*" "grok-4.7*" "grok-4.20-multi-agent*" {
 				thinking-efforts "minimal" "low" "medium" "high" "xhigh"
 			}
 		}

package/src/compat/rules/providers/amazon-bedrock.kdl

@@ -1,7 +1,7 @@
 // Provider-wire compat for "amazon-bedrock"; regenerated from the frozen census using deployment contract selectors.
 
 provider "amazon-bedrock" {
-	default-model "us.anthropic.claude-opus-4-8"
+	default-model "us.anthropic.claude-opus-5-5"
 
 	// The Converse assembler positions content blocks by wire index
 	// (`amazon-bedrock.ts`), so a block can land above text already rendered.

package/src/compat/rules/providers/anthropic.kdl

@@ -1,7 +1,7 @@
 // Provider-wire compat for "anthropic"; regenerated from the frozen census using deployment contract selectors.
 
 provider "anthropic" {
-	default-model "claude-opus-4-8"
+	default-model "claude-opus-5-5"
 	env "ANTHROPIC_API_KEY"
 	discovery label="Anthropic"
 	web-search "anthropic"

package/src/compat/rules/providers/cloudflare-ai-gateway.kdl

@@ -1,7 +1,7 @@
 // Provider-wire compat for "cloudflare-ai-gateway"; regenerated from the frozen census using deployment contract selectors.
 
 provider "cloudflare-ai-gateway" {
-	default-model "anthropic/claude-opus-4-8"
+	default-model "anthropic/claude-opus-5"
 	env "CLOUDFLARE_AI_GATEWAY_API_KEY"
 	discovery label="Cloudflare AI Gateway"
 

package/src/compat/rules/providers/commandcode.kdl

@@ -9,7 +9,7 @@
 // dials to a few further ids — MiniMaxAI/MiniMax-M3 and meta/muse-spark-1.3's
 // `max` — which stay out of this change.
 provider "commandcode" {
-	default-model "claude-sonnet-4-6"
+	default-model "claude-sonnet-5"
 	env "COMMAND_CODE_API_KEY" "COMMANDCODE_API_KEY"
 	allow-unauthenticated #true
 	dynamic-models-authoritative #true

package/src/compat/rules/providers/cursor.kdl

@@ -1,7 +1,7 @@
 // Provider-wire compat for "cursor"; regenerated from the frozen census using deployment contract selectors.
 
 provider "cursor" {
-	default-model "claude-4.6-opus-high"
+	default-model "claude-opus-5-high"
 	env "CURSOR_ACCESS_TOKEN"
 	discovery label="Cursor" oauth-provider="cursor" {
 		env "CURSOR_API_KEY"

package/src/compat/rules/providers/google-antigravity.kdl

@@ -17,6 +17,11 @@ provider "google-antigravity" {
 		}
 	}
 
+	// Routed wire profiles overwrite caller caps with fixed output limits.
+	// Conservatively reject requested bounds for this provider, including
+	// logical ids whose effort routing selects a profiled wire id later.
+	preserves-max-output-tokens #false
+
 	class "anthropic" {
 		family "opus" {
 			thinking-mode "budget"

package/src/compat/rules/providers/kilo.kdl

@@ -1,7 +1,7 @@
 // Provider-wire compat for "kilo"; regenerated from the frozen census using deployment contract selectors.
 
 provider "kilo" {
-	default-model "anthropic/claude-opus-4.8"
+	default-model "anthropic/claude-opus-5"
 	env "KILO_API_KEY"
 	discovery label="Kilo Gateway" allow-unauthenticated=#true
 

package/src/compat/rules/providers/litellm.kdl

@@ -1,7 +1,7 @@
 // Catalog entry for "litellm"; no deployment-contract compat rules are needed.
 
 provider "litellm" {
-	default-model "claude-opus-4-8"
+	default-model "claude-opus-5-5"
 	env "LITELLM_API_KEY"
 	discovery label="LiteLLM" allow-unauthenticated=#true
 }

package/src/compat/rules/providers/native-tools.kdl

@@ -0,0 +1,4 @@
+// Cursor always exposes server-owned native operations, even with an empty tool catalog.
+on-api "cursor-agent" {
+	requires-native-tools #true
+}

package/src/compat/rules/providers/opencode-zen.kdl

@@ -1,7 +1,7 @@
 // Provider-wire compat for "opencode-zen"; regenerated from the frozen census using deployment contract selectors.
 
 provider "opencode-zen" {
-	default-model "claude-opus-4-8"
+	default-model "claude-opus-5"
 	env "OPENCODE_API_KEY"
 	dynamic-models-authoritative #true
 

package/src/compat/rules/providers/output-limits.kdl

@@ -0,0 +1,4 @@
+// These transports do not encode caller output limits, regardless of provider or model name.
+on-api "openai-codex-responses" "cursor-agent" "gitlab-duo-agent" {
+	omit-max-output-tokens #true
+}