@oh-my-pi/pi-catalog 15.12.2 → 15.12.4

package/CHANGELOG.md

@@ -2,6 +2,25 @@
 
 ## [Unreleased]
 
+## [15.12.4] - 2026-06-13
+
+### Added
+
+- Added bundled Fireworks models `deepseek-v4-flash`, `kimi-k2.7-code`, `minimax-m2.5`, `minimax-m3`, `nemotron-3-ultra-nvfp4`, `qwen3.6-plus`, and `qwen3.7-plus`
+- Changed
+
+### Changed
+
+- Model `contextWindow`/`maxTokens` are now `number | null`; discovery emits `null` when a provider reports no limit, replacing the `222222`/`8888` (`UNK_CONTEXT_WINDOW`/`UNK_MAX_TOKENS`) sentinels (now removed). Bundled `models.json` unknown limits are `null`.
+- Changed the `github-copilot` model context window to `524288` tokens
+- Changed Fireworks model discovery to source the control-plane `List Models` API (`GET /v1/accounts/fireworks/models?filter=supports_serverless=true`) instead of the OpenAI-compatible `/v1/models` inference listing. The inference endpoint returns a sparse, account-specific subset that omits on-demand serverless models (e.g. `kimi-k2.7-code`), so newly published serverless models stayed invisible in the picker until hand-added to the bundled catalog. The control-plane catalog enumerates every serverless model with capability metadata (`supportsServerless`/`supportsTools`/`supportsImageInput`/`contextLength`/`displayName`), paginated and filtered to tool-capable `READY` entries, then merged with bundled/models.dev references — the Kimi K2 max-output clamp and DeepSeek V4 thinking-toggle strip are preserved, and unbundled models default to reasoning so `buildModel` derives the Fireworks effort map. New serverless releases now surface automatically with no catalog edits.
+
+### Fixed
+
+- Filled missing `contextWindow` and `maxTokens` in generated `models.json` for proxy/reseller variants by inheriting limits from canonical-family and segment-reference models
+- Ignored zero-cost `x-ai` subscription entries as reference sources when backfilling limits so inflated values are not propagated
+- Fixed the model cache opening with `PRAGMA journal_mode=WAL` before `PRAGMA busy_timeout`, so concurrent omp startups could crash inside `getDb()` on `SQLITE_BUSY` during WAL recovery instead of waiting through the transient lock. The busy handler is now installed before the first lock-taking statement ([#2421](https://github.com/can1357/oh-my-pi/issues/2421)).
+
 ## [15.11.8] - 2026-06-12
 
 ### Fixed

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

@@ -165,6 +165,7 @@ export declare function isFireworksKimiK2ModelId(modelId: string): boolean;
  * on Fireworks-backed providers, leaving every other model untouched.
  */
 export declare function clampFireworksKimiMaxTokens(modelId: string, candidate: number): number;
+export declare function clampFireworksKimiMaxTokens(modelId: string, candidate: number | null): number | null;
 /**
  * Fireworks DeepSeek V4 accepts effort via `reasoning_effort` but rejects the
  * DeepSeek-native binary `thinking` toggle when both are present.
@@ -343,7 +344,6 @@ export interface AnthropicModelManagerConfig {
     fetch?: FetchImpl;
 }
 export declare function anthropicModelManagerOptions(config?: AnthropicModelManagerConfig): ModelManagerOptions<"anthropic-messages">;
-export { UNK_CONTEXT_WINDOW, UNK_MAX_TOKENS } from "./discovery-constants";
 /** Describes how to map models.dev API data for a single provider. */
 export interface ModelsDevProviderDescriptor {
     /** Key in the models.dev API response JSON (e.g., "anthropic", "amazon-bedrock") */
@@ -386,3 +386,4 @@ export interface ModelsDevProviderDescriptor {
 export declare function mapModelsDevToModels(data: Record<string, unknown>, descriptors: readonly ModelsDevProviderDescriptor[]): ModelSpec<Api>[];
 /** All provider descriptors for models.dev data mapping in generate-models.ts. */
 export declare const MODELS_DEV_PROVIDER_DESCRIPTORS: readonly ModelsDevProviderDescriptor[];
+export {};

package/dist/types/types.d.ts

@@ -373,8 +373,8 @@ export interface Model<TApi extends Api = Api> {
     };
     /** Premium Copilot requests charged per user-initiated request (defaults to 1). */
     premiumMultiplier?: number;
-    contextWindow: number;
-    maxTokens: number;
+    contextWindow: number | null;
+    maxTokens: number | null;
     /**
      * When `true`, providers MUST omit `max_output_tokens` (Responses) /
      * `max_tokens` / `max_completion_tokens` (Completions) from the outbound

package/dist/types/utils.d.ts

@@ -1,6 +1,9 @@
 export { isRecord } from "@oh-my-pi/pi-utils";
 export declare function toNumber(value: unknown): number | undefined;
 export declare function toPositiveNumber(value: unknown, fallback: number): number;
+export declare function toPositiveNumber(value: unknown, fallback: number | null): number | null;
+/** Positive finite number, or `null` when the value is missing/non-positive. */
+export declare function toPositiveNumberOrNull(value: unknown): number | null;
 export declare function toBoolean(value: unknown): boolean | undefined;
 export declare function isAnthropicOAuthToken(key: string): boolean;
 /**

package/package.json

@@ -1,7 +1,7 @@
 {
 	"type": "module",
 	"name": "@oh-my-pi/pi-catalog",
-	"version": "15.12.2",
+	"version": "15.12.4",
 	"description": "Model catalog for omp: bundled model database, provider discovery descriptors, model identity, classification, and equivalence",
 	"homepage": "https://omp.sh",
 	"author": "Can Boluk",
@@ -34,11 +34,11 @@
 	},
 	"dependencies": {
 		"@bufbuild/protobuf": "^2.12.0",
-		"@oh-my-pi/pi-utils": "15.12.2",
-		"zod": "4.4.3"
+		"@oh-my-pi/pi-utils": "15.12.4",
+		"zod": "^4"
 	},
 	"devDependencies": {
-		"@oh-my-pi/pi-ai": "15.12.2",
+		"@oh-my-pi/pi-ai": "15.12.4",
 		"@types/bun": "^1.3.14"
 	},
 	"engines": {

package/src/discovery/antigravity.ts

@@ -1,4 +1,4 @@
-import * as z from "zod/v4";
+import { z } from "zod/v4";
 import type { ModelSpec } from "../types";
 import { toPositiveNumber } from "../utils";
 import { ANTIGRAVITY_VARIANT_COLLAPSE_TABLE, collapseEffortVariants } from "../variant-collapse";

package/src/discovery/codex.ts

@@ -1,4 +1,4 @@
-import * as z from "zod/v4";
+import { z } from "zod/v4";
 import type { ModelSpec } from "../types";
 import { isRecord } from "../utils";
 import { CODEX_BASE_URL, OPENAI_HEADER_VALUES, OPENAI_HEADERS } from "../wire/codex";

package/src/discovery/cursor.ts

@@ -1,6 +1,6 @@
 import * as http2 from "node:http2";
 import { create, fromBinary, toBinary } from "@bufbuild/protobuf";
-import * as z from "zod/v4";
+import { z } from "zod/v4";
 import { getBundledModels } from "../models";
 import { toModelSpec } from "../provider-models/bundled-references";
 import type { Model, ModelSpec } from "../types";

package/src/discovery/gemini.ts

@@ -1,7 +1,6 @@
-import * as z from "zod/v4";
+import { z } from "zod/v4";
 import { getBundledModels } from "../models";
 import { toModelSpec } from "../provider-models/bundled-references";
-import { UNK_CONTEXT_WINDOW, UNK_MAX_TOKENS } from "../provider-models/discovery-constants";
 import type { FetchImpl, Model, ModelSpec } from "../types";
 
 const GOOGLE_GENERATIVE_AI_BASE_URL = "https://generativelanguage.googleapis.com/v1beta";
@@ -148,7 +147,9 @@ function normalizeBaseUrl(baseUrl?: string): string {
 	return value.replace(/\/+$/, "");
 }
 
-function normalizePositiveInt(value: number | undefined, fallback: number): number {
+function normalizePositiveInt(value: number | undefined, fallback: number): number;
+function normalizePositiveInt(value: number | undefined, fallback: number | null): number | null;
+function normalizePositiveInt(value: number | undefined, fallback: number | null): number | null {
 	if (typeof value !== "number" || !Number.isFinite(value) || value <= 0) {
 		return fallback;
 	}
@@ -178,8 +179,8 @@ function normalizeModel(
 	}
 
 	const reference = bundledById.get(id);
-	const contextWindow = normalizePositiveInt(item.inputTokenLimit, reference?.contextWindow ?? UNK_CONTEXT_WINDOW);
-	const maxTokens = normalizePositiveInt(item.outputTokenLimit, reference?.maxTokens ?? UNK_MAX_TOKENS);
+	const contextWindow = normalizePositiveInt(item.inputTokenLimit, reference?.contextWindow ?? null);
+	const maxTokens = normalizePositiveInt(item.outputTokenLimit, reference?.maxTokens ?? null);
 	const name = normalizeModelName(item.displayName, reference?.name ?? id);
 
 	if (reference) {

package/src/discovery/openai-compatible.ts

@@ -1,5 +1,4 @@
-import * as z from "zod/v4";
-import { UNK_CONTEXT_WINDOW, UNK_MAX_TOKENS } from "../provider-models/discovery-constants";
+import { z } from "zod/v4";
 import type { Api, FetchImpl, ModelSpec, Provider } from "../types";
 
 const MODELS_PATH = "/models";
@@ -165,8 +164,8 @@ export async function fetchOpenAICompatibleModels<TApi extends Api>(
 			reasoning: false,
 			input: ["text"],
 			cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
-			contextWindow: UNK_CONTEXT_WINDOW,
-			maxTokens: UNK_MAX_TOKENS,
+			contextWindow: null,
+			maxTokens: null,
 		};
 
 		// `mapModel` returning null skips the entry (documented contract); only a

package/src/identity/equivalence.ts

@@ -61,10 +61,10 @@ const FAMILY_EXTRACTION_PATTERNS = [
 function shouldReplaceReference(existing: Model<Api> | undefined, candidate: Model<Api>): boolean {
 	if (!existing) return true;
 	if (candidate.contextWindow !== existing.contextWindow) {
-		return candidate.contextWindow > existing.contextWindow;
+		return (candidate.contextWindow ?? 0) > (existing.contextWindow ?? 0);
 	}
 	if (candidate.maxTokens !== existing.maxTokens) {
-		return candidate.maxTokens > existing.maxTokens;
+		return (candidate.maxTokens ?? 0) > (existing.maxTokens ?? 0);
 	}
 	return existing.provider !== "openai" && candidate.provider === "openai";
 }

package/src/identity/reference.ts

@@ -34,10 +34,10 @@ export function isZeroCostXaiOAuthReference(candidate: Model<Api>): boolean {
 function shouldReplaceReference(existing: Model<Api> | undefined, candidate: Model<Api>): boolean {
 	if (!existing) return true;
 	if (candidate.contextWindow !== existing.contextWindow) {
-		return candidate.contextWindow > existing.contextWindow;
+		return (candidate.contextWindow ?? 0) > (existing.contextWindow ?? 0);
 	}
 	if (candidate.maxTokens !== existing.maxTokens) {
-		return candidate.maxTokens > existing.maxTokens;
+		return (candidate.maxTokens ?? 0) > (existing.maxTokens ?? 0);
 	}
 	const existingHasCachePricing = existing.cost.cacheRead > 0 || existing.cost.cacheWrite > 0;
 	const candidateHasCachePricing = candidate.cost.cacheRead > 0 || candidate.cost.cacheWrite > 0;

package/src/model-cache.ts

@@ -7,10 +7,12 @@ import { getModelDbPath } from "@oh-my-pi/pi-utils";
 import type { Api, Model, ModelSpec } from "./types";
 
 // Rows persist ModelSpec JSON (sparse `compat`, never the resolved record);
-// the model manager rebuilds via `buildModel` on load. v5 invalidates rows
-// predating effort-tier variant collapsing (raw `-low`/`-high`/`-thinking`
-// member ids); v4 dropped the pre-efforts ThinkingConfig shape.
-const CACHE_SCHEMA_VERSION = 5;
+// the model manager rebuilds via `buildModel` on load. v6 invalidates rows
+// that may contain the retired unknown-limit sentinels (222222/8888); v5
+// invalidated rows predating effort-tier variant collapsing (raw
+// `-low`/`-high`/`-thinking` member ids); v4 dropped the pre-efforts
+// ThinkingConfig shape.
+const CACHE_SCHEMA_VERSION = 6;
 
 interface CacheRow {
 	provider_id: string;
@@ -51,8 +53,10 @@ function getDb(dbPath?: string): Database {
 		sharedDb.close();
 	}
 	const db = new Database(resolvedPath, { create: true });
-	db.run("PRAGMA journal_mode = WAL");
+	// Install the busy handler BEFORE any lock-taking statement. See
+	// https://github.com/can1357/oh-my-pi/issues/2421.
 	db.run("PRAGMA busy_timeout = 3000");
+	db.run("PRAGMA journal_mode = WAL");
 	db.run(`
 		CREATE TABLE IF NOT EXISTS model_cache (
 			provider_id TEXT PRIMARY KEY,

package/src/model-manager.ts

@@ -363,11 +363,13 @@ function preferDiscoveryName(discoveryName: string, fallbackName: string, modelI
 	return normalizedDiscoveryName;
 }
 
-function preferDiscoveryLimit(discoveryLimit: number, fallbackLimit: number): number {
-	if (!Number.isFinite(discoveryLimit) || discoveryLimit <= 0) {
+function preferDiscoveryLimit(discoveryLimit: number, fallbackLimit: number): number;
+function preferDiscoveryLimit(discoveryLimit: number | null, fallbackLimit: number | null): number | null;
+function preferDiscoveryLimit(discoveryLimit: number | null, fallbackLimit: number | null): number | null {
+	if (discoveryLimit === null || !Number.isFinite(discoveryLimit) || discoveryLimit <= 0) {
 		return fallbackLimit;
 	}
-	if (discoveryLimit === 4096 && fallbackLimit > discoveryLimit) {
+	if (discoveryLimit === 4096 && fallbackLimit !== null && fallbackLimit > discoveryLimit) {
 		return fallbackLimit;
 	}
 	return discoveryLimit;
@@ -428,11 +430,11 @@ function isModelLike(value: unknown): value is ModelSpec<Api> {
 	}
 	// Finite positive: NaN > 0 is false, +Infinity < Infinity is false.
 	const cw = v.contextWindow;
-	if (typeof cw !== "number" || !(cw > 0 && cw < Infinity)) {
+	if (cw !== null && (typeof cw !== "number" || !(cw > 0 && cw < Infinity))) {
 		return false;
 	}
 	const mt = v.maxTokens;
-	if (typeof mt !== "number" || !(mt > 0 && mt < Infinity)) {
+	if (mt !== null && (typeof mt !== "number" || !(mt > 0 && mt < Infinity))) {
 		return false;
 	}
 	return true;