fix(provider-cache): extract models from provider.list().all response

OpenCode SDK does not expose client.model.list API. This caused the
provider-models cache to always be empty (models: {}), which in turn
caused delegate-task categories with requiresModel (e.g., 'deep',
'artistry') to fail with misleading 'Unknown category' errors.

Changes:
- connected-providers-cache.ts: Extract models from provider.list()
  response's .all array instead of calling non-existent client.model.list
- category-resolver.ts: Distinguish between 'unknown category' and
  'model not available' errors with clearer error messages
- Add comprehensive tests for both fixes

Bug chain:
client.model?.list is undefined -> empty cache -> isModelAvailable
returns false for requiresModel categories -> null returned from
resolveCategoryConfig -> 'Unknown category' error (wrong message)

src/shared/connected-providers-cache.test.ts

@@ -0,0 +1,133 @@
+import { describe, test, expect, beforeEach, afterEach, spyOn } from "bun:test"
+import { existsSync, mkdirSync, rmSync } from "fs"
+import { join } from "path"
+import * as dataPath from "./data-path"
+import { updateConnectedProvidersCache, readProviderModelsCache } from "./connected-providers-cache"
+
+const TEST_CACHE_DIR = join(import.meta.dir, "__test-cache__")
+
+describe("updateConnectedProvidersCache", () => {
+	let cacheDirSpy: ReturnType<typeof spyOn>
+
+	beforeEach(() => {
+		cacheDirSpy = spyOn(dataPath, "getOmoOpenCodeCacheDir").mockReturnValue(TEST_CACHE_DIR)
+		if (existsSync(TEST_CACHE_DIR)) {
+			rmSync(TEST_CACHE_DIR, { recursive: true })
+		}
+		mkdirSync(TEST_CACHE_DIR, { recursive: true })
+	})
+
+	afterEach(() => {
+		cacheDirSpy.mockRestore()
+		if (existsSync(TEST_CACHE_DIR)) {
+			rmSync(TEST_CACHE_DIR, { recursive: true })
+		}
+	})
+
+	test("extracts models from provider.list().all response", async () => {
+		//#given
+		const mockClient = {
+			provider: {
+				list: async () => ({
+					data: {
+						connected: ["openai", "anthropic"],
+						all: [
+							{
+								id: "openai",
+								name: "OpenAI",
+								env: [],
+								models: {
+									"gpt-5.3-codex": { id: "gpt-5.3-codex", name: "GPT-5.3 Codex" },
+									"gpt-5.2": { id: "gpt-5.2", name: "GPT-5.2" },
+								},
+							},
+							{
+								id: "anthropic",
+								name: "Anthropic",
+								env: [],
+								models: {
+									"claude-opus-4-6": { id: "claude-opus-4-6", name: "Claude Opus 4.6" },
+									"claude-sonnet-4-5": { id: "claude-sonnet-4-5", name: "Claude Sonnet 4.5" },
+								},
+							},
+						],
+					},
+				}),
+			},
+		}
+
+		//#when
+		await updateConnectedProvidersCache(mockClient)
+
+		//#then
+		const cache = readProviderModelsCache()
+		expect(cache).not.toBeNull()
+		expect(cache!.connected).toEqual(["openai", "anthropic"])
+		expect(cache!.models).toEqual({
+			openai: ["gpt-5.3-codex", "gpt-5.2"],
+			anthropic: ["claude-opus-4-6", "claude-sonnet-4-5"],
+		})
+	})
+
+	test("writes empty models when provider has no models", async () => {
+		//#given
+		const mockClient = {
+			provider: {
+				list: async () => ({
+					data: {
+						connected: ["empty-provider"],
+						all: [
+							{
+								id: "empty-provider",
+								name: "Empty",
+								env: [],
+								models: {},
+							},
+						],
+					},
+				}),
+			},
+		}
+
+		//#when
+		await updateConnectedProvidersCache(mockClient)
+
+		//#then
+		const cache = readProviderModelsCache()
+		expect(cache).not.toBeNull()
+		expect(cache!.models).toEqual({})
+	})
+
+	test("writes empty models when all field is missing", async () => {
+		//#given
+		const mockClient = {
+			provider: {
+				list: async () => ({
+					data: {
+						connected: ["openai"],
+					},
+				}),
+			},
+		}
+
+		//#when
+		await updateConnectedProvidersCache(mockClient)
+
+		//#then
+		const cache = readProviderModelsCache()
+		expect(cache).not.toBeNull()
+		expect(cache!.models).toEqual({})
+	})
+
+	test("does nothing when client.provider.list is not available", async () => {
+		//#given
+		const mockClient = {}
+
+		//#when
+		await updateConnectedProvidersCache(mockClient)
+
+		//#then
+		const cache = readProviderModelsCache()
+		expect(cache).toBeNull()
+	})
+})

src/shared/connected-providers-cache.ts

@@ -149,10 +149,12 @@ export function writeProviderModelsCache(data: { models: Record<string, string[]
  */
 export async function updateConnectedProvidersCache(client: {
 	provider?: {
-		list?: () => Promise<{ data?: { connected?: string[] } }>
-	}
-	model?: {
-		list?: () => Promise<{ data?: Array<{ id: string; provider: string }> }>
+		list?: () => Promise<{
+			data?: {
+				connected?: string[]
+				all?: Array<{ id: string; models?: Record<string, unknown> }>
+			}
+		}>
 	}
 }): Promise<void> {
 	if (!client?.provider?.list) {
@@ -167,31 +169,23 @@ export async function updateConnectedProvidersCache(client: {
 
 		writeConnectedProvidersCache(connected)
 
-		// Always update provider-models cache (overwrite with fresh data)
-		let modelsByProvider: Record<string, string[]> = {}
-		if (client.model?.list) {
-			try {
-				const modelsResult = await client.model.list()
-				const models = modelsResult.data ?? []
+		const modelsByProvider: Record<string, string[]> = {}
+		const allProviders = result.data?.all ?? []
 
-				for (const model of models) {
-					if (!modelsByProvider[model.provider]) {
-						modelsByProvider[model.provider] = []
-					}
-					modelsByProvider[model.provider].push(model.id)
+		for (const provider of allProviders) {
+			if (provider.models) {
+				const modelIds = Object.keys(provider.models)
+				if (modelIds.length > 0) {
+					modelsByProvider[provider.id] = modelIds
 				}
-
-				log("[connected-providers-cache] Fetched models from API", {
-					providerCount: Object.keys(modelsByProvider).length,
-					totalModels: models.length,
-				})
-			} catch (modelErr) {
-				log("[connected-providers-cache] Error fetching models, writing empty cache", { error: String(modelErr) })
 			}
-		} else {
-			log("[connected-providers-cache] client.model.list not available, writing empty cache")
 		}
 
+		log("[connected-providers-cache] Extracted models from provider list", {
+			providerCount: Object.keys(modelsByProvider).length,
+			totalModels: Object.values(modelsByProvider).reduce((sum, ids) => sum + ids.length, 0),
+		})
+
 		writeProviderModelsCache({
 			models: modelsByProvider,
 			connected,