diff --git a/src/agents/utils.test.ts b/src/agents/utils.test.ts
index 66a37a18..352c1a61 100644
--- a/src/agents/utils.test.ts
+++ b/src/agents/utils.test.ts
@@ -1,7 +1,8 @@
-import { describe, test, expect, beforeEach } from "bun:test"
+import { describe, test, expect, beforeEach, spyOn, afterEach } from "bun:test"
 import { createBuiltinAgents } from "./utils"
 import type { AgentConfig } from "@opencode-ai/sdk"
 import { clearSkillCache } from "../features/opencode-skill-loader/skill-content"
+import * as connectedProvidersCache from "../shared/connected-providers-cache"
 
 const TEST_DEFAULT_MODEL = "anthropic/claude-opus-4-5"
 
@@ -46,17 +47,32 @@ describe("createBuiltinAgents with model overrides", () => {
     expect(agents.sisyphus.reasoningEffort).toBeUndefined()
   })
 
-  test("Oracle uses first fallback entry when no availableModels provided (no cache scenario)", async () => {
-    // #given - no available models simulates CI without model cache
+  test("Oracle uses connected provider when no availableModels but connected cache exists", async () => {
+    // #given - connected providers cache exists with openai
+    const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(["openai"])
 
     // #when
     const agents = await createBuiltinAgents([], {}, undefined, TEST_DEFAULT_MODEL)
 
-    // #then - uses first fallback entry (openai/gpt-5.2) instead of system default
+    // #then - uses openai from connected cache
     expect(agents.oracle.model).toBe("openai/gpt-5.2")
     expect(agents.oracle.reasoningEffort).toBe("medium")
     expect(agents.oracle.textVerbosity).toBe("high")
     expect(agents.oracle.thinking).toBeUndefined()
+    cacheSpy.mockRestore()
+  })
+
+  test("Oracle created without model field when no cache exists (first run scenario)", async () => {
+    // #given - no cache at all (first run)
+    const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(null)
+
+    // #when
+    const agents = await createBuiltinAgents([], {}, undefined, TEST_DEFAULT_MODEL)
+
+    // #then - oracle should be created with system default model (fallback to systemDefaultModel)
+    expect(agents.oracle).toBeDefined()
+    expect(agents.oracle.model).toBe(TEST_DEFAULT_MODEL)
+    cacheSpy.mockRestore()
   })
 
   test("Oracle with GPT model override has reasoningEffort, no thinking", async () => {
@@ -107,26 +123,42 @@ describe("createBuiltinAgents with model overrides", () => {
 })
 
 describe("createBuiltinAgents without systemDefaultModel", () => {
-  test("creates agents successfully without systemDefaultModel", async () => {
-    // #given - no systemDefaultModel provided
+  test("creates agents with connected provider when cache exists", async () => {
+    // #given - connected providers cache exists
+    const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(["openai"])
 
     // #when
     const agents = await createBuiltinAgents([], {}, undefined, undefined)
 
-    // #then - agents should still be created using fallback chain
+    // #then - agents should use connected provider from fallback chain
     expect(agents.oracle).toBeDefined()
     expect(agents.oracle.model).toBe("openai/gpt-5.2")
+    cacheSpy.mockRestore()
   })
 
-  test("sisyphus uses fallback chain when systemDefaultModel undefined", async () => {
-    // #given - no systemDefaultModel
+  test("agents NOT created when no cache and no systemDefaultModel (first run without defaults)", async () => {
+    // #given - no cache and no system default
+    const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(null)
 
     // #when
     const agents = await createBuiltinAgents([], {}, undefined, undefined)
 
-    // #then - sisyphus should use its fallback chain
+    // #then - oracle should NOT be created (resolveModelWithFallback returns undefined)
+    expect(agents.oracle).toBeUndefined()
+    cacheSpy.mockRestore()
+  })
+
+  test("sisyphus uses connected provider when cache exists", async () => {
+    // #given - connected providers cache exists with anthropic
+    const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(["anthropic"])
+
+    // #when
+    const agents = await createBuiltinAgents([], {}, undefined, undefined)
+
+    // #then - sisyphus should use anthropic from connected cache
     expect(agents.sisyphus).toBeDefined()
     expect(agents.sisyphus.model).toBe("anthropic/claude-opus-4-5")
+    cacheSpy.mockRestore()
   })
 })
 
diff --git a/src/shared/model-resolver.test.ts b/src/shared/model-resolver.test.ts
index d4b0dde0..eba415e4 100644
--- a/src/shared/model-resolver.test.ts
+++ b/src/shared/model-resolver.test.ts
@@ -1,6 +1,7 @@
-import { describe, expect, test, spyOn, beforeEach, afterEach } from "bun:test"
+import { describe, expect, test, spyOn, beforeEach, afterEach, mock } from "bun:test"
 import { resolveModel, resolveModelWithFallback, type ModelResolutionInput, type ExtendedModelResolutionInput, type ModelResolutionResult, type ModelSource } from "./model-resolver"
 import * as logger from "./logger"
+import * as connectedProvidersCache from "./connected-providers-cache"
 
 describe("resolveModel", () => {
   describe("priority chain", () => {
@@ -336,8 +337,48 @@ describe("resolveModelWithFallback", () => {
       expect(logSpy).toHaveBeenCalledWith("No available model found in fallback chain, falling through to system default")
     })
 
-    test("uses first fallback entry when availableModels is empty (no cache scenario)", () => {
-      // #given - empty availableModels simulates CI environment without model cache
+    test("returns undefined when availableModels empty and no connected providers cache exists", () => {
+      // #given - both model cache and connected-providers cache are missing (first run)
+      const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(null)
+      const input: ExtendedModelResolutionInput = {
+        fallbackChain: [
+          { providers: ["anthropic"], model: "claude-opus-4-5" },
+        ],
+        availableModels: new Set(),
+        systemDefaultModel: undefined, // no system default configured
+      }
+
+      // #when
+      const result = resolveModelWithFallback(input)
+
+      // #then - should return undefined to let OpenCode use Provider.defaultModel()
+      expect(result).toBeUndefined()
+      cacheSpy.mockRestore()
+    })
+
+    test("uses connected provider when availableModels empty but connected providers cache exists", () => {
+      // #given - model cache missing but connected-providers cache exists
+      const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(["openai", "google"])
+      const input: ExtendedModelResolutionInput = {
+        fallbackChain: [
+          { providers: ["anthropic", "openai"], model: "claude-opus-4-5" },
+        ],
+        availableModels: new Set(),
+        systemDefaultModel: "google/gemini-3-pro",
+      }
+
+      // #when
+      const result = resolveModelWithFallback(input)
+
+      // #then - should use openai (second provider) since anthropic not in connected cache
+      expect(result!.model).toBe("openai/claude-opus-4-5")
+      expect(result!.source).toBe("provider-fallback")
+      cacheSpy.mockRestore()
+    })
+
+    test("falls through to system default when no cache and systemDefaultModel is provided", () => {
+      // #given - no cache but system default is configured
+      const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(null)
       const input: ExtendedModelResolutionInput = {
         fallbackChain: [
           { providers: ["anthropic"], model: "claude-opus-4-5" },
@@ -349,9 +390,10 @@ describe("resolveModelWithFallback", () => {
       // #when
       const result = resolveModelWithFallback(input)
 
-      // #then - should use first fallback entry, not system default
-      expect(result!.model).toBe("anthropic/claude-opus-4-5")
-      expect(result!.source).toBe("provider-fallback")
+      // #then - should fall through to system default
+      expect(result!.model).toBe("google/gemini-3-pro")
+      expect(result!.source).toBe("system-default")
+      cacheSpy.mockRestore()
     })
 
     test("returns system default when fallbackChain is not provided", () => {
diff --git a/src/shared/model-resolver.ts b/src/shared/model-resolver.ts
index 2fb8a07e..627d1ab1 100644
--- a/src/shared/model-resolver.ts
+++ b/src/shared/model-resolver.ts
@@ -58,25 +58,26 @@ export function resolveModelWithFallback(
 			const connectedProviders = readConnectedProvidersCache()
 			const connectedSet = connectedProviders ? new Set(connectedProviders) : null
 
-			for (const entry of fallbackChain) {
-				for (const provider of entry.providers) {
-					if (connectedSet === null || connectedSet.has(provider)) {
-						const model = `${provider}/${entry.model}`
-						log("Model resolved via fallback chain (no model cache, using connected provider)", { 
-							provider, 
-							model: entry.model, 
-							variant: entry.variant,
-							hasConnectedCache: connectedSet !== null
-						})
-						return { model, source: "provider-fallback", variant: entry.variant }
+			// When no cache exists at all, skip fallback chain and fall through to system default
+			// This allows OpenCode to use Provider.defaultModel() as the final fallback
+			if (connectedSet === null) {
+				log("No cache available, skipping fallback chain to use system default")
+			} else {
+				for (const entry of fallbackChain) {
+					for (const provider of entry.providers) {
+						if (connectedSet.has(provider)) {
+							const model = `${provider}/${entry.model}`
+							log("Model resolved via fallback chain (no model cache, using connected provider)", { 
+								provider, 
+								model: entry.model, 
+								variant: entry.variant,
+							})
+							return { model, source: "provider-fallback", variant: entry.variant }
+						}
 					}
 				}
+				log("No matching provider in connected cache, falling through to system default")
 			}
-			const firstEntry = fallbackChain[0]
-			const firstProvider = firstEntry.providers[0]
-			const model = `${firstProvider}/${firstEntry.model}`
-			log("Model resolved via fallback chain (no cache at all, using first entry)", { provider: firstProvider, model: firstEntry.model, variant: firstEntry.variant })
-			return { model, source: "provider-fallback", variant: firstEntry.variant }
 		}
 
 		for (const entry of fallbackChain) {