fix(hooks): extract model from assistant messages with flat modelID/providerID

OpenCode API returns different structures for user vs assistant messages:
- User: info.model = { providerID, modelID } (nested)
- Assistant: info.modelID, info.providerID (flat top-level)

Previous code only checked nested format, causing model info loss when
continuation hooks fired after assistant messages.

Files modified:
- todo-continuation-enforcer.ts
- ralph-loop/index.ts
- sisyphus-task/tools.ts
- background-agent/manager.ts

Added test for assistant message model extraction.

src/hooks/todo-continuation-enforcer.test.ts

@@ -829,4 +829,50 @@ describe("todo-continuation-enforcer", () => {
     expect(promptCalls[0].text).toContain("TODO CONTINUATION")
     expect("model" in promptCalls[0]).toBe(true)
   })
+
+  test("should extract model from assistant message with flat modelID/providerID", async () => {
+    // #given - session with assistant message that has flat modelID/providerID (OpenCode API format)
+    const sessionID = "main-assistant-model"
+    setMainSession(sessionID)
+
+    // OpenCode returns assistant messages with flat modelID/providerID, not nested model object
+    const mockMessagesWithAssistant = [
+      { info: { id: "msg-1", role: "user", agent: "Sisyphus", model: { providerID: "openai", modelID: "gpt-5.2" } } },
+      { info: { id: "msg-2", role: "assistant", agent: "Sisyphus", modelID: "gpt-5.2", providerID: "openai" } },
+    ]
+
+    const mockInput = {
+      client: {
+        session: {
+          todo: async () => ({
+            data: [{ id: "1", content: "Task 1", status: "pending", priority: "high" }],
+          }),
+          messages: async () => ({ data: mockMessagesWithAssistant }),
+          prompt: async (opts: any) => {
+            promptCalls.push({
+              sessionID: opts.path.id,
+              agent: opts.body.agent,
+              model: opts.body.model,
+              text: opts.body.parts[0].text,
+            })
+            return {}
+          },
+        },
+        tui: { showToast: async () => ({}) },
+      },
+      directory: "/tmp/test",
+    } as any
+
+    const hook = createTodoContinuationEnforcer(mockInput, {
+      backgroundManager: createMockBackgroundManager(false),
+    })
+
+    // #when - session goes idle
+    await hook.handler({ event: { type: "session.idle", properties: { sessionID } } })
+    await new Promise(r => setTimeout(r, 2500))
+
+    // #then - model should be extracted from assistant message's flat modelID/providerID
+    expect(promptCalls.length).toBe(1)
+    expect(promptCalls[0].model).toEqual({ providerID: "openai", modelID: "gpt-5.2" })
+  })
 })