feat(FN-1191): hot-swap active executor sessions on model changes
- Show resolved default executor, validator, and planning models in the task Model tab - Pass merged settings into the Model tab from TaskDetailModal so default badges reflect effective runtime resolution - Hot-swap active single-session executor models when task overrides change, including fallback to project defaults when overrides are cleared - Add dashboard and executor tests for default model display, hot-swap behavior, fallback logic, and failure logging - Document hot-swap behavior and limitations in AGENTS.md and add a patch changeset for @gsxdsm/fusion
This commit is contained in:
@@ -88,6 +88,14 @@ vi.mock("@mariozechner/pi-coding-agent", () => {
|
||||
open: vi.fn().mockReturnValue(mockSessionManager),
|
||||
inMemory: vi.fn().mockReturnValue(mockSessionManager),
|
||||
},
|
||||
ModelRegistry: vi.fn().mockImplementation(() => ({
|
||||
find: vi.fn(),
|
||||
refresh: vi.fn(),
|
||||
})),
|
||||
AuthStorage: {
|
||||
create: vi.fn().mockReturnValue({}),
|
||||
},
|
||||
getAgentDir: vi.fn().mockReturnValue("/tmp/agent-dir"),
|
||||
};
|
||||
});
|
||||
|
||||
@@ -2812,6 +2820,196 @@ describe("TaskExecutor pause behavior", () => {
|
||||
});
|
||||
});
|
||||
|
||||
describe("TaskExecutor executor model hot-swap", () => {
|
||||
const buildUpdatedTask = (overrides: Partial<Task> = {}): Task => ({
|
||||
id: "FN-001",
|
||||
title: "Model task",
|
||||
description: "Test model updates",
|
||||
column: "in-progress",
|
||||
paused: false,
|
||||
dependencies: [],
|
||||
steps: [],
|
||||
currentStep: 0,
|
||||
log: [],
|
||||
createdAt: new Date().toISOString(),
|
||||
updatedAt: new Date().toISOString(),
|
||||
...overrides,
|
||||
});
|
||||
|
||||
const flushTaskUpdated = async () => {
|
||||
await new Promise((resolve) => setTimeout(resolve, 20));
|
||||
};
|
||||
|
||||
beforeEach(() => {
|
||||
vi.clearAllMocks();
|
||||
});
|
||||
|
||||
it("hot-swaps executor model on active session when modelProvider/modelId change", async () => {
|
||||
const store = createMockStore();
|
||||
const setModel = vi.fn().mockResolvedValue(undefined);
|
||||
const findModel = vi.fn().mockReturnValue({
|
||||
provider: { name: "openai" },
|
||||
id: "gpt-4o",
|
||||
name: "GPT-4o",
|
||||
});
|
||||
|
||||
const executor = new TaskExecutor(store, "/tmp/test");
|
||||
(executor as any)._modelRegistry = { find: findModel };
|
||||
(executor as any).activeSessions.set("FN-001", {
|
||||
session: { setModel, dispose: vi.fn() },
|
||||
seenSteeringIds: new Set(),
|
||||
lastModelProvider: "anthropic",
|
||||
lastModelId: "claude-sonnet-4-5",
|
||||
});
|
||||
|
||||
store._trigger("task:updated", buildUpdatedTask({
|
||||
modelProvider: "openai",
|
||||
modelId: "gpt-4o",
|
||||
}));
|
||||
|
||||
await flushTaskUpdated();
|
||||
|
||||
expect(setModel).toHaveBeenCalledTimes(1);
|
||||
expect(setModel).toHaveBeenCalledWith(expect.objectContaining({
|
||||
provider: expect.objectContaining({ name: "openai" }),
|
||||
id: "gpt-4o",
|
||||
}));
|
||||
expect(store.logEntry).toHaveBeenCalledWith("FN-001", "Model changed to openai/gpt-4o");
|
||||
});
|
||||
|
||||
it("does not attempt hot-swap when no active session exists", async () => {
|
||||
const store = createMockStore();
|
||||
const setModel = vi.fn().mockResolvedValue(undefined);
|
||||
|
||||
new TaskExecutor(store, "/tmp/test");
|
||||
|
||||
store._trigger("task:updated", buildUpdatedTask({
|
||||
modelProvider: "openai",
|
||||
modelId: "gpt-4o",
|
||||
}));
|
||||
|
||||
await flushTaskUpdated();
|
||||
|
||||
expect(setModel).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it("does not hot-swap when model fields are unchanged", async () => {
|
||||
const store = createMockStore();
|
||||
const setModel = vi.fn().mockResolvedValue(undefined);
|
||||
const findModel = vi.fn();
|
||||
|
||||
const executor = new TaskExecutor(store, "/tmp/test");
|
||||
(executor as any)._modelRegistry = { find: findModel };
|
||||
(executor as any).activeSessions.set("FN-001", {
|
||||
session: { setModel, dispose: vi.fn() },
|
||||
seenSteeringIds: new Set(),
|
||||
lastModelProvider: "anthropic",
|
||||
lastModelId: "claude-sonnet-4-5",
|
||||
});
|
||||
|
||||
store._trigger("task:updated", buildUpdatedTask({
|
||||
modelProvider: "anthropic",
|
||||
modelId: "claude-sonnet-4-5",
|
||||
}));
|
||||
|
||||
await flushTaskUpdated();
|
||||
|
||||
expect(findModel).not.toHaveBeenCalled();
|
||||
expect(setModel).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it("hot-swaps to settings default when override is cleared", async () => {
|
||||
const store = createMockStore();
|
||||
const setModel = vi.fn().mockResolvedValue(undefined);
|
||||
const findModel = vi.fn().mockReturnValue({
|
||||
provider: { name: "openai" },
|
||||
id: "gpt-4o",
|
||||
name: "GPT-4o",
|
||||
});
|
||||
|
||||
store.getSettings.mockResolvedValue({
|
||||
defaultProvider: "openai",
|
||||
defaultModelId: "gpt-4o",
|
||||
});
|
||||
|
||||
const executor = new TaskExecutor(store, "/tmp/test");
|
||||
(executor as any)._modelRegistry = { find: findModel };
|
||||
(executor as any).activeSessions.set("FN-001", {
|
||||
session: { setModel, dispose: vi.fn() },
|
||||
seenSteeringIds: new Set(),
|
||||
lastModelProvider: "anthropic",
|
||||
lastModelId: "claude-sonnet-4-5",
|
||||
});
|
||||
|
||||
store._trigger("task:updated", buildUpdatedTask({
|
||||
modelProvider: undefined,
|
||||
modelId: undefined,
|
||||
}));
|
||||
|
||||
await flushTaskUpdated();
|
||||
|
||||
expect(findModel).toHaveBeenCalledWith("openai", "gpt-4o");
|
||||
expect(setModel).toHaveBeenCalledTimes(1);
|
||||
});
|
||||
|
||||
it("logs error and continues when setModel fails", async () => {
|
||||
const store = createMockStore();
|
||||
const setModel = vi.fn().mockRejectedValue(new Error("API key not found"));
|
||||
const findModel = vi.fn().mockReturnValue({
|
||||
provider: { name: "openai" },
|
||||
id: "gpt-4o",
|
||||
name: "GPT-4o",
|
||||
});
|
||||
|
||||
const executor = new TaskExecutor(store, "/tmp/test");
|
||||
(executor as any)._modelRegistry = { find: findModel };
|
||||
(executor as any).activeSessions.set("FN-001", {
|
||||
session: { setModel, dispose: vi.fn() },
|
||||
seenSteeringIds: new Set(),
|
||||
lastModelProvider: "anthropic",
|
||||
lastModelId: "claude-sonnet-4-5",
|
||||
});
|
||||
|
||||
store._trigger("task:updated", buildUpdatedTask({
|
||||
modelProvider: "openai",
|
||||
modelId: "gpt-4o",
|
||||
}));
|
||||
|
||||
await flushTaskUpdated();
|
||||
|
||||
expect(store.logEntry).toHaveBeenCalledWith("FN-001", "Model change failed: API key not found");
|
||||
expect((executor as any).activeSessions.has("FN-001")).toBe(true);
|
||||
});
|
||||
|
||||
it("does not attempt hot-swap on paused task", async () => {
|
||||
const store = createMockStore();
|
||||
const setModel = vi.fn().mockResolvedValue(undefined);
|
||||
const dispose = vi.fn();
|
||||
const findModel = vi.fn();
|
||||
|
||||
const executor = new TaskExecutor(store, "/tmp/test");
|
||||
(executor as any)._modelRegistry = { find: findModel };
|
||||
(executor as any).activeSessions.set("FN-001", {
|
||||
session: { setModel, dispose },
|
||||
seenSteeringIds: new Set(),
|
||||
lastModelProvider: "anthropic",
|
||||
lastModelId: "claude-sonnet-4-5",
|
||||
});
|
||||
|
||||
store._trigger("task:updated", buildUpdatedTask({
|
||||
paused: true,
|
||||
modelProvider: "openai",
|
||||
modelId: "gpt-4o",
|
||||
}));
|
||||
|
||||
await flushTaskUpdated();
|
||||
|
||||
expect(dispose).toHaveBeenCalledTimes(1);
|
||||
expect(findModel).not.toHaveBeenCalled();
|
||||
expect(setModel).not.toHaveBeenCalled();
|
||||
});
|
||||
});
|
||||
|
||||
describe("TaskExecutor global pause behavior", () => {
|
||||
beforeEach(() => {
|
||||
vi.clearAllMocks();
|
||||
|
||||
@@ -9,7 +9,7 @@ import { generateWorktreeName, slugify } from "./worktree-names.js";
|
||||
import { Type, type Static } from "@mariozechner/pi-ai";
|
||||
import { createKbAgent, describeModel, promptWithFallback, compactSessionContext } from "./pi.js";
|
||||
import { reviewStep, type ReviewVerdict } from "./reviewer.js";
|
||||
import { SessionManager, type ToolDefinition, type AgentSession } from "@mariozechner/pi-coding-agent";
|
||||
import { AuthStorage, ModelRegistry, SessionManager, getAgentDir, type ToolDefinition, type AgentSession } from "@mariozechner/pi-coding-agent";
|
||||
import { PRIORITY_EXECUTE, type AgentSemaphore } from "./concurrency.js";
|
||||
import type { WorktreePool } from "./worktree-pool.js";
|
||||
import { AgentLogger } from "./agent-logger.js";
|
||||
@@ -241,6 +241,8 @@ export class TaskExecutor {
|
||||
private activeSessions = new Map<string, {
|
||||
session: AgentSession;
|
||||
seenSteeringIds: Set<string>;
|
||||
lastModelProvider?: string | null;
|
||||
lastModelId?: string | null;
|
||||
}>();
|
||||
/** Active step-session executors per task (mutually exclusive with activeSessions). */
|
||||
private activeStepExecutors = new Map<string, StepSessionExecutor>();
|
||||
@@ -262,6 +264,16 @@ export class TaskExecutor {
|
||||
private totalSpawnedCount = 0;
|
||||
/** Token cap detector for proactive context compaction. */
|
||||
private tokenCapDetector = new TokenCapDetector();
|
||||
private _modelRegistry?: InstanceType<typeof ModelRegistry>;
|
||||
|
||||
private get modelRegistry(): InstanceType<typeof ModelRegistry> {
|
||||
if (!this._modelRegistry) {
|
||||
const authStorage = AuthStorage.create();
|
||||
this._modelRegistry = new ModelRegistry(authStorage, join(getAgentDir(), "models.json"));
|
||||
this._modelRegistry.refresh();
|
||||
}
|
||||
return this._modelRegistry;
|
||||
}
|
||||
|
||||
/** Returns the set of task IDs currently being executed. */
|
||||
getExecutingTaskIds(): Set<string> {
|
||||
@@ -344,6 +356,42 @@ export class TaskExecutor {
|
||||
return;
|
||||
}
|
||||
|
||||
// Handle executor model hot-swap on active single-session executions
|
||||
if (this.activeSessions.has(task.id) && !task.paused) {
|
||||
const activeEntry = this.activeSessions.get(task.id)!;
|
||||
const providerChanged = task.modelProvider !== activeEntry.lastModelProvider;
|
||||
const modelIdChanged = task.modelId !== activeEntry.lastModelId;
|
||||
|
||||
if (providerChanged || modelIdChanged) {
|
||||
activeEntry.lastModelProvider = task.modelProvider;
|
||||
activeEntry.lastModelId = task.modelId;
|
||||
|
||||
const settings = await this.store.getSettings();
|
||||
const newProvider = task.modelProvider && task.modelId
|
||||
? task.modelProvider
|
||||
: settings?.defaultProvider;
|
||||
const newModelId = task.modelProvider && task.modelId
|
||||
? task.modelId
|
||||
: settings?.defaultModelId;
|
||||
|
||||
if (newProvider && newModelId) {
|
||||
try {
|
||||
const model = this.modelRegistry.find(newProvider, newModelId);
|
||||
if (model) {
|
||||
await activeEntry.session.setModel(model);
|
||||
executorLog.log(`${task.id}: executor model hot-swapped to ${newProvider}/${newModelId}`);
|
||||
await this.store.logEntry(task.id, `Model changed to ${newProvider}/${newModelId}`);
|
||||
} else {
|
||||
executorLog.log(`${task.id}: model ${newProvider}/${newModelId} not found in registry for hot-swap`);
|
||||
}
|
||||
} catch (err: any) {
|
||||
executorLog.error(`${task.id}: failed to hot-swap model: ${err.message}`);
|
||||
await this.store.logEntry(task.id, `Model change failed: ${err.message}`);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Handle steering comments - inject new ones into the running session
|
||||
// Only process if session is active (activeSessions check is sufficient
|
||||
// since entries are only added when a task is in-progress)
|
||||
@@ -1061,7 +1109,12 @@ export class TaskExecutor {
|
||||
seenSteeringIds.add(comment.id);
|
||||
}
|
||||
}
|
||||
this.activeSessions.set(task.id, { session, seenSteeringIds });
|
||||
this.activeSessions.set(task.id, {
|
||||
session,
|
||||
seenSteeringIds,
|
||||
lastModelProvider: detail.modelProvider,
|
||||
lastModelId: detail.modelId,
|
||||
});
|
||||
|
||||
// Register with stuck task detector for heartbeat monitoring
|
||||
stuckDetector?.trackTask(task.id, session);
|
||||
@@ -1232,7 +1285,12 @@ export class TaskExecutor {
|
||||
// Reassign so finally{} disposes the correct session
|
||||
session = retrySession;
|
||||
sessionRef.current = retrySession;
|
||||
this.activeSessions.set(task.id, { session: retrySession, seenSteeringIds });
|
||||
this.activeSessions.set(task.id, {
|
||||
session: retrySession,
|
||||
seenSteeringIds,
|
||||
lastModelProvider: detail.modelProvider,
|
||||
lastModelId: detail.modelId,
|
||||
});
|
||||
stuckDetector?.trackTask(task.id, retrySession);
|
||||
|
||||
const retryPrompt = [
|
||||
|
||||
Reference in New Issue
Block a user