Compare commits
7 Commits
fix/issue-
...
fix/issue-
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
b1946a6397 | ||
|
|
6edbc9638a | ||
|
|
af32f2e258 | ||
|
|
e7e6bd0608 | ||
|
|
7f86103666 | ||
|
|
2c6ba98920 | ||
|
|
80dee4d2c9 |
@@ -3678,16 +3678,6 @@
|
||||
"minimum": 0
|
||||
}
|
||||
},
|
||||
"maxDepth": {
|
||||
"type": "integer",
|
||||
"minimum": 1,
|
||||
"maximum": 9007199254740991
|
||||
},
|
||||
"maxDescendants": {
|
||||
"type": "integer",
|
||||
"minimum": 1,
|
||||
"maximum": 9007199254740991
|
||||
},
|
||||
"staleTimeoutMs": {
|
||||
"type": "number",
|
||||
"minimum": 60000
|
||||
|
||||
@@ -3,54 +3,6 @@ import { ZodError } from "zod/v4"
|
||||
import { BackgroundTaskConfigSchema } from "./background-task"
|
||||
|
||||
describe("BackgroundTaskConfigSchema", () => {
|
||||
describe("maxDepth", () => {
|
||||
describe("#given valid maxDepth (3)", () => {
|
||||
test("#when parsed #then returns correct value", () => {
|
||||
const result = BackgroundTaskConfigSchema.parse({ maxDepth: 3 })
|
||||
|
||||
expect(result.maxDepth).toBe(3)
|
||||
})
|
||||
})
|
||||
|
||||
describe("#given maxDepth below minimum (0)", () => {
|
||||
test("#when parsed #then throws ZodError", () => {
|
||||
let thrownError: unknown
|
||||
|
||||
try {
|
||||
BackgroundTaskConfigSchema.parse({ maxDepth: 0 })
|
||||
} catch (error) {
|
||||
thrownError = error
|
||||
}
|
||||
|
||||
expect(thrownError).toBeInstanceOf(ZodError)
|
||||
})
|
||||
})
|
||||
})
|
||||
|
||||
describe("maxDescendants", () => {
|
||||
describe("#given valid maxDescendants (50)", () => {
|
||||
test("#when parsed #then returns correct value", () => {
|
||||
const result = BackgroundTaskConfigSchema.parse({ maxDescendants: 50 })
|
||||
|
||||
expect(result.maxDescendants).toBe(50)
|
||||
})
|
||||
})
|
||||
|
||||
describe("#given maxDescendants below minimum (0)", () => {
|
||||
test("#when parsed #then throws ZodError", () => {
|
||||
let thrownError: unknown
|
||||
|
||||
try {
|
||||
BackgroundTaskConfigSchema.parse({ maxDescendants: 0 })
|
||||
} catch (error) {
|
||||
thrownError = error
|
||||
}
|
||||
|
||||
expect(thrownError).toBeInstanceOf(ZodError)
|
||||
})
|
||||
})
|
||||
})
|
||||
|
||||
describe("syncPollTimeoutMs", () => {
|
||||
describe("#given valid syncPollTimeoutMs (120000)", () => {
|
||||
test("#when parsed #then returns correct value", () => {
|
||||
|
||||
@@ -4,8 +4,6 @@ export const BackgroundTaskConfigSchema = z.object({
|
||||
defaultConcurrency: z.number().min(1).optional(),
|
||||
providerConcurrency: z.record(z.string(), z.number().min(0)).optional(),
|
||||
modelConcurrency: z.record(z.string(), z.number().min(0)).optional(),
|
||||
maxDepth: z.number().int().min(1).optional(),
|
||||
maxDescendants: z.number().int().min(1).optional(),
|
||||
/** Stale timeout in milliseconds - interrupt tasks with no activity for this duration (default: 180000 = 3 minutes, minimum: 60000 = 1 minute) */
|
||||
staleTimeoutMs: z.number().min(60000).optional(),
|
||||
/** Timeout for tasks that never received any progress update, falling back to startedAt (default: 600000 = 10 minutes, minimum: 60000 = 1 minute) */
|
||||
|
||||
@@ -1637,25 +1637,6 @@ describe("BackgroundManager - Non-blocking Queue Integration", () => {
|
||||
}
|
||||
}
|
||||
|
||||
function createMockClientWithSessionChain(
|
||||
sessions: Record<string, { directory: string; parentID?: string }>
|
||||
) {
|
||||
return {
|
||||
session: {
|
||||
create: async (_args?: any) => ({ data: { id: `ses_${crypto.randomUUID()}` } }),
|
||||
get: async ({ path }: { path: { id: string } }) => ({
|
||||
data: sessions[path.id] ?? { directory: "/test/dir" },
|
||||
}),
|
||||
prompt: async () => ({}),
|
||||
promptAsync: async () => ({}),
|
||||
messages: async () => ({ data: [] }),
|
||||
todo: async () => ({ data: [] }),
|
||||
status: async () => ({ data: {} }),
|
||||
abort: async () => ({}),
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
beforeEach(() => {
|
||||
// given
|
||||
mockClient = createMockClient()
|
||||
@@ -1850,98 +1831,6 @@ describe("BackgroundManager - Non-blocking Queue Integration", () => {
|
||||
expect(updatedTask.startedAt.getTime()).toBeGreaterThanOrEqual(queuedAt.getTime())
|
||||
}
|
||||
})
|
||||
|
||||
test("should track rootSessionID and spawnDepth from the parent chain", async () => {
|
||||
// given
|
||||
manager.shutdown()
|
||||
manager = new BackgroundManager(
|
||||
{
|
||||
client: createMockClientWithSessionChain({
|
||||
"session-depth-2": { directory: "/test/dir", parentID: "session-depth-1" },
|
||||
"session-depth-1": { directory: "/test/dir", parentID: "session-root" },
|
||||
"session-root": { directory: "/test/dir" },
|
||||
}),
|
||||
directory: tmpdir(),
|
||||
} as unknown as PluginInput,
|
||||
{ maxDepth: 3 },
|
||||
)
|
||||
|
||||
const input = {
|
||||
description: "Test task",
|
||||
prompt: "Do something",
|
||||
agent: "test-agent",
|
||||
parentSessionID: "session-depth-2",
|
||||
parentMessageID: "parent-message",
|
||||
}
|
||||
|
||||
// when
|
||||
const task = await manager.launch(input)
|
||||
|
||||
// then
|
||||
expect(task.rootSessionID).toBe("session-root")
|
||||
expect(task.spawnDepth).toBe(3)
|
||||
})
|
||||
|
||||
test("should block launches that exceed maxDepth", async () => {
|
||||
// given
|
||||
manager.shutdown()
|
||||
manager = new BackgroundManager(
|
||||
{
|
||||
client: createMockClientWithSessionChain({
|
||||
"session-depth-3": { directory: "/test/dir", parentID: "session-depth-2" },
|
||||
"session-depth-2": { directory: "/test/dir", parentID: "session-depth-1" },
|
||||
"session-depth-1": { directory: "/test/dir", parentID: "session-root" },
|
||||
"session-root": { directory: "/test/dir" },
|
||||
}),
|
||||
directory: tmpdir(),
|
||||
} as unknown as PluginInput,
|
||||
{ maxDepth: 3 },
|
||||
)
|
||||
|
||||
const input = {
|
||||
description: "Test task",
|
||||
prompt: "Do something",
|
||||
agent: "test-agent",
|
||||
parentSessionID: "session-depth-3",
|
||||
parentMessageID: "parent-message",
|
||||
}
|
||||
|
||||
// when
|
||||
const result = manager.launch(input)
|
||||
|
||||
// then
|
||||
await expect(result).rejects.toThrow("background_task.maxDepth=3")
|
||||
})
|
||||
|
||||
test("should block launches when maxDescendants is reached", async () => {
|
||||
// given
|
||||
manager.shutdown()
|
||||
manager = new BackgroundManager(
|
||||
{
|
||||
client: createMockClientWithSessionChain({
|
||||
"session-root": { directory: "/test/dir" },
|
||||
}),
|
||||
directory: tmpdir(),
|
||||
} as unknown as PluginInput,
|
||||
{ maxDescendants: 1 },
|
||||
)
|
||||
|
||||
const input = {
|
||||
description: "Test task",
|
||||
prompt: "Do something",
|
||||
agent: "test-agent",
|
||||
parentSessionID: "session-root",
|
||||
parentMessageID: "parent-message",
|
||||
}
|
||||
|
||||
await manager.launch(input)
|
||||
|
||||
// when
|
||||
const result = manager.launch(input)
|
||||
|
||||
// then
|
||||
await expect(result).rejects.toThrow("background_task.maxDescendants=1")
|
||||
})
|
||||
})
|
||||
|
||||
describe("pending task can be cancelled", () => {
|
||||
|
||||
@@ -47,14 +47,6 @@ import { MESSAGE_STORAGE } from "../hook-message-injector"
|
||||
import { join } from "node:path"
|
||||
import { pruneStaleTasksAndNotifications } from "./task-poller"
|
||||
import { checkAndInterruptStaleTasks } from "./task-poller"
|
||||
import {
|
||||
createSubagentDepthLimitError,
|
||||
createSubagentDescendantLimitError,
|
||||
getMaxRootDescendants,
|
||||
getMaxSubagentDepth,
|
||||
resolveSubagentSpawnContext,
|
||||
type SubagentSpawnContext,
|
||||
} from "./subagent-spawn-limits"
|
||||
|
||||
type OpencodeClient = PluginInput["client"]
|
||||
|
||||
@@ -119,7 +111,6 @@ export class BackgroundManager {
|
||||
private completionTimers: Map<string, ReturnType<typeof setTimeout>> = new Map()
|
||||
private idleDeferralTimers: Map<string, ReturnType<typeof setTimeout>> = new Map()
|
||||
private notificationQueueByParent: Map<string, Promise<void>> = new Map()
|
||||
private rootDescendantCounts: Map<string, number>
|
||||
private enableParentSessionNotifications: boolean
|
||||
readonly taskHistory = new TaskHistory()
|
||||
|
||||
@@ -144,42 +135,10 @@ export class BackgroundManager {
|
||||
this.tmuxEnabled = options?.tmuxConfig?.enabled ?? false
|
||||
this.onSubagentSessionCreated = options?.onSubagentSessionCreated
|
||||
this.onShutdown = options?.onShutdown
|
||||
this.rootDescendantCounts = new Map()
|
||||
this.enableParentSessionNotifications = options?.enableParentSessionNotifications ?? true
|
||||
this.registerProcessCleanup()
|
||||
}
|
||||
|
||||
async assertCanSpawn(parentSessionID: string): Promise<SubagentSpawnContext> {
|
||||
const spawnContext = await resolveSubagentSpawnContext(this.client, parentSessionID)
|
||||
const maxDepth = getMaxSubagentDepth(this.config)
|
||||
if (spawnContext.childDepth > maxDepth) {
|
||||
throw createSubagentDepthLimitError({
|
||||
childDepth: spawnContext.childDepth,
|
||||
maxDepth,
|
||||
parentSessionID,
|
||||
rootSessionID: spawnContext.rootSessionID,
|
||||
})
|
||||
}
|
||||
|
||||
const maxDescendants = getMaxRootDescendants(this.config)
|
||||
const descendantCount = this.rootDescendantCounts.get(spawnContext.rootSessionID) ?? 0
|
||||
if (descendantCount >= maxDescendants) {
|
||||
throw createSubagentDescendantLimitError({
|
||||
rootSessionID: spawnContext.rootSessionID,
|
||||
descendantCount,
|
||||
maxDescendants,
|
||||
})
|
||||
}
|
||||
|
||||
return spawnContext
|
||||
}
|
||||
|
||||
private registerRootDescendant(rootSessionID: string): number {
|
||||
const nextCount = (this.rootDescendantCounts.get(rootSessionID) ?? 0) + 1
|
||||
this.rootDescendantCounts.set(rootSessionID, nextCount)
|
||||
return nextCount
|
||||
}
|
||||
|
||||
async launch(input: LaunchInput): Promise<BackgroundTask> {
|
||||
log("[background-agent] launch() called with:", {
|
||||
agent: input.agent,
|
||||
@@ -192,28 +151,16 @@ export class BackgroundManager {
|
||||
throw new Error("Agent parameter is required")
|
||||
}
|
||||
|
||||
const spawnContext = await this.assertCanSpawn(input.parentSessionID)
|
||||
const descendantCount = this.registerRootDescendant(spawnContext.rootSessionID)
|
||||
|
||||
log("[background-agent] spawn guard passed", {
|
||||
parentSessionID: input.parentSessionID,
|
||||
rootSessionID: spawnContext.rootSessionID,
|
||||
childDepth: spawnContext.childDepth,
|
||||
descendantCount,
|
||||
})
|
||||
|
||||
// Create task immediately with status="pending"
|
||||
const task: BackgroundTask = {
|
||||
id: `bg_${crypto.randomUUID().slice(0, 8)}`,
|
||||
status: "pending",
|
||||
queuedAt: new Date(),
|
||||
rootSessionID: spawnContext.rootSessionID,
|
||||
// Do NOT set startedAt - will be set when running
|
||||
// Do NOT set sessionID - will be set when running
|
||||
description: input.description,
|
||||
prompt: input.prompt,
|
||||
agent: input.agent,
|
||||
spawnDepth: spawnContext.childDepth,
|
||||
parentSessionID: input.parentSessionID,
|
||||
parentMessageID: input.parentMessageID,
|
||||
parentModel: input.parentModel,
|
||||
@@ -258,7 +205,7 @@ export class BackgroundManager {
|
||||
// Trigger processing (fire-and-forget)
|
||||
this.processKey(key)
|
||||
|
||||
return { ...task }
|
||||
return task
|
||||
}
|
||||
|
||||
private async processKey(key: string): Promise<void> {
|
||||
@@ -928,7 +875,6 @@ export class BackgroundManager {
|
||||
}
|
||||
}
|
||||
|
||||
this.rootDescendantCounts.delete(sessionID)
|
||||
SessionCategoryRegistry.remove(sessionID)
|
||||
}
|
||||
|
||||
@@ -1663,7 +1609,6 @@ Use \`background_output(task_id="${task.id}")\` to retrieve this result when rea
|
||||
this.pendingNotifications.clear()
|
||||
this.pendingByParent.clear()
|
||||
this.notificationQueueByParent.clear()
|
||||
this.rootDescendantCounts.clear()
|
||||
this.queuesByKey.clear()
|
||||
this.processingKeys.clear()
|
||||
this.unregisterProcessCleanup()
|
||||
|
||||
@@ -1,79 +0,0 @@
|
||||
import type { BackgroundTaskConfig } from "../../config/schema"
|
||||
import type { OpencodeClient } from "./constants"
|
||||
|
||||
export const DEFAULT_MAX_SUBAGENT_DEPTH = 3
|
||||
export const DEFAULT_MAX_ROOT_DESCENDANTS = 50
|
||||
|
||||
export interface SubagentSpawnContext {
|
||||
rootSessionID: string
|
||||
parentDepth: number
|
||||
childDepth: number
|
||||
}
|
||||
|
||||
export function getMaxSubagentDepth(config?: BackgroundTaskConfig): number {
|
||||
return config?.maxDepth ?? DEFAULT_MAX_SUBAGENT_DEPTH
|
||||
}
|
||||
|
||||
export function getMaxRootDescendants(config?: BackgroundTaskConfig): number {
|
||||
return config?.maxDescendants ?? DEFAULT_MAX_ROOT_DESCENDANTS
|
||||
}
|
||||
|
||||
export async function resolveSubagentSpawnContext(
|
||||
client: OpencodeClient,
|
||||
parentSessionID: string
|
||||
): Promise<SubagentSpawnContext> {
|
||||
const visitedSessionIDs = new Set<string>()
|
||||
let rootSessionID = parentSessionID
|
||||
let currentSessionID = parentSessionID
|
||||
let parentDepth = 0
|
||||
|
||||
while (true) {
|
||||
if (visitedSessionIDs.has(currentSessionID)) {
|
||||
throw new Error(`Detected a session parent cycle while resolving ${parentSessionID}`)
|
||||
}
|
||||
|
||||
visitedSessionIDs.add(currentSessionID)
|
||||
|
||||
const session = await client.session.get({
|
||||
path: { id: currentSessionID },
|
||||
}).catch(() => null)
|
||||
|
||||
const nextParentSessionID = session?.data?.parentID
|
||||
if (!nextParentSessionID) {
|
||||
rootSessionID = currentSessionID
|
||||
break
|
||||
}
|
||||
|
||||
currentSessionID = nextParentSessionID
|
||||
parentDepth += 1
|
||||
}
|
||||
|
||||
return {
|
||||
rootSessionID,
|
||||
parentDepth,
|
||||
childDepth: parentDepth + 1,
|
||||
}
|
||||
}
|
||||
|
||||
export function createSubagentDepthLimitError(input: {
|
||||
childDepth: number
|
||||
maxDepth: number
|
||||
parentSessionID: string
|
||||
rootSessionID: string
|
||||
}): Error {
|
||||
const { childDepth, maxDepth, parentSessionID, rootSessionID } = input
|
||||
return new Error(
|
||||
`Subagent spawn blocked: child depth ${childDepth} exceeds background_task.maxDepth=${maxDepth}. Parent session: ${parentSessionID}. Root session: ${rootSessionID}. Continue in an existing subagent session instead of spawning another.`
|
||||
)
|
||||
}
|
||||
|
||||
export function createSubagentDescendantLimitError(input: {
|
||||
rootSessionID: string
|
||||
descendantCount: number
|
||||
maxDescendants: number
|
||||
}): Error {
|
||||
const { rootSessionID, descendantCount, maxDescendants } = input
|
||||
return new Error(
|
||||
`Subagent spawn blocked: root session ${rootSessionID} already has ${descendantCount} descendants, which meets background_task.maxDescendants=${maxDescendants}. Reuse an existing session instead of spawning another.`
|
||||
)
|
||||
}
|
||||
@@ -19,13 +19,11 @@ export interface TaskProgress {
|
||||
export interface BackgroundTask {
|
||||
id: string
|
||||
sessionID?: string
|
||||
rootSessionID?: string
|
||||
parentSessionID: string
|
||||
parentMessageID: string
|
||||
description: string
|
||||
prompt: string
|
||||
agent: string
|
||||
spawnDepth?: number
|
||||
status: BackgroundTaskStatus
|
||||
queuedAt?: Date
|
||||
startedAt?: Date
|
||||
|
||||
@@ -26,6 +26,11 @@ export const RETRYABLE_ERROR_PATTERNS = [
|
||||
/rate.?limit/i,
|
||||
/too.?many.?requests/i,
|
||||
/quota.?exceeded/i,
|
||||
/quota\s+will\s+reset\s+after/i,
|
||||
/all\s+credentials\s+for\s+model/i,
|
||||
/cool(?:ing)?\s+down/i,
|
||||
/cooldown/i,
|
||||
/exhausted\s+your\s+capacity/i,
|
||||
/usage\s+limit\s+has\s+been\s+reached/i,
|
||||
/service.?unavailable/i,
|
||||
/overloaded/i,
|
||||
|
||||
@@ -6,9 +6,11 @@ import { extractStatusCode, extractErrorName, classifyErrorType, isRetryableErro
|
||||
import { createFallbackState, prepareFallback } from "./fallback-state"
|
||||
import { getFallbackModelsForSession } from "./fallback-models"
|
||||
import { SessionCategoryRegistry } from "../../shared/session-category-registry"
|
||||
import { createSessionStatusHandler } from "./session-status-handler"
|
||||
|
||||
export function createEventHandler(deps: HookDeps, helpers: AutoRetryHelpers) {
|
||||
const { config, pluginConfig, sessionStates, sessionLastAccess, sessionRetryInFlight, sessionAwaitingFallbackResult, sessionFallbackTimeouts } = deps
|
||||
const sessionStatusHandler = createSessionStatusHandler(deps, helpers)
|
||||
|
||||
const handleSessionCreated = (props: Record<string, unknown> | undefined) => {
|
||||
const sessionInfo = props?.info as { id?: string; model?: string } | undefined
|
||||
@@ -33,6 +35,7 @@ export function createEventHandler(deps: HookDeps, helpers: AutoRetryHelpers) {
|
||||
sessionRetryInFlight.delete(sessionID)
|
||||
sessionAwaitingFallbackResult.delete(sessionID)
|
||||
helpers.clearSessionFallbackTimeout(sessionID)
|
||||
sessionStatusHandler.clearRetryKey(sessionID)
|
||||
SessionCategoryRegistry.remove(sessionID)
|
||||
}
|
||||
}
|
||||
@@ -191,6 +194,7 @@ export function createEventHandler(deps: HookDeps, helpers: AutoRetryHelpers) {
|
||||
if (event.type === "session.deleted") { handleSessionDeleted(props); return }
|
||||
if (event.type === "session.stop") { await handleSessionStop(props); return }
|
||||
if (event.type === "session.idle") { handleSessionIdle(props); return }
|
||||
if (event.type === "session.status") { await sessionStatusHandler.handleSessionStatus(props); return }
|
||||
if (event.type === "session.error") { await handleSessionError(props); return }
|
||||
}
|
||||
}
|
||||
|
||||
@@ -387,6 +387,133 @@ describe("runtime-fallback", () => {
|
||||
expect(fallbackLog?.data).toMatchObject({ from: "openai/gpt-5.3-codex", to: "anthropic/claude-opus-4-6" })
|
||||
})
|
||||
|
||||
test("should trigger fallback on session.status auto-retry signal", async () => {
|
||||
const promptCalls: unknown[] = []
|
||||
const hook = createRuntimeFallbackHook(
|
||||
createMockPluginInput({
|
||||
session: {
|
||||
messages: async () => ({
|
||||
data: [
|
||||
{
|
||||
info: { role: "user" },
|
||||
parts: [{ type: "text", text: "continue" }],
|
||||
},
|
||||
],
|
||||
}),
|
||||
promptAsync: async (args: unknown) => {
|
||||
promptCalls.push(args)
|
||||
return {}
|
||||
},
|
||||
},
|
||||
}),
|
||||
{
|
||||
config: createMockConfig({ notify_on_fallback: false }),
|
||||
pluginConfig: createMockPluginConfigWithCategoryFallback(["openai/gpt-5.4"]),
|
||||
}
|
||||
)
|
||||
|
||||
const sessionID = "test-session-status-auto-retry"
|
||||
SessionCategoryRegistry.register(sessionID, "test")
|
||||
|
||||
await hook.event({
|
||||
event: {
|
||||
type: "session.created",
|
||||
properties: { info: { id: sessionID, model: "quotio/claude-opus-4-6" } },
|
||||
},
|
||||
})
|
||||
|
||||
await hook.event({
|
||||
event: {
|
||||
type: "session.status",
|
||||
properties: {
|
||||
sessionID,
|
||||
status: {
|
||||
type: "retry",
|
||||
attempt: 1,
|
||||
next: 476,
|
||||
message: "All credentials for model claude-opus-4-6 are cooling down [retrying in 7m 56s attempt #1]",
|
||||
},
|
||||
},
|
||||
},
|
||||
})
|
||||
|
||||
const signalLog = logCalls.find((c) => c.msg.includes("Detected provider auto-retry signal in session.status"))
|
||||
expect(signalLog).toBeDefined()
|
||||
|
||||
const fallbackLog = logCalls.find((c) => c.msg.includes("Preparing fallback"))
|
||||
expect(fallbackLog).toBeDefined()
|
||||
expect(fallbackLog?.data).toMatchObject({ from: "quotio/claude-opus-4-6", to: "openai/gpt-5.4" })
|
||||
expect(promptCalls).toHaveLength(1)
|
||||
})
|
||||
|
||||
test("should deduplicate session.status countdown updates for the same retry attempt", async () => {
|
||||
const promptCalls: unknown[] = []
|
||||
const hook = createRuntimeFallbackHook(
|
||||
createMockPluginInput({
|
||||
session: {
|
||||
messages: async () => ({
|
||||
data: [
|
||||
{
|
||||
info: { role: "user" },
|
||||
parts: [{ type: "text", text: "continue" }],
|
||||
},
|
||||
],
|
||||
}),
|
||||
promptAsync: async (args: unknown) => {
|
||||
promptCalls.push(args)
|
||||
return {}
|
||||
},
|
||||
},
|
||||
}),
|
||||
{
|
||||
config: createMockConfig({ notify_on_fallback: false }),
|
||||
pluginConfig: createMockPluginConfigWithCategoryFallback(["openai/gpt-5.4"]),
|
||||
}
|
||||
)
|
||||
|
||||
const sessionID = "test-session-status-countdown-dedup"
|
||||
SessionCategoryRegistry.register(sessionID, "test")
|
||||
|
||||
await hook.event({
|
||||
event: {
|
||||
type: "session.created",
|
||||
properties: { info: { id: sessionID, model: "quotio/claude-opus-4-6" } },
|
||||
},
|
||||
})
|
||||
|
||||
await hook.event({
|
||||
event: {
|
||||
type: "session.status",
|
||||
properties: {
|
||||
sessionID,
|
||||
status: {
|
||||
type: "retry",
|
||||
attempt: 1,
|
||||
next: 476,
|
||||
message: "All credentials for model claude-opus-4-6 are cooling down [retrying in 7m 56s attempt #1]",
|
||||
},
|
||||
},
|
||||
},
|
||||
})
|
||||
|
||||
await hook.event({
|
||||
event: {
|
||||
type: "session.status",
|
||||
properties: {
|
||||
sessionID,
|
||||
status: {
|
||||
type: "retry",
|
||||
attempt: 1,
|
||||
next: 475,
|
||||
message: "All credentials for model claude-opus-4-6 are cooling down [retrying in 7m 55s attempt #1]",
|
||||
},
|
||||
},
|
||||
},
|
||||
})
|
||||
|
||||
expect(promptCalls).toHaveLength(1)
|
||||
})
|
||||
|
||||
test("should NOT trigger fallback on auto-retry signal when timeout_seconds is 0", async () => {
|
||||
const hook = createRuntimeFallbackHook(createMockPluginInput(), {
|
||||
config: createMockConfig({ notify_on_fallback: false, timeout_seconds: 0 }),
|
||||
|
||||
160
src/hooks/runtime-fallback/session-status-handler.ts
Normal file
160
src/hooks/runtime-fallback/session-status-handler.ts
Normal file
@@ -0,0 +1,160 @@
|
||||
import type { HookDeps } from "./types"
|
||||
import type { AutoRetryHelpers } from "./auto-retry"
|
||||
import { HOOK_NAME } from "./constants"
|
||||
import { log } from "../../shared/logger"
|
||||
import { isRetryableError } from "./error-classifier"
|
||||
import { createFallbackState, prepareFallback } from "./fallback-state"
|
||||
import { getFallbackModelsForSession } from "./fallback-models"
|
||||
import { extractRetryAttempt, extractRetryStatusModel, normalizeRetryStatusMessage } from "../../shared/retry-status-utils"
|
||||
|
||||
type SessionStatus = {
|
||||
type?: string
|
||||
message?: string
|
||||
attempt?: number
|
||||
}
|
||||
|
||||
function resolveInitialModel(
|
||||
props: Record<string, unknown> | undefined,
|
||||
retryMessage: string,
|
||||
resolvedAgent: string | undefined,
|
||||
pluginConfig: HookDeps["pluginConfig"],
|
||||
): string | undefined {
|
||||
const eventModel = typeof props?.model === "string" ? props.model : undefined
|
||||
if (eventModel) {
|
||||
return eventModel
|
||||
}
|
||||
|
||||
const retryModel = extractRetryStatusModel(retryMessage)
|
||||
if (retryModel) {
|
||||
return retryModel
|
||||
}
|
||||
|
||||
const agentConfig = resolvedAgent
|
||||
? pluginConfig?.agents?.[resolvedAgent as keyof typeof pluginConfig.agents]
|
||||
: undefined
|
||||
|
||||
return typeof agentConfig?.model === "string" ? agentConfig.model : undefined
|
||||
}
|
||||
|
||||
export function createSessionStatusHandler(deps: HookDeps, helpers: AutoRetryHelpers): {
|
||||
clearRetryKey: (sessionID: string) => void
|
||||
handleSessionStatus: (props: Record<string, unknown> | undefined) => Promise<void>
|
||||
} {
|
||||
const {
|
||||
config,
|
||||
pluginConfig,
|
||||
sessionStates,
|
||||
sessionLastAccess,
|
||||
sessionRetryInFlight,
|
||||
sessionAwaitingFallbackResult,
|
||||
} = deps
|
||||
const sessionStatusRetryKeys = new Map<string, string>()
|
||||
|
||||
const clearRetryKey = (sessionID: string): void => {
|
||||
sessionStatusRetryKeys.delete(sessionID)
|
||||
}
|
||||
|
||||
const handleSessionStatus = async (props: Record<string, unknown> | undefined): Promise<void> => {
|
||||
const sessionID = props?.sessionID as string | undefined
|
||||
const status = props?.status as SessionStatus | undefined
|
||||
const agent = props?.agent as string | undefined
|
||||
const timeoutEnabled = config.timeout_seconds > 0
|
||||
|
||||
if (!sessionID || status?.type !== "retry" || !timeoutEnabled) {
|
||||
return
|
||||
}
|
||||
|
||||
const retryMessage = typeof status.message === "string" ? status.message : ""
|
||||
if (!retryMessage || !isRetryableError({ message: retryMessage }, config.retry_on_errors)) {
|
||||
return
|
||||
}
|
||||
|
||||
const currentState = sessionStates.get(sessionID)
|
||||
const retryAttempt = extractRetryAttempt(status.attempt, retryMessage)
|
||||
const retryModel =
|
||||
(typeof props?.model === "string" ? props.model : undefined) ??
|
||||
extractRetryStatusModel(retryMessage) ??
|
||||
currentState?.currentModel ??
|
||||
"unknown-model"
|
||||
const retryKey = `${retryAttempt}:${retryModel}:${normalizeRetryStatusMessage(retryMessage)}`
|
||||
|
||||
if (sessionStatusRetryKeys.get(sessionID) === retryKey) {
|
||||
return
|
||||
}
|
||||
sessionStatusRetryKeys.set(sessionID, retryKey)
|
||||
|
||||
if (sessionRetryInFlight.has(sessionID)) {
|
||||
log(`[${HOOK_NAME}] Overriding in-flight retry due to provider session.status retry signal`, {
|
||||
sessionID,
|
||||
retryModel,
|
||||
})
|
||||
await helpers.abortSessionRequest(sessionID, "session.status.retry-signal")
|
||||
sessionRetryInFlight.delete(sessionID)
|
||||
}
|
||||
|
||||
sessionAwaitingFallbackResult.delete(sessionID)
|
||||
|
||||
const resolvedAgent = await helpers.resolveAgentForSessionFromContext(sessionID, agent)
|
||||
const fallbackModels = getFallbackModelsForSession(sessionID, resolvedAgent, pluginConfig)
|
||||
|
||||
if (fallbackModels.length === 0) {
|
||||
log(`[${HOOK_NAME}] No fallback models configured`, { sessionID, agent: resolvedAgent ?? agent })
|
||||
return
|
||||
}
|
||||
|
||||
let state = currentState
|
||||
if (!state) {
|
||||
const initialModel = resolveInitialModel(props, retryMessage, resolvedAgent, pluginConfig)
|
||||
if (!initialModel) {
|
||||
log(`[${HOOK_NAME}] session.status retry missing model info, cannot fallback`, { sessionID })
|
||||
return
|
||||
}
|
||||
|
||||
state = createFallbackState(initialModel)
|
||||
sessionStates.set(sessionID, state)
|
||||
}
|
||||
|
||||
sessionLastAccess.set(sessionID, Date.now())
|
||||
|
||||
if (state.pendingFallbackModel) {
|
||||
log(`[${HOOK_NAME}] Clearing pending fallback due to provider session.status retry signal`, {
|
||||
sessionID,
|
||||
pendingFallbackModel: state.pendingFallbackModel,
|
||||
})
|
||||
state.pendingFallbackModel = undefined
|
||||
}
|
||||
|
||||
log(`[${HOOK_NAME}] Detected provider auto-retry signal in session.status`, {
|
||||
sessionID,
|
||||
model: state.currentModel,
|
||||
retryAttempt,
|
||||
})
|
||||
|
||||
const result = prepareFallback(sessionID, state, fallbackModels, config)
|
||||
|
||||
if (result.success && config.notify_on_fallback) {
|
||||
await deps.ctx.client.tui
|
||||
.showToast({
|
||||
body: {
|
||||
title: "Model Fallback",
|
||||
message: `Switching to ${result.newModel?.split("/").pop() || result.newModel} for next request`,
|
||||
variant: "warning",
|
||||
duration: 5000,
|
||||
},
|
||||
})
|
||||
.catch(() => {})
|
||||
}
|
||||
|
||||
if (result.success && result.newModel) {
|
||||
await helpers.autoRetryWithFallback(sessionID, result.newModel, resolvedAgent, "session.status")
|
||||
return
|
||||
}
|
||||
|
||||
log(`[${HOOK_NAME}] Fallback preparation failed`, { sessionID, error: result.error })
|
||||
}
|
||||
|
||||
return {
|
||||
clearRetryKey,
|
||||
handleSessionStatus,
|
||||
}
|
||||
}
|
||||
@@ -6,7 +6,7 @@ import { _resetForTesting, setMainSession } from "../features/claude-code-sessio
|
||||
import { createModelFallbackHook, clearPendingModelFallback } from "../hooks/model-fallback/hook"
|
||||
|
||||
describe("createEventHandler - model fallback", () => {
|
||||
const createHandler = (args?: { hooks?: any }) => {
|
||||
const createHandler = (args?: { hooks?: any; pluginConfig?: any }) => {
|
||||
const abortCalls: string[] = []
|
||||
const promptCalls: string[] = []
|
||||
|
||||
@@ -26,7 +26,7 @@ describe("createEventHandler - model fallback", () => {
|
||||
},
|
||||
},
|
||||
} as any,
|
||||
pluginConfig: {} as any,
|
||||
pluginConfig: (args?.pluginConfig ?? {}) as any,
|
||||
firstMessageVariantGate: {
|
||||
markSessionCreated: () => {},
|
||||
clear: () => {},
|
||||
@@ -213,6 +213,121 @@ describe("createEventHandler - model fallback", () => {
|
||||
expect(output.message["variant"]).toBe("max")
|
||||
})
|
||||
|
||||
test("deduplicates session.status countdown updates for the same retry attempt", async () => {
|
||||
//#given
|
||||
const sessionID = "ses_status_retry_dedup"
|
||||
setMainSession(sessionID)
|
||||
clearPendingModelFallback(sessionID)
|
||||
const modelFallback = createModelFallbackHook()
|
||||
const { handler, abortCalls, promptCalls } = createHandler({ hooks: { modelFallback } })
|
||||
|
||||
await handler({
|
||||
event: {
|
||||
type: "message.updated",
|
||||
properties: {
|
||||
info: {
|
||||
id: "msg_user_status_dedup",
|
||||
sessionID,
|
||||
role: "user",
|
||||
modelID: "claude-opus-4-6-thinking",
|
||||
providerID: "anthropic",
|
||||
agent: "Sisyphus (Ultraworker)",
|
||||
},
|
||||
},
|
||||
},
|
||||
})
|
||||
|
||||
//#when
|
||||
await handler({
|
||||
event: {
|
||||
type: "session.status",
|
||||
properties: {
|
||||
sessionID,
|
||||
status: {
|
||||
type: "retry",
|
||||
attempt: 1,
|
||||
message:
|
||||
"Bad Gateway: {\"error\":{\"message\":\"unknown provider for model claude-opus-4-6-thinking\"}} [retrying in 27s attempt #1]",
|
||||
next: 27,
|
||||
},
|
||||
},
|
||||
},
|
||||
})
|
||||
|
||||
await handler({
|
||||
event: {
|
||||
type: "session.status",
|
||||
properties: {
|
||||
sessionID,
|
||||
status: {
|
||||
type: "retry",
|
||||
attempt: 1,
|
||||
message:
|
||||
"Bad Gateway: {\"error\":{\"message\":\"unknown provider for model claude-opus-4-6-thinking\"}} [retrying in 26s attempt #1]",
|
||||
next: 26,
|
||||
},
|
||||
},
|
||||
},
|
||||
})
|
||||
|
||||
//#then
|
||||
expect(abortCalls).toEqual([sessionID])
|
||||
expect(promptCalls).toEqual([sessionID])
|
||||
})
|
||||
|
||||
test("does not trigger model fallback from session.status when runtime fallback is enabled", async () => {
|
||||
//#given
|
||||
const sessionID = "ses_status_retry_runtime_enabled"
|
||||
setMainSession(sessionID)
|
||||
clearPendingModelFallback(sessionID)
|
||||
const modelFallback = createModelFallbackHook()
|
||||
const runtimeFallback = {
|
||||
event: async () => {},
|
||||
"chat.message": async () => {},
|
||||
}
|
||||
const { handler, abortCalls, promptCalls } = createHandler({
|
||||
hooks: { modelFallback, runtimeFallback },
|
||||
pluginConfig: { runtime_fallback: { enabled: true } },
|
||||
})
|
||||
|
||||
await handler({
|
||||
event: {
|
||||
type: "message.updated",
|
||||
properties: {
|
||||
info: {
|
||||
id: "msg_user_status_runtime_enabled",
|
||||
sessionID,
|
||||
role: "user",
|
||||
modelID: "claude-opus-4-6-thinking",
|
||||
providerID: "anthropic",
|
||||
agent: "Sisyphus (Ultraworker)",
|
||||
},
|
||||
},
|
||||
},
|
||||
})
|
||||
|
||||
//#when
|
||||
await handler({
|
||||
event: {
|
||||
type: "session.status",
|
||||
properties: {
|
||||
sessionID,
|
||||
status: {
|
||||
type: "retry",
|
||||
attempt: 1,
|
||||
message:
|
||||
"Bad Gateway: {\"error\":{\"message\":\"unknown provider for model claude-opus-4-6-thinking\"}} [retrying in 27s attempt #1]",
|
||||
next: 27,
|
||||
},
|
||||
},
|
||||
},
|
||||
})
|
||||
|
||||
//#then
|
||||
expect(abortCalls).toEqual([])
|
||||
expect(promptCalls).toEqual([])
|
||||
})
|
||||
|
||||
test("advances main-session fallback chain across repeated session.error retries end-to-end", async () => {
|
||||
//#given
|
||||
const abortCalls: string[] = []
|
||||
|
||||
@@ -18,6 +18,7 @@ import {
|
||||
import { resetMessageCursor } from "../shared";
|
||||
import { log } from "../shared/logger";
|
||||
import { shouldRetryError } from "../shared/model-error-classifier";
|
||||
import { extractRetryAttempt, extractRetryStatusModel, normalizeRetryStatusMessage } from "../shared/retry-status-utils";
|
||||
import { clearSessionModel, setSessionModel } from "../shared/session-model-state";
|
||||
import { deleteSessionTools } from "../shared/session-tools-store";
|
||||
import { lspManager } from "../tools";
|
||||
@@ -342,10 +343,15 @@ export function createEventHandler(args: {
|
||||
const sessionID = props?.sessionID as string | undefined;
|
||||
const status = props?.status as { type?: string; attempt?: number; message?: string; next?: number } | undefined;
|
||||
|
||||
if (sessionID && status?.type === "retry" && isModelFallbackEnabled) {
|
||||
if (sessionID && status?.type === "retry" && !isRuntimeFallbackEnabled && isModelFallbackEnabled) {
|
||||
try {
|
||||
const retryMessage = typeof status.message === "string" ? status.message : "";
|
||||
const retryKey = `${status.attempt ?? "?"}:${status.next ?? "?"}:${retryMessage}`;
|
||||
const retryAttempt = extractRetryAttempt(status.attempt, retryMessage);
|
||||
const retryModel =
|
||||
extractRetryStatusModel(retryMessage) ??
|
||||
lastKnownModelBySession.get(sessionID)?.modelID ??
|
||||
"unknown-model";
|
||||
const retryKey = `${retryAttempt}:${retryModel}:${normalizeRetryStatusMessage(retryMessage)}`;
|
||||
if (lastHandledRetryStatusKey.get(sessionID) === retryKey) {
|
||||
return;
|
||||
}
|
||||
|
||||
41
src/shared/retry-status-utils.test.ts
Normal file
41
src/shared/retry-status-utils.test.ts
Normal file
@@ -0,0 +1,41 @@
|
||||
import { describe, expect, test } from "bun:test"
|
||||
|
||||
import { extractRetryAttempt, extractRetryStatusModel, normalizeRetryStatusMessage } from "./retry-status-utils"
|
||||
|
||||
describe("retry-status-utils", () => {
|
||||
test("extracts retry attempt from explicit status attempt", () => {
|
||||
//#given
|
||||
const attempt = 6
|
||||
|
||||
//#when
|
||||
const result = extractRetryAttempt(attempt, "The usage limit has been reached [retrying in 27s attempt #6]")
|
||||
|
||||
//#then
|
||||
expect(result).toBe(6)
|
||||
})
|
||||
|
||||
test("extracts retry model from cooldown status text", () => {
|
||||
//#given
|
||||
const message = "All credentials for model claude-opus-4-6 are cooling down [retrying in 7m 56s attempt #1]"
|
||||
|
||||
//#when
|
||||
const result = extractRetryStatusModel(message)
|
||||
|
||||
//#then
|
||||
expect(result).toBe("claude-opus-4-6")
|
||||
})
|
||||
|
||||
test("normalizes countdown jitter to a stable cooldown class", () => {
|
||||
//#given
|
||||
const firstMessage = "All credentials for model claude-opus-4-6 are cooling down [retrying in 7m 56s attempt #1]"
|
||||
const secondMessage = "All credentials for model claude-opus-4-6 are cooling down [retrying in 7m 55s attempt #1]"
|
||||
|
||||
//#when
|
||||
const firstResult = normalizeRetryStatusMessage(firstMessage)
|
||||
const secondResult = normalizeRetryStatusMessage(secondMessage)
|
||||
|
||||
//#then
|
||||
expect(firstResult).toBe("cooldown")
|
||||
expect(secondResult).toBe("cooldown")
|
||||
})
|
||||
})
|
||||
51
src/shared/retry-status-utils.ts
Normal file
51
src/shared/retry-status-utils.ts
Normal file
@@ -0,0 +1,51 @@
|
||||
const RETRY_COUNTDOWN_PATTERN = /\[\s*retrying\s+in[^\]]*\]/gi
|
||||
|
||||
function collapseWhitespace(value: string): string {
|
||||
return value.toLowerCase().replace(/\s+/g, " ").trim()
|
||||
}
|
||||
|
||||
export function extractRetryAttempt(attempt: number | undefined, message: string): number | "?" {
|
||||
if (typeof attempt === "number" && Number.isFinite(attempt)) {
|
||||
return attempt
|
||||
}
|
||||
|
||||
const parsedAttempt = message.match(/attempt\s*#\s*(\d+)/i)?.[1]
|
||||
return parsedAttempt ? Number.parseInt(parsedAttempt, 10) : "?"
|
||||
}
|
||||
|
||||
export function extractRetryStatusModel(message: string): string | undefined {
|
||||
return message.match(/model\s+([a-z0-9._/-]+)(?=\s+(?:are|is)\b)/i)?.[1]?.toLowerCase()
|
||||
}
|
||||
|
||||
export function normalizeRetryStatusMessage(message: string): string {
|
||||
const normalizedMessage = collapseWhitespace(message.replace(RETRY_COUNTDOWN_PATTERN, " "))
|
||||
if (!normalizedMessage) {
|
||||
return "retry"
|
||||
}
|
||||
|
||||
if (/all\s+credentials\s+for\s+model|cool(?:ing)?\s+down|cooldown|exhausted\s+your\s+capacity/.test(normalizedMessage)) {
|
||||
return "cooldown"
|
||||
}
|
||||
|
||||
if (/too\s+many\s+requests/.test(normalizedMessage)) {
|
||||
return "too-many-requests"
|
||||
}
|
||||
|
||||
if (/quota\s+will\s+reset\s+after|quota\s*exceeded/.test(normalizedMessage)) {
|
||||
return "quota"
|
||||
}
|
||||
|
||||
if (/usage\s+limit\s+has\s+been\s+reached|limit\s+reached/.test(normalizedMessage)) {
|
||||
return "usage-limit"
|
||||
}
|
||||
|
||||
if (/rate\s+limit/.test(normalizedMessage)) {
|
||||
return "rate-limit"
|
||||
}
|
||||
|
||||
if (/service.?unavailable|temporarily.?unavailable|overloaded/.test(normalizedMessage)) {
|
||||
return "service-unavailable"
|
||||
}
|
||||
|
||||
return normalizedMessage
|
||||
}
|
||||
@@ -12,4 +12,4 @@ export const CALL_OMO_AGENT_DESCRIPTION = `Spawn explore/librarian agent. run_in
|
||||
|
||||
Available: {agents}
|
||||
|
||||
Pass \`session_id=<id>\` to continue previous agent with full context. Nested subagent depth is tracked automatically and blocked past the configured limit. Prompts MUST be in English. Use \`background_output\` for async results.`
|
||||
Pass \`session_id=<id>\` to continue previous agent with full context. Prompts MUST be in English. Use \`background_output\` for async results.`
|
||||
|
||||
@@ -4,14 +4,12 @@ import type { BackgroundManager } from "../../features/background-agent"
|
||||
import { createCallOmoAgent } from "./tools"
|
||||
|
||||
describe("createCallOmoAgent", () => {
|
||||
const assertCanSpawnMock = mock(() => Promise.resolve(undefined))
|
||||
const mockCtx = {
|
||||
client: {},
|
||||
directory: "/test",
|
||||
} as unknown as PluginInput
|
||||
|
||||
const mockBackgroundManager = {
|
||||
assertCanSpawn: assertCanSpawnMock,
|
||||
launch: mock(() => Promise.resolve({
|
||||
id: "test-task-id",
|
||||
sessionID: null,
|
||||
@@ -101,25 +99,4 @@ describe("createCallOmoAgent", () => {
|
||||
//#then
|
||||
expect(result).not.toContain("disabled via disabled_agents")
|
||||
})
|
||||
|
||||
test("should return a tool error when sync spawn depth validation fails", async () => {
|
||||
//#given
|
||||
assertCanSpawnMock.mockRejectedValueOnce(new Error("Subagent spawn blocked: child depth 4 exceeds background_task.maxDepth=3."))
|
||||
const toolDef = createCallOmoAgent(mockCtx, mockBackgroundManager, [])
|
||||
const executeFunc = toolDef.execute as Function
|
||||
|
||||
//#when
|
||||
const result = await executeFunc(
|
||||
{
|
||||
description: "Test",
|
||||
prompt: "Test prompt",
|
||||
subagent_type: "explore",
|
||||
run_in_background: false,
|
||||
},
|
||||
{ sessionID: "test", messageID: "msg", agent: "test", abort: new AbortController().signal },
|
||||
)
|
||||
|
||||
//#then
|
||||
expect(result).toContain("background_task.maxDepth=3")
|
||||
})
|
||||
})
|
||||
|
||||
@@ -57,14 +57,6 @@ export function createCallOmoAgent(
|
||||
return await executeBackground(args, toolCtx, backgroundManager, ctx.client)
|
||||
}
|
||||
|
||||
if (!args.session_id) {
|
||||
try {
|
||||
await backgroundManager.assertCanSpawn(toolCtx.sessionID)
|
||||
} catch (error) {
|
||||
return `Error: ${error instanceof Error ? error.message : String(error)}`
|
||||
}
|
||||
}
|
||||
|
||||
return await executeSync(args, toolCtx, ctx)
|
||||
},
|
||||
})
|
||||
|
||||
@@ -23,19 +23,12 @@ export async function executeSyncTask(
|
||||
fallbackChain?: import("../../shared/model-requirements").FallbackEntry[],
|
||||
deps: SyncTaskDeps = syncTaskDeps
|
||||
): Promise<string> {
|
||||
const { manager, client, directory, onSyncSessionCreated, syncPollTimeoutMs } = executorCtx
|
||||
const { client, directory, onSyncSessionCreated, syncPollTimeoutMs } = executorCtx
|
||||
const toastManager = getTaskToastManager()
|
||||
let taskId: string | undefined
|
||||
let syncSessionID: string | undefined
|
||||
|
||||
try {
|
||||
const spawnContext = typeof manager?.assertCanSpawn === "function"
|
||||
? await manager.assertCanSpawn(parentContext.sessionID)
|
||||
: {
|
||||
rootSessionID: parentContext.sessionID,
|
||||
parentDepth: 0,
|
||||
childDepth: 1,
|
||||
}
|
||||
const createSessionResult = await deps.createSyncSession(client, {
|
||||
parentSessionID: parentContext.sessionID,
|
||||
agentToUse,
|
||||
@@ -97,7 +90,6 @@ export async function executeSyncTask(
|
||||
run_in_background: args.run_in_background,
|
||||
sessionId: sessionID,
|
||||
sync: true,
|
||||
spawnDepth: spawnContext.childDepth,
|
||||
command: args.command,
|
||||
model: categoryModel ? { providerID: categoryModel.providerID, modelID: categoryModel.modelID } : undefined,
|
||||
},
|
||||
|
||||
Reference in New Issue
Block a user