fix(circuit-breaker): wire target-aware detection into background manager

This commit is contained in:
tad-hq
2026-03-17 13:40:46 -06:00
parent 1fdce01fd2
commit 5d5755f29d
2 changed files with 203 additions and 23 deletions

View File

@@ -236,4 +236,181 @@ describe("BackgroundManager circuit breaker", () => {
expect(task.progress?.countedToolPartIDs).toEqual(["tool-1"])
})
})
describe("#given same tool reading different files", () => {
test("#when tool events arrive with state.input #then task keeps running", async () => {
const manager = createManager({
circuitBreaker: {
windowSize: 20,
repetitionThresholdPercent: 80,
},
})
const task: BackgroundTask = {
id: "task-diff-files-1",
sessionID: "session-diff-files-1",
parentSessionID: "parent-1",
parentMessageID: "msg-1",
description: "Reading different files",
prompt: "work",
agent: "explore",
status: "running",
startedAt: new Date(Date.now() - 60_000),
progress: {
toolCalls: 0,
lastUpdate: new Date(Date.now() - 60_000),
},
}
getTaskMap(manager).set(task.id, task)
for (let i = 0; i < 20; i++) {
manager.handleEvent({
type: "message.part.updated",
properties: {
part: {
sessionID: task.sessionID,
type: "tool",
tool: "read",
state: { status: "running", input: { filePath: `/src/file-${i}.ts` } },
},
},
})
}
await flushAsyncWork()
expect(task.status).toBe("running")
expect(task.progress?.toolCalls).toBe(20)
})
})
describe("#given same tool reading same file repeatedly", () => {
test("#when tool events arrive with state.input #then task is cancelled with bare tool name in error", async () => {
const manager = createManager({
circuitBreaker: {
windowSize: 20,
repetitionThresholdPercent: 80,
},
})
const task: BackgroundTask = {
id: "task-same-file-1",
sessionID: "session-same-file-1",
parentSessionID: "parent-1",
parentMessageID: "msg-1",
description: "Reading same file repeatedly",
prompt: "work",
agent: "explore",
status: "running",
startedAt: new Date(Date.now() - 60_000),
progress: {
toolCalls: 0,
lastUpdate: new Date(Date.now() - 60_000),
},
}
getTaskMap(manager).set(task.id, task)
for (let i = 0; i < 20; i++) {
manager.handleEvent({
type: "message.part.updated",
properties: {
part: {
sessionID: task.sessionID,
type: "tool",
tool: "read",
state: { status: "running", input: { filePath: "/src/same.ts" } },
},
},
})
}
await flushAsyncWork()
expect(task.status).toBe("cancelled")
expect(task.error).toContain("repeatedly called read")
expect(task.error).not.toContain("::")
})
})
describe("#given circuit breaker enabled is false", () => {
test("#when repetitive tools arrive #then task keeps running", async () => {
const manager = createManager({
circuitBreaker: {
enabled: false,
windowSize: 20,
repetitionThresholdPercent: 80,
},
})
const task: BackgroundTask = {
id: "task-disabled-1",
sessionID: "session-disabled-1",
parentSessionID: "parent-1",
parentMessageID: "msg-1",
description: "Disabled circuit breaker task",
prompt: "work",
agent: "explore",
status: "running",
startedAt: new Date(Date.now() - 60_000),
progress: {
toolCalls: 0,
lastUpdate: new Date(Date.now() - 60_000),
},
}
getTaskMap(manager).set(task.id, task)
for (let i = 0; i < 20; i++) {
manager.handleEvent({
type: "message.part.updated",
properties: {
sessionID: task.sessionID,
type: "tool",
tool: "read",
},
})
}
await flushAsyncWork()
expect(task.status).toBe("running")
})
})
describe("#given circuit breaker enabled is false but absolute cap is low", () => {
test("#when max tool calls exceeded #then task is still cancelled by absolute cap", async () => {
const manager = createManager({
maxToolCalls: 3,
circuitBreaker: {
enabled: false,
windowSize: 10,
repetitionThresholdPercent: 95,
},
})
const task: BackgroundTask = {
id: "task-cap-disabled-1",
sessionID: "session-cap-disabled-1",
parentSessionID: "parent-1",
parentMessageID: "msg-1",
description: "Backstop task with disabled circuit breaker",
prompt: "work",
agent: "explore",
status: "running",
startedAt: new Date(Date.now() - 60_000),
progress: {
toolCalls: 0,
lastUpdate: new Date(Date.now() - 60_000),
},
}
getTaskMap(manager).set(task.id, task)
for (const toolName of ["read", "grep", "edit"]) {
manager.handleEvent({
type: "message.part.updated",
properties: { sessionID: task.sessionID, type: "tool", tool: toolName },
})
}
await flushAsyncWork()
expect(task.status).toBe("cancelled")
expect(task.error).toContain("maximum tool call limit (3)")
})
})
})

View File

@@ -74,7 +74,7 @@ interface MessagePartInfo {
sessionID?: string
type?: string
tool?: string
state?: { status?: string }
state?: { status?: string; input?: Record<string, unknown> }
}
interface EventProperties {
@@ -918,29 +918,32 @@ export class BackgroundManager {
task.progress.lastTool = partInfo.tool
const circuitBreaker = resolveCircuitBreakerSettings(this.config)
if (partInfo.tool) {
task.progress.toolCallWindow = recordToolCall(
task.progress.toolCallWindow,
partInfo.tool,
circuitBreaker
)
task.progress.toolCallWindow = recordToolCall(
task.progress.toolCallWindow,
partInfo.tool,
circuitBreaker,
partInfo.state?.input
)
const loopDetection = detectRepetitiveToolUse(task.progress.toolCallWindow)
if (loopDetection.triggered) {
log("[background-agent] Circuit breaker: repetitive tool usage detected", {
taskId: task.id,
agent: task.agent,
sessionID,
toolName: loopDetection.toolName,
repeatedCount: loopDetection.repeatedCount,
sampleSize: loopDetection.sampleSize,
thresholdPercent: loopDetection.thresholdPercent,
})
void this.cancelTask(task.id, {
source: "circuit-breaker",
reason: `Subagent repeatedly called ${loopDetection.toolName} ${loopDetection.repeatedCount}/${loopDetection.sampleSize} times in the recent tool-call window (${loopDetection.thresholdPercent}% threshold). This usually indicates an infinite loop. The task was automatically cancelled to prevent excessive token usage.`,
})
return
}
if (circuitBreaker.enabled) {
const loopDetection = detectRepetitiveToolUse(task.progress.toolCallWindow)
if (loopDetection.triggered) {
log("[background-agent] Circuit breaker: repetitive tool usage detected", {
taskId: task.id,
agent: task.agent,
sessionID,
toolName: loopDetection.toolName,
repeatedCount: loopDetection.repeatedCount,
sampleSize: loopDetection.sampleSize,
thresholdPercent: loopDetection.thresholdPercent,
})
void this.cancelTask(task.id, {
source: "circuit-breaker",
reason: `Subagent repeatedly called ${loopDetection.toolName} ${loopDetection.repeatedCount}/${loopDetection.sampleSize} times in the recent tool-call window (${loopDetection.thresholdPercent}% threshold). This usually indicates an infinite loop. The task was automatically cancelled to prevent excessive token usage.`,
})
return
}
}
}
const maxToolCalls = circuitBreaker.maxToolCalls