fix: reduce session.messages() calls with event-based caching to prevent memory leaks
- Replace session.messages() fetch in context-window-monitor with message.updated event cache - Replace session.messages() fetch in preemptive-compaction with message.updated event cache - Add per-session transcript cache (5min TTL) to avoid full rebuild per tool call - Remove session.messages() from background-agent polling (use event-based progress) - Add TTL pruning to todo-continuation-enforcer session state Map - Add setInterval.unref() to tool-input-cache cleanup timer Fixes #1222
This commit is contained in:
popododo0720
@@ -1,132 +1,155 @@
|
||||
import { describe, expect, mock, test } from "bun:test"
|
||||
import { createPreemptiveCompactionHook } from "./preemptive-compaction.ts"
|
||||
import { describe, it, expect, mock, beforeEach } from "bun:test"
|
||||
import { createPreemptiveCompactionHook } from "./preemptive-compaction"
|
||||
|
||||
function createMockCtx() {
|
||||
return {
|
||||
client: {
|
||||
session: {
|
||||
messages: mock(() => Promise.resolve({ data: [] })),
|
||||
summarize: mock(() => Promise.resolve({})),
|
||||
},
|
||||
tui: {
|
||||
showToast: mock(() => Promise.resolve()),
|
||||
},
|
||||
},
|
||||
directory: "/tmp/test",
|
||||
}
|
||||
}
|
||||
|
||||
describe("preemptive-compaction", () => {
|
||||
const sessionID = "preemptive-compaction-session"
|
||||
let ctx: ReturnType<typeof createMockCtx>
|
||||
|
||||
function createMockCtx(overrides?: {
|
||||
messages?: ReturnType<typeof mock>
|
||||
summarize?: ReturnType<typeof mock>
|
||||
}) {
|
||||
const messages = overrides?.messages ?? mock(() => Promise.resolve({ data: [] }))
|
||||
const summarize = overrides?.summarize ?? mock(() => Promise.resolve())
|
||||
beforeEach(() => {
|
||||
ctx = createMockCtx()
|
||||
})
|
||||
|
||||
return {
|
||||
client: {
|
||||
session: {
|
||||
messages,
|
||||
summarize,
|
||||
},
|
||||
tui: {
|
||||
showToast: mock(() => Promise.resolve()),
|
||||
// #given event caches token info from message.updated
|
||||
// #when tool.execute.after is called
|
||||
// #then session.messages() should NOT be called
|
||||
it("should use cached token info instead of fetching session.messages()", async () => {
|
||||
const hook = createPreemptiveCompactionHook(ctx as never)
|
||||
const sessionID = "ses_test1"
|
||||
|
||||
// Simulate message.updated with token info below threshold
|
||||
await hook.event({
|
||||
event: {
|
||||
type: "message.updated",
|
||||
properties: {
|
||||
info: {
|
||||
role: "assistant",
|
||||
sessionID,
|
||||
providerID: "anthropic",
|
||||
modelID: "claude-sonnet-4-5",
|
||||
finish: true,
|
||||
tokens: {
|
||||
input: 50000,
|
||||
output: 1000,
|
||||
reasoning: 0,
|
||||
cache: { read: 5000, write: 0 },
|
||||
},
|
||||
},
|
||||
},
|
||||
},
|
||||
directory: "/tmp/test",
|
||||
} as never
|
||||
}
|
||||
})
|
||||
|
||||
test("triggers summarize when usage exceeds threshold", async () => {
|
||||
// #given
|
||||
const messages = mock(() =>
|
||||
Promise.resolve({
|
||||
data: [
|
||||
{
|
||||
info: {
|
||||
role: "assistant",
|
||||
providerID: "anthropic",
|
||||
modelID: "claude-opus-4-6",
|
||||
tokens: {
|
||||
input: 180000,
|
||||
output: 0,
|
||||
reasoning: 0,
|
||||
cache: { read: 0, write: 0 },
|
||||
},
|
||||
},
|
||||
},
|
||||
],
|
||||
})
|
||||
)
|
||||
const summarize = mock(() => Promise.resolve())
|
||||
const hook = createPreemptiveCompactionHook(createMockCtx({ messages, summarize }))
|
||||
const output = { title: "", output: "", metadata: {} }
|
||||
|
||||
// #when
|
||||
const output = { title: "", output: "test", metadata: null }
|
||||
await hook["tool.execute.after"](
|
||||
{ tool: "Read", sessionID, callID: "call-1" },
|
||||
{ tool: "bash", sessionID, callID: "call_1" },
|
||||
output
|
||||
)
|
||||
|
||||
// #then
|
||||
expect(summarize).toHaveBeenCalled()
|
||||
expect(ctx.client.session.messages).not.toHaveBeenCalled()
|
||||
})
|
||||
|
||||
test("triggers summarize for non-anthropic providers when usage exceeds threshold", async () => {
|
||||
//#given
|
||||
const messages = mock(() =>
|
||||
Promise.resolve({
|
||||
data: [
|
||||
{
|
||||
info: {
|
||||
role: "assistant",
|
||||
providerID: "openai",
|
||||
modelID: "gpt-5.2",
|
||||
tokens: {
|
||||
input: 180000,
|
||||
output: 0,
|
||||
reasoning: 0,
|
||||
cache: { read: 0, write: 0 },
|
||||
},
|
||||
},
|
||||
},
|
||||
],
|
||||
})
|
||||
)
|
||||
const summarize = mock(() => Promise.resolve())
|
||||
const hook = createPreemptiveCompactionHook(createMockCtx({ messages, summarize }))
|
||||
const output = { title: "", output: "", metadata: {} }
|
||||
// #given no cached token info
|
||||
// #when tool.execute.after is called
|
||||
// #then should skip without fetching
|
||||
it("should skip gracefully when no cached token info exists", async () => {
|
||||
const hook = createPreemptiveCompactionHook(ctx as never)
|
||||
|
||||
//#when
|
||||
const output = { title: "", output: "test", metadata: null }
|
||||
await hook["tool.execute.after"](
|
||||
{ tool: "Read", sessionID, callID: "call-3" },
|
||||
{ tool: "bash", sessionID: "ses_none", callID: "call_1" },
|
||||
output
|
||||
)
|
||||
|
||||
//#then
|
||||
expect(summarize).toHaveBeenCalled()
|
||||
expect(ctx.client.session.messages).not.toHaveBeenCalled()
|
||||
})
|
||||
|
||||
test("does not summarize when usage is below threshold", async () => {
|
||||
// #given
|
||||
const messages = mock(() =>
|
||||
Promise.resolve({
|
||||
data: [
|
||||
{
|
||||
info: {
|
||||
role: "assistant",
|
||||
providerID: "anthropic",
|
||||
modelID: "claude-opus-4-6",
|
||||
tokens: {
|
||||
input: 100000,
|
||||
output: 0,
|
||||
reasoning: 0,
|
||||
cache: { read: 0, write: 0 },
|
||||
},
|
||||
// #given usage above 78% threshold
|
||||
// #when tool.execute.after runs
|
||||
// #then should trigger summarize
|
||||
it("should trigger compaction when usage exceeds threshold", async () => {
|
||||
const hook = createPreemptiveCompactionHook(ctx as never)
|
||||
const sessionID = "ses_high"
|
||||
|
||||
// 170K input + 10K cache = 180K → 90% of 200K
|
||||
await hook.event({
|
||||
event: {
|
||||
type: "message.updated",
|
||||
properties: {
|
||||
info: {
|
||||
role: "assistant",
|
||||
sessionID,
|
||||
providerID: "anthropic",
|
||||
modelID: "claude-sonnet-4-5",
|
||||
finish: true,
|
||||
tokens: {
|
||||
input: 170000,
|
||||
output: 1000,
|
||||
reasoning: 0,
|
||||
cache: { read: 10000, write: 0 },
|
||||
},
|
||||
},
|
||||
],
|
||||
})
|
||||
)
|
||||
const summarize = mock(() => Promise.resolve())
|
||||
const hook = createPreemptiveCompactionHook(createMockCtx({ messages, summarize }))
|
||||
const output = { title: "", output: "", metadata: {} }
|
||||
},
|
||||
},
|
||||
})
|
||||
|
||||
// #when
|
||||
const output = { title: "", output: "test", metadata: null }
|
||||
await hook["tool.execute.after"](
|
||||
{ tool: "Read", sessionID, callID: "call-2" },
|
||||
{ tool: "bash", sessionID, callID: "call_1" },
|
||||
output
|
||||
)
|
||||
|
||||
// #then
|
||||
expect(summarize).not.toHaveBeenCalled()
|
||||
expect(ctx.client.session.messages).not.toHaveBeenCalled()
|
||||
expect(ctx.client.session.summarize).toHaveBeenCalled()
|
||||
})
|
||||
|
||||
// #given session deleted
|
||||
// #then cache should be cleaned up
|
||||
it("should clean up cache on session.deleted", async () => {
|
||||
const hook = createPreemptiveCompactionHook(ctx as never)
|
||||
const sessionID = "ses_del"
|
||||
|
||||
await hook.event({
|
||||
event: {
|
||||
type: "message.updated",
|
||||
properties: {
|
||||
info: {
|
||||
role: "assistant",
|
||||
sessionID,
|
||||
providerID: "anthropic",
|
||||
modelID: "claude-sonnet-4-5",
|
||||
finish: true,
|
||||
tokens: { input: 180000, output: 0, reasoning: 0, cache: { read: 10000, write: 0 } },
|
||||
},
|
||||
},
|
||||
},
|
||||
})
|
||||
|
||||
await hook.event({
|
||||
event: {
|
||||
type: "session.deleted",
|
||||
properties: { info: { id: sessionID } },
|
||||
},
|
||||
})
|
||||
|
||||
const output = { title: "", output: "test", metadata: null }
|
||||
await hook["tool.execute.after"](
|
||||
{ tool: "bash", sessionID, callID: "call_1" },
|
||||
output
|
||||
)
|
||||
|
||||
expect(ctx.client.session.summarize).not.toHaveBeenCalled()
|
||||
})
|
||||
})
|
||||
|
||||
Reference in New Issue
Block a user