fix(ralph-loop): guard compaction continuation ownership

This commit is contained in:
YeonGyu-Kim
2026-05-14 13:43:47 +09:00
parent d16d47a0b4
commit 9e6185266d
11 changed files with 252 additions and 101 deletions
@@ -23,6 +23,23 @@ import type { BackgroundManager } from "../../features/background-agent"
import { TaskHistory } from "../../features/background-agent/task-history"
import { setCompactionAgentConfigCheckpoint } from "../../shared/compaction-agent-config-checkpoint"
type PromptAsyncInput = {
path: { id: string }
body: {
noReply?: boolean
agent?: string
model?: { providerID: string; modelID: string }
tools?: Record<string, boolean | "allow" | "deny" | "ask">
parts: Array<{
type: "text"
text: string
synthetic?: true
metadata?: { compaction_continue?: true }
}>
}
query?: { directory: string }
}
function createMockContext(
messageResponses: Array<Array<{ info?: Record<string, unknown> }>>,
promptAsyncMock = mock(async () => ({})),
@@ -148,7 +165,7 @@ describe("createCompactionContextInjector", () => {
describe("agent checkpoint recovery", () => {
it("re-injects checkpointed agent config after compaction when latest agent is lost", async () => {
//#given
const promptAsyncMock = mock(async () => ({}))
const promptAsyncMock = mock(async (_input: PromptAsyncInput) => ({}))
const ctx = createMockContext(
[
[
@@ -201,27 +218,22 @@ describe("createCompactionContextInjector", () => {
})
//#then
expect(promptAsyncMock).toHaveBeenCalledWith({
path: { id: "ses_checkpoint" },
body: {
noReply: true,
agent: "atlas",
model: { providerID: "openai", modelID: "gpt-5" },
tools: { bash: true },
parts: [
{
type: "text",
text: expect.stringContaining("restore checkpointed session agent configuration"),
},
],
},
query: { directory: "/tmp/test" },
})
const recoveryCall = promptAsyncMock.mock.calls[0]?.[0]
expect(recoveryCall?.path).toEqual({ id: "ses_checkpoint" })
expect(recoveryCall?.body.noReply).toBe(true)
expect(recoveryCall?.body.agent).toBe("atlas")
expect(recoveryCall?.body.model).toEqual({ providerID: "openai", modelID: "gpt-5" })
expect(recoveryCall?.body.tools).toEqual({ bash: true })
expect(recoveryCall?.body.parts[0]?.type).toBe("text")
expect(recoveryCall?.body.parts[0]?.text).toContain("restore checkpointed session agent configuration")
expect(recoveryCall?.body.parts[0]?.synthetic).toBe(true)
expect(recoveryCall?.body.parts[0]?.metadata).toEqual({ compaction_continue: true })
expect(recoveryCall?.query).toEqual({ directory: "/tmp/test" })
})
it("re-injects checkpointed agent config during autocontinue before synthetic continue", async () => {
//#given
const promptAsyncMock = mock(async () => ({}))
const promptAsyncMock = mock(async (_input: PromptAsyncInput) => ({}))
const ctx = createMockContext(
[
[
@@ -273,22 +285,17 @@ describe("createCompactionContextInjector", () => {
//#then
expect(restored).toBe(true)
expect(promptAsyncMock).toHaveBeenCalledWith({
path: { id: "ses_autocontinue_checkpoint" },
body: {
noReply: true,
agent: "atlas",
model: { providerID: "openai", modelID: "gpt-5" },
tools: { bash: true },
parts: [
{
type: "text",
text: expect.stringContaining("restore checkpointed session agent configuration"),
},
],
},
query: { directory: "/tmp/test" },
})
const recoveryCall = promptAsyncMock.mock.calls[0]?.[0]
expect(recoveryCall?.path).toEqual({ id: "ses_autocontinue_checkpoint" })
expect(recoveryCall?.body.noReply).toBe(true)
expect(recoveryCall?.body.agent).toBe("atlas")
expect(recoveryCall?.body.model).toEqual({ providerID: "openai", modelID: "gpt-5" })
expect(recoveryCall?.body.tools).toEqual({ bash: true })
expect(recoveryCall?.body.parts[0]?.type).toBe("text")
expect(recoveryCall?.body.parts[0]?.text).toContain("restore checkpointed session agent configuration")
expect(recoveryCall?.body.parts[0]?.synthetic).toBe(true)
expect(recoveryCall?.body.parts[0]?.metadata).toEqual({ compaction_continue: true })
expect(recoveryCall?.query).toEqual({ directory: "/tmp/test" })
})
it("clears stale checkpoint when the next compaction capture has no prompt config", async () => {
@@ -314,7 +321,7 @@ describe("createCompactionContextInjector", () => {
it("recovers after five consecutive assistant messages with no text", async () => {
//#given
const promptAsyncMock = mock(async () => ({}))
const promptAsyncMock = mock(async (_input: PromptAsyncInput) => ({}))
const ctx = createMockContext(
[
[
@@ -375,15 +382,10 @@ describe("createCompactionContextInjector", () => {
//#then
expect(promptAsyncMock).toHaveBeenCalledTimes(1)
expect(promptAsyncMock).toHaveBeenCalledWith(
expect.objectContaining({
path: { id: "ses_no_text_tail" },
body: expect.objectContaining({
noReply: true,
agent: "atlas",
}),
}),
)
const recoveryCall = promptAsyncMock.mock.calls[0]?.[0]
expect(recoveryCall?.path).toEqual({ id: "ses_no_text_tail" })
expect(recoveryCall?.body.noReply).toBe(true)
expect(recoveryCall?.body.agent).toBe("atlas")
})
})
})
@@ -15,7 +15,12 @@ type PromptAsyncInput = {
agent?: string
model?: { providerID: string; modelID: string }
tools?: Record<string, boolean>
parts: Array<{ type: "text"; text: string }>
parts: Array<{
type: "text"
text: string
synthetic?: true
metadata?: { compaction_continue?: true }
}>
}
query?: { directory: string }
}
@@ -96,46 +101,31 @@ describe("createCompactionContextInjector recovery", () => {
it("re-injects after compaction when agent and model match but tools are missing", async () => {
//#given
const promptAsyncRecorder = createPromptAsyncRecorder()
const checkpointedPromptConfig = [
{
info: {
role: "user",
agent: "atlas",
model: { providerID: "openai", modelID: "gpt-5" },
tools: { bash: true },
},
},
]
const incompletePromptConfig = [
{
info: {
role: "user",
agent: "atlas",
model: { providerID: "openai", modelID: "gpt-5" },
},
},
]
const ctx = createMockContext(
[
[
{
info: {
role: "user",
agent: "atlas",
model: { providerID: "openai", modelID: "gpt-5" },
tools: { bash: true },
},
},
],
[
{
info: {
role: "user",
agent: "atlas",
model: { providerID: "openai", modelID: "gpt-5" },
},
},
],
[
{
info: {
role: "user",
agent: "atlas",
model: { providerID: "openai", modelID: "gpt-5" },
},
},
],
[
{
info: {
role: "user",
agent: "atlas",
model: { providerID: "openai", modelID: "gpt-5" },
tools: { bash: true },
},
},
],
checkpointedPromptConfig,
incompletePromptConfig,
incompletePromptConfig,
checkpointedPromptConfig,
],
promptAsyncRecorder.promptAsync,
)
@@ -157,6 +147,55 @@ describe("createCompactionContextInjector recovery", () => {
expect(promptAsyncRecorder.calls[0]?.body.tools).toEqual({ bash: true })
})
it("marks the recovery prompt as synthetic compaction continuation", async () => {
//#given
const promptAsyncRecorder = createPromptAsyncRecorder()
const incompletePromptConfig = [
{
info: {
role: "user",
agent: "atlas",
model: { providerID: "openai", modelID: "gpt-5" },
},
},
]
const recoveredPromptConfig = [
{
info: {
role: "user",
agent: "atlas",
model: { providerID: "openai", modelID: "gpt-5" },
tools: { bash: true },
},
},
]
const ctx = createMockContext(
[
recoveredPromptConfig,
incompletePromptConfig,
incompletePromptConfig,
recoveredPromptConfig,
],
promptAsyncRecorder.promptAsync,
)
const injector = createCompactionContextInjector({ ctx })
//#when
await injector.capture("ses_synthetic_recovery")
await injector.event({
event: {
type: "session.compacted",
properties: { sessionID: "ses_synthetic_recovery" },
},
})
//#then
expect(promptAsyncRecorder.calls.length).toBe(1)
const recoveryPart = promptAsyncRecorder.calls[0]?.body.parts[0]
expect(recoveryPart?.synthetic).toBe(true)
expect(recoveryPart?.metadata).toEqual({ compaction_continue: true })
})
it("retries recovery when the recovered prompt config still mismatches expected model or tools", async () => {
//#given
const promptAsyncRecorder = createPromptAsyncRecorder()
@@ -5,7 +5,7 @@ import {
import {
getCompactionAgentConfigCheckpoint,
} from "../../shared/compaction-agent-config-checkpoint"
import { createInternalAgentTextPart } from "../../shared/internal-initiator-marker"
import { createInternalAgentContinuationTextPart } from "../../shared/internal-initiator-marker"
import { log } from "../../shared/logger"
import { setSessionModel } from "../../shared/session-model-state"
import { setSessionTools } from "../../shared/session-tools-store"
@@ -88,7 +88,7 @@ export function createRecoveryLogic(
agent: launchAgent ?? expectedPromptConfig.agent,
...(model ? { model } : {}),
...(tools ? { tools } : {}),
parts: [createInternalAgentTextPart(AGENT_RECOVERY_PROMPT)],
parts: [createInternalAgentContinuationTextPart(AGENT_RECOVERY_PROMPT)],
},
query: { directory: ctx.directory },
})
@@ -0,0 +1,77 @@
/// <reference path="../../../bun-test.d.ts" />
import { describe, expect, test } from "bun:test"
import { createRalphLoopEventHandler } from "./ralph-loop-event-handler"
import type { IterationCommitExpectation, RalphLoopState } from "./types"
describe("ralph-loop iteration commit ownership", () => {
test("#given reset strategy creates a new session #when dispatch commits #then CAS expects the new owner", async () => {
// given
const commitExpectations: IterationCommitExpectation[] = []
let state: RalphLoopState | null = {
active: true,
iteration: 1,
max_iterations: 5,
completion_promise: "DONE",
started_at: new Date().toISOString(),
prompt: "Keep working",
session_id: "session-old",
strategy: "reset",
}
const handler = createRalphLoopEventHandler({
directory: "/tmp/ralph-loop-iteration-commit-ownership",
client: {
session: {
messages: async () => ({ data: [] }),
create: async () => ({ data: { id: "session-new" } }),
promptAsync: async () => ({}),
},
tui: {
showToast: async () => ({}),
selectSession: async () => ({}),
},
},
} as never, {
directory: "/tmp/ralph-loop-iteration-commit-ownership",
apiTimeoutMs: 5000,
idleSettleMs: 0,
getTranscriptPath: () => undefined,
loopState: {
getState: () => state,
clear: () => {
state = null
return true
},
setSessionID: (sessionID: string) => {
if (!state) return null
state = { ...state, session_id: sessionID }
return state
},
incrementIteration: (expected?: IterationCommitExpectation) => {
if (expected) {
commitExpectations.push(expected)
}
if (!state) return null
state = { ...state, iteration: state.iteration + 1 }
return state
},
markVerificationPending: () => state,
setVerificationSessionID: () => state,
restartAfterFailedVerification: () => state,
clearVerificationState: () => state,
},
})
// when
await handler({
event: { type: "session.idle", properties: { sessionID: "session-old" } },
})
// then
expect(commitExpectations).toEqual([
{ iteration: 1, sessionID: "session-new" },
])
expect(state?.iteration).toBe(2)
expect(state?.session_id).toBe("session-new")
})
})
@@ -16,7 +16,7 @@ type ContinuationOptions = {
}
export type ContinuationResult =
| { status: "dispatched" }
| { status: "dispatched"; sessionID: string }
| { status: "session_creation_rejected" }
| { status: "dispatch_rejected"; error: unknown }
@@ -61,10 +61,10 @@ export async function continueIteration(
previousSessionID: options.previousSessionID,
newSessionID,
})
return { status: "dispatched" }
return { status: "dispatch_rejected", error: "state commit failed after reset dispatch" }
}
return { status: "dispatched" }
return { status: "dispatched", sessionID: newSessionID }
}
try {
@@ -81,5 +81,5 @@ export async function continueIteration(
return { status: "dispatch_rejected", error }
}
return { status: "dispatched" }
return { status: "dispatched", sessionID: options.previousSessionID }
}
@@ -1,4 +1,4 @@
import type { RalphLoopOptions, RalphLoopState } from "./types"
import type { IterationCommitExpectation, RalphLoopOptions, RalphLoopState } from "./types"
import {
DEFAULT_COMPLETION_PROMISE,
DEFAULT_MAX_ITERATIONS,
@@ -86,8 +86,8 @@ export function createLoopStateController(options: {
return clearState(directory, stateDir)
},
incrementIteration(): RalphLoopState | null {
return incrementIteration(directory, stateDir)
incrementIteration(expected?: IterationCommitExpectation): RalphLoopState | null {
return incrementIteration(directory, stateDir, expected)
},
setSessionID(sessionID: string): RalphLoopState | null {
@@ -5,6 +5,7 @@ import { extractOracleSessionID, isOracleVerified } from "./oracle-verification-
import type { RalphLoopState } from "./types"
import { handleFailedVerification } from "./verification-failure-handler"
import { withTimeout } from "./with-timeout"
import type { IterationCommitExpectation } from "./types"
type OpenCodeSessionMessage = {
info?: { role?: string }
@@ -83,7 +84,7 @@ async function detectOracleVerificationFromParentSession(
type LoopStateController = {
restartAfterFailedVerification: (sessionID: string, messageCountAtStart?: number) => RalphLoopState | null
clearVerificationState: (sessionID: string, messageCountAtStart?: number) => RalphLoopState | null
incrementIteration: () => RalphLoopState | null
incrementIteration: (expected?: IterationCommitExpectation) => RalphLoopState | null
clear: () => boolean
setVerificationSessionID: (sessionID: string, verificationSessionID: string) => RalphLoopState | null
}
@@ -2,7 +2,7 @@ import type { PluginInput } from "@opencode-ai/plugin"
import { log } from "../../shared/logger"
import { resolveMessageEventSessionID, resolveSessionEventID } from "../../shared/event-session-id"
import { isSessionActive } from "../shared/session-idle-settle"
import type { RalphLoopOptions, RalphLoopState } from "./types"
import type { IterationCommitExpectation, RalphLoopOptions, RalphLoopState } from "./types"
import { HOOK_NAME } from "./constants"
import { handleDetectedCompletion } from "./completion-handler"
import {
@@ -18,7 +18,7 @@ const RAPID_IDLE_DEDUP_MS = 500
type LoopStateController = {
getState: () => RalphLoopState | null
clear: () => boolean
incrementIteration: () => RalphLoopState | null
incrementIteration: (expected?: IterationCommitExpectation) => RalphLoopState | null
setSessionID: (sessionID: string) => RalphLoopState | null
markVerificationPending: (sessionID: string) => RalphLoopState | null
setVerificationSessionID: (sessionID: string, verificationSessionID: string) => RalphLoopState | null
@@ -377,11 +377,21 @@ export function createRalphLoopEventHandler(
return
}
const committed = options.loopState.incrementIteration()
const committed = options.loopState.incrementIteration({
iteration: stateBeforeCommit.iteration,
sessionID: result.sessionID,
})
if (committed) {
showIterationToast(ctx, committed)
} else {
log(`[${HOOK_NAME}] Dispatch succeeded but iteration commit failed`, { sessionID })
options.loopState.clear()
showToastBestEffort(ctx, {
title: "Ralph Loop Failed",
message: "Dispatch succeeded but iteration commit failed",
variant: "warning",
duration: 5000,
})
}
return
}
@@ -532,12 +542,22 @@ export function createRalphLoopEventHandler(
return
}
const committed = options.loopState.incrementIteration()
const committed = options.loopState.incrementIteration({
iteration: stateBeforeCommit.iteration,
sessionID: result.sessionID,
})
if (committed) {
showIterationToast(ctx, committed)
runtimeErrorRetriedSessions.set(sessionID, committed.iteration)
} else {
log(`[${HOOK_NAME}] Dispatch succeeded but iteration commit failed after runtime error`, { sessionID })
options.loopState.clear()
showToastBestEffort(ctx, {
title: "Ralph Loop Failed",
message: "Dispatch succeeded but iteration commit failed",
variant: "warning",
duration: 5000,
})
}
return
}
+9 -2
View File
@@ -1,7 +1,7 @@
import { existsSync, readFileSync, writeFileSync, unlinkSync, mkdirSync } from "node:fs"
import { dirname, join } from "node:path"
import { parseFrontmatter } from "../../shared/frontmatter"
import type { RalphLoopState } from "./types"
import type { IterationCommitExpectation, RalphLoopState } from "./types"
import { DEFAULT_STATE_FILE, DEFAULT_COMPLETION_PROMISE, DEFAULT_MAX_ITERATIONS } from "./constants"
export function getStateFilePath(directory: string, customPath?: string): string {
@@ -151,10 +151,17 @@ export function clearState(directory: string, customPath?: string): boolean {
export function incrementIteration(
directory: string,
customPath?: string
customPath?: string,
expected?: IterationCommitExpectation,
): RalphLoopState | null {
const state = readState(directory, customPath)
if (!state) return null
if (
expected
&& (state.iteration !== expected.iteration || state.session_id !== expected.sessionID)
) {
return null
}
state.iteration += 1
if (writeState(directory, state, customPath)) {
+5
View File
@@ -17,6 +17,11 @@ export interface RalphLoopState {
strategy?: "reset" | "continue"
}
export interface IterationCommitExpectation {
iteration: number
sessionID: string
}
export interface RalphLoopOptions {
config?: RalphLoopConfig
getTranscriptPath?: (sessionId: string) => string
@@ -3,14 +3,14 @@ import { log } from "../../shared/logger"
import { buildVerificationFailurePrompt } from "./continuation-prompt-builder"
import { HOOK_NAME } from "./constants"
import { injectContinuationPrompt } from "./continuation-prompt-injector"
import type { RalphLoopState } from "./types"
import type { IterationCommitExpectation, RalphLoopState } from "./types"
type LoopStateController = {
clearVerificationState: (
sessionID: string,
messageCountAtStart?: number,
) => RalphLoopState | null
incrementIteration: () => RalphLoopState | null
incrementIteration: (expected?: IterationCommitExpectation) => RalphLoopState | null
clear: () => boolean
}