root/goodbuddy
1
0
Fork 0
Code Issues Pull Requests Actions 5 Packages Projects Releases Wiki Activity

fix: recover remote conversations after uncertain prompts

Browse Source 
An interrupted managed SSH prompt could leave its ACP binding as the permanent owner of the conversation, so every later user message failed with the same uncertain-recovery error. A later explicit prompt now retires that binding and starts a fresh ACP session without replaying the uncertain operation.

Ask-mode Runtime startup also waited on the wrong bubblewrap executable identity. The Agent now supervises the bounded transition to the signed Runtime or model-bridge executable, and the Agent version advances to 0.11.10.

Release note: 修复远程 ACP 请求中断后同一会话无法继续输入，以及 Ask 模式可能在模型调用前启动失败的问题。
This commit is contained in:
mesalogo
2026-08-30 11:02:20 +08:00
parent 8e08ab0bac
commit 967796539f
8 changed files with 164 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/agent-daemon/direct-linux-stdio-process-owner.test.ts
+41
View File
@@ -119,6 +119,47 @@ describe('direct Linux stdio Runtime ownership', () => {
registry.close()
})
it('waits for bubblewrap to exec the supervised bridge helper', async () => {
const registry = createRegistry()
const child = fakeChild()
const bwrapIdentity = identity()
const helperIdentity = {
...bwrapIdentity,
executablePath: '/agent/node'
}
const spawn: DirectLinuxStdioSpawn = () => {
queueMicrotask(() => child.emit('spawn'))
return child
}
const readProcessIdentity = vi
.fn()
.mockResolvedValueOnce(bwrapIdentity)
.mockResolvedValue(helperIdentity)
const owner = await launchDirectLinuxStdioProcessOwner({
manifest: manifest(),
profile: {
...profile(),
processExecutable: '/agent/node'
},
identity: { launchId: 'launch-1', processId: 'process-1' },
installationId: 'installation-1',
registry,
deadlineAt: '2030-01-01T00:00:00.000Z',
maximumInputBytes: 1024,
platform: 'linux',
spawn,
randomOwnerToken: () => 'a'.repeat(32),
readProcessIdentity
})
expect(readProcessIdentity).toHaveBeenCalledTimes(2)
expect(owner.processIdentity).toEqual(helperIdentity)
child.exitCode = 0
child.emit('close', 0, null)
registry.close()
})
it('rejects PID reuse before sending any signal', async () => {
const registry = createRegistry()
const child = fakeChild()
src/agent-daemon/direct-linux-stdio-process-owner.ts
+78 -10
View File
@@ -31,6 +31,7 @@ const DEFAULT_MAXIMUM_STDIN_WRITE_BYTES = 1024 * 1024
const DEFAULT_MAXIMUM_OUTPUT_QUEUE_CHUNKS = 128
const DEFAULT_MAXIMUM_LISTENERS = 8
const DEFAULT_STOP_TIMEOUT_MS = 10_000
const DEFAULT_LAUNCH_IDENTITY_TIMEOUT_MS = 5_000
const TERM_GRACE_MS = 2_000
const POLL_INTERVAL_MS = 25
const OWNER_TOKEN_ENVIRONMENT_NAME = 'GOODBUDDY_RUNTIME_OWNER_TOKEN'
@@ -603,8 +604,18 @@ export async function launchDirectLinuxStdioProcessOwner(
await waitForSpawn(child, options.signal, timeoutMs)
if (child.pid === undefined) throw new Error('Runtime spawn did not return a PID')
const readIdentity = options.readProcessIdentity ?? readLinuxRuntimeProcessIdentity
const processIdentity = await readIdentity(child.pid)
assertLaunchedIdentity(processIdentity, profile)
const processIdentity = await waitForLaunchedIdentity({
child,
pid: child.pid,
profile,
readIdentity,
signal: options.signal,
deadline: Math.min(
Date.parse(effectiveDeadlineAt),
now() + DEFAULT_LAUNCH_IDENTITY_TIMEOUT_MS
),
now
})
const supervisorIdentityDigest = supervisorDigest({
installationId,
ownerId,
@@ -871,15 +882,72 @@ function validateProfile(profile: OpenCodeLaunchProfile): OpenCodeLaunchProfile
}
}
function assertLaunchedIdentity(
identity: LinuxRuntimeProcessIdentity,
async function waitForLaunchedIdentity(input: {
child: DirectLinuxStdioChild
pid: number
profile: OpenCodeLaunchProfile
): void {
if (
identity.executablePath !== profile.processExecutable ||
identity.processGroupId !== identity.pid
) {
throw identityError('Spawned Runtime does not match the launch identity')
readIdentity: typeof readLinuxRuntimeProcessIdentity
signal?: AbortSignal
deadline: number
now: () => number
}): Promise<LinuxRuntimeProcessIdentity> {
for (;;) {
input.signal?.throwIfAborted()
if (
input.child.exitCode !== null ||
input.child.signalCode !== null
) {
throw new DirectLinuxStdioProcessOwnerError(
'Runtime process exited during launch',
'process'
)
}
let identity: LinuxRuntimeProcessIdentity
try {
identity = await input.readIdentity(input.pid)
} catch (error) {
if (!isMissingProcess(error)) {
throw error
}
if (input.now() >= input.deadline) {
throw new DirectLinuxStdioProcessOwnerError(
'Runtime launch identity was not observed',
'process'
)
}
await delay(
Math.min(
POLL_INTERVAL_MS,
Math.max(1, input.deadline - input.now())
)
)
continue
}
if (identity.processGroupId !== identity.pid) {
throw identityError(
'Spawned Runtime does not match the launch identity'
)
}
if (identity.executablePath === input.profile.processExecutable) {
return identity
}
if (identity.executablePath !== input.profile.executable) {
throw identityError(
'Spawned Runtime does not match the launch identity'
)
}
if (input.now() >= input.deadline) {
throw new DirectLinuxStdioProcessOwnerError(
'Runtime launch did not reach its supervised executable',
'process'
)
}
await delay(
Math.min(
POLL_INTERVAL_MS,
Math.max(1, input.deadline - input.now())
)
)
}
}
src/agent-daemon/opencode-runtime-profile.test.ts
+3
View File
@@ -241,6 +241,9 @@ describe('OpenCode bubblewrap launch profile', () => {
'--opencode-entrypoint',
resolve(fixture.bundleDirectory, 'bin', 'opencode')
])
expect(profile.processExecutable).toBe(
resolve(agentInstallationDirectory, 'node')
)
expect(profile.args.join('\0')).not.toMatch(
/api[-_]?key|authorization|bearer|(?:^|\0)--token(?:\0|$)/iu
)
src/agent-daemon/opencode-runtime-profile.ts
+1 -1
View File
@@ -266,7 +266,7 @@ export function createOpenCodeLaunchProfile(input: {
return {
executable: OPENCODE_BWRAP_EXECUTABLE,
processExecutable: OPENCODE_BWRAP_EXECUTABLE,
processExecutable: runtimeCommand.executable,
args,
cwd: scratchDirectory,
env: {
src/main/agent/acp-remote-runtime.test.ts
+25 -13
View File
@@ -599,7 +599,7 @@ describe('AcpRemoteRuntime', () => {
})
it.each(['prompt-running', 'outcome-unknown'] as const)(
'does not replace a %s binding after identity changes',
'retires a %s binding before starting an explicit later prompt',
async (state) => {
const store = new MemoryRuntimeSessionBindingStore()
const active = {
@@ -625,7 +625,13 @@ describe('AcpRemoteRuntime', () => {
lastMainAckSequence: '0'
}
await store.put(active)
const factory = vi.fn(async () => fakeServer().channel)
const replacement = fakeServer()
const factory = vi.fn(
async (bindingId: string) => {
expect(bindingId).not.toBe(active.bindingId)
return replacement.channel
}
)
const instance = factoryRuntime(factory, store, {
identity: {
...identity,
@@ -633,22 +639,28 @@ describe('AcpRemoteRuntime', () => {
}
})
await expect(
collect(
instance.run(
{ ...request, requestId: 'prompt-2' },
new AbortController().signal
)
await collect(
instance.run(
{ ...request, requestId: 'prompt-2' },
new AbortController().signal
)
).rejects.toThrow('不会自动重放')
)
expect(factory).not.toHaveBeenCalled()
expect(factory).toHaveBeenCalledOnce()
expect(factory).not.toHaveBeenCalledWith(active.bindingId)
await expect(
store.getById(active.bindingId)
).resolves.toMatchObject({
bindingId: active.bindingId,
state: 'closed',
activePromptOperationId: undefined
})
await expect(
store.getByConversation(request.conversationId)
).resolves.toMatchObject({
bindingId: active.bindingId,
state: 'outcome-unknown',
activePromptOperationId: request.requestId
bindingId: factory.mock.calls[0]![0],
state: 'ready',
activePromptOperationId: undefined
})
await instance.dispose()
}
src/main/agent/acp-remote-runtime.ts
+9 -14
View File
@@ -833,7 +833,7 @@ export class AcpRemoteRuntime implements AgentRuntime {
return interrupted
}
private async persistRejectedPrompt(
private async persistClosedBinding(
binding: RuntimeSessionBinding
): Promise<RuntimeSessionBinding> {
const closed = runtimeSessionBindingSchema.parse({
@@ -1198,24 +1198,19 @@ export class AcpRemoteRuntime implements AgentRuntime {
request: AgentExecutionRequest,
signal: AbortSignal
): Promise<SessionRecord> {
const old = await this.awaitLocalOperation(
let binding = await this.awaitLocalOperation(
'读取会话绑定',
this.options.bindingStore.getByConversation(conversationId),
signal
)
if (
old &&
old.state !== 'closed' &&
old.state !== 'ready'
binding &&
binding.state !== 'closed' &&
binding.state !== 'ready'
) {
await this.persistInterrupted(old)
throw new Error(
old.state === 'prompt-running'
? '远端 ACP 会话存在未确认的活动请求，结果未知且不会自动重放'
: '远端 ACP 会话恢复状态不确定，已中断且不会自动重放'
)
await this.persistClosedBinding(binding)
binding = undefined
}
let binding = old
let bindingId = binding?.bindingId ?? randomUUID()
if (
binding?.state === 'ready' &&
@@ -1437,7 +1432,7 @@ export class AcpRemoteRuntime implements AgentRuntime {
error,
'runtime/preparePrompt'
)
? this.persistRejectedPrompt(binding)
? this.persistClosedBinding(binding)
: this.persistInterrupted(binding)
await persist.catch(() => undefined)
}
@@ -1483,7 +1478,7 @@ export class AcpRemoteRuntime implements AgentRuntime {
error,
'runtime/preparePrompt'
)
? this.persistRejectedPrompt(current.binding)
? this.persistClosedBinding(current.binding)
: this.persistInterrupted(current.binding)
current.binding = await persist.catch(() => current.binding)
this.sessions.delete(conversationId)