fix: make managed SSH sessions fast and resilient
GoodBuddy Agents / Validate Agent source (push) Canceled after 0s
GoodBuddy Agents / Build Linux arm64 Agent (push) Canceled after 0s
GoodBuddy Agents / Build Linux x64 Agent (push) Canceled after 0s
Cross-platform packages / Validate source (push) Canceled after 0s
Cross-platform packages / Authorize desktop packaging (push) Canceled after 0s
Cross-platform packages / linux arm64 (push) Canceled after 0s
Cross-platform packages / macos arm64 (push) Canceled after 0s
Cross-platform packages / windows arm64 (push) Canceled after 0s
Cross-platform packages / linux x64 (push) Canceled after 0s
Cross-platform packages / macos x64 (push) Canceled after 0s
Cross-platform packages / windows x64 (push) Canceled after 0s
Cross-platform packages / Publish GitHub and OSS release (push) Canceled after 0s

Managed SSH project selection repeatedly activated the remote Host and could
leave idle ACP bindings rejected as stale-controller after a controller
generation change. Host environment updates also coupled project state to
component installation evidence and presented a crowded control surface.

Project selection is now local-only, one Host connection serves compatible
project and conversation callers, idle bindings are safely replaced only
after proven controller takeover, and active prompts keep exact resume/replay.
Remote environment setup now uses explicit signed compound package
preparation with bounded transfer, rollback, recovery, and clearer settings.

Managed Hosts must be updated to separately distributed Agent 0.11.6 before
the daemon-side controller recovery fix takes effect. Desktop packages do not
embed the Agent or remote Runtime, and existing project data is preserved.

Release note: 托管 SSH 项目切换不再重复连接,同一 Host 可顺畅承载多个项目和对话;同时修复重连后的 stale-controller,并优化远程环境安装、更新与状态布局。
This commit is contained in:
mesalogo
2026-08-29 10:58:19 +08:00
parent eb947213c8
commit 459cc21e3d
117 changed files with 19876 additions and 9664 deletions
+172 -11
View File
@@ -155,11 +155,7 @@ class MemoryAcpJournal implements RuntimeAcpJournal {
}
class FakeProcess implements RuntimeAcpProcessOwner {
readonly identity: RuntimeAcpProcessIdentity = {
launchId: 'launch-1',
processId: 'process-1',
supervisorIdentityDigest: digest('9')
}
readonly identity: RuntimeAcpProcessIdentity
readonly writes: Uint8Array[] = []
readonly stops: string[] = []
readonly prompts: Array<{
@@ -167,15 +163,24 @@ class FakeProcess implements RuntimeAcpProcessOwner {
maximumInputBytes: number
}> = []
completions = 0
reconciliation: RuntimeAcpProcessReconciliation = {
identity: this.identity,
state: 'running',
processTree: 'running'
}
reconciliation: RuntimeAcpProcessReconciliation
#listener?: (
output: RuntimeAcpProcessOutput
) => void | Promise<void>
constructor(identity = '1') {
this.identity = {
launchId: `launch-${identity}`,
processId: `process-${identity}`,
supervisorIdentityDigest: digest(identity)
}
this.reconciliation = {
identity: this.identity,
state: 'running',
processTree: 'running'
}
}
beginPrompt(input: {
deadlineAt: string
maximumInputBytes: number
@@ -238,6 +243,8 @@ function harness(input: {
now?: number
maximumOutputBytes?: number
bridgeCloseError?: boolean
uniqueProcesses?: boolean
outputGate?: Promise<void>
} = {}) {
const workMode = input.workMode ?? 'ask'
let now = input.now ?? 1_000
@@ -275,10 +282,13 @@ function harness(input: {
workMode: launch.workMode,
scratch: launch.scratch
})
return process
return input.uniqueProcesses && launches.length > 1
? new FakeProcess(String(launches.length))
: process
}),
now: () => now,
outputSink: vi.fn(async (frame) => {
await input.outputGate
outputFrames.push(Buffer.from(frame.payload).toString())
}),
blobSink,
@@ -644,6 +654,113 @@ describe('RuntimeAcpBackend', () => {
).rejects.toMatchObject({ code: 'stale-controller' })
})
it('reopens a detached idle binding after a proven same-controller takeover', async () => {
const fixture = harness()
await open(fixture)
await invoke(
fixture,
'runtime/preparePrompt',
fixture.preparation()
)
await invoke(fixture, 'runtime/completePrompt', {
bindingId: 'binding-1',
operationId: 'request-1',
requestId: 'request-1'
})
fixture.context.abort.abort()
await new Promise<void>((resolve) => setImmediate(resolve))
const replacement = protocolContext({
generation: 2,
connectionId: 'connection-2'
})
replacement.controllerTakeoverProven = true
await expect(
fixture.backend.methods['runtime/openAcpChannel']!(
fixture.openRequest,
replacement
)
).resolves.toMatchObject({
bindingId: 'binding-1',
channelEpoch: '1001'
})
expect(fixture.process.stops).toEqual(['binding-closed'])
expect(fixture.journal.retired).toContainEqual({
controllerId: 'controller-1',
bindingId: 'binding-1',
channelEpoch: '1000'
})
})
it('drains the detached old epoch before replacing an idle binding', async () => {
let releaseOutput!: () => void
const outputGate = new Promise<void>((resolve) => {
releaseOutput = resolve
})
const fixture = harness({ outputGate })
await open(fixture)
await invoke(
fixture,
'runtime/preparePrompt',
fixture.preparation()
)
const pendingOutput = fixture.process.emit('stdout', 'pending')
await new Promise<void>((resolve) => setImmediate(resolve))
await invoke(fixture, 'runtime/completePrompt', {
bindingId: 'binding-1',
operationId: 'request-1',
requestId: 'request-1'
})
fixture.context.abort.abort()
await new Promise<void>((resolve) => setImmediate(resolve))
const replacement = protocolContext({
generation: 2,
connectionId: 'connection-2'
})
replacement.controllerTakeoverProven = true
let replaced = false
const reopen = fixture.backend.methods[
'runtime/openAcpChannel'
]!(fixture.openRequest, replacement).then((result) => {
replaced = true
return result
})
await new Promise<void>((resolve) => setImmediate(resolve))
expect(replaced).toBe(false)
releaseOutput()
await pendingOutput
await expect(reopen).resolves.toMatchObject({
bindingId: 'binding-1',
channelEpoch: '1001'
})
expect(fixture.journal.frames).toContainEqual(
expect.objectContaining({
bindingId: 'binding-1',
channelEpoch: '1000',
sequence: '1'
})
)
})
it('does not adopt an idle binding without exact takeover proof', async () => {
const fixture = harness()
await open(fixture)
fixture.context.abort.abort()
await new Promise<void>((resolve) => setImmediate(resolve))
await expect(
fixture.backend.methods['runtime/openAcpChannel']!(
fixture.openRequest,
protocolContext({
generation: 2,
connectionId: 'connection-2'
})
)
).rejects.toMatchObject({ code: 'stale-controller' })
})
it('reopens a definitively closed stable binding with a fresh epoch and generation', async () => {
const fixture = harness()
await open(fixture)
@@ -799,6 +916,13 @@ describe('RuntimeAcpBackend', () => {
generation: 2,
connectionId: 'connection-2'
})
resumedContext.controllerTakeoverProven = true
await expect(
fixture.backend.methods['runtime/openAcpChannel']!(
fixture.openRequest,
resumedContext
)
).rejects.toMatchObject({ code: 'stale-controller' })
await expect(
fixture.backend.methods['runtime/resumeAcpChannel']!(
{
@@ -1019,6 +1143,43 @@ describe('RuntimeAcpBackend', () => {
).rejects.toMatchObject({ code: 'identity' })
expect(fixture.process.stops).toEqual(['identity-conflict'])
})
it('runs independent conversations for two workspaces on one controller', async () => {
const fixture = harness({ uniqueProcesses: true })
await open(fixture)
const secondOpen = {
...fixture.openRequest,
bindingId: 'binding-2',
workspaceIdentity: 'workspace-identity-2'
}
await invoke(
fixture,
'runtime/openAcpChannel',
secondOpen
)
await Promise.all([
invoke(
fixture,
'runtime/preparePrompt',
fixture.preparation()
),
invoke(
fixture,
'runtime/preparePrompt',
fixture.preparation({
bindingId: 'binding-2',
operationId: 'request-2',
requestId: 'request-2',
channelEpoch: '1001',
workspaceIdentity: 'workspace-identity-2'
})
)
])
expect(fixture.launches).toHaveLength(2)
expect(fixture.process.stops).toEqual([])
})
})
async function open(fixture: Harness): Promise<Record<string, unknown>> {