refactor: remove UI identity translations

This commit is contained in:
Tianyi Cui
2026-07-14 02:09:09 +08:00
parent 709cc7200e
commit 61136b22bb
12 changed files with 100 additions and 110 deletions

View File

@@ -8,7 +8,7 @@ It is a **client-driver / UI plugin**, the structured analogue of the readline `
`apply(ctx, config)` — wires an `AgentSideConnection` (from `@agentclientprotocol/sdk`) to `process.stdin`/`process.stdout` and implements the ACP `Agent` method surface.
`inject: ['agents', 'sessions', 'sessionPersistence', 'tools', 'userInteraction']` — programs against the interface packages only (never `dsh-agent-loop`). `sessionPersistence` is required because `initialize` advertises `loadSession: true`; `tools` lets a tool own how its calls render (`presentCall`/`presentResult`) — the bridge looks the definition up by name and falls back to a generic presentation when a tool declares none (see Tool-call presentation). `userInteraction` lets agent-owned `ask_user_question` calls become ACP form elicitations routed to the owning session.
`inject: ['agents', 'sessionPersistence', 'tools', 'userInteraction']` — programs against the interface packages only (never `dsh-agent-loop`). `sessionPersistence` is required because `initialize` advertises `loadSession: true`; `tools` lets a tool own how its calls render (`presentCall`/`presentResult`) — the bridge looks the definition up by name and falls back to a generic presentation when a tool declares none (see Tool-call presentation). `userInteraction` lets agent-owned `ask_user_question` calls become ACP form elicitations routed to the owning session.
### Config
@@ -36,7 +36,7 @@ The `initialize` handshake reports a fixed server identity (`agentInfo: { name:
## Multi-session
The bridge multiplexes N sessions over one connection. Live sessions are held in a `Map<sessionId, SessionRecord>` (forward) with a `WeakMap<Agent, sessionId>` reverse map so agent-scoped approval events demultiplex in O(1). Every `session/event` is routed strictly to its owning record, so concurrent sessions never cross-settle or interleave their `session/update` notifications. State is per session: one in-flight prompt each, `session/cancel` aborts and settles only its own agent/prompt, and disposal drains every live session in parallel to quiescence. Permission prompts follow the same ownership: the `approval/request` answerer resolves the owning session through the reverse map and prompts only there.
The bridge multiplexes N sessions over one connection. Live sessions are held in a `Map<sessionId, SessionRecord>` keyed by the shared agent/session id. Agent-scoped events derive that id from `agent.session.id` and verify the record owns the exact agent object, so a foreign same-id object cannot claim the bridge's session. Every `session/event` is routed strictly to its owning record, so concurrent sessions never cross-settle or interleave their `session/update` notifications. State is per session: one in-flight prompt each, `session/cancel` aborts and settles only its own agent/prompt, and disposal drains every live session in parallel to quiescence. Permission prompts follow the same ownership and prompt only the matching session.
## Session config options

View File

@@ -18,12 +18,11 @@
* turn about to start) + settle the in-flight prompt
*
* Multi-session (RFC 011): N concurrent sessions per connection, each mapped to
* its own `ReactLoopAgent`. Sessions are keyed by id in `sessions` (forward) with an
* `agent→sessionId` reverse map for O(1) demux of `agent/*` events; every
* `session/event` and `agent/*` event is routed strictly to its owning session
* record, so two sessions streaming at once never interleave their
* `session/update` notifications. Permission prompts ride the same ownership
* map: the bridge answers `approval/request` for its own agents over
* its own `ReactLoopAgent`. Sessions are keyed by their shared agent/session id;
* every `session/event` and `agent/*` event is routed strictly to its owning
* session record, so two sessions streaming at once never interleave their
* `session/update` notifications. Permission prompts use the same identity: the
* bridge answers `approval/request` for its own agents over
* `session/request_permission` (see the approval answerer below) — whether a
* call ASKS is policy (a hook or plugin returning `ask`), not the bridge's.
*
@@ -106,9 +105,7 @@ export const name = 'acp'
// because `initialize` advertises `loadSession: true`. `tools` lets a tool own
// how its calls render (`presentCall`/`presentResult`); the bridge looks up the
// definition by name and falls back to a generic presentation when absent.
// TODO(acp-session-inject): drop `sessions`; this bridge never reads
// ctx.sessions, and agent/session ownership is already behind ctx.agents.
export const inject = ['agents', 'sessions', 'sessionPersistence', 'tools', 'userInteraction']
export const inject = ['agents', 'sessionPersistence', 'tools', 'userInteraction']
/**
* Build an ACP "invalid params" error whose human detail rides in the message.
@@ -268,7 +265,6 @@ export const Config: Schema<AcpConfig> = Schema.object({
* map keyed by id (RFC 011 multi-session).
*/
interface SessionRecord {
sessionId: SessionId
agent: Agent
/**
* The owned-agent disposer (from the {@link AgentHandle} the factory returned).
@@ -353,15 +349,8 @@ export function apply(ctx: Context, config: AcpConfig): void {
// this warn sink so a throwing tool presenter is logged, not propagated.
const makePresenter = (agent?: Agent): ToolPresenter => new ToolPresenter(tools, (message) => { logger.warn(message) }, agent)
// TODO(derive-acp-session-id): derive an event's id from agent.session and
// verify sessions.get(id)?.agent === agent; then remove this reverse map and
// SessionRecord.sessionId, whose sole read duplicates the same identity.
// Live sessions keyed by id (RFC 011 multi-session), plus an agent→sessionId
// reverse map so `agent/*` events (which carry only the Agent) demux in O(1).
// The forward record and weak reverse entry are installed together; removing
// the record releases its strong Agent reference, so the WeakMap entry expires.
// Live sessions keyed by their shared agent/session id (RFC 011 multi-session).
const sessions = new Map<SessionId, SessionRecord>()
const bySession = new WeakMap<Agent, SessionId>()
// Session ids whose `session/load` is mid-`resume()` (the slot is reserved
// before the async resume so a pipelined load/new for the SAME id can't create
// two agents). Distinct ids load concurrently; a given id loads once at a time.
@@ -382,20 +371,26 @@ export function apply(ctx: Context, config: AcpConfig): void {
// `notify` never observes it unset — no undefined guard needed.
let conn: AgentSideConnection
/** Return the bridge-owned record for an agent, rejecting same-id impostors. */
const ownedRecord = (agent: Agent): SessionRecord | undefined => {
const rec = sessions.get(agent.session.id)
return rec?.agent === agent ? rec : undefined
}
userInteraction.registerProvider({
async ask(request: AskUserQuestionRequest): Promise<AskUserQuestionAnswer> {
if (request.agent === undefined) {
throw new UserInteractionError('ACP user questions must come from an agent-owned request', 'NO_AGENT')
}
const sessionId = bySession.get(request.agent)
if (sessionId === undefined) {
const rec = ownedRecord(request.agent)
if (rec === undefined) {
throw new UserInteractionError('ACP user question has no matching session', 'NO_SESSION')
}
const answers: AskUserQuestionAnswerItem[] = []
for (const question of request.questions) {
const options = question.options ?? []
const response = await withAbort(conn.unstable_createElicitation(
elicitationForQuestion(sessionId, question, options),
elicitationForQuestion(rec.agent.session.id, question, options),
), request.signal).catch((error: unknown) => {
if (error instanceof UserInteractionError) throw error
throw new UserInteractionError('ACP elicitation request failed', 'ASK_FAILED', { cause: error })
@@ -496,7 +491,7 @@ export function apply(ctx: Context, config: AcpConfig): void {
const rec = sessions.get(session.header.id)
if (rec === undefined) return
try {
streamSessionEventUpdate(rec.sessionId, event, notify, rec.presenter, {
streamSessionEventUpdate(rec.agent.session.id, event, notify, rec.presenter, {
enabled: rec.terminalEnabled,
cwd: session.header.cwd,
}, { includeUserMessages: false })
@@ -527,12 +522,12 @@ export function apply(ctx: Context, config: AcpConfig): void {
// allow_always is a grant-storage design the approval RFC defers, so the
// prompt never offers a durable grant the harness could not honor.
ctx.on('approval/request', (req, next) => {
const sessionId = bySession.get(req.agent)
const rec = ownedRecord(req.agent)
// The protocol requires `toolCall` (the prompt renders attached to it), so
// a request without a callId has nothing to attach to — delegate.
if (sessionId === undefined || req.callId === undefined) return next()
if (rec === undefined || req.callId === undefined) return next()
return conn.requestPermission({
sessionId,
sessionId: rec.agent.session.id,
toolCall: { toolCallId: req.callId },
options: [
{ optionId: 'allow-once', name: 'Allow once', kind: 'allow_once' },
@@ -639,8 +634,7 @@ export function apply(ctx: Context, config: AcpConfig): void {
// turn) leaves the switch pending — it runs no step, so nothing executes
// or assembles under a stale value.
ctx.on('agent/prompt-submit', (agent, _content, _source, next) => {
const sessionId = bySession.get(agent)
const rec = sessionId === undefined ? undefined : sessions.get(sessionId)
const rec = ownedRecord(agent)
if (rec !== undefined) flushPendingSwitches(rec)
return next()
})
@@ -699,9 +693,7 @@ export function apply(ctx: Context, config: AcpConfig): void {
await handle.dispose()
throw internalError('connection closed during session/new')
}
bySession.set(handle.agent, sessionId)
sessions.set(sessionId, {
sessionId,
agent: handle.agent,
dispose: () => handle.dispose(),
presenter: makePresenter(handle.agent),
@@ -773,13 +765,11 @@ export function apply(ctx: Context, config: AcpConfig): void {
throw invalidParams('connection closed during session/load')
}
const agent = handle.agent
bySession.set(agent, sessionId)
// Snapshot the terminal capability ONCE for this session (used by both
// the replay below and the post-load live stream) so a later
// `initialize` can't desync the call/result of a tool card.
const terminalEnabled = terminalOutputCap
const record: SessionRecord = {
sessionId,
agent,
dispose: () => handle.dispose(),
presenter: makePresenter(agent),

View File

@@ -90,9 +90,12 @@ describe('acp bridge — approval answerer', () => {
await harness.ctx.plugin(ApprovalService)
harness.onPermission = () => ({ outcome: { outcome: 'selected', optionId: 'allow-once' } })
// Not created through the bridge: no bySession entry, so the answerer must
// call next() — nobody else answers, so the seam fails closed.
const foreign = { session: { events: [{ type: 'turn/start' }], append: () => ({}) } } as unknown as Agent
const { agent } = await ownedAgentRequest(harness)
// Even an impostor that claims the bridge-owned session id must delegate:
// ownership requires the exact Agent object stored in the session record.
const foreign = {
session: { id: agent.session.id, events: [{ type: 'turn/start' }], append: () => ({}) },
} as unknown as Agent
await expect(harness.ctx.approval.request({ agent: foreign, toolName: 'echo', callId: CallId('c') }))
.resolves.toBe('unavailable')
expect(harness.permissionRequests).toHaveLength(0)

View File

@@ -205,7 +205,8 @@ describe('acp bridge', () => {
await expect(harness.ctx.userInteraction.ask({ questions: [{ id: 'x', question: 'No agent?' }] }))
.rejects.toMatchObject({ name: 'UserInteractionError', code: 'NO_AGENT' })
await expect(harness.ctx.userInteraction.ask({ agent: { id: 'other' } as typeof agent, questions: [{ id: 'x', question: 'No session?' }] }))
const impostor = { session: { id: agent.session.id } } as typeof agent
await expect(harness.ctx.userInteraction.ask({ agent: impostor, questions: [{ id: 'x', question: 'No session?' }] }))
.rejects.toMatchObject({ code: 'NO_SESSION' })
harness.onElicitation = () => ({ action: 'cancel' })

View File

@@ -4,7 +4,7 @@ The **SDK server plugin** (`jsonrpc`): mounting it serves a stdio JSON-RPC serve
## Wiring
`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`) and demuxes `subagent/end` through the registry. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`); a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`.
`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches only parent lineage because the child may be disposed before `subagent/end`. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`); a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`.
## Config

View File

@@ -58,11 +58,6 @@ interface SessionRecord {
activePrompt: boolean
}
interface SubagentRecord {
childSessionId: string
parentSessionId: string | undefined
}
/**
* The SDK server over a booted harness context. Constructing it subscribes to
* the context's `session/event`, `session/created`, `agent/created`, and
@@ -76,7 +71,7 @@ export class HarnessSdkServer {
private llmFiber: { dispose(): Promise<void> } | undefined
private readonly sessions = new Map<string, SessionRecord>()
private readonly sessionCreations = new Map<string, Promise<SessionRecord>>()
private readonly subagentSessions = new Map<string, SubagentRecord>()
private readonly subagentParents = new Map<SessionId, SessionId>()
private readonly disposers: (() => void)[] = []
private shutdownTask: Promise<Record<string, never>> | undefined
private shuttingDown = false
@@ -100,29 +95,22 @@ export class HarnessSdkServer {
childSessionId: String(session.id),
})
}))
// Cache agent → session lineage on creation: by the time `subagent/end`
// fires the child agent may already be disposed and gone from the registry.
// Cache parent lineage on creation: by the time `subagent/end` fires the
// child agent may already be disposed and gone from the registry. The child
// session id needs no cache because it is the shared agent/session id.
this.disposers.push(ctx.on('agent/created', (agent) => {
this.subagentSessions.set(String(agent.id), {
childSessionId: String(agent.session.id),
parentSessionId: agent.session.header.parentSession === undefined
? undefined
: String(agent.session.header.parentSession),
})
const parentSessionId = agent.session.header.parentSession
if (parentSessionId !== undefined) this.subagentParents.set(agent.id, parentSessionId)
}))
this.disposers.push(ctx.on('subagent/end', (info: SubagentRunEndInfo) => {
const rec = this.subagentSessions.get(String(info.id))
const agent = this.ctx.agents.get(info.id)
const childSessionId = rec?.childSessionId ?? (agent === undefined ? undefined : String(agent.session.id))
const parentSessionId = rec?.parentSessionId ?? (
agent?.session.header.parentSession === undefined ? undefined : String(agent.session.header.parentSession)
)
if (childSessionId === undefined) return
const parentSessionId = this.subagentParents.get(info.id) ?? agent?.session.header.parentSession
this.subagentParents.delete(info.id)
this.transport.notify('subagent.finished', {
provider: info.provider,
agentId: String(info.id),
...(parentSessionId === undefined ? {} : { parentSessionId }),
childSessionId,
...(parentSessionId === undefined ? {} : { parentSessionId: String(parentSessionId) }),
childSessionId: String(info.id),
status: info.stopReason === 'completed' ? 'ok' : 'error',
stopReason: info.stopReason,
...(info.lastAssistantMessage === undefined ? {} : { lastAssistantMessage: info.lastAssistantMessage }),
@@ -195,7 +183,7 @@ export class HarnessSdkServer {
this.sessionCreations.clear()
const records = [...this.sessions.values()]
this.sessions.clear()
this.subagentSessions.clear()
this.subagentParents.clear()
const failures: unknown[] = []
while (this.disposers.length > 0) {
try {

View File

@@ -272,6 +272,9 @@ describe('HarnessSdkServer', () => {
meta: { cwd: storageDir, parentSession: SessionId('main') },
agentOptions: { model: 'deepseek' },
})
// The backend may dispose the child before publishing its run outcome;
// only the cached parent lineage should be needed at this point.
await handle.dispose()
await settleSubagent(ctx, parentHandle.agent, {
provider: 'spawn',
id: SessionId('child-session'),
@@ -292,7 +295,6 @@ describe('HarnessSdkServer', () => {
},
})
await handle.dispose()
await parentHandle.dispose()
await server.shutdown()
} finally {
@@ -301,7 +303,7 @@ describe('HarnessSdkServer', () => {
}
})
it('falls back to live agent lineage for uncached subagent end events', async () => {
it('falls back to live lineage and treats the shared id as the child session id', async () => {
const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-fallback-'))
const ctx = await makeHarness(storageDir)
let parentHandle: AgentHandle | undefined
@@ -365,10 +367,16 @@ describe('HarnessSdkServer', () => {
stopReason: 'error',
},
})
expect(transport.notifications.some(n =>
n.method === 'subagent.finished'
&& n.params?.agentId === 'missing-child-agent',
)).toBe(false)
expect(transport.notifications).toContainEqual({
method: 'subagent.finished',
params: {
provider: 'fork',
agentId: 'missing-child-agent',
childSessionId: 'missing-child-agent',
status: 'error',
stopReason: 'error',
},
})
await server.shutdown()
} finally {