fix(sdk): harden runtime lifecycle and JSON-RPC

Keep DeepSeekHarness.run() reusable, but make ownership of its lazy
runtime process explicit. Document the context-manager/close contract and
update every construction example to use a context manager so repeated runs
remain valid without encouraging leaked subprocesses.

Contain notification predicate failures at the subscription boundary. Remove
only the subscriber whose callback raised, deliver that exception through its
queue, and continue dispatching to healthy subscribers so arbitrary callback
code cannot terminate the shared reader thread or strand later requests.

Enforce one in-flight prompt per server session with an atomic activePrompt
guard. Route overlap through the existing -32603 handler-error response and
clear the guard in finally, preserving parallel prompts across sessions and
sequential reuse without changing JSON-RPC request or notification shapes.

Use StringDecoder for line framing so a UTF-8 code point split across Buffer
chunks is not corrupted. Add a queued-write flush barrier, and make memoized
shutdown await it before disposal and exit while retaining exactly-once
cleanup when shutdown calls race or flushing fails.

Cover callback isolation, same-session exclusion, cross-session concurrency,
split multibyte input, delayed writes, racing shutdown, and flush failure with
deterministic tests.
This commit is contained in:
Tianyi Cui
2026-07-13 20:53:20 +08:00
parent fe3777cf27
commit d5e894edf4
16 changed files with 315 additions and 55 deletions
+25 -13
View File
@@ -36,7 +36,10 @@ export interface InitializeResult {
serverInfo: { name: string; version: string }
}
/** Parameters of a `session/prompt` request (one user turn on one SDK session). */
/**
* Parameters of a `session/prompt` request: one user turn on one SDK session,
* with at most one in flight per session.
*/
export interface SessionPromptParams {
/** The SDK-side session id; an unknown id lazily creates the agent+session pair. */
sessionId: string
@@ -53,6 +56,7 @@ export interface SessionPromptResult {
interface SessionRecord {
handle: AgentHandle
lastTurnEnd: TurnEndReason | undefined
activePrompt: boolean
}
interface SubagentRecord {
@@ -147,22 +151,30 @@ export class HarnessSdkServer {
/**
* Handle `session/prompt`: get-or-create the session's agent, send the
* content as the user message, await turn settle (quiescence), then notify
* `session.finished` with the settled turn's outcome.
* `session.finished` with the settled turn's outcome. A session accepts at
* most one prompt at a time; an overlapping request fails immediately while
* other sessions remain independent.
* @param params - the target session id and prompt content.
* @returns `{ accepted: true }` after the turn settled.
*/
async prompt(params: SessionPromptParams): Promise<SessionPromptResult> {
const rec = await this.getOrCreateSession(params.sessionId)
rec.lastTurnEnd = undefined
rec.handle.agent.send(params.contentBlocks)
await rec.handle.agent.whenIdle()
const status = this.finishedStatus(rec.lastTurnEnd)
this.transport.notify('session.finished', {
sessionId: params.sessionId,
status,
reason: rec.lastTurnEnd,
})
return { accepted: true }
if (rec.activePrompt) throw new Error(`session already has an active prompt: ${params.sessionId}`)
rec.activePrompt = true
try {
rec.lastTurnEnd = undefined
rec.handle.agent.send(params.contentBlocks)
await rec.handle.agent.whenIdle()
const status = this.finishedStatus(rec.lastTurnEnd)
this.transport.notify('session.finished', {
sessionId: params.sessionId,
status,
reason: rec.lastTurnEnd,
})
return { accepted: true }
} finally {
rec.activePrompt = false
}
}
/**
@@ -248,7 +260,7 @@ export class HarnessSdkServer {
meta: { cwd: this.cwd },
agentOptions: { model: this.model },
})
const rec: SessionRecord = { handle, lastTurnEnd: undefined }
const rec: SessionRecord = { handle, lastTurnEnd: undefined, activePrompt: false }
this.sessions.set(sessionId, rec)
return rec
}