@tanstack/ai-sandbox
Version:
Provider-agnostic sandbox layer for TanStack AI — run harness adapters inside isolated sandboxes (defineSandbox, defineWorkspace, withSandbox) with a uniform SandboxHandle, workspace bootstrap, policy, and resumable lifecycle.
139 lines (138 loc) • 7.39 kB
TypeScript
import { ProcessOptions, SandboxHandle } from './contracts.js';
import { RunStore } from '@tanstack/ai';
export interface SpawnNdjsonOptions extends ProcessOptions {
/**
* Called for each raw stdout line that is non-empty but fails JSON parsing
* (e.g. a CLI banner). Defaults to ignoring it. Stderr is never parsed.
*/
onNonJsonLine?: (line: string) => void;
/**
* Written to the process stdin (then stdin is closed) right after spawn —
* e.g. the agent prompt for `claude -p`. Avoids putting the prompt in argv.
*/
input?: string;
/**
* Route the agent's stdout through an in-sandbox journal rather than holding
* its pipe directly.
*
* This is what makes a run survive host death: with nothing piped, there is
* no reader whose disappearance can SIGPIPE the agent, and a later host reads
* the same file from byte 0. Opt-in so every existing caller (and every
* existing test) is unaffected.
*/
journal?: JournalOptions;
}
/** Journaling configuration for {@link spawnNdjson}. */
export interface JournalOptions {
/** Run id the journal path is derived from. Must match across hosts. */
runId: string;
/** Journal directory. Defaults to `/tmp/tanstack-runs`. */
dir?: string;
/**
* Read an EXISTING journal instead of starting the agent. The read still
* begins at byte 0 — the alignment step, not the reader, decides what has
* already been delivered.
*/
attach?: boolean;
/** Poll interval for providers that cannot follow. */
pollIntervalMs?: number;
/**
* Run record store, consulted ONLY on an attach and only when the journal is
* absent, to tell "not written yet" from "will never be written" (see
* `attach-preflight.ts`). Optional so an attach with no store wired keeps the
* bounded wait while losing the unknown/terminal classification.
*/
runs?: RunStore;
/**
* Bounded wait for a live run's journal to appear on an attach, AND — on every
* path, attach or fresh — the bound on the read's first byte
* (`ReadJournalOptions.firstByteTimeoutMs`). One knob for both because they
* bound the same question from two sides: the preflight covers "the file does
* not exist", the read covers "the file exists but nothing is writing to it",
* and a caller that widens one always means to widen the other.
*
* Defaults to `DEFAULT_ATTACH_JOURNAL_WAIT_MS`.
*/
attachWaitMs?: number;
}
type JournaledOptions = SpawnNdjsonOptions & {
journal: JournalOptions;
};
/** Split a stream of arbitrary string chunks into complete lines. */
export declare function toLines(chunks: AsyncIterable<string>): AsyncIterable<string>;
/**
* Start the agent with its stdout (and the `{"__exit":N}` sentinel) redirected
* into the journal, then return.
*
* Deliberately does NOT wait for the process and does NOT read its stdout: the
* whole point of journaling is that the host holds no handle on the agent's
* output, so a host that dies mid-run cannot take the agent down with it (no
* pipe to SIGPIPE). The spawned process is left running in the sandbox; the
* sentinel line the wrapper appends on exit is how anyone — this host or a
* successor — learns it finished. Stdin is still written directly to the
* spawned process, exactly as the unjournaled path does, since that transport
* is unaffected by where stdout goes.
*/
export declare function startJournaledAgent(handle: SandboxHandle, command: string, options: JournaledOptions): Promise<void>;
/**
* Read a run's journal and yield each line parsed as JSON.
*
* Always reads from byte 0 — the alignment step (a later phase), not this
* reader, decides what a client has already seen. Stops at the `{"__exit":N}`
* sentinel, and throws for a non-zero N so the calling adapter's existing
* `catch` turns it into a `RUN_ERROR`, the same observable outcome the
* unjournaled path produces from a non-zero `wait()`. There is nothing to
* `wait()` on here: the host holds a `tail`, not the agent process, so the
* sentinel line IS the exit code.
*
* The sentinel is also what bounds journal growth: reaching it means the run is
* terminal, and a terminal run's record is the event log, so both journal files
* are deleted before this iterable finishes. The ordering below is load-bearing
* and is asserted, not merely commented:
*
* - The sentinel is captured and the loop is `break`-ed, so the source's
* `finally` kills the `tail` BEFORE the `rm` runs — the reader is stopped, then
* its input is deleted, never the other way round.
* - `exitCode` stays `undefined` if the journal stream ends without a sentinel.
* NOTHING is deleted on that path either way — the run may be mid-flight and a
* successor host may still need every byte — but the two causes are then
* separated by `options.signal.aborted`: an aborted consumer returns quietly,
* while a stream that died on its own (killed `tail`, destroyed sandbox, torn
* pipe) THROWS. Returning for both is how a truncated read used to reach the
* client as a normally-completing run.
* - A non-zero sentinel deletes too. The run is terminal either way.
* - The stderr sidecar is read BEFORE the deletion that destroys it, so a
* non-zero exit carries up to {@link STDERR_ERROR_CHARS} chars of the agent's
* own diagnostics, exactly as the unjournaled path below does. That closes the
* "Known regression" this function used to document; the read is bounded and
* failure-swallowing (see {@link readStderrTail}), so it cannot turn a run
* failure into a cleanup failure.
*
* On an ATTACH (`journal.attach === true`) the read is preceded by
* {@link awaitAttachableJournal}, which fails fast for a runId the store does not
* know or has already terminalized and otherwise waits a BOUNDED time for a live
* run's journal to appear. Without it, an attach to a runId with no journal
* created an empty one (`journalFollowCommand` does that deliberately) and tailed
* it forever — no sentinel, no error, no timeout.
*
* One case this does NOT bound: a run that reaches its sentinel while DETACHED
* has no host reading it, so nothing observes the sentinel and nothing here
* runs. Sweeping those is `pruneJournals`' job (`journal-sweep.ts`): it consults
* the run store's status for each journal it finds and deletes only the terminal
* ones, from a cron the application schedules rather than from a run.
*/
export declare function readJournalNdjson(handle: SandboxHandle, options: JournaledOptions): AsyncIterable<unknown>;
/**
* Spawn `command` in the sandbox and yield each stdout line parsed as JSON.
*
* Without `options.journal`, behavior is byte-identical to before: resolves
* the spawn handle's exit via `wait()` after stdout closes; a non-zero exit
* with no events surfaced is the adapter's concern to detect.
*
* With `options.journal`, the agent's stdout is redirected into an in-sandbox
* journal (unless `journal.attach` is set, meaning a run already in flight)
* and then read back from byte 0 — one code path for a fresh run and an
* attach, both going through {@link readJournalNdjson}.
*/
export declare function spawnNdjson(handle: SandboxHandle, command: string, options?: SpawnNdjsonOptions): AsyncIterable<unknown>;
export {};