@relayflows/sdk 2.0.31 → 2.0.32

package/src/cli.ts

@@ -9,6 +9,10 @@ import type { CliModelSource } from './cli-adapter.js';
 import { renderProgress, type ProgressEvent } from './progress.js';
 import type { JournalEvent } from './journal-reader.js';
 import { createObserverSession } from './cli/observer-session.js';
+import {
+  cloudMirrorRequested, createCloudMirrorSession, mirrorSourceFromJournal, mirrorSourceFromPath,
+  type CloudMirrorReceipt,
+} from './cli/cloud-mirror-session.js';
 import { realpathSync } from 'node:fs';
 import { pathToFileURL } from 'node:url';
 import {
@@ -54,6 +58,7 @@ import {
   resolveObserverLinkEnv,
   type MintObserverOptions,
 } from './observer-link.js';
+import { packageVersion } from './package-version.js';
 
 export type { CheckInputDiagnostic, CheckReport } from './cli/check.js';
 
@@ -95,8 +100,8 @@ export type ParsedArgs =
   | { command: 'schedules'; json: boolean }
   | { command: 'unschedule'; scheduleId: string; json: boolean }
   | { command: 'check'; json: boolean; watch: boolean; value: string }
-  | { command: 'run'; bucket: string | undefined; reuseFromRunId: string | undefined; localAgent: boolean; agentCapacity: number | undefined; dataDir: string; input: string | undefined; json: boolean; spawn: boolean; noObserverLink: boolean; allowHumanInfluenced: boolean; value: string }
-  | { command: 'resume'; localAgent: boolean; agentCapacity: number | undefined; dataDir: string; json: boolean; spawn: boolean; noObserverLink: boolean; allowHumanInfluenced: boolean; value: string }
+  | { command: 'run'; bucket: string | undefined; reuseFromRunId: string | undefined; localAgent: boolean; agentCapacity: number | undefined; dataDir: string; input: string | undefined; json: boolean; spawn: boolean; noObserverLink: boolean; cloudMirror: boolean; allowHumanInfluenced: boolean; value: string }
+  | { command: 'resume'; localAgent: boolean; agentCapacity: number | undefined; dataDir: string; json: boolean; spawn: boolean; noObserverLink: boolean; cloudMirror: boolean; allowHumanInfluenced: boolean; value: string }
   | { command: 'answer'; dataDir: string; json: boolean; spawn: boolean; note: string | undefined; by: string | undefined; runId: string; waitId: string; answer: boolean }
   | RunsArgs
   | LogsArgs
@@ -126,13 +131,13 @@ const USAGE = [
   'flows run <flow>@sha256:<digest> [--bucket <file-bucket-uri>] [--data-dir <dir>] [--json]',
   'flows check [--watch] [--json] <flow.ts|flow.yaml|spec.json>',
   'flows serve-webhook --data-dir <dir> --port <p> [--allow <name>[,<name>]]',
-  'flows run [--json] [--no-spawn] [--no-observer-link] [--data-dir <dir>] [--local-agent [--agent-capacity <n>]] [--reuse-from <run-id>] <flow.yaml|spec.json>',
+  'flows run [--json] [--no-spawn] [--no-observer-link] [--cloud-mirror] [--data-dir <dir>] [--local-agent [--agent-capacity <n>]] [--reuse-from <run-id>] <flow.yaml|spec.json>',
   'flows run --cloud [--json] [--wait] [--sync-code] [--no-connect] <flow.yaml|spec.json>',
   'flows run --cloud [--json] [--wait] [--sync-code] [--no-connect] <flow.ts> --input <inline-json-or-file>',
   'flows sync [--json] [--dry-run] [--dir <path>] <run-id>',
-  'flows run [--json] [--no-spawn] [--no-observer-link] [--data-dir <dir>] [--local-agent [--agent-capacity <n>]] <flow.ts> --input <inline-json-or-file>',
+  'flows run [--json] [--no-spawn] [--no-observer-link] [--cloud-mirror] [--data-dir <dir>] [--local-agent [--agent-capacity <n>]] <flow.ts> --input <inline-json-or-file>',
   'flows tick start --schedule-id <id> --interval-ms <ms> [--epoch-ms <ms>] [--max-catch-up <n>] [--poll-interval-ms <ms>] [--data-dir <dir>] <spec.json>',
-  'flows resume [--allow-human-influenced] [--json] [--no-spawn] [--no-observer-link] [--data-dir <dir>] [--local-agent [--agent-capacity <n>]] <run-id>',
+  'flows resume [--allow-human-influenced] [--json] [--no-spawn] [--no-observer-link] [--cloud-mirror] [--data-dir <dir>] [--local-agent [--agent-capacity <n>]] <run-id>',
   'flows answer [--json] [--no-spawn] [--data-dir <dir>] [--note <text>] [--by <identity>] <run-id> <wait-id> <yes|no>',
   'flows replay [--allow-human-influenced] [--json] [--data-dir <dir>] <run-id> [--at <step-id>]',
   'flows status [--json] [--data-dir <dir>] [--tail <n>] [<run-id>]',
@@ -161,6 +166,12 @@ const PROCESS_IO: CliIo = {
 
 /** Optional knobs for an embedded caller. `bin/flows.js` passes none. */
 export interface RunCliOptions {
+  /**
+   * Version to print for a self-contained executable that cannot read the
+   * installed package manifest. Normal package entrypoints leave this unset.
+   */
+  version?: string;
+
   /**
    * Cancellation for the long-running verbs (`run --cloud`, `check --watch`,
    * `serve-webhook`, `hn-monitor start`, `tick start`).
@@ -202,6 +213,10 @@ export async function runCli(
   io: CliIo = PROCESS_IO,
   options: RunCliOptions = {},
 ): Promise<CliExitCode> {
+  if (args.length === 1 && (args[0] === '--version' || args[0] === '-V')) {
+    io.stdout(options.version ?? packageVersion());
+    return 0;
+  }
   if (args.length === 1 && (args[0] === '--help' || args[0] === '-h')) {
     io.stdout(USAGE);
     return 0;
@@ -315,25 +330,59 @@ export async function runCli(
   // effect of an invocation that is about to be refused for bad input.
   const startedSteps = new Map<string, number>();
   const observer = parsed.noObserverLink ? undefined : createObserverSession(parsed.command, io);
+  const runnerLog: string[] = [];
+  // Opt-in, unlike the observer link beside it. The observer is the default
+  // way to watch a local run: it is free, it needs only a workspace key, and
+  // it carries a step projection. The dashboard is the richer, hosted view —
+  // it stores the flow source, every step's transcript and this invocation's
+  // own output — so a local run joins it because someone asked, never because
+  // a login happened to be lying around.
+  const mirror = !(parsed.cloudMirror || cloudMirrorRequested(process.env))
+    ? undefined
+    : createCloudMirrorSession({
+      source: parsed.command === 'run'
+        ? mirrorSourceFromPath(parsed.value, parsed.input, parsed.dataDir)
+        : mirrorSourceFromJournal(parsed.dataDir),
+      dataDir: parsed.dataDir,
+      log: () => runnerLog,
+      requested: parsed.cloudMirror ? 'flag' : 'env',
+    }, io);
+  // Everything this invocation prints, kept in order, so the mirror can upload
+  // it as the run's `runner.log` — the object the dashboard's log pane reads,
+  // and the sandbox's own equivalent. A declarative run emits no progress
+  // events at all, so building the log out of those would have left the pane
+  // empty for exactly the runs that are easiest to follow.
+  const logged: CliIo = mirror === undefined ? io : {
+    ...io,
+    stdout: line => { runnerLog.push(line); io.stdout(line); },
+    stderr: line => { runnerLog.push(line); io.stderr(line); },
+  };
   const showProgress = (event: ProgressEvent): void => {
     if (event.type === 'step.started') startedSteps.set(event.stepId, performance.now());
-    if (!parsed.json) for (const line of renderProgress([event])) io.stderr(line);
+    if (!parsed.json) for (const line of renderProgress([event])) logged.stderr(line);
     observer?.onProgress(event);
+    mirror?.onProgress(event);
   };
   const lifecycle = {
     ...(parsed.command === 'run' ? { bucket: parsed.bucket } : {}),
     allowHumanInfluenced: parsed.allowHumanInfluenced,
-    onPtyReady: (path: string) => io.stderr(`PTY ${path}`),
+    onPtyReady: (path: string) => logged.stderr(`PTY ${path}`),
     ...(parsed.command === 'run' && parsed.reuseFromRunId !== undefined ? { reuseFromRunId: parsed.reuseFromRunId } : {}),
     localAgent: parsed.localAgent,
     ...(parsed.agentCapacity === undefined ? {} : { agentCapacity: parsed.agentCapacity }),
     onProgress: showProgress,
-    ...(observer === undefined ? {} : {
-      onJournalEntry: (entry: JournalEvent) => observer.onJournalEntry(entry),
-      onRunStarted: (run: { runId: string; flow: string; resumed?: boolean }) => observer.onRunStarted(run),
+    ...(observer === undefined && mirror === undefined ? {} : {
+      onJournalEntry: (entry: JournalEvent) => {
+        observer?.onJournalEntry(entry);
+        mirror?.onJournalEntry(entry);
+      },
+      onRunStarted: (run: { runId: string; flow: string; resumed?: boolean }) => {
+        observer?.onRunStarted(run);
+        mirror?.onRunStarted(run);
+      },
     }),
     onWait: (progress: RunProgress) => {
-      emitWait(progress, io);
+      emitWait(progress, logged);
       const now = performance.now();
       if (!startedSteps.has(progress.stepId)) startedSteps.set(progress.stepId, now);
       showProgress({ type: 'step.running', stepId: progress.stepId, stepType: progress.stepType,
@@ -361,12 +410,17 @@ export async function runCli(
   // preflight) is worse than printing `Observer:` on a later line, so we
   // emit the run report immediately and finalize the observer link after.
   if (parsed.json) {
-    const observerUrl = await observerUrlFrom(observerMint, io);
-    emitRunReport(execution, parsed.json, io, observerUrl);
+    const observerUrl = await observerUrlFrom(observerMint, logged);
+    emitRunReport(execution, parsed.json, logged, observerUrl, await mirror?.receipt());
+    // Last, and after the report: the run's own output is what the mirror
+    // uploads, and a run's exit code has never waited on Cloud. The mirror
+    // bounds itself and never rejects.
+    await mirror?.finish(execution.report);
     return execution.exitCode;
   }
-  emitRunReport(execution, parsed.json, io);
-  await finalizeObserverLine(observerMint, io);
+  emitRunReport(execution, parsed.json, logged);
+  await finalizeObserverLine(observerMint, logged);
+  await mirror?.finish(execution.report);
   return execution.exitCode;
 }
 
@@ -593,6 +647,7 @@ function parseArgs(args: readonly string[]): ParsedArgs | undefined {
   let sawDataDir = false;
   let spawn = true;
   let noObserverLink = false;
+  let cloudMirror = false;
   let input: string | undefined;
   let sawInput = false;
   let reuseFromRunId: string | undefined;
@@ -651,6 +706,14 @@ function parseArgs(args: readonly string[]): ParsedArgs | undefined {
       noObserverLink = true;
       continue;
     }
+    if (argument === '--cloud-mirror') {
+      // Only meaningful where a local run exists to mirror. Refused on `check`
+      // (which starts nothing) and, below, on `--cloud` (which IS the hosted
+      // run), so the flag never silently no-ops.
+      if (command === 'check' || cloudMirror) return undefined;
+      cloudMirror = true;
+      continue;
+    }
     if (argument === '--data-dir') {
       const value = args[index + 1];
       if (command === 'check' || sawDataDir || value === undefined || value.startsWith('-')) return undefined;
@@ -694,7 +757,8 @@ function parseArgs(args: readonly string[]): ParsedArgs | undefined {
     // observer-link opt-out -- describes nothing there and is refused rather
     // than ignored. `--input` is the authored body's argument and travels with
     // the source, so it is accepted exactly where a local run accepts it.
-    if (allowHumanInfluenced || sawDataDir || !spawn || localAgent || noObserverLink || reuseFromRunId !== undefined) return undefined;
+    if (allowHumanInfluenced || sawDataDir || !spawn || localAgent || noObserverLink || cloudMirror
+      || reuseFromRunId !== undefined) return undefined;
     if (sawInput && !isAuthoredFlowPath(positionals[0]!)) return undefined;
     return { command: 'cloud-run', value: positionals[0]!, json, wait, input, syncCode, noConnect };
   }
@@ -705,8 +769,8 @@ function parseArgs(args: readonly string[]): ParsedArgs | undefined {
   return command === 'check'
     ? { command, json, watch, value: positionals[0]! }
     : command === 'run'
-      ? { command, bucket, reuseFromRunId, localAgent, agentCapacity, dataDir, input, json, spawn, noObserverLink, allowHumanInfluenced, value: positionals[0]! }
-      : { command, localAgent, agentCapacity, dataDir, json, spawn, noObserverLink, allowHumanInfluenced, value: positionals[0]! };
+      ? { command, bucket, reuseFromRunId, localAgent, agentCapacity, dataDir, input, json, spawn, noObserverLink, cloudMirror, allowHumanInfluenced, value: positionals[0]! }
+      : { command, localAgent, agentCapacity, dataDir, json, spawn, noObserverLink, cloudMirror, allowHumanInfluenced, value: positionals[0]! };
 }
 
 /**
@@ -1029,6 +1093,7 @@ function emitRunReport(
   json: boolean,
   io: CliIo,
   observerUrl?: string,
+  mirror?: CloudMirrorReceipt,
 ): void {
   const { report } = execution;
   emitDiagnostics(report.diagnostics, io);
@@ -1036,7 +1101,17 @@ function emitRunReport(
     // Fold `observerUrl` into the JSON report as a sibling of `runId`, so
     // downstream tooling that consumes `--json` gets the same signal a
     // human reader gets from the plain-text `Observer:` line.
-    const payload = observerUrl === undefined ? report : { ...report, observerUrl };
+    //
+    // `cloudRunId` and `dashboardUrl` ride beside it for the same reason, and
+    // they close a sharper gap: the report's own `runId` is the *journal's*,
+    // and every hosted read verb (`flows status --cloud`, `flows logs`,
+    // `flows runs`) takes Cloud's. Without these a script that mirrored a run
+    // had no handle on it at all, and a human had to read one out of a URL.
+    const payload = {
+      ...report,
+      ...(observerUrl === undefined ? {} : { observerUrl }),
+      ...(mirror === undefined ? {} : mirror),
+    };
     io.stdout(JSON.stringify(payload));
     return;
   }

package/src/cloud-deploy.ts

@@ -23,18 +23,22 @@ import { assertNoUseDependencies, collectExtensionSubmissions } from './flow-ext
  * inside a fresh branch of the deployment's repository.
  */
 
-export const FLOW_TRIGGER_PROVIDERS = ['github', 'linear', 'jira', 'shortcut', 'slack'] as const;
+export const FLOW_TRIGGER_PROVIDERS = ['github', 'gitlab', 'linear', 'jira', 'shortcut', 'slack'] as const;
 export type FlowTriggerProvider = (typeof FLOW_TRIGGER_PROVIDERS)[number];
 
 /** Settings Cloud's launcher prefilter reads per provider (`flow-trigger-sources.ts`). */
 const PROVIDER_SETTINGS: Record<FlowTriggerProvider, readonly string[]> = {
   // `events`: `issues` (default) or `pull_request` — which GitHub records
-  // wake the listener (AgentWorkforce/cloud#3772).
-  github: ['repository', 'labels', 'contains', 'events'],
+  // wake the listener (AgentWorkforce/cloud#3772). `reviews`, `checks` and
+  // `comments` opt a pull_request source out of its extra subscriptions.
+  github: ['repository', 'labels', 'contains', 'events', 'reviews', 'checks', 'comments'],
+  gitlab: ['project', 'labels', 'contains', 'events'],
   slack: ['channel', 'contains'],
-  linear: ['team', 'contains'],
-  jira: ['project', 'contains'],
-  shortcut: ['workspace', 'contains'],
+  // `events`: `issues` (default), `assigned` (issues assigned to the agent's
+  // connected app user), or `all` — which Linear records wake the listener.
+  linear: ['team', 'project', 'labels', 'contains', 'events'],
+  jira: ['project', 'labels', 'contains'],
+  shortcut: ['workspace', 'team', 'labels', 'contains'],
 };
 const MAX_SOURCE_BYTES = 256_000;
 const MAX_SETTING_LENGTH = 500;
@@ -135,12 +139,26 @@ export function parseTriggerSource(value: string): FlowTriggerSource {
       if (key === 'events') {
         // Cloud's enum is lowercase; send it that way whatever the shell typed.
         const events = setting.toLowerCase();
-        if (!['issues', 'pull_request'].includes(events)) {
-          throw new CloudFlowError('invalid_input', `github events must be "issues" or "pull_request", got "${setting}".`);
+        const valid =
+          provider === 'gitlab' ? ['issues', 'merge_request']
+            : provider === 'linear' ? ['issues', 'assigned', 'all']
+              : ['issues', 'pull_request'];
+        if (!valid.includes(events)) {
+          throw new CloudFlowError('invalid_input',
+            `${provider} events must be ${valid.map(v => `"${v}"`).join(' or ')}, got "${setting}".`);
         }
         settings[key] = events;
         continue;
       }
+      if (provider === 'github' && (key === 'reviews' || key === 'checks' || key === 'comments')) {
+        // Subscription opt-outs are boolean; Cloud refuses any other value.
+        const toggle = setting.toLowerCase();
+        if (!['true', 'false'].includes(toggle)) {
+          throw new CloudFlowError('invalid_input', `github ${key} must be "true" or "false", got "${setting}".`);
+        }
+        settings[key] = toggle;
+        continue;
+      }
       settings[key] = setting;
     }
   }

package/src/cloud-mirror-ledger.ts

@@ -0,0 +1,161 @@
+// Which Cloud run mirrored which journal, remembered between invocations.
+//
+// A journal outlives the process that started it: `flows run` parks on an
+// `f.human`, exits, and some time later a different `flows resume` picks the
+// same journal up. Cloud models that second attempt as its own run row — its
+// own hosted resume mints a fresh run id too — so a parked-then-resumed flow
+// is two rows however it is driven. What made that read as two *unrelated*
+// pieces of work was that the resuming process had no idea the first attempt
+// existed: nothing on disk connected the journal to the Cloud run mirroring
+// it, so the second registration could not name its predecessor.
+//
+// This is that connection, and deliberately nothing more.
+//
+// ## What is stored, and what is not
+//
+// The run id and the deployment that issued it. **Never the credential.** The
+// run token can write this run's steps and read the workspace's runs; leaving
+// one in a dotfile under a developer's home directory, for every run they
+// have ever started, would be a worse trade than the feature is worth. A
+// resume mints its own credential the same way the first attempt did — the
+// registration request it already makes.
+//
+// So an entry is not a capability. Everything in it is already in the URL the
+// first attempt printed to the terminal.
+//
+// ## Failure is not an error
+//
+// Every operation here is best-effort and silent. A missing entry means the
+// resumed run registers without naming a predecessor, which is exactly what
+// happened before this file existed; an unreadable or corrupt one means the
+// same. A mirror is an observer, and bookkeeping for an observer must never
+// be able to fail a run.
+
+import { mkdir, readFile, readdir, stat, unlink, writeFile } from 'node:fs/promises';
+import { join, resolve } from 'node:path';
+
+/** Where the ledger lives, beside the journals it describes. */
+export const LEDGER_DIRECTORY = 'cloud-runs';
+/**
+ * How long an entry is worth keeping.
+ *
+ * A resume of a two-week-old parked run is a real thing; a resume of a run
+ * from last quarter is not the case this serves, and a ledger that only grows
+ * is a directory nobody ever looks at filling up forever.
+ */
+export const LEDGER_MAX_AGE_MS = 30 * 24 * 60 * 60 * 1_000;
+/** Entries kept. Past it, the oldest are dropped on the next write. */
+export const LEDGER_MAX_ENTRIES = 500;
+
+/** One journal's mirror, as the ledger records it. */
+export interface LedgerEntry {
+  /** Cloud's run id for the attempt that mirrored this journal. */
+  cloudRunId: string;
+  /** The deployment that issued it; an entry from another one is not this one's. */
+  apiUrl: string;
+}
+
+const JOURNAL_RUN_ID = /^[A-Za-z0-9][A-Za-z0-9_-]{0,127}$/u;
+const CLOUD_RUN_ID = /^[A-Za-z0-9_-]{1,128}$/u;
+
+function entryPath(dataDir: string, journalRunId: string): string {
+  return join(resolve(dataDir), LEDGER_DIRECTORY, `${journalRunId}.json`);
+}
+
+/**
+ * Record that `journalRunId` is mirrored by `entry.cloudRunId`.
+ *
+ * Written with mode 0600 for the same reason the journals are private: it
+ * names runs in someone's workspace, and a shared machine should not publish
+ * that. It is not a secret — there is nothing here to steal — but it is
+ * nobody else's business either.
+ */
+export async function recordMirroredRun(
+  dataDir: string,
+  journalRunId: string,
+  entry: LedgerEntry,
+): Promise<void> {
+  if (!JOURNAL_RUN_ID.test(journalRunId) || !CLOUD_RUN_ID.test(entry.cloudRunId)) return;
+  const directory = join(resolve(dataDir), LEDGER_DIRECTORY);
+  try {
+    await mkdir(directory, { recursive: true, mode: 0o700 });
+    await writeFile(
+      entryPath(dataDir, journalRunId),
+      JSON.stringify({ cloudRunId: entry.cloudRunId, apiUrl: entry.apiUrl }),
+      { mode: 0o600 },
+    );
+  } catch {
+    // A resume that cannot name its predecessor is the behaviour this file
+    // improves on, not a failure of the run.
+    return;
+  }
+  await prune(directory);
+}
+
+/**
+ * The Cloud run mirroring this journal, if one is recorded *for this
+ * deployment*.
+ *
+ * The deployment check is not bookkeeping. A developer who ran a flow against
+ * staging and resumes it against production must not have the resumed run
+ * claim to continue a run id that means something else there — or, worse,
+ * nothing at all, which Cloud would refuse and which would read as a bug in
+ * the resume rather than in the pairing.
+ */
+export async function readMirroredRun(
+  dataDir: string,
+  journalRunId: string,
+  apiUrl: string,
+): Promise<string | undefined> {
+  if (!JOURNAL_RUN_ID.test(journalRunId)) return undefined;
+  let parsed: unknown;
+  try {
+    parsed = JSON.parse(await readFile(entryPath(dataDir, journalRunId), 'utf8'));
+  } catch {
+    return undefined;
+  }
+  if (parsed === null || typeof parsed !== 'object' || Array.isArray(parsed)) return undefined;
+  const entry = parsed as Record<string, unknown>;
+  if (typeof entry['cloudRunId'] !== 'string' || !CLOUD_RUN_ID.test(entry['cloudRunId'])) return undefined;
+  if (entry['apiUrl'] !== apiUrl) return undefined;
+  return entry['cloudRunId'];
+}
+
+/** Drop entries past their age, then past the count. Never throws. */
+async function prune(directory: string): Promise<void> {
+  try {
+    const names = (await readdir(directory)).filter(name => name.endsWith('.json'));
+    if (names.length <= LEDGER_MAX_ENTRIES) {
+      // Still age out: a data dir that never reaches the count cap would
+      // otherwise keep its first entry forever.
+      await dropOlderThan(directory, names, Date.now() - LEDGER_MAX_AGE_MS);
+      return;
+    }
+    const ages = await Promise.all(names.map(async name => {
+      try {
+        return { name, at: (await stat(join(directory, name))).mtimeMs };
+      } catch {
+        return { name, at: 0 };
+      }
+    }));
+    ages.sort((left, right) => right.at - left.at);
+    await Promise.all(ages.slice(LEDGER_MAX_ENTRIES).map(entry =>
+      unlink(join(directory, entry.name)).catch(() => undefined)));
+    await dropOlderThan(directory, ages.slice(0, LEDGER_MAX_ENTRIES).map(entry => entry.name),
+      Date.now() - LEDGER_MAX_AGE_MS);
+  } catch {
+    return;
+  }
+}
+
+async function dropOlderThan(directory: string, names: string[], floor: number): Promise<void> {
+  await Promise.all(names.map(async name => {
+    try {
+      if ((await stat(join(directory, name))).mtimeMs < floor) {
+        await unlink(join(directory, name));
+      }
+    } catch {
+      return;
+    }
+  }));
+}