dirpush 0.1.0 → 0.1.2

package/.agents/skills/dirpush/SKILL.md

@@ -61,7 +61,7 @@ Workers read `dirpush capabilities` at the start of a session: email verificatio
 - **"Set up dirpush"** / **"set up this product"** / **"add a product"**: `dirpush init <product-id>`, run the Setup check above if `dirpush capabilities` says it hasn't been done, then help the user fill `workspace/products/<id>/product.yaml` (and the shared `workspace/identity.yaml`, `permissions.yaml` the first time). Validate with `dirpush product show --product <id>`.
 - **"Find N free directories I haven't submitted to and submit"**: `dirpush directories recommend --free --unsubmitted --limit N --product <id>`, show the list, `dirpush submissions enqueue <dir-id…> --product <id>`, then run the loop.
 - **"Continue my launch"**: the whole routine, no other instructions needed (nothing from a previous conversation is either):
-  1. `dirpush actions` — tell the human what's waiting on them.
+  1. `dirpush actions` — tell the human what's waiting on them. Google sign-in, CAPTCHAs and bot checks: tell them to run `dirpush checks` in their terminal (it walks them through each one and hands the jobs back); never solve them yourself.
   2. `dirpush submissions check` — marks pending listings live (skip if run in the last day).
   3. Run the loop until `work next` is empty. Jobs still showing another worker with an expired lease are abandoned: `work next` hands them to you; continue from their last step.
   4. Queue empty → `dirpush directories recommend --free --unsubmitted --limit 10 --product <id>`, show the list, enqueue only what the human approves.

package/README.md

@@ -24,7 +24,8 @@ dirpush init acme                # sets up ~/.dirpush and installs the agent ski
 | `dirpush directories recommend --free --unsubmitted --product <id>` | Directories that fit and haven't been tried |
 | `dirpush submissions list --product <id>` | Every submission and its outcome |
 | `dirpush submissions check` | Re-check pending listings and mark live ones |
-| `dirpush todo list` | What needs you: CAPTCHAs, verification emails, questions |
+| `dirpush actions` | What needs you: CAPTCHAs, verification emails, questions |
+| `dirpush checks` | Your part, guided: sign into Google, then clear CAPTCHAs and bot checks one by one; agents pick each job back up |
 | `dirpush registry updates [--apply]` | Update your registry from the published one on dirpush.com |
 | `dirpush registry audit` | Measure link type, noindex and bot checks on real listing pages |
 | `dirpush submissions add <id or URL>` | Record a listing you made yourself |

package/package.json

@@ -37,7 +37,7 @@
     "url": "https://github.com/baronunread/dirpush.git"
   },
   "homepage": "https://dirpush.com",
-  "version": "0.1.0",
+  "version": "0.1.2",
   "keywords": [
     "directories",
     "startup",

package/scripts/ab

@@ -20,7 +20,7 @@ AB="agent-browser --headed --session ${AB_SESSION:-default} --profile ${AB_PROFI
 # instead of launching a second Chrome on the same profile.
 PORT="${LAUNCH_BROWSER_PORT:-9222}"
 if [ -z "$AB_PROFILE" ] && curl -s -m 1 "http://127.0.0.1:$PORT/json/version" >/dev/null 2>&1; then
-  exec perl -e 'alarm shift; exec @ARGV' "${AB_TIMEOUT:-90}" agent-browser --session "${AB_SESSION:-default}" --cdp "$PORT" "$@"
+  exec perl -e 'alarm shift; exec @ARGV or die "cannot run $ARGV[0]: $!\n"' "${AB_TIMEOUT:-90}" agent-browser --session "${AB_SESSION:-default}" --cdp "$PORT" "$@"
 fi
 for host in mail.google.com gmail.com www.gmail.com inbox.google.com \
   drive.google.com drive.usercontent.google.com docs.google.com sheets.google.com slides.google.com forms.google.com \
@@ -37,4 +37,4 @@ for path in "b/*/ManageAccount*" "ManageAccount*" "security*" "*/personal-info*"
 done
 # Per-call time limit (AB_TIMEOUT seconds, default 90): a hung call (seen on file uploads) must not freeze a worker.
 # Exit 142 = timed out; then run `dirpush ab close` and start over from the last checkpoint.
-exec perl -e 'alarm shift; exec @ARGV' "${AB_TIMEOUT:-90}" $AB "$CHROME" "$@"
+exec perl -e 'alarm shift; exec @ARGV or die "cannot run $ARGV[0]: $!\n"' "${AB_TIMEOUT:-90}" $AB "$CHROME" "$@"

package/scripts/google-login

@@ -7,7 +7,11 @@ PKG="$(cd "$(dirname "$0")/.." && pwd)"
 if [ -n "$LAUNCH_HOME" ]; then H="$LAUNCH_HOME"; elif [ -d "$PKG/.git" ]; then H="$PKG"; else H="$HOME/.dirpush"; fi
 mkdir -p "$H/data" && cd "$H"
 agent-browser close >/dev/null 2>&1
-# The agents' Chrome (`launch browser start`) holds the same profile; close it so this window owns it.
+# The agents' Chrome (`dirpush browser start`) holds the same profile; close it so this window owns it.
 bun "$PKG/src/cli.ts" browser stop >/dev/null 2>&1
-open -na "Google Chrome" --args --user-data-dir="$PWD/data/browser-profile" --use-mock-keychain --password-store=basic \
-  --no-first-run "https://accounts.google.com/ServiceLogin?continue=https%3A%2F%2Fwww.google.com%2F"
+# Wait for the profile lock to go, then run Chrome in the foreground: this returns when the human quits it (⌘Q),
+# so `dirpush checks` can carry on. A separate --user-data-dir is its own Chrome process; the human's Chrome is untouched.
+for i in 1 2 3 4 5 6 7 8 9 10; do [ -L data/browser-profile/SingletonLock ] || break; sleep 0.5; done
+"/Applications/Google Chrome.app/Contents/MacOS/Google Chrome" --user-data-dir="$PWD/data/browser-profile" \
+  --use-mock-keychain --password-store=basic --no-first-run --no-default-browser-check \
+  "https://accounts.google.com/ServiceLogin?continue=https%3A%2F%2Fwww.google.com%2F" >/dev/null 2>&1

package/src/checks.ts

@@ -0,0 +1,130 @@
+/**
+ * `dirpush checks`: the human's part of a launch, in the terminal. Google sign-in first, in plain Chrome with no
+ * automation attached (Google refuses sign-in in a window software is driving); then each CAPTCHA or bot check,
+ * opened in the agents' Chrome. Agents never solve these: this hands each job back once the human has.
+ */
+import { createInterface } from "node:readline/promises";
+import { join } from "node:path";
+import { and, eq, gt, inArray } from "drizzle-orm";
+import { HOME, PKG, type Db } from "./db";
+import { jobs } from "./db/schema";
+import * as J from "./jobs";
+import { loadDirectory } from "./registry";
+
+const color = process.stdout.isTTY && !process.env.NO_COLOR;
+const paint = (code: string) => (s: string) => (color ? `\x1b[${code}m${s}\x1b[0m` : s);
+const bold = paint("1"), dim = paint("2"), green = paint("32"), yellow = paint("33"), cyan = paint("36");
+const env = { ...process.env, LAUNCH_HOME: HOME };
+const script = (name: string, ...args: string[]) =>
+  Bun.spawnSync([join(PKG, "scripts", name), ...args], { env, stdin: "ignore", stdout: "ignore", stderr: "ignore" }).exitCode;
+
+/** One keypress, no Enter needed. Enter comes back as "\r"; Ctrl-C quits. */
+async function key(prompt: string, keys: string): Promise<string> {
+  process.stdout.write(prompt);
+  process.stdin.setRawMode(true);
+  process.stdin.resume();
+  try {
+    for (;;) {
+      const k = await new Promise<string>((r) => process.stdin.once("data", (b: Buffer) => r(b.toString())));
+      if (k === "\x03") { process.stdout.write("\n"); process.exit(130); }
+      const ch = k === "\r" || k === "\n" ? "\r" : k.toLowerCase();
+      if (keys.includes(ch)) { process.stdout.write(ch === "\r" ? "\n" : `${ch}\n`); return ch; }
+    }
+  } finally {
+    process.stdin.setRawMode(false);
+    process.stdin.pause();
+  }
+}
+
+async function ask(prompt: string) {
+  const rl = createInterface({ input: process.stdin, output: process.stdout });
+  try { return (await rl.question(prompt)).trim(); } finally { rl.close(); }
+}
+
+const WHAT: Record<string, string> = {
+  captcha: "Tick the CAPTCHA, then do whatever the note above asks.",
+  bot_protection: "Wait for the “checking your browser” page to pass, or tick its box if it shows one.",
+};
+
+export async function checks(db: Db, opts: { product?: string; types: string[] }) {
+  if (!process.stdin.isTTY) throw new Error("checks is interactive: run `dirpush checks` yourself in a terminal");
+  const blocked = (types: string[]) => db.select().from(jobs)
+    .where(and(eq(jobs.kind, "submission"), eq(jobs.status, "blocked"), inArray(jobs.blockType, types))).all()
+    .filter((j) => !opts.product || j.productId === opts.product);
+  const google = blocked(["google_login"]);
+  const queue = blocked(opts.types);
+  const handedBack: string[] = [], byYou: string[] = [], skipped: string[] = [];
+  let signedIn = false;
+
+  const summary = () => {
+    console.log(`\n${bold("Done for now.")}`);
+    if (handedBack.length) console.log(`${green("✓")} Back to the agents: ${handedBack.join(", ")}`);
+    if (byYou.length) console.log(`${green("✓")} Submitted by you: ${byYou.join(", ")}`);
+    if (skipped.length) console.log(`${dim("·")} Skipped, still waiting: ${skipped.join(", ")}`);
+    if (handedBack.length) console.log(`\nNext: ask your agent to ${bold("“continue my launch”")}.`);
+  };
+
+  const googleSignIn = async () => {
+    const busy = db.select().from(jobs).where(and(eq(jobs.status, "running"), gt(jobs.leaseExpiresAt, Date.now()))).all();
+    if (busy.length) {
+      console.log(yellow(`An agent is using the browser right now (${busy.map((j) => j.subject).join(", ")}). Signing in closes that window.`));
+      if ((await key(`${cyan("[enter]")} close it and sign in   ${cyan("[n]")} not now `, "\rn")) === "n") return false;
+    }
+    console.log(`A normal Chrome window opens on Google's sign-in page (the agents' own profile, nothing automated).`);
+    console.log(`Sign in, then ${bold("quit that window with ⌘Q")} to come back here.`);
+    script("google-login"); // returns when that Chrome quits
+    const ok = (await key(`Signed in?  ${cyan("[y]")} yes   ${cyan("[n]")} no `, "yn")) === "y";
+    if (ok) signedIn = true;
+    else console.log(dim("No problem: run `dirpush checks` again whenever you want to retry."));
+    return ok;
+  };
+
+  console.log(`${bold("dirpush checks")}  ${dim(`${google.length} need Google sign-in · ${queue.length} CAPTCHAs or bot checks`)}`);
+  if (!google.length && !queue.length) return console.log("Nothing is waiting on you.");
+  console.log(dim("Agents never solve these; you do, and each job goes back to them."));
+
+  if (google.length) {
+    console.log(`\n${bold("1. Sign into Google")}  ${dim(google.map((j) => j.subject).join(", "))}`);
+    console.log("These directories use “Sign in with Google”. Sign in once and the agents can use it from then on.");
+    const k = await key(`${cyan("[enter]")} sign in now   ${cyan("[n]")} later   ${cyan("[q]")} quit `, "\rnq");
+    if (k === "q") return summary();
+    if (k === "\r" && (await googleSignIn())) {
+      for (const j of google) { J.unblock(db, j.id, "human signed into Google in the agents' Chrome profile"); handedBack.push(j.subject); }
+    } else skipped.push(...google.map((j) => j.subject));
+  }
+
+  for (const [i, job] of queue.entries()) {
+    const dir = await loadDirectory(job.subject).then((d) => d.directory).catch(() => null);
+    const url = job.blockMessage?.match(/https?:\/\/[^\s)'"”]+/)?.[0]?.replace(/[.,;:]$/, "") ?? dir?.submission_url ?? dir?.website;
+    const open = () => {
+      if (!url) return console.log(yellow("No page saved for this one; open the directory yourself."));
+      if (script("ab", "open", url) === 0) script("show-browser");
+      else console.log(yellow(`Couldn't open the agents' Chrome. Open it yourself: ${url}`));
+    };
+    console.log(`\n${bold(`${google.length ? i + 2 : i + 1}. ${dir?.name ?? job.subject}`)}  ${dim(`${i + 1} of ${queue.length}`)}`);
+    if (job.blockMessage) console.log(dim(job.blockMessage));
+    if (url) console.log(`${dim("Page:")} ${url}`);
+    console.log(WHAT[job.blockType ?? ""] ?? "Do what the note above asks.");
+    console.log(dim("Asked to sign in with Google? Press g: Google refuses sign-in in the agents' window."));
+    console.log(dim("Check never passes there? Submit it from your own browser instead, then press s."));
+    open();
+    for (;;) {
+      const k = await key(`${cyan("enter")} done  ${cyan("s")} I submitted it  ${cyan("o")} reopen  ${cyan("g")} Google sign-in  ${cyan("n")} skip  ${cyan("q")} quit › `, "\rsognq");
+      if (k === "o") { open(); continue; }
+      if (k === "g") { if (!signedIn) await googleSignIn(); open(); continue; }
+      if (k === "q") return summary();
+      if (k === "n") skipped.push(job.subject);
+      else if (k === "\r") {
+        J.unblock(db, job.id, "human cleared the check in the agents' Chrome; continue in the same browser session");
+        handedBack.push(job.subject);
+      } else {
+        const link = await ask(`Listing URL, if there is one ${dim("(enter to skip)")}: `);
+        J.recordManual(db, job.id, "pending", link || undefined);
+        byYou.push(job.subject);
+      }
+      break;
+    }
+  }
+  summary();
+}
+

package/src/cli.ts

@@ -19,6 +19,7 @@ import { auditDirectory, auditDirectoryBrowser } from "./audit";
 import { browserStatus, newPassword, startBrowser, stopBrowser, vaultLogin } from "./browser";
 import { accountsFor, backfillAccounts, listAccounts } from "./accounts";
 import { detect, loadCapabilities, saveCapabilities } from "./capabilities";
+import { checks } from "./checks";
 import { ratingDomain, ratingHistory, refreshRatings } from "./ratings";
 import { fetchRegistryFile, registrySource, registryUpdates } from "./registry-updates";
 import { loadIdentity, loadPermissions, loadProduct, permission, productIds, resolveProductId, PRODUCTS, utm, WORKSPACE } from "./workspace";
@@ -523,6 +524,9 @@ const commands: Record<string, (() => Promise<unknown> | unknown) | undefined> =
       .orderBy(desc(productApprovals.id)).get() ?? null;
   },
   "assets capture-complete": () => consumeProductApproval(db, Number(arg(0, "approval-id"))),
+  /** The human's part, interactive: Google sign-in, then CAPTCHAs and bot checks one by one (src/checks.ts). */
+  "checks": async () => { await checks(db, { product: flags.product, types: (flags.type ?? "captcha,bot_protection").split(",").map((t) => t.trim()) }); process.exit(0); },
+
   /** Everything waiting on the human, grouped. --product narrows it. */
   "actions": () => {
     const mine = <T extends { productId: string }>(xs: T[]) => xs.filter((x) => !flags.product || !x.productId || x.productId === flags.product);
@@ -661,6 +665,7 @@ const HELP: [string, [string, string][]][] = [
     ["products list", "all products in this workspace"],
     ["permission <group.action>", "automatic | confirm | never for an action, e.g. accounts.oauth_google"],
     ["actions [--product id]", "everything waiting on the human, grouped"],
+    ["checks [--type captcha,bot_protection] [--product id]", "for the human: sign into Google, then clear CAPTCHAs and bot checks one by one; each job goes back to the agents"],
   ]],
   ["Work loop", [
     ["work next [--claim]", "next submission job (unknown ones first); --claim leases it to you"],