{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreifrky26h3tduojvtlmidl34pcpd2gg3x3b664yn7ytqvy7yyekqve",
    "uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3ml4foum2o4u2"
  },
  "path": "/t/codex-v0-128-0-shipped-a-virtual-pet-and-a-goal-system-here-is-why-both-actually-matter/175762#post_1",
  "publishedAt": "2026-05-05T12:46:43.000Z",
  "site": "https://discuss.huggingface.co",
  "tags": [
    "EvoLink"
  ],
  "textContent": "#\n\n**TL;DR:** OpenAI’s Codex CLI v0.128.0 adds `/goal` (persistent cross-session objectives) and `/pet` (animated agent status indicator). `/goal` is the bigger deal – it shifts AI coding from stateless request-response to stateful goal-driven agents. `/pet` solves agent observability by showing you what Codex is doing without tailing logs.\n\n* * *\n\n## The Setup\n\nEvery AI coding assistant has the same problem: it forgets what it was doing the moment you close the terminal.\n\nYou ask it to refactor a module. It gets halfway through. You close the terminal, grab lunch, come back – blank slate. You re-explain. It starts over.\n\nThis is not a context window issue. It is an **intent persistence** gap. The model has no mechanism to track your objective across session boundaries.\n\n## The Fix: /goal\n\nCodex v0.128.0 introduces `/goal` – a persistent objective system with four operations:\n\nCommand | Function\n---|---\n`/goal create` | Define a persistent objective\n`/goal pause` | Suspend with progress preserved\n`/goal resume` | Restore execution context and continue\n`/goal clear` | Mark complete or abandon\n\nThe critical detail: `/goal resume` does not just remember the goal text. It restores the execution context through app-server APIs and model tools, so Codex can continue making progress from where it stopped.\n\nGreg Brockman described this as a “built-in Ralph loop” – a persistent agent loop that keeps working toward a defined objective until it is achieved.\n\n### Why This Matters\n\nThis is the first mainstream AI coding tool to ship **goal-driven agent behavior** as a core feature. The interaction model shifts from:\n\n**Old:** You ask → it answers → session ends → you re-explain next time\n\n**New:** You define a goal → it works across sessions → it resumes automatically → it finishes\n\nFor multi-day refactors, coverage campaigns, and migration checklists, this is transformative.\n\n## The Surprise: /pet\n\nThe second feature is `/pet` – type it and an animated creature appears in your Codex interface.\n\nIt is not decorative. The pet reflects Codex’s background state:\n\n  * Active task = animated pet\n\n  * Tests passed = celebration\n\n  * Error/stuck = reaction\n\n  * Idle = sleeping\n\n\n\n\n9to5Mac called them “little Dynamic Island-ish messengers.” Sam Altman said: “This isn’t the most important thing we’ve done, but it’s more useful than it looks.”\n\n`/hatch` generates custom pets based on your project context. One developer got a pixel-art dog named “Meme” tagged “The Goodest Boy.”\n\n### The Real Value\n\n**Agent observability.** When your AI assistant runs a 30-minute task, knowing whether it is progressing or stuck – without checking logs – is genuinely useful. `/pet` is a status indicator wearing a costume.\n\n## The Market Signal\n\nWhen Cursor, Claude Code, and Codex generate similar quality code, differentiation moves to:\n\nDimension | Old | New\n---|---|---\nTask scope | Single-turn | Multi-session goals\nVisibility | Terminal output | Ambient indicators\nSession model | Stateless | Stateful\nUX design | Functional | Personality + delight\n\nCore functionality parity → experience becomes the differentiator. Same pattern as every tool category before it.\n\n## v0.128.0 Full Changelog\n\nFeature | Detail\n---|---\n`/goal` | Persistent cross-session objectives\n`/pet` + `/hatch` | Agent status companion + custom generation\n`codex update` | Self-update from terminal\n`/side` | Parallel conversation panel\nTUI keymaps | Custom keyboard shortcuts\nPlugin marketplace | One-click community plugins\nSession import | Import from external agents\n\n## What to Do\n\n  * **Already using Codex?** Try `/goal` for multi-session tasks. Use `/pet` for ambient monitoring.\n\n  * **Evaluating tools?** Add task persistence and agent observability to your criteria.\n\n  * **Multi-model setup?** The fragmentation tax (separate APIs, auth, billing) is real. EvoLink unifies 30+ models behind one gateway with smart routing.\n\n\n\n\n* * *",
  "title": "Codex v0.128.0 Shipped a Virtual Pet and a Goal System. Here Is Why Both Actually Matter"
}