#ActionCache loop

3 messages · Page 1 of 1 (latest)

lilac roseBOT
#

Hi @dire hazel. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:

#

It sounds like you installed the @convex-dev/action-cache component and now something (likely its cron job or internal actions) is still running even after you removed your own usage.

From the docs, ActionCache installs a component into your Convex app via convex.config.ts:

// convex/convex.config.ts
import { defineApp } from "convex/server";
import cache from "@convex-dev/action-cache/convex.config.js";

const app = defineApp();
app.use(cache);

export default app;

and then you create instances of ActionCache that run internal actions and a daily cleanup cron. [Action Cache]

If you’ve:

  1. Deleted all your own ActionCache code and calls, and
  2. Removed the component from convex.config.ts (deleted the import and app.use(cache)),

then there shouldn’t be any remaining ActionCache cron or actions in that deployment once it’s re-deployed. [Action Cache]

So, to “fully” clean it out:

  1. Confirm convex.config.ts is clean

    • No @convex-dev/action-cache import.
    • No app.use(cache) (or similar) call.

  2. Ensure code is actually deployed

    • Stop any running npx convex dev and start it again so it re-syncs code; or
    • If this is a prod/staging deployment, push again (npx convex deploy) so the new config (without the component) is live.

  3. If it’s still looping after that
    The knowledge sources don’t describe a persistent “stuck ActionCache loop” once the component is removed, so there’s no documented extra cleanup step. I’d suspect either:

    • A still-running older dev server process using the old config, or
    • Another component / cron / action (not ActionCache) causing the behavior.
#

If after verifying all of the above and redeploying you still see ActionCache‑like activity, there isn’t enough detail in the docs or Discord threads here to give a precise next step. In that case, I’d recommend:

  • Grabbing logs around which function is being invoked repeatedly (look for components.actionCache or cron invocations).
  • Sharing those logs and a minimal repro in Discord so staff can inspect it (the docs don’t cover this failure mode).

Note: you can ask me a follow up question by @ mentioning me again :speech_balloon: