pi-auto-resume

Continue a Pi session by itself after a rate limit. No more typing "lanjutkan" because the run stopped at a 429.

Pi already retries transient errors three times with a short backoff. When that budget is spent, the run stops and waits for you — even though the error usually says exactly when the limit lifts:

503: {"message":"[claude/claude-opus-5-5] [429]: {... "rate_limit_error" ...} (reset after 8s)"}

This package reads that hint, waits until the reset, and sends a marked continuation:

⚙ auto-resume (rate limit reset 14:32, waited 9s):
The previous attempt stopped because of a rate limit.
Continue from the last step, and do not repeat tool calls that already succeeded.

English is the default. Switch to Indonesian with /auto-resume language id.

Install

pi install npm:@fahrizkyputra/pi-auto-resume

When it acts

Situation	What happens
Rate limit (429, rate_limit_error, "too many requests", "overloaded") with a reset hint, after Pi's own retries gave up	Waits for the reset (+1.5s slack), then sends the continuation
Plan window (5-hour or weekly): Usage limit reached for 5 hour. Your limit will reset at 2026-08-12 17:11:22	Waits until that real end, however long, then continues. A wait over 6 hours gets one extra notice with the day and time
Failure with no time at all: a rate limit that says nothing about when, or a network/stream failure (Stream ended without finish_reason, terminated, Connection error, fetch failed, upstream connection lost)	Retries on a growing pause, 30s, 1m, 2m, 5m, then stops and reports
Money and credential problems (Insufficient Balance, insufficient_quota, billing, subscription, a monthly limit, MODEL_NOT_IN_PLAN, an expired token)	Reports only; waiting does not fix those
The resumed run immediately fails with the same error	Stops and reports: waiting did not help
The next reset hint is much further away (8s → 20m → 3h)	Stops and reports: the limit is getting worse
You type anything, press Esc, or switch session	The scheduled resume is cancelled
Pi is closed while waiting	The schedule is gone (nothing persists)

Which time wins

9router (and some providers) put two times in one message:

Usage limit reached for 5 hour. Your limit will reset at 2026-08-12 17:11:22   ← the window really ends here
(reset after 2s)                                                                ← the gateway's own pause between retries

The (reset after 2s) is only how long the gateway waits before its own next try. Following it would resume 12 hours too early and fail again. So the order is: a stated end of a plan window first, then response headers (retry-after-ms, retry-after, x-ratelimit-reset-after, x-ratelimit-reset), then the other text hints (reset after 8s, 1m 4s, 1h 2m 3s, try again in 2 minutes, resets at 18:00). The gateway's pause is still used for ordinary rate limits, where it is the right wait.

A time written without a zone (2026-08-12 17:11:22) is read as Beijing time (UTC+8): that is how Z.ai (GLM) writes it, and in 32 of 32 such errors in real sessions it was the only reading that made sense for a 5-hour window (read as UTC, none did). If a provider of yours writes another zone, set zonelessOffsetHours. A time written to the second counts as the end of that second, so the resume never lands just before the limit lifts. Times with an explicit zone (Z, +07:00, UTC) are always taken as written.

Waits of hours or days are safe: the timer checks the wall clock every 15 seconds, so a laptop that slept resumes on time and there is no 24.8-day limit of a plain timer.

While waiting, the status bar shows ⏳ limit: resuming 14:32 (2m 10s), and you get a notification when the resume is scheduled and when it is sent.

Commands

Command	What it does
/auto-resume	Status: pending resume, resumes sent in this session, config path
/auto-resume cancel	Cancel the pending resume
/auto-resume off / on	Disable or enable (persisted to the config file)
/auto-resume language en / id	Language of the continuation, notifications, and status bar (persisted)
/auto-resume config	Show the effective configuration

Configuration

~/.pi/agent/auto-resume.json (or $PI_CODING_AGENT_DIR/auto-resume.json). Every field is optional:

{
  "enabled": true,
  "notify": true,
  "language": "en",
  "maxWaitMs": 0,
  "maxResumes": 0,
  "slackMs": 1500,
  "backoffMs": [30000, 60000, 120000, 300000],
  "zonelessOffsetHours": 8
}

language is "en" (default) or "id". It sets every text the package produces: the continuation, the ⚙ auto-resume header, notifications, and the status bar countdown.

Language	Built-in continuation
en	The previous attempt stopped because of a rate limit. Continue from the last step, and do not repeat tool calls that already succeeded.
id	Percobaan sebelumnya terhenti karena rate limit. Lanjutkan dari langkah terakhir, dan jangan ulangi tool call yang sudah berhasil.

Add "continuationPrompt": "..." to replace the built-in text with your own. A custom prompt is used as-is in either language; the header still follows language.

maxWaitMs and maxResumes default to 0, meaning no limit: the package waits as long as the hint says, including until a weekly limit resets. Set maxWaitMs (for example 21600000 for 6 hours) if you would rather be told than wait that long. The loop guards above are what stop a pointless cycle.

backoffMs is the list of pauses for failures that carry no time, one per retry; when it runs out, the package reports. It restarts after any run that ends cleanly. zonelessOffsetHours is the UTC offset used for times written without a zone.

Notes

• The package only acts after Pi reports agent_settled with an errored last message, so it never races Pi's built-in retry.
• Every resume is a normal turn and costs a model call.
• The continuation is an ordinary user message with the ⚙ auto-resume marker, so the transcript shows it was not you.

Development

npm install
npm test          # node:test, no Pi required
npm run typecheck
npm run test:e2e  # real Pi over RPC against a local server that answers 429, then succeeds
PI_AUTO_RESUME_LANGUAGE=id npm run test:e2e   # same check in Indonesian

License

MIT