docs(cheatsheets): add long-running/overnight jobs cheat sheet
This commit is contained in:
saravanakumardb1
parent
932951dbaf
commit
5df580d999
@ -12,15 +12,17 @@
|
|||||||
|
|
||||||
## What's here
|
## What's here
|
||||||
|
|
||||||
Quick, dense reference cards for the three terminal AI agents we use to delegate
|
Quick, dense reference cards for the terminal AI agents we use to delegate coding work,
|
||||||
coding work. Each sheet is **task-oriented** — commands, modes, session management,
|
plus an operational guide for running them **non-stop overnight**. Each sheet is
|
||||||
config, and the ByteLyst-specific guardrails — not a marketing overview.
|
**task-oriented** — commands, modes, session management, config, and the ByteLyst-specific
|
||||||
|
guardrails — not a marketing overview.
|
||||||
|
|
||||||
| CLI | Cheat sheet | Best for |
|
| CLI | Cheat sheet | Best for |
|
||||||
| ------------------ | -------------------------------------------- | ------------------------------------------------------------------------------- |
|
| ------------------ | -------------------------------------------- | ------------------------------------------------------------------------------- |
|
||||||
| 🤖 **Devin** | [`devin-cli.md`](./devin-cli.md) | Long-running autonomous sessions; delegate a scoped roadmap and walk away |
|
| 🤖 **Devin** | [`devin-cli.md`](./devin-cli.md) | Long-running autonomous sessions; delegate a scoped roadmap and walk away |
|
||||||
| 🟣 **Claude Code** | [`claude-code-cli.md`](./claude-code-cli.md) | Interactive pair-programming in the terminal; deep multi-file edits with review |
|
| 🟣 **Claude Code** | [`claude-code-cli.md`](./claude-code-cli.md) | Interactive pair-programming in the terminal; deep multi-file edits with review |
|
||||||
| 🟢 **Codex CLI** | [`codex-cli.md`](./codex-cli.md) | Fast local edits + scriptable `exec` runs in CI / one-shot automation |
|
| 🟢 **Codex CLI** | [`codex-cli.md`](./codex-cli.md) | Fast local edits + scriptable `exec` runs in CI / one-shot automation |
|
||||||
|
| 🌙 **Long-running jobs** | [`long-running-jobs.md`](./long-running-jobs.md) | Running ANY of the above non-stop, unattended overnight (sleep/disconnect survival + best practices) |
|
||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
@ -95,4 +97,4 @@ and the per-repo `AGENTS.md`. Put them in the agent's opening prompt every time:
|
|||||||
3. Add it to the table above.
|
3. Add it to the table above.
|
||||||
4. Commit: `docs(cheatsheets): update <cli> CLI cheat sheet`.
|
4. Commit: `docs(cheatsheets): update <cli> CLI cheat sheet`.
|
||||||
|
|
||||||
_Last updated: 2026-05-28_
|
_Last updated: 2026-05-30_
|
||||||
|
|||||||
171
AI.dev/CHEATSHEETS/long-running-jobs.md
Normal file
171
AI.dev/CHEATSHEETS/long-running-jobs.md
Normal file
@ -0,0 +1,171 @@
|
|||||||
|
# 🌙 Overnight / Long-Running Agent Runs — Cheat Sheet
|
||||||
|
|
||||||
|
> **What it is:** how to run a multi-hour, unattended AI coding job (Devin / Claude Code /
|
||||||
|
> Codex / Copilot CLI) **non-stop** without it dying when the machine sleeps or the
|
||||||
|
> terminal closes — plus the ByteLyst best practices that make an unattended run *safe*.
|
||||||
|
> **Best for:** delegating a scoped roadmap (e.g. a 10-hour Phase build) and walking away
|
||||||
|
> overnight.
|
||||||
|
> **Companion docs:** the per-CLI sheets ([`devin-cli.md`](./devin-cli.md),
|
||||||
|
> [`claude-code-cli.md`](./claude-code-cli.md), [`codex-cli.md`](./codex-cli.md)) and the
|
||||||
|
> canonical [`../SKILLS/agent-behavior-guidelines.md`](../SKILLS/agent-behavior-guidelines.md).
|
||||||
|
|
||||||
|
> 🧠 **The whole problem in one line:** an unattended run has two enemies — the **machine
|
||||||
|
> sleeping** and the **terminal/session dying**. `caffeinate` kills the first, `tmux` the
|
||||||
|
> second, and a **checkpoint file** saves you from everything else (reboot, crash, power loss).
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## The two failure modes (and what fixes each)
|
||||||
|
|
||||||
|
| Failure mode | What happens | Fix |
|
||||||
|
| ------------ | ------------ | --- |
|
||||||
|
| **Machine sleeps** (idle timeout / lid closed) | CPU + network suspend → job freezes mid-step, connections drop | **`caffeinate`** (macOS) / `systemd-inhibit` (Linux) — keep it plugged in, lid open |
|
||||||
|
| **Terminal/session dies** (window closed, app crash/update, SSH drop, logout) | Job receives `SIGHUP` and is killed | **`tmux`** / `screen` — the job is owned by the tmux server, not the window |
|
||||||
|
| **Reboot / crash / power loss** | Everything dies, including tmux | **Checkpoint + resume** — the job writes progress to a file; re-running resumes it |
|
||||||
|
|
||||||
|
`caffeinate` and `tmux` are **complementary**, not alternatives — use both for a real overnight run.
|
||||||
|
|
||||||
|
## `caffeinate` (macOS) — stop the Mac from sleeping
|
||||||
|
|
||||||
|
```bash
|
||||||
|
caffeinate -dimsu <your-command> # stays awake only while <command> runs
|
||||||
|
```
|
||||||
|
|
||||||
|
| Flag | Prevents |
|
||||||
|
| ---- | -------- |
|
||||||
|
| `-d` | **display** sleep |
|
||||||
|
| `-i` | **idle** sleep |
|
||||||
|
| `-m` | **disk** sleep |
|
||||||
|
| `-s` | system sleep (on AC power) |
|
||||||
|
| `-u` | declares **user active** |
|
||||||
|
|
||||||
|
> ⚠️ **Lid caveat:** `caffeinate` keeps the Mac awake, but **closing the lid still sleeps
|
||||||
|
> most Macs** unless on AC power with an external display (clamshell) or the right pmset.
|
||||||
|
> For overnight: **keep it plugged in and the lid open.**
|
||||||
|
|
||||||
|
## `tmux` — survive a closed terminal / disconnect
|
||||||
|
|
||||||
|
```bash
|
||||||
|
tmux new -s phase3 # start a named, detachable session
|
||||||
|
# ... launch your job inside it ...
|
||||||
|
# Ctrl-b then d # DETACH — job keeps running with no terminal attached
|
||||||
|
tmux attach -t phase3 # reattach later (after reconnect, or a new window)
|
||||||
|
tmux ls # list running sessions
|
||||||
|
```
|
||||||
|
|
||||||
|
- **Local Mac:** still useful — the job survives **closing the terminal app, an app
|
||||||
|
crash/auto-update, or logout** (a plain terminal job dies on all of these). It does
|
||||||
|
**nothing** for sleep — that's `caffeinate`'s job.
|
||||||
|
- **Over SSH:** essential — the job survives the SSH connection dropping.
|
||||||
|
|
||||||
|
**Linux equivalents:** `systemd-inhibit --what=idle:sleep <cmd>` (sleep), `screen` or
|
||||||
|
`tmux` (session), or `nohup <cmd> &` + `disown` (cheapest detach, no reattach).
|
||||||
|
|
||||||
|
## Putting it together
|
||||||
|
|
||||||
|
```bash
|
||||||
|
tmux new -s phase3
|
||||||
|
# inside the session:
|
||||||
|
caffeinate -dimsu <agent-cli> <all-allowed flag> "<the overnight prompt>" 2>&1 | tee ~/phase3.log
|
||||||
|
# Ctrl-b d to detach and walk away; tmux attach -t phase3 in the morning
|
||||||
|
```
|
||||||
|
|
||||||
|
`| tee ~/phase3.log` captures the full run to disk so you have the log even if the
|
||||||
|
scrollback is gone.
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Best practices for an unattended agent run
|
||||||
|
|
||||||
|
1. **Green baseline first.** Run the verify gate (`pnpm build && pnpm test`, browsers
|
||||||
|
installed) **before** launching, so the agent starts from a known-clean state — never
|
||||||
|
debug a pre-existing red suite at 2am.
|
||||||
|
2. **Self-contained roadmap, slice-by-slice.** Point the agent at a doc that encodes
|
||||||
|
scope, per-slice verify commands, and a done-definition (see [`../PROMPTS/`](../PROMPTS/)).
|
||||||
|
One slice = one commit + push.
|
||||||
|
3. **Checkpoint + resume.** The job must write progress to a file (e.g.
|
||||||
|
`docs/<phase>-progress.md`: slice, status, commit SHA, gate result). If it dies for any
|
||||||
|
reason, **re-running the same prompt resumes** from the first not-DONE slice. This is
|
||||||
|
your safety net for the failures `caffeinate`/`tmux` can't catch.
|
||||||
|
4. **Failure protocol, not thrash.** Tell it: max N honest attempts per slice, then commit
|
||||||
|
`wip(...) BLOCKED:` + mark FAILED + move to the next **independent** slice. Order slices
|
||||||
|
so the independent ones come first.
|
||||||
|
5. **Never merge unattended.** Push to a feature branch and open **one PR** — a human
|
||||||
|
reviews + merges in the morning. The agent must **never touch `main`**.
|
||||||
|
6. **Tests are sacred.** Never weaken/skip a test to go green — fix the code (see the
|
||||||
|
canonical guidelines). State this explicitly in the prompt.
|
||||||
|
7. **Scope + push-auth ready.** Cache git credentials / `gh auth login` first so the
|
||||||
|
overnight `push` never blocks on a prompt. Confirm push rights to the target remote.
|
||||||
|
8. **All-allowed flag.** Launch with the CLI's auto-approve flag so it never pauses for
|
||||||
|
permission (`--permission-mode dangerous` for Devin, `--dangerously-skip-permissions`
|
||||||
|
for Claude Code, `--dangerously-bypass-approvals-and-sandbox` for Codex — confirm with
|
||||||
|
`<cli> --help`).
|
||||||
|
|
||||||
|
## ByteLyst-specific gotchas (the ones that silently fail overnight)
|
||||||
|
|
||||||
|
- **Corp proxy.** `pnpm install` and Playwright browser downloads will **TLS-fail** behind
|
||||||
|
the intercepting proxy unless `NODE_EXTRA_CA_CERTS` (proxy CA) is set. **Prefer running
|
||||||
|
off-corp** for overnight jobs — simplest reliable path. (A proxy-blocked `pnpm install`
|
||||||
|
is the classic cause of an overnight job that "did nothing".)
|
||||||
|
- **Playwright e2e.** Slices with browser tests need `npx playwright install --with-deps`
|
||||||
|
**before** the run, or the e2e gate fails.
|
||||||
|
- **Workspace, not registry.** `@bytelyst/*` link via `workspace:*` from sibling
|
||||||
|
`packages/*` — run from the monorepo so they resolve locally; no registry needed for the
|
||||||
|
build itself.
|
||||||
|
- **Side-by-side repos.** If the prompt file lives in a sibling repo (e.g. the gigafactory
|
||||||
|
job lives in `learning_ai_devops_tools` but runs in `learning_ai_common_plat`), clone
|
||||||
|
**both under the same parent** so the `../` relative path resolves.
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Worked example — the gigafactory Phase 3 overnight run
|
||||||
|
|
||||||
|
```bash
|
||||||
|
# 1) bootstrap a clean baseline (once)
|
||||||
|
cd ~/code/mygh/learning_ai_common_plat && git pull && corepack enable \
|
||||||
|
&& pnpm install && pnpm build && pnpm test \
|
||||||
|
&& (cd dashboards/tracker-web && npx playwright install --with-deps)
|
||||||
|
cd ~/code/mygh/learning_ai_devops_tools && git pull # prompt + roadmap repo
|
||||||
|
|
||||||
|
# 2) launch non-stop
|
||||||
|
cd ~/code/mygh/learning_ai_common_plat
|
||||||
|
tmux new -s phase3
|
||||||
|
caffeinate -dimsu <agent-cli> <all-allowed flag> \
|
||||||
|
"Read ~/code/mygh/learning_ai_devops_tools/agent-queue/docs/jobs/phase3-overnight.md and execute it exactly: branch feat/gigafactory-phase3 off origin/main, implement Phase 3 slice-by-slice, verify each slice green before the next, checkpoint to docs/gigafactory-phase3-progress.md, commit+push per slice, open ONE PR and NEVER merge, never weaken tests (use the 3-attempt failure protocol), end with the consolidated report." \
|
||||||
|
2>&1 | tee ~/phase3.log
|
||||||
|
# Ctrl-b d to detach
|
||||||
|
```
|
||||||
|
|
||||||
|
In the morning: `tmux attach -t phase3`, read the consolidated report, then review +
|
||||||
|
merge the PR slice-by-slice.
|
||||||
|
|
||||||
|
## Troubleshooting
|
||||||
|
|
||||||
|
| Symptom | Likely cause | Fix |
|
||||||
|
| ------- | ------------ | --- |
|
||||||
|
| Job froze partway, no error | Mac slept (idle or **lid closed**) | Use `caffeinate -dimsu`; plug in; lid open |
|
||||||
|
| Job vanished when I closed Terminal | No tmux — `SIGHUP` killed it | Run inside `tmux`; reattach with `tmux attach` |
|
||||||
|
| "Did nothing" / 0 commits overnight | `pnpm install` TLS-failed on corp proxy | Run **off-corp**, or set `NODE_EXTRA_CA_CERTS` |
|
||||||
|
| e2e slice failed immediately | Playwright browsers not installed | `npx playwright install --with-deps` before launch |
|
||||||
|
| Push at end blocked / hung | git/gh auth not cached | `gh auth login` / cache credentials first |
|
||||||
|
| Re-ran prompt, it redid finished work | No checkpoint file read | Ensure the job reads `*-progress.md` and resumes |
|
||||||
|
|
||||||
|
## Quick-reference card
|
||||||
|
|
||||||
|
```text
|
||||||
|
caffeinate -dimsu <cmd> # macOS: stay awake while <cmd> runs (lid open + on AC!)
|
||||||
|
systemd-inhibit --what=idle:sleep <cmd> # Linux equivalent
|
||||||
|
tmux new -s <name> # detachable session (Ctrl-b d = detach)
|
||||||
|
tmux attach -t <name> # reattach (tmux ls = list)
|
||||||
|
... | tee ~/run.log # capture full output to disk
|
||||||
|
# launch: tmux -> caffeinate -dimsu <cli> <auto-approve flag> "<prompt>" | tee log
|
||||||
|
# safety net: checkpoint file + re-run prompt to resume; push to branch, never merge
|
||||||
|
```
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
**Related:** [`devin-cli.md`](./devin-cli.md) · [`claude-code-cli.md`](./claude-code-cli.md) ·
|
||||||
|
[`codex-cli.md`](./codex-cli.md) · [`../PROMPTS/`](../PROMPTS/) ·
|
||||||
|
[`../SKILLS/agent-behavior-guidelines.md`](../SKILLS/agent-behavior-guidelines.md)
|
||||||
|
|
||||||
|
_Last updated: 2026-05-30 · confirm CLI auto-approve flags against your installed version (`<cli> --help`)._
|
||||||
Loading…
Reference in New Issue
Block a user