wehub-resource-sync
91 lines
3.4 KiB
JSON
91 lines
3.4 KiB
JSON
{
|
|
"lesson": "35-initialization-scripts",
|
|
"title": "Initialization Scripts for Agents",
|
|
"questions": [
|
|
{
|
|
"stage": "pre",
|
|
"question": "What does an init script eliminate?",
|
|
"options": [
|
|
"Latency from inference",
|
|
"The per-session setup tax: probing runtime, listing the repo, retrying the same checks each new session",
|
|
"Provider rate limits",
|
|
"Authn tokens"
|
|
],
|
|
"correct": 1,
|
|
"explanation": "The script pays the tax once and writes the answers into init_report.json the agent reads."
|
|
},
|
|
{
|
|
"stage": "pre",
|
|
"question": "What is the init script's failure-mode contract?",
|
|
"options": [
|
|
"Fail soft and continue",
|
|
"Fail loud, fail fast, fail in one place; refuse to start when the workbench is broken",
|
|
"Always succeed",
|
|
"Retry forever"
|
|
],
|
|
"correct": 1,
|
|
"explanation": "The whole point is to refuse to start when the workbench is broken; silent fallback defeats the purpose."
|
|
},
|
|
{
|
|
"stage": "check",
|
|
"question": "Which is NOT one of the probes the lesson lists?",
|
|
"options": [
|
|
"Runtime versions",
|
|
"Dependency availability",
|
|
"Test command resolvability",
|
|
"Token-by-token sampling temperature"
|
|
],
|
|
"correct": 3,
|
|
"explanation": "Probes include runtime versions, deps, test command, paths, env vars, state freshness, last-known-good commit."
|
|
},
|
|
{
|
|
"stage": "check",
|
|
"question": "Why does the lesson say init must be idempotent?",
|
|
"options": [
|
|
"It satisfies SOC 2",
|
|
"Running it twice should be a no-op except for a fresh timestamp, so it can be wired into CI, hooks, or a pre-task slash command",
|
|
"Idempotence saves money",
|
|
"It is required by JSON Schema"
|
|
],
|
|
"correct": 1,
|
|
"explanation": "Idempotence makes init safe to call from many entry points (hooks, CI, slash command)."
|
|
},
|
|
{
|
|
"stage": "check",
|
|
"question": "What is last-known-good commit anchoring?",
|
|
"options": [
|
|
"The most recent commit by the team lead",
|
|
"Probe the current commit against an LKG file; refuse to start if the diff exceeds a budget without human ratification",
|
|
"The earliest commit in the repo",
|
|
"The merge base of HEAD and main"
|
|
],
|
|
"correct": 1,
|
|
"explanation": "Cloudflare's AI Code Review scopes reviewers against the LKG to prevent drift compounding across sessions."
|
|
},
|
|
{
|
|
"stage": "post",
|
|
"question": "What does the lock file with TTL pattern do?",
|
|
"options": [
|
|
"Locks the repo from edits",
|
|
"Writes prereqs.lock after a successful probe pass; subsequent runs trust the lock for 24h and skip expensive probes if the manifest hash matches",
|
|
"Blocks all writes for 24 hours",
|
|
"Disables CI"
|
|
],
|
|
"correct": 1,
|
|
"explanation": "Same shape as Docker layer caches: idempotent probe + content hash = skip."
|
|
},
|
|
{
|
|
"stage": "post",
|
|
"question": "What should NEVER appear in the init hot path?",
|
|
"options": [
|
|
"Local filesystem reads",
|
|
"Network calls, LLM calls, external license checks; probes are deterministic plumbing under three seconds",
|
|
"Reading env vars",
|
|
"Reading the lockfile"
|
|
],
|
|
"correct": 1,
|
|
"explanation": "A probe that calls an LLM is a workflow, not a probe; keep init deterministic."
|
|
}
|
|
]
|
|
}
|