teqo-backup/scripts/agent-claim.mjs
Francisco Solla 680ff56754 feat(agent-pool): orquestrador de pool de workers Cursor Cloud (fases A–D) (#65)
* feat(agent-pool): fundacao read-only do orquestrador (fase A)

- docs/plans/agent-pool-orchestrator.md: plano completo (14 secoes)
- buildClaimQueue extraido de agent-claim para agent-github (comportamento identico, pinado)
- agent-pool-eligibility: isAutonomousClaimable puro e fail-closed + buildPoolQueue
- agent-pool-state: parsePoolConfig, marcadores pool-worker, classifyPoolClaim, spawn plan, auto-stop
- agent-pool-github: leitura de repo variables (degrada nao-estrito), claims/PRs/migration-lock
- pnpm agent:pool -- status|tick --dry-run (inspecao local; live chega na fase B)
- 34 specs unit novos (992/992 verde); lint/tsc/knip/cycles/format verdes

Co-authored-by: Francisco Solla <fsolla@users.noreply.github.com>

* feat(agent-pool): spawn remoto de workers via Cursor API (fase B)

- agent-pool-cursor: client fino da Cloud Agents API v1 (fetch injetavel; CursorApiError com status/body)
- agent-pool-models: resolvePoolModel contra /v1/models (id/alias, sufixo -fast -> param, fallback composer-2.5 com warn)
- agent-pool-prompt: contrato do worker (claim pre-feito, pula passo 1; PR base stage + Closes #N; promote proibido)
- claim coordenado no tick: lock otimista + flip + marcador; agentId idempotente bc-<uuid>; 409 recupera; rollback em falha de spawn
- agent:pool workflow --action start|stop|pause|resume|tick|status (variables POOL_*); doctor; wrappers gh workflow run
- .github/workflows/agent-pool.yml (dispatch-only; schedule/triggers na fase C)
- 19 specs novos (1011/1011); lint/tsc/knip/cycles/format verdes

Co-authored-by: Francisco Solla <fsolla@users.noreply.github.com>

* feat(agent-pool): ciclo de vida do supervisor (fase C)

- derivePoolClaims com status real dos runs (getCursorRun), heal de spawn via agentId deterministico, cancel de duplicatas
- reconcilePoolClaims: falha terminal -> comentario + blocked + archive; merge concluido -> slot livre + archive
- auto-stop real: fila drenada + zero ativos -> POOL_ENABLED=false (exclusoes migration-busy nao desligam)
- job summary markdown (GITHUB_STEP_SUMMARY) — superficie remota de status
- workflow: schedule */10min + pull_request closed em stage (ativam na default branch apos promote)
- 2 specs novos (1013/1013); lint/tsc/knip/cycles/format verdes

Co-authored-by: Francisco Solla <fsolla@users.noreply.github.com>

* docs(agent-pool): runbook operacional e adendo do spike (fase D)

- skill agent-pool: runbook humano (pre-requisitos, start/stop/pause remoto, ciclo de vida, triage, smoke de aceite)
- AGENT-OPS: linha na tabela de comandos + secao Agent pool (canal, secrets, ativacao pos-promote)
- CHANGELOG-AGENTS: entrada curta da entrega
- engineering-audit: pause/resume do pool no protocolo do modo solitario
- plano secao 14.1: evidencias do spike 2026-07-30 (environment repo-file confirmado, id bc-<uuid>, degradacao 403, pendencias do primeiro run com CURSOR_API_KEY)

Co-authored-by: Francisco Solla <fsolla@users.noreply.github.com>

* fix(test): teardown flake no homeSearchUi.unit.spec (dono do CI)

O scheduler do react (prefetch do next/link) podia disparar apos o teardown
do jsdom e derrubar o job unit com 'window is not defined' (run 30587862940).
afterEach(cleanup) — padrao dos 14 specs irmaos.

Co-authored-by: Francisco Solla <fsolla@users.noreply.github.com>

---------

Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Francisco Solla <fsolla@users.noreply.github.com>
2026-07-30 20:08:34 -03:00

113 lines
3.7 KiB
JavaScript

/**
* `pnpm agent:claim` — claim the next trackable issue for this agent run.
*
* Queue: open issues labeled `ready`, filtered to UNBLOCKED (every frontmatter
* `depends` id is closed or labeled `done`/`in-prod`), ordered by `prio:P0..P3`
* then oldest first. `--dry-run` prints the queue without claiming.
*
* Lock otimista: re-reads the issue right before flipping labels, refuses if
* someone else already took it (`in-progress` present / `ready` gone), then
* swaps ready→in-progress and leaves a claim comment with the run timestamp.
*
* Output: the brief on stdout (issue, id, priority, plan/spec body) — the
* agent reads it and starts; it does NOT create the branch (Cursor worktrees
* own that) and it never merges anywhere. PRs go `--base stage`.
*/
import {
buildClaimQueue,
dieAgent,
gh,
ghJson,
issuesById,
labelNames,
parseArgs,
parseFrontmatter,
setLabels,
} from './lib/agent-github.mjs'
const die = dieAgent('claim')
const { flags } = parseArgs(process.argv.slice(2), new Set(['issue']))
const openReady = ghJson([
'issue',
'list',
'--state',
'open',
'--label',
'ready',
'--limit',
'200',
'--json',
'number,title,body,labels,createdAt',
])
// Queue builder lives in agent-github.mjs (shared with the agent pool —
// identical ordering/filtering, pinned by agentPoolEligibility.unit.spec.ts).
const queue = buildClaimQueue(openReady, issuesById())
if (flags['dry-run'] || flags['dryrun']) {
console.log(`[agent:claim] ${queue.length} unblocked ready issue(s):`)
for (const entry of queue) {
const model = entry.meta.model ? ` model:${entry.meta.model}` : ''
console.log(` #${entry.issue.number} [${entry.priority}]${model} ${entry.issue.title}`)
}
process.exit(0)
}
const pick = flags.issue
? queue.find((entry) => entry.issue.number === Number(flags.issue))
: queue[0]
if (!pick) {
die(
flags.issue
? `Issue #${flags.issue} is not claimable (missing, not ready, or blocked by deps).`
: 'Nothing to claim — no unblocked issues labeled `ready`. Run with --dry-run to inspect.',
)
}
// Optimistic lock: re-read right before flipping.
const fresh = ghJson(['issue', 'view', String(pick.issue.number), '--json', 'number,labels,state'])
const freshLabels = labelNames(fresh)
if (
fresh.state !== 'OPEN' ||
!freshLabels.includes('ready') ||
freshLabels.includes('in-progress')
) {
die(`Issue #${pick.issue.number} was just claimed or closed by someone else. Re-run claim.`)
}
setLabels(pick.issue.number, { add: ['in-progress'], remove: ['ready'] })
gh([
'issue',
'comment',
String(pick.issue.number),
'--body',
`Claimed by agent run at ${new Date().toISOString()}. Lock otimista: outro claim deve falhar e re-rodar \`pnpm agent:claim\`.`,
])
const { rest } = parseFrontmatter(pick.issue.body)
console.log(`\n[agent:claim] Claimed #${pick.issue.number} — ${pick.issue.title}`)
console.log(` id: ${pick.meta.id ?? '(none)'} priority: ${pick.priority}`)
if (pick.meta.model) {
console.log(
` model: ${pick.meta.model} (propriedade da Issue — verificar, não recalcular; ver skill model-selection)`,
)
} else {
console.log(
' model: ausente — aplicar model-selection uma vez e registrar na Issue (gh issue edit)',
)
}
if (pick.satisfiedWithoutIssue.length > 0) {
console.log(
` deps sem issue (roadmap entregue, satisfeitas): ${pick.satisfiedWithoutIssue.join(', ')}`,
)
}
console.log(` url: https://github.com/fsolla/teqo/issues/${pick.issue.number}`)
console.log('\n--- spec ---\n')
console.log(rest.trim() || '(empty body — see linked plan)')
console.log(
'\n[agent:claim] Fluxo: implementar → fast gate → gh pr create --base stage (Closes #' +
`${pick.issue.number}) → PARAR. Promote a main é humano (pnpm agent:promote --i-am-human).`,
)