Cursor's Create-Agent API defaults omitted `fast` to true, so pool
workers requesting composer-2.5 were billed as composer-2.5-fast.
Co-authored-by: Francisco Solla <fsolla@users.noreply.github.com>
agent-pr-workflow was correct but not alwaysApply, so Cloud agents
followed ManagePullRequest's draft default. Make the rule always-on,
document the ManagePullRequest path, and narrow the engineering-audit
"no auto-merge" exception to the audit sign-off PR only.
Skill no longer reads as start-only: always emit pool status + eligible
queue with the next maxSlots highlighted; ask before start when off;
when already on, stay in session monitoring without auto-restart.
cursor-grok-4.5-{low,medium,high}[-fast] and kimi-k3-low were falling
back to composer-2.5 against live /v1/models (grok-4.5 + effort,
kimi-k3 + reasoning). Teach resolvePoolModel the mapping, document
when to pick each Grok effort in model-selection, and align plan/work
skills.
Remove stage/promote/Neon smoke. PR CI targets main; ci.yml full-suite
verifier deploys via vercel CLI and requeues when HEAD moves. Pool uses
POOL_GITHUB_TOKEN and POOL_BASE_REF=main. Docs/skills/rules retargeted.
- Precheck solitário fail-closed (pnpm agent:pool -- status; gh read-only no Cloud não pausa o pool)
- Sign-off em modo autônomo = PR dos artefatos (Ready, base stage); P0/P1 e guardrails de misses executam na sessão
- Harvest kind:agent-miss: investigação via gh issue view; fechamento via Closes #N + flip determinístico do issue-done-on-stage-merge.yml
- Âncora de delta: foco no churn desde a data do último Pass em vez de --since=3months
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Francisco Solla <fsolla@users.noreply.github.com>
Document native Postgres on Cloud (no db:start) and that gate:fast/push need no DB. Print rename_chat title in agent:claim brief; reinforce rename_chat + pnpm push (not raw --no-verify) in work-issue skill.
* feat(ops): auto-promote stage→main e merge em stage sem exigir head
Substitui o promote manual por workflow disparado no ci-stage green,
relaxa strict na proteção de stage (script configure:branch-protection)
e documenta o novo paradigma em AGENT-OPS e work-issue.
* style: format AGENT-OPS and configure-branch-protection for ci-pr
* feat(ops): pnpm push com ensure-repo-deps determinístico
Bootstrap install + Husky antes de todo push (pnpm push e pre-push).
Documenta fluxo canônico em work-issue, agent-pr-workflow e AGENT-OPS.
* fix(ops): pnpm push roda gate no script, sem depender do Husky
Cloud environment.json chama prepare explicitamente após install.
* test(int): isolate advisor portfolio search from shared cairu slug
Parallel int specs were stomping municipality.advisors on the fixed
cairu row; allocate per-test municipalities instead.
* 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>
- ci-pr.yml: split the serial checks job into parallel lint/format/
typecheck/knip/cycles + unit/int (vitest --changed vs PR base via
scripts/test-affected.mjs, full fallback on high-risk paths) + e2e
(manifest path->spec via scripts/e2e-affected.mjs, blocking) + build;
migration-lock gains checkout + pull-requests:read (fixes the failures
that blocked PR #50)
- ci.yml (main): full safety net — seed:minimal + int full + build + e2e
- package.json: gate:fast / gate:push; .husky/pre-push runs gate:push
- docs: "Dono do PR, dono do CI" policy in AGENT-OPS + work-issue +
engineering-standards; changelog entry; plans for OPS3-OPS7
Fold duplicated campanha access, loaders, list/filter/form shells, and scripts into shared modules; reorganize utilities by domain; stabilize e2e; and document prevention-first audit workflow so the same smells cannot creep back in.
Embeds approved literature→persona→interview research in docs/research/, adds inteligencia-campanha master plan with child specs, updates roadmap/PRODUCT/AGENTS, and extends roadmap skills with data-presentation guidance.
Document the in-context editing default for /campanha staff surfaces in PRODUCT.md, a Cursor rule, the project notebook, and the roadmap plan template.
Extract dashboard cards into focused components (queues, upcoming plans, leadership status, recently visited, choropleth legend), compile the roadmap for outcome-oriented tracking, document the customer job and improve-app journey, and tighten roadmap skills with decision-quality gates.
Extract CampaignAuthPageShell and shared copy tokens across login, forgot-password, and reset-password flows; add adaptive inputMode, credential error a11y, and roadmap skill updates from the FD2 critique pass.
Wire husky with a typecheck script, await the async avatar update guard, harden Onda 0 consent unit tests, and extend the roadmap implementation skill with Impeccable UI gates.
Update AGENTS.md, the local-database and payload-migrations skills, and the
README to reflect the shipped Post/Tag collections, the electoral `hidden`
visibility control and fail-closed `isPostVisible` rule, the mixed-ISR `posts`
cache model with self-revalidating afterChange hooks, the `db:seed:posts` seed,
and the required post-seed/direct-DB revalidation via POST /api/revalidate.
Local dev and the test suite previously defaulted to the live production
Neon database, and running the tests mutated prod data. Add guardrails plus
a proper local Postgres + migrations workflow so production can't be hit by
mistake:
- docker-compose: local Postgres 17 (matches prod) + auto-created teqo_test
- dev guard refuses a non-local DATABASE_URL; tests refuse non-_test databases
- .env.test isolates the suite; vitest/playwright load it and fail closed
- Payload migrations set up (push disabled); build runs `payload migrate`,
so deploys apply pending migrations to prod automatically
- baseline `initial` migration + idempotent consent.text varchar->jsonb fix
- `pnpm db:pull` copies prod content locally, excluding supporter PII
- docs (README, AGENTS.md) + agent skills for the local-db/migration workflow