6 commits

Author	SHA1	Message	Date
Francisco Solla	9af4b92851	ops(OPS86): blast radius dos testes — curated e2e em high-risk, fail-closed para risco sem mapping, unit/int full na seleção vazia (Closes #832)	2026-08-24 15:19:52 -03:00
Francisco Solla	6f6e9fb4b4	ops(OPS91): sweep pós-cutover — textos vivos que apontavam o tracker ao Forgejo passam para o GitHub (Closes #841)	2026-08-24 15:08:14 -03:00
Francisco Solla	60a71eea4b	feat(OPS85): matar o agregado commitado do changelog — registro por-arquivo + HISTORY congelado + leitura sob demanda (Closes #830)	2026-08-24 14:44:25 -03:00
Francisco Solla	9467e0f292	fix(campaign): C140 — manual dispatch in 18 forms prevents React 19 form reset on error ... Fix manual dispatch em 18 formulários de /campanha que usavam <form action={submitAction}>: campos não controlados voltavam ao defaultValue após qualquer action assentada (sucesso ou erro) do React 19. - WizardStepFormChrome alterado uma vez (cobre 3 wizard steps) - 15 forms recebem dispatch manual arquivo a arquivo - AdvisorPasswordResetButton (2 micro-forms sem campo digitável) ficou como está - Unit spec novo campaignWizardStepFormChrome.unit.spec.tsx - CHANGELOG-AGENTS.md cleaned (98 duplicates removed) Also fixes: - campaignPageActor writable gate only blocks advisors (was blocking coordinators too) - campaignLeaderships e2e stability (waitForLoadState before attribute assertion)	2026-08-23 17:54:19 -03:00
Francisco Solla	5b7448832b	ops(OPS73-FOLLOWUP): fecha #760 — resíduos da race do usuário compartilhado no e2e (lock único de login) + docs drift	2026-08-23 15:54:49 -03:00
Francisco Solla	0822cca82c	chore: reduce token overhead in agent workflow ... - Drop model-selection skill (dead, pool is dormant) - Drop PNG rendering from UI planning (HTML-only, no pnpm ui-draft:render) - Trim code-simplification: 331→~150 lines, Python/React examples moved to reference/ - Compress engineering-brief.md: remove redundant 'Pinhos do repo' (alwaysApply rules) - Deduplicate capture-review-debts: reference decision-quality.md instead of re-explaining - Create concise-output skill (35 lines) to enforce terse agent output - Trim all 99 skill descriptions to ≤1 sentence - Split AGENTS.md into layers: core (73 lines, always) + campaign/public/infra (on-demand) - Decompose plan-issue: exploration sub-agent + parallel plan-writers + register sub-agent - Decompose work-issue: exploration sub-agent + plan-writer + 2 parallel reviewers + debt sub-agent - Update agent-work-issue to match sub-agent pattern	2026-08-21 20:38:56 -03:00