@polymorphism-tech/morph-spec 9.0.0 → 9.1.0

package/framework/standards/ai-agents/durable-workflows-hitl.md

@@ -226,7 +226,7 @@ public sealed class PostgresCheckpointStore(NpgsqlDataSource dataSource) : IChec
 
 `Microsoft.Agents.AI.DurableTask` (prerelease) adds durability backed by the **Azure Durable Task Scheduler**, including cost-efficient multi-day HITL waits with zero compute cost while paused. Even its "bring-your-own-compute / self-hosted" mode still requires a Durable Task Scheduler backend (`Microsoft.DurableTask.*.AzureManaged` packages) — self-hosted means your own worker process, not an Azure-free backend.
 
-This framework deploys to VPS/Coolify by default and does not adopt Azure as a default dependency (see `ai-agents-setup` §3.4 on Azure OpenAI). For that reason, `Microsoft.Agents.AI.DurableTask` is **not adopted as default** here. The `CheckpointManager` + custom `ICheckpointStore` pattern above covers the same durability need without an Azure dependency. Only reach for the Durable Task extension when a specific client already runs on Azure and needs multi-day/serverless HITL waits — record that decision in `decisions.md`.
+This framework deploys to VPS/Coolify by default and does not adopt Azure as a default dependency (see `ai-agents-setup` §3.4 on Azure OpenAI). For that reason, `Microsoft.Agents.AI.DurableTask` is **not adopted as default** here. The `CheckpointManager` + custom `ICheckpointStore` pattern above covers the same durability need without an Azure dependency. Only reach for the Durable Task extension when a specific client already runs on Azure and needs multi-day/serverless HITL waits — record that decision in `plan.md` (`## Decisões`).
 
 ---
 
@@ -248,12 +248,12 @@ This framework deploys to VPS/Coolify by default and does not adopt Azure as a d
 
 ## Checklist (verifiable in review)
 
-- [ ] `ai-agents-workflows`' HITL or long-running criterion is documented in `decisions.md` before this standard is applied.
+- [ ] `ai-agents-workflows`' HITL or long-running criterion is documented in `plan.md` (`## Decisões`) before this standard is applied.
 - [ ] Every HITL wait point uses `RequestPort` + handles `RequestInfoEvent`.
 - [ ] A `CheckpointManager` is wired whenever the workflow can pause across a process restart — `CreateInMemory()` is acceptable only for tests/demos.
 - [ ] If a custom `ICheckpointStore` was implemented, it persists to infrastructure already owned by the project (e.g., Neon Postgres), not a new ad hoc store.
 - [ ] Executors with instance state implement `OnCheckpointingAsync` and `OnCheckpointRestoredAsync`.
-- [ ] `Microsoft.Agents.AI.DurableTask` is present only if the project already runs on Azure and the choice is recorded in `decisions.md` — ciente de que, desde a 1.17, o pacote vive em repositório separado e ficou para trás do framework.
+- [ ] `Microsoft.Agents.AI.DurableTask` is present only if the project already runs on Azure and the choice is recorded in `plan.md` (`## Decisões`) — ciente de que, desde a 1.17, o pacote vive em repositório separado e ficou para trás do framework.
 - [ ] Toda tool com efeito irreversível está embrulhada em `ApprovalRequiredAIFunction` **ou** tem um guard determinístico documentado — e a escolha entre os dois está escrita.
 - [ ] A resposta de aprovação é enviada na **mesma** `AgentSession`, num laço que checa pendências depois de cada run.
 - [ ] Nenhum `Workflow` foi criado apenas para pausar uma tool de um agente único.

package/framework/standards/ai-agents/guardrails.md

@@ -189,7 +189,7 @@ primeira pergunta a fazer quando um guard "nunca reprova nada".
 ## Checklist (verifiable in review)
 
 - [ ] Toda regra com consequência real existe como condição em código, não apenas no prompt
-- [ ] O choke-point escolhido está nomeado no `decisions.md`, com o que ele pega
+- [ ] O choke-point escolhido está nomeado no `plan.md` (`## Decisões`), com o que ele pega
 - [ ] O middleware de tool devolve **vocabulário fechado** de desfecho
 - [ ] Argumento obrigatório ausente é barrado **sem** executar a tool, lendo o schema da própria função
 - [ ] Nenhum identificador com efeito vem do modelo — todos vêm da closure do turno

package/framework/standards/ai-agents/multi-agent-patterns.md

@@ -178,13 +178,13 @@ Tenho múltiplos agents — qual padrão usar?
 | Handoff sem `turnLimit` nem condição de término | Dois agentes devolvem a conversa um ao outro indefinidamente | `.WithAutonomousMode(turnLimit:)` ou `.WithTerminationCondition(...)` |
 | `Id` de agente gerado a cada boot num workflow de handoff | O destino do handoff deixa de existir entre reinícios | `Id` estável, vindo de configuração |
 | Group chat com 5+ agentes | O gerente gasta os turnos escolhendo quem fala | ≤ 3 agentes; acima disso, repense a decomposição |
-| Agents com responsabilidades sobrepostas | Nenhum dos dois sabe quando agir; o LLM fica confuso | Fronteiras claras de responsabilidade; documente em `decisions.md`. |
+| Agents com responsabilidades sobrepostas | Nenhum dos dois sabe quando agir; o LLM fica confuso | Fronteiras claras de responsabilidade; documente em `plan.md` (`## Decisões`). |
 
 ---
 
 ## Checklist (verifiable in review)
 
-- [ ] Foi verificado em `decisions.md` que single agent não resolve?
+- [ ] Foi verificado em `plan.md` (`## Decisões`) que single agent não resolve?
 - [ ] O padrão escolhido é o mais simples que atende ao requisito? (Tool < Sequential imperativo < Workflow)
 - [ ] `agent.AsAIFunction()` usado para composição local (não `AIFunctionFactory.Create` desnecessariamente)?
 - [ ] Agents usando alias do Model Registry — nenhum model string hardcoded?

package/framework/standards/ai-agents/observability-patterns.md

@@ -313,7 +313,7 @@ Workflow para diagnosticar um incidente relatado ("o agente X respondeu errado/l
 2. **Suba do trace raiz para os spans filhos.** O span raiz mostra a duração total; os filhos (`Function Calling`, `IChatClient`) mostram onde o tempo/erro realmente está. Não assuma — meça. Um "agente lento" é quase sempre UM tool call específico (chamada de API externa, query sem índice), não o LLM.
 3. **Correlacione com métricas antes de teorizar.** Confira a tabela "What to Monitor" abaixo pelo período do incidente — um pico de `tool call failure rate` ou `token usage` aponta a causa mais rápido que ler traces individuais um a um.
 4. **Reproduza com Debug ligado, nunca em produção.** Se a causa não estiver clara nos atributos estruturados, habilite `Debug` (com dados sensíveis, se necessário) num ambiente de staging com o mesmo input — nunca habilite log de prompt/response completo em produção para investigar.
-5. **Documente a causa raiz em `decisions.md`** se a investigação levar a uma mudança de arquitetura (novo middleware de retry, novo timeout, novo cache) — não só no commit message.
+5. **Documente a causa raiz em `plan.md` (`## Decisões`)** se a investigação levar a uma mudança de arquitetura (novo middleware de retry, novo timeout, novo cache) — não só no commit message.
 
 ### What to Monitor
 

package/framework/standards/ai-agents/production.md

@@ -202,7 +202,7 @@ Na **1.18** (2026-08-18) essa superfície foi renomeada. Nomes atuais, medidos p
 
 **Duas advertências que valem mais que os nomes:**
 
-1. **O pacote é prerelease.** `Microsoft.Agents.AI.Hosting` não tem versão estável (apurado 2026-09-08). Isolamento multi-tenant por esse caminho é adoção de preview — registre em `decisions.md`.
+1. **O pacote é prerelease.** `Microsoft.Agents.AI.Hosting` não tem versão estável (apurado 2026-09-08). Isolamento multi-tenant por esse caminho é adoção de preview — registre em `plan.md` (`## Decisões`).
 2. **A chave vem da credencial, nunca do payload.** Uma chave derivada de algo que o cliente envia é uma chave que o cliente escolhe. `UseClaimsBasedAgentIsolation()` existe exatamente para não deixar essa decisão passar pelo corpo do request.
 
 ### Invocação concorrente de tools é opt-in desde 1.18

package/framework/standards/ai-agents/prompt-sources.md

@@ -5,7 +5,7 @@
 > **Keywords:** prompt sources, prompts in db, agent prompts, prompt versioning, prompt hot-reload, editable instructions, prompt management, prompt por tenant, spec publicado, reconciliação de prompt
 > **Read by Claude in:** implement (quando as instruções de um agente precisam viver fora do código) e troubleshoot (quando a versão que rodou não é a que se esperava)
 
-**Verified against:** Microsoft.Agents.AI 1.20.0 + Microsoft.Extensions.AI 10.9.0 (ai-pin 2026-09-08). **Verificação documental**, sem cláusula `provado por` — o ai-kit não traz loader de prompt, e os dois mecanismos descritos aqui são destilados de três produtos em produção. As **quatro** superfícies de API que este standard cita foram medidas por reflexão, e vivem em **três assemblies diferentes** — o carimbo diz onde remedir, então o nome importa: `IChatClient.AsAIAgent(instructions:, name:)` é `Microsoft.Extensions.AI.ChatClientExtensions`, em **`Microsoft.Agents.AI` 1.20.0** (medida em 2026-09-08); `AIAgent.RunAsync` (as oito sobrecargas) e `AIAgent.CreateSessionAsync` são de `Microsoft.Agents.AI.AIAgent`, na assembly **`Microsoft.Agents.AI.Abstractions` 1.20.0** — **remedidas** em 2026-09-09, porque a leitura de 2026-09-08 estava errada no *quê*, e a de 2026-09-09 estava errada no *onde* (as duas retificações estão no callout abaixo); e `builder.AddAIAgent` (§Keyed singleton) é `Microsoft.Agents.AI.Hosting.HostApplicationBuilderAgentExtensions` — cinco sobrecargas, na assembly **`Microsoft.Agents.AI.Hosting` 1.20.0.0**, que vem do pacote **`Microsoft.Agents.AI.Hosting` `1.20.0-preview.260831.1`**: ele é **prerelease** e está **FORA do `ai-pin.json`** (apurado em `scripts/api-probe/companions.json`, 2026-09-08) — quem adotar esta seção registra a dependência prerelease em `decisions.md`, como manda `ai-agents-production`. **Duas ressalvas de escopo**, porque um carimbo que não as diz promete mais do que mediu: `Microsoft.Agents.AI.Abstractions` e `Microsoft.Extensions.AI.Abstractions` são nomes de **assembly** (elas viajam dentro dos pacotes `Microsoft.Agents.AI` e `Microsoft.Extensions.AI`), não ids de pacote; e `IMemoryCache`/`DbContext`, usados no padrão de cache e na §Keyed singleton, são superfícies de ASP.NET Core e EF Core — **fora do pin, não medidas aqui, verificação documental**. Last-verified: 2026-09-08.
+**Verified against:** Microsoft.Agents.AI 1.20.0 + Microsoft.Extensions.AI 10.9.0 (ai-pin 2026-09-08). **Verificação documental**, sem cláusula `provado por` — o ai-kit não traz loader de prompt, e os dois mecanismos descritos aqui são destilados de três produtos em produção. As **quatro** superfícies de API que este standard cita foram medidas por reflexão, e vivem em **três assemblies diferentes** — o carimbo diz onde remedir, então o nome importa: `IChatClient.AsAIAgent(instructions:, name:)` é `Microsoft.Extensions.AI.ChatClientExtensions`, em **`Microsoft.Agents.AI` 1.20.0** (medida em 2026-09-08); `AIAgent.RunAsync` (as oito sobrecargas) e `AIAgent.CreateSessionAsync` são de `Microsoft.Agents.AI.AIAgent`, na assembly **`Microsoft.Agents.AI.Abstractions` 1.20.0** — **remedidas** em 2026-09-09, porque a leitura de 2026-09-08 estava errada no *quê*, e a de 2026-09-09 estava errada no *onde* (as duas retificações estão no callout abaixo); e `builder.AddAIAgent` (§Keyed singleton) é `Microsoft.Agents.AI.Hosting.HostApplicationBuilderAgentExtensions` — cinco sobrecargas, na assembly **`Microsoft.Agents.AI.Hosting` 1.20.0.0**, que vem do pacote **`Microsoft.Agents.AI.Hosting` `1.20.0-preview.260831.1`**: ele é **prerelease** e está **FORA do `ai-pin.json`** (apurado em `scripts/api-probe/companions.json`, 2026-09-08) — quem adotar esta seção registra a dependência prerelease em `plan.md` (`## Decisões`), como manda `ai-agents-production`. **Duas ressalvas de escopo**, porque um carimbo que não as diz promete mais do que mediu: `Microsoft.Agents.AI.Abstractions` e `Microsoft.Extensions.AI.Abstractions` são nomes de **assembly** (elas viajam dentro dos pacotes `Microsoft.Agents.AI` e `Microsoft.Extensions.AI`), não ids de pacote; e `IMemoryCache`/`DbContext`, usados no padrão de cache e na §Keyed singleton, são superfícies de ASP.NET Core e EF Core — **fora do pin, não medidas aqui, verificação documental**. Last-verified: 2026-09-08.
 
 ---
 
@@ -356,7 +356,7 @@ rastreabilidade (hash em span, prompt cru só em harness) está em `ai-agents-ob
 - [ ] `GetActivePromptAsync` throws `InvalidOperationException` (not returns null) when no active prompt found
 - [ ] Versionamento pattern followed: INSERT + flip, never UPDATE content
 - [ ] At least one seed row per `agent_key` in migrations or seed script
-- [ ] A fonte escolhida (banco versionado × composição por tenant) está nomeada no `decisions.md`,
+- [ ] A fonte escolhida (banco versionado × composição por tenant) está nomeada no `plan.md` (`## Decisões`),
       com a pergunta "o texto varia por cliente?" respondida
 - [ ] No caminho composto: a moldura e o YAML estão versionados no repo, e o blob publicado **não** é
       editado à mão

package/framework/standards/ai-agents/providers/model-registry.md

@@ -185,7 +185,7 @@ Going through `Microsoft.Extensions.AI` (`IChatClient`) or the MAF (`AIAgent`) k
 | **Anthropic Claude** | `anthropic` | Confirm current SDK on NuGet before use | ignora o campo | Adapt provider client to `IChatClient` |
 | **Azure OpenAI** (opt-in, not default) | `azure-openai` | `Azure.AI.OpenAI` + `Azure.Identity` — confirm exact versions on NuGet before use | segue o OpenAI | Add only when a client requires data residency |
 
-> **Restore trap, measured 2026-09-08:** `Microsoft.Extensions.AI.OpenAI` 10.9.0 declares `OpenAI (>= 2.12.0 && < 2.13.0)`. Pairing it with the pinned `OpenAI` 2.13.0 emits **NU1608** on restore. Either pin `OpenAI` to 2.12.x alongside the bridge, or accept the warning knowingly and write the decision in `decisions.md`. Do not discover this in CI.
+> **Restore trap, measured 2026-09-08:** `Microsoft.Extensions.AI.OpenAI` 10.9.0 declares `OpenAI (>= 2.12.0 && < 2.13.0)`. Pairing it with the pinned `OpenAI` 2.13.0 emits **NU1608** on restore. Either pin `OpenAI` to 2.12.x alongside the bridge, or accept the warning knowingly and write the decision in `plan.md` (`## Decisões`). Do not discover this in CI.
 
 **No floating ranges.** Every `PackageReference` above is an exact version. A floating `2.*` on a weekly-cadence SDK is how ProspectPRO bought a `MissingMethodException` on the Responses API **after paying for the call** (`docs/specs/elevacao-9/brutos/scan-prospectpro.md:55`).
 

package/framework/standards/ai-agents/rag-custom-pgvector.md

@@ -179,7 +179,7 @@ Registered on the agent with `tools: [AIFunctionFactory.Create(tool.SearchAsync)
 
 The `tenant_id` filter is **never a tool parameter** (that would allow the LLM to cross tenant boundaries). It is injected via a constructor dependency — e.g., a scoped `ITenantContext` or a `Guid currentTenantId` resolved from the authenticated request. See §Multi-tenant below.
 
-Note on raw Npgsql vs EF Core: the EF Core LINQ form above is the default (`ApplicationDbContext` in the slice, no raw SQL). A raw `NpgsqlDataSource` query is acceptable only with a `decisions.md` justification (e.g. a project with no EF Core model for this table). The legacy `VectorSearchTool.cs.template` still uses raw SQL and `EmbeddingService`; prefer the block above.
+Note on raw Npgsql vs EF Core: the EF Core LINQ form above is the default (`ApplicationDbContext` in the slice, no raw SQL). A raw `NpgsqlDataSource` query is acceptable only with a `plan.md` (`## Decisões`) justification (e.g. a project with no EF Core model for this table). The legacy `VectorSearchTool.cs.template` still uses raw SQL and `EmbeddingService`; prefer the block above.
 
 ---
 
@@ -319,7 +319,7 @@ ALTER TABLE kb_embeddings ENABLE ROW LEVEL SECURITY;
 - [ ] `VectorSearchTool` registered on the agent via `AIFunctionFactory.Create(tool.SearchAsync)`.
 - [ ] No `Microsoft.SemanticKernel` references in the project.
 - [ ] Vector dimensions consistent between embedding model and `vector(N)` column definition.
-- [ ] RLS enabled on `kb_embeddings` (or equivalent app-level guard documented in `decisions.md`).
+- [ ] RLS enabled on `kb_embeddings` (or equivalent app-level guard documented in `plan.md` (`## Decisões`)).
 - [ ] Ingestion follows §*Ingestão delta por lookup-key*: a pure `Plan(...)` produces `Added`/`Updated`/`Removed`/`Unchanged`, and `Unchanged` is never re-embedded.
 - [ ] No `DELETE`-everything-then-reinsert: `Removed` is applied **after** `Added`/`Updated`, in the same transaction — there is no window where the search returns empty.
 - [ ] `Updated` is an **upsert** on a deterministic id, never delete+insert.

package/framework/standards/ai-agents/setup.md

@@ -62,7 +62,7 @@ Está adicionando um agente AI a um projeto .NET?
 <!-- Azure OpenAI (somente se data residency exigir) — confira Azure.AI.OpenAI + Azure.Identity no NuGet -->
 ```
 
-> **Armadilha de restore, medida em 2026-09-08:** `Microsoft.Extensions.AI.OpenAI` 10.9.0 declara a dependência `OpenAI (>= 2.12.0 && < 2.13.0)`. Com o `OpenAI` **2.13.0** do pin, o `dotnet restore` emite **NU1608** (*"Versão detectada do pacote fora da restrição de dependência"*). Duas saídas honestas: fixar `OpenAI` em 2.12.x ao lado da ponte, **ou** aceitar o aviso conscientemente e registrar a decisão em `decisions.md`. Não descubra isso no CI.
+> **Armadilha de restore, medida em 2026-09-08:** `Microsoft.Extensions.AI.OpenAI` 10.9.0 declara a dependência `OpenAI (>= 2.12.0 && < 2.13.0)`. Com o `OpenAI` **2.13.0** do pin, o `dotnet restore` emite **NU1608** (*"Versão detectada do pacote fora da restrição de dependência"*). Duas saídas honestas: fixar `OpenAI` em 2.12.x ao lado da ponte, **ou** aceitar o aviso conscientemente e registrar a decisão em `plan.md` (`## Decisões`). Não descubra isso no CI.
 
 > **De onde vem cada extensão** (medido por reflexão sobre as assemblies do pin, 2026-09-08):
 > | Extensão | Assembly que a publica | Namespace do `using` |
@@ -155,7 +155,7 @@ Fontes, ambas lidas em 2026-09-08:
 
 A Responses API **armazena por padrão**. OpenAI, mesmo guia, verbatim: *"Responses are stored by default. Chat completions are stored by default for new accounts. To disable storage when using either API, set `store: false`."* Respostas retidas ficam 30 dias no provedor.
 
-Projetos desta casa mantêm o histórico **próprio** (ver `ai-agents-agent-session`), então não se quer uma segunda cópia da conversa no provedor. **Regra: `store: false` explícito.** Quem quiser o oposto registra o porquê em `decisions.md`.
+Projetos desta casa mantêm o histórico **próprio** (ver `ai-agents-agent-session`), então não se quer uma segunda cópia da conversa no provedor. **Regra: `store: false` explícito.** Quem quiser o oposto registra o porquê em `plan.md` (`## Decisões`).
 
 O MAF tem um atalho de primeira classe para isso — medido na assembly `Microsoft.Agents.AI.OpenAI` 1.20.0:
 

package/framework/standards/ai-agents/sweet-spot.md

@@ -105,11 +105,11 @@ You may need to step outside the sweet spot when:
 
 ## Checklist (verifiable in review)
 
-- [ ] Was each agent designed as single-agent BEFORE reaching for multi-agent? (Check `decisions.md`.)
+- [ ] Was each agent designed as single-agent BEFORE reaching for multi-agent? (Check `plan.md` (`## Decisões`).)
 - [ ] If a Workflow is used, is fan-in/out or HITL checkpointing genuinely present? Or could `foreach + LINQ` replace it?
 - [ ] Are the 4 features (Chat, Structured Output, Tools, RAG Custom) all present where applicable?
 - [ ] Are hosted agent services avoided?
-- [ ] Nenhum agente carrega mais de ~12 tools sem uma decisão escrita em `decisions.md` sobre a poda
+- [ ] Nenhum agente carrega mais de ~12 tools sem uma decisão escrita em `plan.md` (`## Decisões`) sobre a poda
 
 ---
 

package/framework/standards/ai-agents/tool-adapters.md

@@ -210,8 +210,6 @@ MORPH_GHLBrain, `src/Morph.GHLBrain/Features/Conversation/Operator/`:
 | `set_lead_fields` | `Tools/SetLeadFieldsTool.cs` | `Ops/DossieOps.cs` | `CamposDesfecho` |
 | `route_lead` | `Tools/RouteLeadTool.cs` | `Ops/TriagemOps.cs` | `TriagemDesfecho` |
 
-As decisões estão em `.morph/features/tools-finas/2-plan/decisions.md` (ADR-1 e ADR-2) daquele repositório.
-
 ## Regras
 
 - **ALWAYS** a regra de uma tool vai numa `sealed class XOps(...)` com construtor primário e `AddScoped` explícito

package/framework/standards/ai-agents/vector-data-extensions.md

@@ -86,7 +86,7 @@ Preview packages are subject to breaking API changes before GA (see the rename `
 |-----------|-----|
 | Default production RAG on Neon/Postgres (this framework's default stack), **already implemented and tested** | **`ai-agents-rag-custom-pgvector`** — framework-owned raw SQL, zero external connector, already the checklisted default. **Não se migra o que funciona** (item D4 da elevação-9) |
 | **Projeto novo** onde a escolha do store ainda não foi cravada, e trocá-lo depois deve custar pouco | `Microsoft.Extensions.VectorData.Abstractions` 10.9.0 + `CommunityToolkit.VectorData.PgVector` 1.0.1 — hoje **ambos estáveis**, o que remove o argumento "é preview" que existia em julho/2026 |
-| Project needs genuine portability across >1 vector backend (a client contract requires swapping Postgres for Qdrant or Azure AI Search later) | `Microsoft.Extensions.VectorData` + o conector correspondente — document the choice in `decisions.md` |
+| Project needs genuine portability across >1 vector backend (a client contract requires swapping Postgres for Qdrant or Azure AI Search later) | `Microsoft.Extensions.VectorData` + o conector correspondente — document the choice in `plan.md` (`## Decisões`) |
 | Prototyping, tests, or demos where an in-memory store is enough | `CommunityToolkit.VectorData.InMemory` 1.0.1 |
 | Ingestão em pipeline (reader → chunker → writer) hoje | Só com `Microsoft.Extensions.DataIngestion`, que **continua preview**: registre a aceitação e um lembrete de revisitar no GA |
 
@@ -175,10 +175,10 @@ This maps conceptually onto the existing custom pattern: `IngestionDocumentReade
 
 - [ ] If `Microsoft.SemanticKernel.Connectors.*` appears in a `.csproj`, it is used only for `VectorStoreCollection`/`VectorStore` types — no `Kernel`, `KernelFunction`, or `ChatHistory` usage anywhere in the project.
 - [ ] No plain `Microsoft.SemanticKernel` (core) package reference.
-- [ ] If VectorData was chosen over custom pgvector, the reason is recorded in `decisions.md` per the decision matrix.
+- [ ] If VectorData was chosen over custom pgvector, the reason is recorded in `plan.md` (`## Decisões`) per the decision matrix.
 - [ ] No new `Microsoft.SemanticKernel.Connectors.*` reference — new work uses `CommunityToolkit.VectorData.*`.
-- [ ] If a preview package (`Microsoft.Extensions.DataIngestion`, or any `*-preview` connector) was adopted, `decisions.md` records the preview-acceptance and a revisit-at-GA note.
-- [ ] Every VectorData/ingestion `PackageReference` carries an exact version — these packages are **not** in `framework/ai-pin.json`, so the project's own `decisions.md` (or a comment) states when the version was checked.
+- [ ] If a preview package (`Microsoft.Extensions.DataIngestion`, or any `*-preview` connector) was adopted, `plan.md` (`## Decisões`) records the preview-acceptance and a revisit-at-GA note.
+- [ ] Every VectorData/ingestion `PackageReference` carries an exact version — these packages are **not** in `framework/ai-pin.json`, so the project's own `plan.md` (`## Decisões`) (or a comment) states when the version was checked.
 - [ ] Embedding model/dimensions consistent between the `VectorStoreVector(N)` attribute and the chosen embedding model.
 
 ---

package/framework/standards/ai-agents/workflows.md

@@ -186,7 +186,7 @@ Sempre use `await using` no `StreamingRun` / `Run` — é `IAsyncDisposable`.
 ## Checklist (verifiable in review)
 
 - [ ] Foi verificado que um `foreach` ou single agent não resolve o problema?
-- [ ] O critério de fan-in/out genuíno ou HITL está documentado em `decisions.md`?
+- [ ] O critério de fan-in/out genuíno ou HITL está documentado em `plan.md` (`## Decisões`)?
 - [ ] `Microsoft.Agents.AI` 1.0.* presente no `.csproj` (sem pacotes preview separados)?
 - [ ] Agents referenciando alias do Model Registry (não model strings hardcoded)?
 - [ ] `await using` no `StreamingRun` / `Run`?

package/framework/standards/architecture/code-comments.md

@@ -62,7 +62,7 @@ Só o **porquê que o código não mostra**:
 ## Tamanho
 
 Uma linha é o normal; teto de ~3. Acima disso o comentário justifica o volume (algoritmo não
-óbvio, armadilha de terceiro com a reprodução). Bloco longo narrando decisões é `decisions.md` com
+óbvio, armadilha de terceiro com a reprodução). Bloco longo narrando decisões é `plan.md` (`## Decisões`) com
 outro nome. Em volume, código de aplicação fica perto de zero: mais de uma linha de comentário a
 cada dez de código é sinal de que os nomes não estão fazendo o trabalho. Arquivo vizinho muito
 comentado não é modelo: código novo segue este padrão, não a densidade do legado.

package/framework/standards/architecture/vertical-slice/vertical-slice.md

@@ -333,7 +333,7 @@ var page = await _db.Books
 (ex.: `SELECT ... FOR UPDATE`, retry de `DbUpdateConcurrencyException`) ou SQL específico
 que o LINQ não expressa, escreva um store hand-written e purpose-built (ex.: `OutboxStore`,
 `LeaseStore`) com métodos nomeados pela intenção — e registre a justificativa em
-`decisions.md`. Nunca um genérico por entidade.
+`plan.md` (`## Decisões`). Nunca um genérico por entidade.
 
 Veja `backend/dotnet/vsa-handler-patterns.md` → "Data Access: DbContext in the Slice".
 

package/framework/standards/backend/api/validation.md

@@ -173,7 +173,7 @@ The state check (`>= Completed`) and the business rule (`RequiresPayment && !IsP
 - [ ] Failures come back as `ValidationError` → 400 ProblemDetails with `errors[]`, never an exception?
 - [ ] Existence / uniqueness / state checks in the handler, returning typed `Error`s?
 - [ ] State checks validate INVALID states, with the error range at 100+?
-- [ ] All flows documented in decisions.md and tested?
+- [ ] All flows documented in plan.md (## Decisões) and tested?
 
 ---
 

package/framework/standards/backend/dotnet/vsa-handler-patterns.md

@@ -225,13 +225,13 @@ public sealed class SearchBooksHandler(
 When a slice needs concurrency control (`SELECT ... FOR UPDATE`, lease/outbox semantics,
 `DbUpdateConcurrencyException` retry loops) or SQL that LINQ cannot express, write a
 **hand-written, purpose-built store** with intention-named methods (e.g. `OutboxStore.ClaimBatchAsync`,
-`LeaseStore.TryAcquireAsync`) — and document the justification in `decisions.md`.
+`LeaseStore.TryAcquireAsync`) — and document the justification in `plan.md` (`## Decisões`).
 Never a generic-per-entity abstraction.
 
 **Rule of thumb:** everything → `ApplicationDbContext` in the slice. Concurrency or
-specific SQL → dedicated hand-written store + `decisions.md` entry. Never reach for raw SQL
+specific SQL → dedicated hand-written store + `plan.md` (`## Decisões`) entry. Never reach for raw SQL
 (`FromSqlRaw`) unless a query genuinely cannot be expressed in LINQ — and document that
-in `decisions.md`.
+in `plan.md` (`## Decisões`).
 
 ---
 
@@ -307,8 +307,8 @@ builder.Services.AddExceptionHandler<CustomExceptionHandler>()
 | Share handlers across features | Each feature has its own handler, even if similar |
 | Use constructor + field for DI | Use primary constructors: `class Handler(IDep dep)` |
 | Group by technical concern (Controllers/, Services/) | Group by feature: `Features/BookFeature/CreateBook/` |
-| Route data access through any indirection layer | Inject `DbContext` and write LINQ in the slice; dedicated store only with `decisions.md` justification |
-| Use raw SQL (`FromSqlRaw` / `ExecuteQuery(string)`) by default | Use LINQ; raw SQL only with a `decisions.md` justification |
+| Route data access through any indirection layer | Inject `DbContext` and write LINQ in the slice; dedicated store only with `plan.md` (`## Decisões`) justification |
+| Use raw SQL (`FromSqlRaw` / `ExecuteQuery(string)`) by default | Use LINQ; raw SQL only with a `plan.md` (`## Decisões`) justification |
 
 ---
 

package/framework/standards/backend/integrations/hangfire/hangfire-jobs.md

@@ -15,7 +15,7 @@ Background job processing for .NET 10 VSA applications with Hangfire on Neon Pos
 
 ## When to use Hangfire
 
-Hangfire is in the stack **only with a real reason**: work that must survive a process restart, run on a schedule, or be retried later (daily reindex, delayed reminders, retrying a flaky third party). Work that fits in the request (send one email after a signup, index one uploaded document) runs in the slice handler. Record the reason in `decisions.md`.
+Hangfire is in the stack **only with a real reason**: work that must survive a process restart, run on a schedule, or be retried later (daily reindex, delayed reminders, retrying a flaky third party). Work that fits in the request (send one email after a signup, index one uploaded document) runs in the slice handler. Record the reason in `plan.md` (`## Decisões`).
 
 Hangfire provides fire-and-forget, delayed and recurring (cron) jobs, continuations, a dashboard and automatic retries.
 

package/framework/standards/backend/integrations/neon-auth/neon-auth.md

@@ -64,7 +64,7 @@ place to audit.
 **The exception process:** a feature that genuinely needs the frontend to reach Neon directly for
 business data (for example, via the Neon MCP `provision_neon_data_api` tool) is an exception, not a
 default — treat it exactly like vertical-slice.md's "Stores dedicados (exceção justificada)" clause:
-document the justification in the feature's `decisions.md` before writing the code. A tool being
+document the justification in the feature's `plan.md` (`## Decisões`) before writing the code. A tool being
 available is not, by itself, justification.
 
 See [Row-Level Security Integration](#row-level-security-integration) for how to constrain a
@@ -727,7 +727,7 @@ Each Neon branch gets its own isolated auth data. This means:
     fetch and cache the JWKS yourself and verify EdDSA signatures manually (BouncyCastle)
 11. **Route business data through the .NET backend by default** — the frontend's only inherent
     reason to talk to Neon directly is its own auth/session SDK; a direct Data API call needs a
-    `decisions.md` ADR (see [Data Access Boundary](#data-access-boundary--backend-first-by-default))
+    `plan.md` (`## Decisões`) ADR (see [Data Access Boundary](#data-access-boundary--backend-first-by-default))
 
 ---
 

package/framework/standards/data/nosql/cache/redis.md

@@ -179,4 +179,4 @@ The minute comes from `TimeProvider` (testable with `FakeTimeProvider`), never `
 - Never omit TTL -- unbounded keys fill memory
 - Never wrap the cache in a `XService`/repository class -- cache-aside is three lines in the handler
 - Never return `null` for "not found" -- the handler returns `Result` with `NotFound`
-- Never swallow `RedisConnectionException` in an empty `catch`: a cache outage must be visible (health check + logs). Falling back to the database while Redis is down is a product decision: record it in `decisions.md` and implement it once, at the cache boundary, not per call site
+- Never swallow `RedisConnectionException` in an empty `catch`: a cache outage must be visible (health check + logs). Falling back to the database while Redis is down is a product decision: record it in `plan.md` (`## Decisões`) and implement it once, at the cache boundary, not per call site

package/framework/standards/data/nosql/cosmos-db.md

@@ -3,7 +3,7 @@
 > **Scope:** data-nosql
 > **Layer:** 3 (opcional — nenhuma rule nem persona o carrega; só sob demanda via `morph-spec standards --find`, depois de a decisão existir)
 > **Keywords:** cosmos-db, nosql, document-database, event-store, partition-key, azure-cosmos
-> **Load When:** `decisions.md` already records the choice of Cosmos DB over Neon for a specific store
+> **Load When:** `plan.md` (`## Decisões`) already records the choice of Cosmos DB over Neon for a specific store
 
 **Verified against:** .NET 10 (SDK 10.0.400-preview) + Microsoft.Azure.Cosmos 3.63.2 + Newtonsoft.Json 13.0.4 — every `csharp` block below compiles with `TreatWarningsAsErrors` against the `Result`/`Error` types of `backend-dotnet-result-pattern`. Last-verified: 2026-10-03.
 
@@ -11,7 +11,7 @@
 
 ## Overview
 
-**Cosmos DB is not part of the stack.** The default store is Neon (Postgres) through EF Core, with the `ApplicationDbContext` used directly in the slice. Reach for Cosmos only when a requirement Postgres cannot meet is written down in `decisions.md` (the "why not Neon" included). Everything below applies the stack conventions to that exception: the client is injected straight into the slice handler, ids are `Guid.CreateVersion7()`, expected failures are `Result` values, and classes are `sealed`.
+**Cosmos DB is not part of the stack.** The default store is Neon (Postgres) through EF Core, with the `ApplicationDbContext` used directly in the slice. Reach for Cosmos only when a requirement Postgres cannot meet is written down in `plan.md` (`## Decisões`) (the "why not Neon" included). Everything below applies the stack conventions to that exception: the client is injected straight into the slice handler, ids are `Guid.CreateVersion7()`, expected failures are `Result` values, and classes are `sealed`.
 
 ## When It Can Be Justified
 
@@ -155,7 +155,7 @@ using var feed = container.GetItemQueryIterator<OrderEvent>(
 
 | Do NOT | Do Instead |
 |--------|------------|
-| Pick Cosmos without a `decisions.md` entry | Neon (Postgres) via EF Core is the default store |
+| Pick Cosmos without a `plan.md` (`## Decisões`) entry | Neon (Postgres) via EF Core is the default store |
 | Wrap `Container` in a generic `CosmosRepository<T>` | Inject the keyed `Container` into the slice handler |
 | `try/catch (CosmosException)` for 404/409 | Stream APIs + `StatusCode` → `Result` |
 | `Guid.NewGuid()` for document ids | `Guid.CreateVersion7()` |

package/framework/standards/frontend/admin-app/forms.md

@@ -16,7 +16,7 @@ An admin app has **one** form pattern. It is the base pattern of `nextjs/forms.m
 - **The Zod schema is shared.** The same schema types the form, validates it, and parses the API response (`admin-app/data-table.md` parses the list query with Zod too). One source of truth per entity.
 - **react-hook-form keeps inputs uncontrolled** — a 30-field form does not re-render on every keystroke, which is what `useState` per field does.
 - **shadcn's current form docs are written around it** (`Field`, `FieldLabel`, `FieldError` + `Controller`).
-- **Coexisting styles are the defect this rule exists for.** Measured in a real admin app: three form styles side by side (react-hook-form in some screens, hand-rolled `useState` in others) — three validation behaviours for one product, and a redesign that changed none of them. A screen that needs something the pattern cannot do registers the exception in `decisions.md`; it does not start a fourth style.
+- **Coexisting styles are the defect this rule exists for.** Measured in a real admin app: three form styles side by side (react-hook-form in some screens, hand-rolled `useState` in others) — three validation behaviours for one product, and a redesign that changed none of them. A screen that needs something the pattern cannot do registers the exception in `plan.md` (`## Decisões`); it does not start a fourth style.
 
 ## Core Rules
 

package/framework/standards/frontend/design-system/art-direction.md

@@ -0,0 +1,88 @@
+# Art Direction — Decide What the Screen Is Before Drawing It
+
+> **Scope:** frontend-design-system
+> **Layer:** 3
+> **Keywords:** art direction, concept, visual metaphor, design direction, template look, generic ui, memorable, mobile-first, brand moment
+> **Load When:** ui-designer active, before any component of a new or changed screen
+
+**Verified against:** the `login-ciclo-do-produto` design round (2026-10-06): a correct, plain design was rejected; a second round with a written direction, an HTML prototype and a screenshot self-review was approved on first sight. Last-verified: 2026-10-06.
+
+---
+
+A design that follows the tokens, has every state and passes WCAG can still be forgettable. What made the difference in practice was not talent but order: a direction written before any component, a real prototype, and a critical look at the rendered result. This standard is the first of the three.
+
+---
+
+## Section 1: Write the Direction First
+
+Before the first component, answer four questions in `1-design/direcao.md`:
+
+1. **Concept in one sentence.** What the screen says, not what it contains. *"The login tells the product cycle in scenes while you sign in."*
+2. **Visual metaphor.** The image that organizes the layout. *Stories; a control room; a ticket being stamped; a garden that grows.*
+3. **What makes it memorable.** The one thing someone would describe to a colleague. If nothing, the direction is not done.
+4. **What it must NOT look like.** Name the generic version you are avoiding (Section 4).
+
+Only then pick components. A component chosen before the direction is chosen by habit.
+
+---
+
+## Section 2: Explore Two or Three Directions
+
+For a new screen or a brand moment (login, onboarding, first screen, empty state, success, showcase), write two or three directions that are **distinct**, not three color variations of one layout. For each: concept, metaphor, the mobile idea, the motion idea, and the risk. Recommend one and say why, in terms of the product and the user, not taste.
+
+A changed screen inside an established system may need only one direction, written the same way, with what changes and why.
+
+---
+
+## Section 3: Good and Bad Directions
+
+| Bad direction | Why it fails | Good direction |
+|---|---|---|
+| "Clean, modern login with the logo and a form." | Describes every login. Nothing to remember. | "The panel tells the product cycle in three scenes, stories-style; the form is a sheet the thumb reaches." |
+| "Dashboard with cards for each metric." | Content, not concept. Layout by habit. | "A control room: one hero number the operator acts on, the rest as quiet instruments around it." |
+| "Empty state with an icon and a button." | The default of every kit. | "The empty list is the first page of a notebook: an illustrated first entry shows what a good one looks like." |
+| "Mobile: same layout, stacked." | Mobile derived, not designed. | "Mobile is an app: bottom sheet, thumb-zone actions, the scene compressed to a strip above." |
+
+---
+
+## Section 4: Template Tells to Avoid
+
+Each one is fine in isolation; together they read as "generated". If the screen has three or more, raise it.
+
+- Raw shadcn look: default radius, default gray border, no brand in any surface.
+- A white card centered on a gray background, logo on top, form inside.
+- A generic icon list (three features, three Lucide icons, three lines of copy).
+- Stack-default or AI-tell fonts with no tracking or scale decision (see `premium-finish` Section 1).
+- Flat solid backgrounds with no light, layer or texture.
+- Mobile as the desktop stacked: centered card, tiny targets, actions out of thumb reach.
+- Motion as decoration: everything fades in, nothing tells a sequence.
+- Made-up numbers on illustrative cards (`R$ 12.430`, `98% satisfaction`).
+
+---
+
+## Section 5: Mobile Is Designed, Not Derived
+
+Draw the phone at 390 px as its own composition: bottom sheet for the primary task, actions in the thumb zone, targets of at least 44 px, the brand scene compressed rather than removed. Then check the desktop is not the phone blown up either.
+
+---
+
+## Section 6: Motion With Intent
+
+Motion should tell something (a sequence, a cause, a state change). Pick the lightest tool that delivers it: CSS transition and `@keyframes`, then CSS scroll-driven animation, then Framer Motion, then GSAP with ScrollTrigger and timelines. Budget: 60 fps, only `transform` and `opacity`, no layout thrash, lazy below the fold. `prefers-reduced-motion` gets a composed static version, designed as carefully as the animated one.
+
+---
+
+## Section 7: Prototype and Self-Review
+
+The direction is proved in a rendered prototype, not in prose: `1-design/prototipos/{screen}.html`, self-contained, using the project's REAL tokens read from its token CSS (the design-system doc can be stale), desktop and phone side by side in a device frame, with animated / static / pause controls. Serve it over local HTTP, screenshot at 1280 and 390, judge against this standard and the system bar (hierarchy, contrast, rhythm, mobile, "does it look like a template?"), fix, repeat. The final screenshots sit next to the HTML.
+
+---
+
+## Checklist
+
+- [ ] `direcao.md` answers concept, metaphor, memorable, must-not-look-like
+- [ ] Two or three distinct directions for a new screen or brand moment, one recommended with a reason
+- [ ] Fewer than three template tells on the final screen
+- [ ] Mobile composed at 390 px on its own terms
+- [ ] Motion tells something, with a composed reduced-motion version
+- [ ] Prototype rendered, screenshotted at 1280 and 390, and revised until it passes

package/framework/standards/frontend/design-system/premium-finish.md

@@ -3,9 +3,9 @@
 > **Scope:** frontend-design-system
 > **Layer:** 3
 > **Keywords:** premium, polish, typography, film grain, atmosphere, load-in, scrim, legibility over video, accent
-> **Load When:** ui-designer active, or the brief asks for a premium or high-end feel
+> **Load When:** ui-designer active (every surface), or the brief asks for a premium or high-end feel
 
-**Verified against:** Production landing pages, CSS-only techniques, no runtime dependency. Last-verified: 2026-08-21.
+**Verified against:** Production landing pages, CSS-only techniques, no runtime dependency; app patterns from an approved login prototype (2026-10-06). Last-verified: 2026-10-06.
 
 ---
 
@@ -148,6 +148,78 @@ Finish with fresh eyes: open the page as if you were the client. Whatever looks
 
 ---
 
+## Section 8: Patterns For App Screens
+
+The finish is not only for marketing pages. Login, onboarding, the first screen after sign-up, an empty state and a success moment are brand moments inside the product, and a data screen also has to look designed: elegant density, illustrated empty states, skeletons with shimmer, transitions between states. These patterns come from an app login that was approved on first sight after a plain one was rejected.
+
+### Bottom sheet on mobile
+
+On a phone the form lives in a sheet anchored to the bottom, inside the thumb zone, with the brand scene above it. Never the desktop card centered and shrunk.
+
+```css
+.sheet {
+  position: fixed; inset: auto 0 0 0;
+  padding: 12px 20px calc(20px + env(safe-area-inset-bottom));
+  border-radius: 24px 24px 0 0;
+  background: var(--surface);
+  box-shadow: 0 -12px 40px color-mix(in oklab, var(--brand) 18%, transparent);
+}
+.sheet::before {
+  content: ''; display: block; width: 36px; height: 4px; margin: 0 auto 16px;
+  border-radius: 2px; background: var(--border);
+}
+.sheet button, .sheet input { min-height: 44px; }
+```
+
+### Stories-style progress
+
+A sequence of scenes reads like stories: thin segmented bars at the top, each filling while its scene is on. One keyframe, the delay per segment, and the scene swap keyed to the same delays.
+
+```css
+.stories { display: flex; gap: 4px; }
+.stories span { flex: 1; height: 3px; border-radius: 2px; background: color-mix(in oklab, var(--fg) 20%, transparent); overflow: hidden; }
+.stories span::after {
+  content: ''; display: block; height: 100%; background: var(--fg);
+  transform: scaleX(0); transform-origin: left;
+  animation: fill var(--beat) linear forwards;
+  animation-delay: calc(var(--i) * var(--beat));
+}
+@keyframes fill { to { transform: scaleX(1); } }
+```
+
+### Synchronized highlight by `animation-delay`
+
+When a scene card lights up while its story bar runs, both share `--i` and `--beat`. No JavaScript timer: the browser keeps them in step, and pausing is one `animation-play-state: paused` on the parent.
+
+### Scene cards without real data
+
+A card that illustrates the product cycle shows shapes, icons and labels, never a metric. A made-up number on a real screen reads as a real number ("R$ 12.430 recovered") and becomes a claim nobody can back. Use bars without values, avatars without names, a check without a count.
+
+### Dot grid faded with `mask-image`
+
+Texture for a hero or a sheet backdrop, cheaper than an image and on brand:
+
+```css
+.dots {
+  background-image: radial-gradient(color-mix(in oklab, var(--fg) 22%, transparent) 1px, transparent 1px);
+  background-size: 16px 16px;
+  mask-image: radial-gradient(ellipse at 50% 30%, #000 30%, transparent 75%);
+}
+```
+
+### Static version for reduced motion
+
+`prefers-reduced-motion: reduce` gets a composed still frame (the best scene, every bar full, the highlight on), not the first frame of a stopped animation.
+
+```css
+@media (prefers-reduced-motion: reduce) {
+  .stories span::after { animation: none; transform: scaleX(1); }
+  .scene { animation: none; opacity: 1; }
+}
+```
+
+---
+
 ## Checklist
 
 - [ ] Display font chosen from the brand, not from stack defaults or the AI-tell list
@@ -157,4 +229,7 @@ Finish with fresh eyes: open the page as if you were the client. Whatever looks
 - [ ] Directional scrim plus text-shadow on every text-over-media block
 - [ ] Accent used in three places or fewer
 - [ ] Details swept: scrollbar, selection, hairlines, hover micro-transitions
+- [ ] App screen: mobile designed on its own (bottom sheet, thumb zone, 44px targets), never the desktop stacked
+- [ ] No invented number or data on a real screen
+- [ ] Reduced motion gets a composed static frame
 - [ ] Fresh-eyes pass done, and it does not read as a template

package/framework/standards/infrastructure/neon/neon-pgvector.md

@@ -19,7 +19,7 @@ Stack: .NET VSA + Neon Serverless Postgres. For the end-to-end RAG pipeline (ing
 - ALWAYS call `UseVector()` on the `UseNpgsql(...)` options builder (EF Core); `NpgsqlDataSourceBuilder.UseVector()` is only for raw Npgsql
 - ALWAYS register the `vector` extension in `OnModelCreating` (`HasPostgresExtension("vector")`)
 - Map vector properties as `Pgvector.Vector` -- EF Core does not map `float[]` or `ReadOnlyMemory<float>` to the `vector` column
-- Query through the `ApplicationDbContext` in the slice handler with the `CosineDistance`/`L2Distance`/`MaxInnerProduct` LINQ translations -- no repository class, no raw SQL from C# without a `decisions.md` justification
+- Query through the `ApplicationDbContext` in the slice handler with the `CosineDistance`/`L2Distance`/`MaxInnerProduct` LINQ translations -- no repository class, no raw SQL from C# without a `plan.md` (`## Decisões`) justification
 - IDs come from the app (`Guid.CreateVersion7()`), never from a `gen_random_uuid()` column default
 
 ## Enable pgvector
@@ -39,7 +39,7 @@ CREATE EXTENSION IF NOT EXISTS vector;
 <PackageReference Include="Pgvector.EntityFrameworkCore" Version="0.3.0" />
 ```
 
-`Pgvector.EntityFrameworkCore` 0.3.0 requires `Npgsql.EntityFrameworkCore.PostgreSQL` >= 9.0.1 and brings `Pgvector` (the `Vector` type and the raw-Npgsql plugin) transitively. The configuration below maps each column to the snake_case names of `backend/database/postgresql/database.md` (`embedding`, `created_at`) with `HasColumnName`; without it EF creates `"Embedding"`, `"CreatedAt"` and every SQL snippet below would have to quote PascalCase names. (A project that wants this for every entity can add `EFCore.NamingConventions` and `UseSnakeCaseNamingConvention()` once, instead of per column -- a project-wide decision for `decisions.md`.)
+`Pgvector.EntityFrameworkCore` 0.3.0 requires `Npgsql.EntityFrameworkCore.PostgreSQL` >= 9.0.1 and brings `Pgvector` (the `Vector` type and the raw-Npgsql plugin) transitively. The configuration below maps each column to the snake_case names of `backend/database/postgresql/database.md` (`embedding`, `created_at`) with `HasColumnName`; without it EF creates `"Embedding"`, `"CreatedAt"` and every SQL snippet below would have to quote PascalCase names. (A project that wants this for every entity can add `EFCore.NamingConventions` and `UseSnakeCaseNamingConvention()` once, instead of per column -- a project-wide decision for `plan.md` (`## Decisões`).)
 
 ### Entity Definition
 
@@ -196,9 +196,9 @@ public sealed class SearchDocumentsHandler(
 
 Storing an embedding is an ordinary EF write in the handler that owns the document: `document.Embedding = new Vector(await embeddings.GenerateVectorAsync(text, cancellationToken: ct));` followed by `SaveChangesAsync`. No `UPDATE ... SET embedding` from C#.
 
-### SQL Functions (only with a `decisions.md` justification)
+### SQL Functions (only with a `plan.md` (`## Decisões`) justification)
 
-When the query must live in the database (called from several apps, or a hybrid score the LINQ translation cannot express), a SQL function is acceptable -- record why in `decisions.md`, call it through EF Core with interpolated parameters, and keep the same distance rules:
+When the query must live in the database (called from several apps, or a hybrid score the LINQ translation cannot express), a SQL function is acceptable -- record why in `plan.md` (`## Decisões`), call it through EF Core with interpolated parameters, and keep the same distance rules:
 
 ```sql
 CREATE OR REPLACE FUNCTION match_documents(
@@ -218,7 +218,7 @@ $$;
 
 ## Hybrid Search (Vector + Full-Text)
 
-Blends the vector score with `ts_rank`. Same rule as above: a SQL function, justified in `decisions.md`.
+Blends the vector score with `ts_rank`. Same rule as above: a SQL function, justified in `plan.md` (`## Decisões`).
 
 ```sql
 CREATE OR REPLACE FUNCTION hybrid_search(

package/framework/templates/CLAUDE.md.core.template

@@ -6,7 +6,7 @@
 
 VSA + .NET 10 + EF Core + Neon (Postgres) + Microsoft Agent Framework + Next.js (App Router) + Tailwind + Framer Motion + Shadcn + Hangfire (quando necessário).
 
-Padrões proibidos por padrão: `Guid.NewGuid()` (use `Guid.CreateVersion7()`), classes não-sealed sem justificativa, exceptions como fluxo de controle, camada de Service/Manager entre handler e dados, repository genérico (`IRepository<T>`/`IUnitOfWork`), SQL cru sem justificativa. Acesso a dados: `ApplicationDbContext` direto no slice (`DbSet<T>` já é repository, `DbContext` já é unit of work); para concorrência ou SQL específico, store dedicado hand-written com justificativa em `decisions.md`.
+Padrões proibidos por padrão: `Guid.NewGuid()` (use `Guid.CreateVersion7()`), classes não-sealed sem justificativa, exceptions como fluxo de controle, camada de Service/Manager entre handler e dados, repository genérico (`IRepository<T>`/`IUnitOfWork`), SQL cru sem justificativa. Acesso a dados: `ApplicationDbContext` direto no slice (`DbSet<T>` já é repository, `DbContext` já é unit of work); para concorrência ou SQL específico, store dedicado hand-written com justificativa em `plan.md` (`## Decisões`).
 
 ## Harness
 
@@ -18,5 +18,5 @@ morph-spec NLH — leia `.morph/framework/MORPH.md` ao iniciar cada sessão. Em
 
 ## Slash commands
 
-- `/morph-proposal {feature}` — entendimento de negócio + use cases, spec e tasks (Gates 1 e 2)
-- `/morph-apply {feature}` — execução autônoma das tarefas + review (Gate 3)
+- `/morph-plan {feature}` — entrevista, `plan.md`, `plan-check` e gate do plano
+- `/morph-apply {feature}` — fatias do plano, `verify` e review (Gate 3)