feat(memory): write-ahead validation via guardian model

**Context:** ROADMAP.md → Memory security → Write-ahead validation

---

## Component

Agent (Python runtime)

## Describe the feature

Route proposed **memory writes** through a guardian model (or rules engine) before persistence. Reject or flag entries that look like injection, secrets, or policy violations.

## Use case

Review-feedback extraction (#27) and agent self-writes can persist attacker-controlled text. A last-line validator reduces poisoned persistence.

## Proposed solution

1. Intercept write path in memory client wrapper.
2. Guardian: lightweight model call or regex+guardrail stack (cost-aware).
3. Modes: `observe` (log only) → `enforce` (block write).
4. Emit `memory_write_rejected` events.
5. Blueprint-configurable per repo.

## Other information

- Complements Bedrock Guardrails on hydration inputs.
- Design context: `docs/design/MEMORY.md`, `docs/design/SECURITY.md`.

- [ ] This might be a breaking change

Empieza leyendo ROADMAP.md y el contexto de diseño en docs/design/MEMORY.md y docs/design/SECURITY.md; después, localiza el wrapper del cliente de memoria y la ruta de escritura del agente. Revisa cómo se gestionan la configuración de blueprint y los eventos antes de decidir entre los enfoques de guardian propuestos. Se considera terminado cuando las escrituras admiten los modos observe y enforce, las escrituras rechazadas emiten eventos memory_write_rejected y el comportamiento se puede configurar por repositorio.

Escrito por el modelo de indexación a partir del texto del issue.