feat(orchestration): PR risk classifier at submission

**Context:** ROADMAP.md → Agent quality → PR risk classification
**Related:** #425 (review routing depends on this), tiered validation draft

---

## Component

API or orchestration

## Describe the feature

Rule-based **PR risk classifier** evaluated at submission (and optionally updated post-agent). Outputs structured risk label(s) that drive model selection, budget defaults, Cedar approval requirements, and human review tier (#425).

## Use case

Not all tasks deserve the same model, budget, or review depth. A docs-only typo fix should not inherit the same gates as a payment-service schema migration.

## Proposed solution

1. Classifier inputs: workflow ref, repo metadata, touched paths (when known), task description signals, Tier 3 validation output (when available).
2. Output schema: `risk_tier: low | medium | high | critical`, `signals: string[]`, `recommended_model`, `recommended_max_budget_usd`.
3. Persist on task record; expose in `bgagent status` and API.
4. Blueprint overrides per repo for path-based rules.
5. Start advisory-only; enable policy gates via Cedar in follow-up.

## Other information

- #425 implements **routing**; this issue implements the **classifier**.
- Design context: `docs/design/EVALUATION.md`, `docs/design/CEDAR_HITL_GATES.md`.

- [ ] This might be a breaking change

Inizia da docs/design/EVALUATION.md e docs/design/CEDAR_HITL_GATES.md, poi esamina #425 per capire in che modo il routing dipende dal classifier. Definisci il classifier esclusivamente consultivo in base agli input e allo schema di output elencati, persisti il risultato nel record del task ed esponilo tramite bgagent status e l’API.

Scritto dal modello di indicizzazione a partire dal testo della issue.