feat(memory): memory extraction replay operator API

**Context:** ROADMAP.md → Memory security → Memory extraction replay
**Related:** #27

---

## Component

API or orchestration

## Describe the feature

Operator API (e.g. `POST /memory/extraction-jobs` or `start_memory_extraction_job`) to **re-run failed PR-review extraction** after webhook or Lambda errors.

## Use case

Transient failures during review-comment extraction leave gaps in learning. Operators should replay without re-running the full agent task.

## Proposed solution

1. Durable job record: PR URL, task_id, last error, status.
2. Idempotent replay from stored webhook payload or GitHub API fetch.
3. CLI: `bgagent memory replay-extraction `.
4. Link outcomes to #27 memory loop metrics.

## Other information

- Design context: `docs/design/MEMORY.md`, `docs/design/ORCHESTRATOR.md`.

- [ ] This might be a breaking change

Start with docs/design/MEMORY.md and docs/design/ORCHESTRATOR.md, then trace the existing memory extraction and orchestration entry points. Define the durable job record, idempotent replay path, operator API, and `bgagent memory replay-extraction` CLI, with outcomes linked to the metrics in #27.

Written by the indexing model from the issue text.