LLM approval answerer for DeepSeek Harness

Key features

• Appeal mode (context'appeal-user-prompts', the default): an LLM-voiced DENY is re-judged ONCE with the session's genuine user prompts attached as intent evidence — extracted deterministically (never LLM-summarized) from user/message events whose source kind is exactly 'user'.
• 0001-approval-auto-policy-and-escalation-action.patch — the 'auto' approval policy, ApprovalRequest.action, ApprovalService.effectivePolicyFor, and the tool/sandbox/permission-presets wiring that carries the escalation action.
• Appeals can only RELAX a denial, never tighten an allowance: they reduce false positives
• they are not a detection upgrade.
• 0002-llm-auto-review-request-purpose.patch — the 'auto-review' LLM request purpose.