Contracts 2, 3, 4 — Option Enumeration / Plan Gap / Direct-Response

Root SSOT: rules/advisory-depth.md §"Contract 2~4" parent: README.md

Contract 2 — Exhaustive Option Enumeration

When the user mentions any ordering, comparison, design choice, or "how should I do X", the agent must enumerate the full option space, not only the option the user happens to have named.

Rule of thumb

If the user names 1 ordering of N items, enumerate all N! orderings.
If the user names 1 design approach, enumerate at least the canonical alternatives (typically 3–5).
If the user asks "which library", enumerate the realistic candidates with their distinct trade-offs.
If the user describes a workflow with N steps, list which steps can be reordered, which can be parallelized, which can be skipped, and which are blocking.

Per-option fields

For each option in the enumeration:

- **케이스 / Case:** <one-line label>
- **적용 상황 / When it fits:** <the situations where this option is the right answer>
- **고려사항 / Considerations:** <what must be true / what must be watched>
- **장점 / Pros:** <concrete, not vague>
- **단점 / Cons:** <concrete, not vague>
- **비교 / Compared to others:** <how this differs from the other options in the same enumeration>

Conditional recommendation (NOT flat)

After enumerating, the agent provides a conditional recommendation:

- If <situation A> → use <option α>, because <reason>.
- If <situation B> → use <option β>, because <reason>.
- If <situation C> → use <option γ>, because <reason>.

Flat recommendations like "X를 추천합니다" are insufficient. The agent always ties recommendations to situations.

Contract 3 — Plan Gap Detection

When the user asks the agent to review, critique, or extend a plan document, the agent must explicitly identify:

Tasks that should be in the plan but are not. For each:
- Why it should be there (tied to the spec or original goal).
- Where it should slot in the order (before / after which existing step).
- What breaks if it is omitted.
Tasks that are in the plan but should not be. For each, the reason for removal and the impact.
Tasks whose ordering is wrong. For each, the corrected ordering and why.
Implicit assumptions in the plan. Surface them as explicit prerequisites.

A plan review that returns only "the plan looks good" is treated as BLOCKED. The agent must surface gaps or explicitly declare "no gaps found, all N tasks needed match the spec" with the matrix of plan-task → spec-section to prove it.

Contract 4 — Direct-Response Template

When the controller answers directly (no subagent dispatch), the response still uses a structured shape. The template scales with question size; sections can be tight one-liners for trivial questions, but they cannot be skipped.

Template

## 1. 질문 이해 / Question understood
- <한 줄 요약>
- 함의된 목표 / Implied goal: <what the user is actually trying to achieve>
- 함의된 제약 / Implied constraints: <budgets, deadlines, stack, scale; pulled from project context or asked if missing>

## 2. 경우의 수 / Option space
- <Option 1>
- <Option 2>
- <Option 3>
- ... (exhaustive per Contract 2)

## 3. 각 경우 분석 / Per-option analysis
### Case 1: <label>
- 적용 상황 / When it fits: ...
- 고려사항 / Considerations: ...
- 장점 / Pros: ...
- 단점 / Cons: ...
### Case 2: ...

## 4. 비교 표 / Comparison matrix
| Option | 적합 상황 | 주요 장점 | 주요 단점 | 비고 |
| --- | --- | --- | --- | --- |

(Required when there are 3+ options. Optional below that.)

## 5. 권고 / Conditional recommendation
- If <situation A> → <option α>, because ...
- If <situation B> → <option β>, because ...
(Flat "추천: X" is forbidden.)

## 6. 다음 결정 / Next decisions
- What the user must decide before the next step
- What information is still missing
- What questions the agent has for the user

Trivial lookups

For trivial single-fact questions (for example "이 메서드는 어디 있나요?"), the template collapses to §1 + a one-line answer with file:line citation, and §2~§6 are written as "해당 없음 / N/A — trivial lookup". The agent still names what it skipped and why; it does not silently drop sections.

Antigravity-specific 메모

Contract 4 의 §1~§6 은 chat 본문 응답에 적용. Stop hook 본문 미수신으로 자동 enforce 불가. agent self-check 단독.
Contract 3 plan review "looks fine" 자동 BLOCKED 는 정책 — runtime enforcement 없음. self-check 로 강제.
사용자가 ordering / 비교를 물으면 (Contract 2 적용) full N! 또는 3~5 canonical alternatives 열거하지 않은 응답은 부족한 advisory 로 자동 폐기.

4.8 KiB Raw Blame History Unescape Escape