feat(gate): 四階段模型閘門改為指定模型優先、能力標籤備援,並以 sdlc-gate 上鎖

What:plan、analyze、implement、maintain 四個 SKILL.md 的第一步從單純的能力標籤檢查,改為「模型閘門與階段上鎖」三段流程:先以 jsc-cli/tools/model-config.sh get {stage} 解析該階段的指定模型鏈,鏈上第一個當前 CLI 可用的模型即為必用模型;沒有設定指定模型時才退回 jsc-cli:models 的能力標籤檢查。閘門通過後執行 jsc-hooks/hooks/sdlc-gate.sh lock {stage} {current-model} 寫入鎖檔,並以 sdlc-gate.sh report 驗證。

Why:原本只驗能力標籤,同一標籤下模型可任意替換,階段中途換模型也無人攔阻,導致產出品質與可重現性不穩定。改為指定模型鏈優先可讓團隊明確指派每階段用哪個模型,標籤備援則保留未設定時的彈性;上鎖後由 hook 在每次 prompt 強制檢查,階段內換模型會被擋下。

How:每個技能的步驟一拆成三小步(解析模型鏈、驗證當前模型、上鎖並驗證鎖檔),各小步附完成條件;maintain 另加第四小步,明確規定只在換階段時重跑閘門,維護階段內跨專案不重複驗證。frontmatter description 同步更新。鎖定自 plan 起手生效,直到下一階段(如 analyze)的閘門重新上鎖前,強制沿用同一模型。

Who:jsc-sdlc 的 plan/analyze/implement/maintain 四個技能,及依賴其閘門行為的 jsc-hooks sdlc-gate hook。

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
2026-08-24 11:36:33 +08:00
co-authored by Claude Fable 5
parent 1153f7f064
commit 2705771c20
4 changed files with 21 additions and 8 deletions
+5 -2
View File
@@ -1,6 +1,6 @@
---
name: analyze
description: SDLC analysis stage. Gate on model capability tags, pick a plan from PLAN_CONTENTS, analyze user stories against the current state (working directory plus REPO_{HASH} inventory for reuse). Run WBS to produce numbered work packages, estimate them with CPM, split each into TDD todos, and write wiki page ANALYZE_{HASH}. Logic only - never write code or modify files. Use after planning and before implementation.
description: SDLC analysis stage. Gate on the designated model (model-config) or capability tags, lock the model for the stage via sdlc-gate, pick a plan from PLAN_CONTENTS, analyze user stories against the current state (working directory plus REPO_{HASH} inventory for reuse). Run WBS to produce numbered work packages, estimate them with CPM, split each into TDD todos, and write wiki page ANALYZE_{HASH}. Logic only - never write code or modify files. Use after planning and before implementation.
---
# analyze
@@ -13,7 +13,10 @@ All wiki reads and writes go through `jsc-gitea:wiki`.
## Steps
1. **Model capability gate**: check the capability tags from `jsc-cli:models` and confirm the current model qualifies for analysis. If not, block the flow and tell the user which model to switch to.
1. **Model gate and stage lock**:
1. Resolve the analyze stage's designated model chain: run `jsc-cli/tools/model-config.sh get analyze`. If it prints a chain, the required model is the first entry of the chain the current CLI can use (fallbacks apply in chain order). If it prints nothing, fall back to the capability-tag check via `jsc-cli:models` (analysis requires the reasoning-high tag).
2. If the current model is not the required model, or fails the tag check, block the flow and tell the user which model to switch to. Completion condition: the current model satisfies the gate.
3. Lock the stage: run `jsc-hooks/hooks/sdlc-gate.sh lock analyze {current-model}`. From now until the next SDLC stage's gate runs, the sdlc-gate hook enforces this model on every prompt; switching models mid-stage gets blocked. Completion condition: the lock file is written, verified with `sdlc-gate.sh report`.
2. Read `PLAN_CONTENTS` via `jsc-gitea:wiki` for plans whose status is the literal 「未分析」 (name and HASH), and read `ANALYZE_CONTENTS` for existing analyses.
3. Let the user choose per `jsc-ask:ask` rules: **extend an existing analysis** or **analyze a new plan**. State the impact scope on every option.
4. Analyze the plan page's user stories one by one against the **current state**, questioning via the `jsc-ask:ask` decision tree until no doubt remains; keep asking while consensus is missing. Current state means: