@sun-asterisk/sungen 3.1.2-beta.98 → 3.1.2-beta.99

package/dist/orchestrator/templates/ai-instructions/claude-cmd-create-test.md

@@ -31,9 +31,10 @@ Parse **name** from `$ARGUMENTS`. If missing, ask the user.
    **Screen**: Verify `qa/screens/<name>/` exists. If not → `/sungen:add-screen` first.
 2. Check if `.feature` file already has scenarios.
    - If yes → use `AskUserQuestion` to ask the update mode (see `sungen-tc-generation` skill — mode depends on which tiers already exist).
-   - If no → fresh creation. Use `AskUserQuestion` to ask generation scope:
-     - **Tier 1 — Critical & High priority** — ~10-15 scenarios/section covering happy paths, core validation, security basics **(Recommended)**
-     - **Full coverage — All tiers at once** — generates Tier 1 + 2 + 3 in one run. Large output (~40-60 scenarios/section), best for experienced users who want complete coverage immediately
+   - If no → fresh creation. **Write the feature file incrementally** (successive `Write`/`Edit`, ≈10-15 scenarios per call) — never emit the whole suite in one response, or it can exceed the model's output-token cap (`API Error: Claude's response exceeded the N output token maximum`). Use `AskUserQuestion` to ask generation scope:
+     - **Tier 1 — Critical & High priority** — ~10-15 scenarios/section: happy paths, core validation, security basics **(Recommended)**
+     - **Full coverage (incremental)** — Tier 1 + 2 + 3, written tier-by-tier in batches (`Write` T1 → `Edit` append T2 → `Edit` append T3). Safe on any output-token budget.
+     - **Full coverage (single pass)** — generate everything in one go (~40-60 scenarios/section). Faster, but **only if you raised your output cap** (`CLAUDE_CODE_MAX_OUTPUT_TOKENS ≥ 64000`) — otherwise it errors mid-generation. For power users on a high-token model/config.
 3. **Read project context + screen requirements**
 
    **Project context** — check `qa/context.md` (project root, not screen-specific):

package/dist/orchestrator/templates/ai-instructions/claude-skill-tc-generation.md

@@ -6,6 +6,9 @@ user-invocable: false
 
 ## ⚠️ Gotchas — read before generating
 
+- **Write incrementally — never emit the whole suite in one response.** Build the `.feature` in batches via successive `Write`/`Edit` (≈10–15 scenarios per call). For **Full coverage**, write tier-by-tier: `Write` Tier 1 → `Edit` append Tier 2 → `Edit` append Tier 3.
+  → One huge `Write` can exceed the model's output-token cap → `API Error: Claude's response exceeded the N output token maximum`. Single-pass full coverage only fits when `CLAUDE_CODE_MAX_OUTPUT_TOKENS ≥ 64000`; otherwise batch. Batching also lets the audit/reviewer run per batch — higher quality.
+
 - `spec_figma.md` exists → read file only, **NEVER** call `mcp__figma__*`
   → PAT auth flow already done by `sungen-capture` (mode figma-pat); re-calling fails or duplicates work.
 

package/dist/orchestrator/templates/ai-instructions/copilot-cmd-create-test.md

@@ -26,9 +26,10 @@ You are a **Senior QA Engineer**. You structure test cases by viewpoint categori
    **Screen**: Verify `qa/screens/${input:name}/` exists. If not → `/sungen-add-screen` first.
 2. Check if `.feature` already has scenarios.
    - If yes → summarize existing coverage and ask update mode (options depend on which tiers already exist — see `sungen-tc-generation` skill for details).
-   - If no → fresh creation. Ask generation scope:
-     - **1) Tier 1 — Critical & High priority** — ~10-15 scenarios/section covering happy paths, core validation, security basics **(Recommended)**
-     - **2) Full coverage — All tiers at once** — generates Tier 1 + 2 + 3 in one run. Large output (~40-60 scenarios/section), best for experienced users who want complete coverage immediately
+   - If no → fresh creation. **Write the feature file incrementally** (successive writes/edits, ≈10-15 scenarios per call) — never emit the whole suite in one response, or it can exceed the model's output-token cap (`response exceeded the N output token maximum`). Ask generation scope:
+     - **1) Tier 1 — Critical & High priority** — ~10-15 scenarios/section: happy paths, core validation, security basics **(Recommended)**
+     - **2) Full coverage (incremental)** — Tier 1 + 2 + 3, written tier-by-tier in batches. Safe on any output-token budget.
+     - **3) Full coverage (single pass)** — everything in one go (~40-60 scenarios/section). Faster, but **only if you raised your output cap** (`CLAUDE_CODE_MAX_OUTPUT_TOKENS ≥ 64000`) — otherwise it errors mid-generation. For power users on a high-token model/config.
 3. **Read project context + screen requirements**
 
    **Project context** — check `qa/context.md` (project root, not screen-specific):

package/dist/orchestrator/templates/ai-instructions/github-skill-sungen-tc-generation.md

@@ -6,6 +6,9 @@ user-invocable: false
 
 ## ⚠️ Gotchas — read before generating
 
+- **Write incrementally — never emit the whole suite in one response.** Build the `.feature` in batches via successive `Write`/`Edit` (≈10–15 scenarios per call). For **Full coverage**, write tier-by-tier: `Write` Tier 1 → `Edit` append Tier 2 → `Edit` append Tier 3.
+  → One huge `Write` can exceed the model's output-token cap → `API Error: Claude's response exceeded the N output token maximum`. Single-pass full coverage only fits when `CLAUDE_CODE_MAX_OUTPUT_TOKENS ≥ 64000`; otherwise batch. Batching also lets the audit/reviewer run per batch — higher quality.
+
 - `spec_figma.md` exists → read file only, **NEVER** call `mcp__figma__*`
   → PAT auth flow already done by `sungen-capture` (mode figma-pat); re-calling fails or duplicates work.
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sun-asterisk/sungen",
-  "version": "3.1.2-beta.98",
+  "version": "3.1.2-beta.99",
   "description": "Deterministic E2E Test Compiler - Gherkin + Selectors → Playwright tests",
   "main": "src/index.ts",
   "types": "src/index.ts",
@@ -33,7 +33,7 @@
     "node": ">=18.0.0"
   },
   "dependencies": {
-    "@sungen/driver-ui": "3.1.2-beta.98",
+    "@sungen/driver-ui": "3.1.2-beta.99",
     "@anthropic-ai/sdk": "^0.71.0",
     "@babel/parser": "^7.28.5",
     "@babel/traverse": "^7.28.5",

package/src/orchestrator/templates/ai-instructions/claude-cmd-create-test.md

@@ -31,9 +31,10 @@ Parse **name** from `$ARGUMENTS`. If missing, ask the user.
    **Screen**: Verify `qa/screens/<name>/` exists. If not → `/sungen:add-screen` first.
 2. Check if `.feature` file already has scenarios.
    - If yes → use `AskUserQuestion` to ask the update mode (see `sungen-tc-generation` skill — mode depends on which tiers already exist).
-   - If no → fresh creation. Use `AskUserQuestion` to ask generation scope:
-     - **Tier 1 — Critical & High priority** — ~10-15 scenarios/section covering happy paths, core validation, security basics **(Recommended)**
-     - **Full coverage — All tiers at once** — generates Tier 1 + 2 + 3 in one run. Large output (~40-60 scenarios/section), best for experienced users who want complete coverage immediately
+   - If no → fresh creation. **Write the feature file incrementally** (successive `Write`/`Edit`, ≈10-15 scenarios per call) — never emit the whole suite in one response, or it can exceed the model's output-token cap (`API Error: Claude's response exceeded the N output token maximum`). Use `AskUserQuestion` to ask generation scope:
+     - **Tier 1 — Critical & High priority** — ~10-15 scenarios/section: happy paths, core validation, security basics **(Recommended)**
+     - **Full coverage (incremental)** — Tier 1 + 2 + 3, written tier-by-tier in batches (`Write` T1 → `Edit` append T2 → `Edit` append T3). Safe on any output-token budget.
+     - **Full coverage (single pass)** — generate everything in one go (~40-60 scenarios/section). Faster, but **only if you raised your output cap** (`CLAUDE_CODE_MAX_OUTPUT_TOKENS ≥ 64000`) — otherwise it errors mid-generation. For power users on a high-token model/config.
 3. **Read project context + screen requirements**
 
    **Project context** — check `qa/context.md` (project root, not screen-specific):

package/src/orchestrator/templates/ai-instructions/claude-skill-tc-generation.md

@@ -6,6 +6,9 @@ user-invocable: false
 
 ## ⚠️ Gotchas — read before generating
 
+- **Write incrementally — never emit the whole suite in one response.** Build the `.feature` in batches via successive `Write`/`Edit` (≈10–15 scenarios per call). For **Full coverage**, write tier-by-tier: `Write` Tier 1 → `Edit` append Tier 2 → `Edit` append Tier 3.
+  → One huge `Write` can exceed the model's output-token cap → `API Error: Claude's response exceeded the N output token maximum`. Single-pass full coverage only fits when `CLAUDE_CODE_MAX_OUTPUT_TOKENS ≥ 64000`; otherwise batch. Batching also lets the audit/reviewer run per batch — higher quality.
+
 - `spec_figma.md` exists → read file only, **NEVER** call `mcp__figma__*`
   → PAT auth flow already done by `sungen-capture` (mode figma-pat); re-calling fails or duplicates work.
 

package/src/orchestrator/templates/ai-instructions/copilot-cmd-create-test.md

@@ -26,9 +26,10 @@ You are a **Senior QA Engineer**. You structure test cases by viewpoint categori
    **Screen**: Verify `qa/screens/${input:name}/` exists. If not → `/sungen-add-screen` first.
 2. Check if `.feature` already has scenarios.
    - If yes → summarize existing coverage and ask update mode (options depend on which tiers already exist — see `sungen-tc-generation` skill for details).
-   - If no → fresh creation. Ask generation scope:
-     - **1) Tier 1 — Critical & High priority** — ~10-15 scenarios/section covering happy paths, core validation, security basics **(Recommended)**
-     - **2) Full coverage — All tiers at once** — generates Tier 1 + 2 + 3 in one run. Large output (~40-60 scenarios/section), best for experienced users who want complete coverage immediately
+   - If no → fresh creation. **Write the feature file incrementally** (successive writes/edits, ≈10-15 scenarios per call) — never emit the whole suite in one response, or it can exceed the model's output-token cap (`response exceeded the N output token maximum`). Ask generation scope:
+     - **1) Tier 1 — Critical & High priority** — ~10-15 scenarios/section: happy paths, core validation, security basics **(Recommended)**
+     - **2) Full coverage (incremental)** — Tier 1 + 2 + 3, written tier-by-tier in batches. Safe on any output-token budget.
+     - **3) Full coverage (single pass)** — everything in one go (~40-60 scenarios/section). Faster, but **only if you raised your output cap** (`CLAUDE_CODE_MAX_OUTPUT_TOKENS ≥ 64000`) — otherwise it errors mid-generation. For power users on a high-token model/config.
 3. **Read project context + screen requirements**
 
    **Project context** — check `qa/context.md` (project root, not screen-specific):

package/src/orchestrator/templates/ai-instructions/github-skill-sungen-tc-generation.md

@@ -6,6 +6,9 @@ user-invocable: false
 
 ## ⚠️ Gotchas — read before generating
 
+- **Write incrementally — never emit the whole suite in one response.** Build the `.feature` in batches via successive `Write`/`Edit` (≈10–15 scenarios per call). For **Full coverage**, write tier-by-tier: `Write` Tier 1 → `Edit` append Tier 2 → `Edit` append Tier 3.
+  → One huge `Write` can exceed the model's output-token cap → `API Error: Claude's response exceeded the N output token maximum`. Single-pass full coverage only fits when `CLAUDE_CODE_MAX_OUTPUT_TOKENS ≥ 64000`; otherwise batch. Batching also lets the audit/reviewer run per batch — higher quality.
+
 - `spec_figma.md` exists → read file only, **NEVER** call `mcp__figma__*`
   → PAT auth flow already done by `sungen-capture` (mode figma-pat); re-calling fails or duplicates work.