qfai 1.0.6 → 1.0.7

package/assets/init/.qfai/assistant/prompts/qfai-configure.md

@@ -0,0 +1,174 @@
+<!--
+QFAI Prompt Body (SSOT)
+- This file is intended to be referenced by tool-specific custom prompt definitions (e.g., Copilot .prompt.md, Claude Code slash commands).
+- Keep tool-specific wrappers thin: "Read this file and follow it."
+-->
+
+---
+
+id: qfai-configure
+title: QFAI Configure (Tune qfai.config.yaml)
+description: "Analyze the repository and tune qfai.config.yaml (testFileGlobs, exclude globs)."
+argument-hint: "[--auto]"
+allowed-tools: [Read, Glob, Write, TodoWrite, Task]
+roles: [DevOpsCIEngineer, QAEngineer, CodeReviewer, Planner]
+mode: evidence-focused
+
+---
+
+# /qfai-configure - Configure QFAI for this repository
+
+## Purpose
+
+Analyze the repository and update `qfai.config.yaml` so QFAI traceability checks (especially SC->Test) are actionable without manual tuning.
+
+## Success Criteria (Definition of Done)
+
+- `qfai.config.yaml` is updated with a **minimal diff** focused on traceability globs.
+- `validation.traceability.testFileGlobs` reflects the real test layout.
+- `validation.traceability.testFileExcludeGlobs` is added only when needed.
+- A validation checklist with evidence (sample matched files) is produced.
+
+## Non-Negotiable Principles (QFAI Articles)
+
+These principles are inspired by "constitution / articles" patterns used by other agent frameworks, but tailored to QFAI.
+
+1. **SDD First (Specification is the source of truth)**  
+   If there is a conflict between code and spec, treat the spec as authoritative and either (a) fix code or (b) raise an explicit Open Question to change the spec.
+
+2. **Traceability is mandatory**  
+   Every meaningful change must be traceable: **Require -> Spec -> Scenario -> Tests -> Code -> Verification evidence**.
+
+3. **Evidence over confidence**  
+   Prefer observable proof (logs, commands, file diffs, test results). If you cannot verify, say so and record it.
+
+4. **Minimize scope, but never hide gaps**  
+   Keep changes minimal, but do not "paper over" missing decisions. If something blocks correctness, stop and ask.
+
+5. **Quality gates are the decision mechanism**  
+   Use tests/lint/typecheck/build/pack verification (whatever the repo defines) as the primary guardrail. Fix until PASS.
+
+6. **Make it runnable**  
+   Outputs must be executable in terminal/CI. Provide copy-paste commands.
+
+7. **User time is expensive**  
+   Ask only the questions that are truly blocking. Everything else: make reasonable assumptions and label them clearly.
+
+## Absolute Rule - Output Language
+
+**All outputs MUST be written in the user's working language for this session.**
+
+- If the user writes in Japanese, output Japanese.
+- If the user writes in English, output English.
+- If the user mixes languages, prefer the dominant language unless explicitly instructed otherwise.  
+  This rule overrides all other stylistic preferences.
+
+## Multi-Role Orchestration (Subagents)
+
+This workflow assumes the environment _may_ support subagents (e.g., Claude Code "Task" tool) or may not.
+
+### If subagents are supported
+
+Delegate to multiple roles and then merge the results. Use a "real-world workflow" order:
+
+- Facilitator -> Interviewer -> Requirements Analyst -> Planner -> Architect -> (Contract Designer) -> Test Engineer -> QA Engineer -> Code Reviewer -> DevOps/CI Engineer
+
+**Pseudo-invocation pattern** (adjust to your tool):
+
+```text
+Task(
+  subagent_type="planner",
+  description="Analyze repo and propose testFileGlobs",
+  prompt="Context: ...\nGoal: Tune qfai.config.yaml\nConstraints: minimal diff\nReturn: globs + evidence"
+)
+```
+
+### If subagents are NOT supported
+
+Simulate roles by running the same sequence yourself:
+
+- Write a short "role output" section per role, then consolidate into the final deliverable(s).
+
+## Constraints
+
+- Only update `qfai.config.yaml` unless explicitly asked.
+- Do **not** modify tests or source code.
+- Avoid overly broad globs (e.g., `**/*`).
+- Exclude generated/output directories (`node_modules`, `.git`, `.qfai`, `dist`, `build`, `coverage`, `.next`, `out`, etc.).
+
+## Step 0 - Load Context (always)
+
+1. Read relevant **project steering** (if present):
+   - `.qfai/assistant/steering/structure.md`
+   - `.qfai/assistant/steering/tech.md`
+   - `.qfai/assistant/steering/product.md`
+   - any additional files under `.qfai/assistant/steering/`
+
+2. Read **project constitution / instructions** (if present):
+   - `.qfai/assistant/instructions/constitution.md`
+   - `.qfai/assistant/instructions/workflow.md` (or equivalent)
+
+3. Inspect repo conventions:
+   - package manager (pnpm/npm/yarn), test runner, lint/typecheck scripts, CI definitions
+   - existing test patterns (unit/integration/e2e)
+
+## Step 0 - Project Analysis (mandatory)
+
+Before editing config, **thoroughly analyze the current project**:
+
+- background and goals
+- directory structure and conventions
+- chosen technologies and versions (runtime, package manager, test runner)
+- test locations (unit/integration/e2e)
+- existing test naming rules (`*.test.*`, `*.spec.*`, `*_test.*`, etc.)
+
+If analysis cannot be performed (missing access), clearly state what could not be verified and proceed with minimal-risk assumptions.
+
+## Step 1 - Identify test frameworks and locations
+
+1. Inspect `package.json` and config files (e.g., `vitest.config.*`, `jest.config.*`, `playwright.config.*`, `pytest.ini`, `go.mod`).
+2. Enumerate directories that contain tests (e.g., `tests/`, `src/`, `e2e/`, `integration/`).
+3. Note naming rules and extensions that indicate test files.
+
+## Step 2 - Propose glob patterns
+
+Provide 3-10 **include globs** that cover all known test locations:
+
+- Prefer explicit patterns (e.g., `src/**/*.test.ts`, `tests/**/*.spec.ts`).
+- Include src-colocated tests if they exist.
+
+Provide **exclude globs** only when necessary (beyond the default exclusions).
+
+## Step 3 - Update `qfai.config.yaml` (minimal diff)
+
+Edit:
+
+- `validation.traceability.testFileGlobs`
+- `validation.traceability.testFileExcludeGlobs` (only if needed)
+
+Keep all other config keys unchanged.
+
+## Step 4 - Evidence sampling
+
+Sample 5-15 actual test files that match the proposed globs.
+
+- If zero matches exist, stop and ask for clarification.
+- If some directories are ambiguous, list them as Open Questions.
+
+## Checkpoints
+
+- [ ] Repository analysis completed (frameworks, test layout, naming rules).
+- [ ] Proposed include/exclude globs with rationale.
+- [ ] `qfai.config.yaml` updated (minimal diff).
+- [ ] Evidence: sample matched files listed.
+
+## Output
+
+Provide:
+
+1. Updated `qfai.config.yaml` (diff or full file, as appropriate).
+2. A short summary of changes and rationale.
+3. Validation checklist with sampled files.
+4. Open questions (blocking vs non-blocking).
+
+Suggest next step: `/qfai-require` (or `/qfai-discuss` if requirements are not ready).

package/assets/init/root/.claude/commands/qfai-configure.md

@@ -0,0 +1,14 @@
+---
+description: "QFAI: Configure qfai.config.yaml based on the repository"
+argument-hint: "[optional notes]"
+---
+
+Follow the canonical QFAI prompt exactly:
+@.qfai/assistant/prompts/qfai-configure.md
+
+Follow the DoD/Checkpoints in the prompt.
+Use the repository as the source of truth.
+
+Additional user notes: $ARGUMENTS
+
+Critical: output must match the user's language.

package/assets/init/root/.claude/commands/qfai-discuss.md

@@ -0,0 +1,14 @@
+---
+description: "QFAI: Discuss an idea and clarify requirements"
+argument-hint: "[optional notes]"
+---
+
+Follow the canonical QFAI prompt exactly:
+@.qfai/assistant/prompts/qfai-discuss.md
+
+Follow the DoD/Checkpoints in the prompt.
+Use the repository as the source of truth.
+
+Additional user notes: $ARGUMENTS
+
+Critical: output must match the user's language.

package/assets/init/root/.claude/commands/qfai-implement.md

@@ -0,0 +1,14 @@
+---
+description: "QFAI: Implement code changes with tests"
+argument-hint: "[optional notes]"
+---
+
+Follow the canonical QFAI prompt exactly:
+@.qfai/assistant/prompts/qfai-implement.md
+
+Follow the DoD/Checkpoints in the prompt.
+Use the repository as the source of truth.
+
+Additional user notes: $ARGUMENTS
+
+Critical: output must match the user's language.

package/assets/init/root/.claude/commands/qfai-require.md

@@ -0,0 +1,14 @@
+---
+description: "QFAI: Create requirements artifacts"
+argument-hint: "[optional notes]"
+---
+
+Follow the canonical QFAI prompt exactly:
+@.qfai/assistant/prompts/qfai-require.md
+
+Follow the DoD/Checkpoints in the prompt.
+Use the repository as the source of truth.
+
+Additional user notes: $ARGUMENTS
+
+Critical: output must match the user's language.

package/assets/init/root/.claude/commands/qfai-scenario-test.md

@@ -0,0 +1,14 @@
+---
+description: "QFAI: Implement acceptance tests from scenarios"
+argument-hint: "[optional notes]"
+---
+
+Follow the canonical QFAI prompt exactly:
+@.qfai/assistant/prompts/qfai-scenario-test.md
+
+Follow the DoD/Checkpoints in the prompt.
+Use the repository as the source of truth.
+
+Additional user notes: $ARGUMENTS
+
+Critical: output must match the user's language.

package/assets/init/root/.claude/commands/qfai-spec.md

@@ -0,0 +1,14 @@
+---
+description: "QFAI: Create specs, contracts, and scenarios"
+argument-hint: "[optional notes]"
+---
+
+Follow the canonical QFAI prompt exactly:
+@.qfai/assistant/prompts/qfai-spec.md
+
+Follow the DoD/Checkpoints in the prompt.
+Use the repository as the source of truth.
+
+Additional user notes: $ARGUMENTS
+
+Critical: output must match the user's language.

package/assets/init/root/.claude/commands/qfai-unit-test.md

@@ -0,0 +1,14 @@
+---
+description: "QFAI: Implement unit tests from specs/scenarios"
+argument-hint: "[optional notes]"
+---
+
+Follow the canonical QFAI prompt exactly:
+@.qfai/assistant/prompts/qfai-unit-test.md
+
+Follow the DoD/Checkpoints in the prompt.
+Use the repository as the source of truth.
+
+Additional user notes: $ARGUMENTS
+
+Critical: output must match the user's language.

package/assets/init/root/.claude/commands/qfai-verify.md

@@ -0,0 +1,14 @@
+---
+description: "QFAI: Run quality gates and produce evidence"
+argument-hint: "[optional notes]"
+---
+
+Follow the canonical QFAI prompt exactly:
+@.qfai/assistant/prompts/qfai-verify.md
+
+Follow the DoD/Checkpoints in the prompt.
+Use the repository as the source of truth.
+
+Additional user notes: $ARGUMENTS
+
+Critical: output must match the user's language.

package/assets/init/root/.codex/README.md

@@ -0,0 +1,16 @@
+# QFAI Codex skills
+
+This directory provides thin Codex skill wrappers for QFAI prompts.
+
+## Canonical prompts
+
+The source of truth is always the prompt body under:
+
+- .qfai/assistant/prompts/
+
+If there is any mismatch, the canonical `.qfai` prompt wins.
+
+## Usage
+
+In Codex CLI, select a skill by name (e.g., `qfai-configure`) and provide your request.
+All outputs must match the user's language.

package/assets/init/root/.codex/skills/qfai-configure/SKILL.md

@@ -0,0 +1,18 @@
+---
+name: qfai-configure
+description: QFAI: Configure qfai.config.yaml based on the repository
+---
+
+This skill is a thin wrapper that forwards to the canonical QFAI prompt in this repository:
+
+- .qfai/assistant/prompts/qfai-configure.md
+
+How to invoke (Codex CLI):
+
+- Select the `qfai-configure` skill, or reference it by name and provide your request.
+
+Instructions:
+
+1. Read the prompt above and follow it precisely.
+2. Use the repository as the source of truth (tools, frameworks, directory structure).
+3. Ensure all outputs match the user's language.

package/assets/init/root/.codex/skills/qfai-discuss/SKILL.md

@@ -0,0 +1,18 @@
+---
+name: qfai-discuss
+description: QFAI: Discuss an idea and clarify requirements
+---
+
+This skill is a thin wrapper that forwards to the canonical QFAI prompt in this repository:
+
+- .qfai/assistant/prompts/qfai-discuss.md
+
+How to invoke (Codex CLI):
+
+- Select the `qfai-discuss` skill, or reference it by name and provide your request.
+
+Instructions:
+
+1. Read the prompt above and follow it precisely.
+2. Use the repository as the source of truth (tools, frameworks, directory structure).
+3. Ensure all outputs match the user's language.

package/assets/init/root/.codex/skills/qfai-implement/SKILL.md

@@ -0,0 +1,18 @@
+---
+name: qfai-implement
+description: QFAI: Implement code changes with tests
+---
+
+This skill is a thin wrapper that forwards to the canonical QFAI prompt in this repository:
+
+- .qfai/assistant/prompts/qfai-implement.md
+
+How to invoke (Codex CLI):
+
+- Select the `qfai-implement` skill, or reference it by name and provide your request.
+
+Instructions:
+
+1. Read the prompt above and follow it precisely.
+2. Use the repository as the source of truth (tools, frameworks, directory structure).
+3. Ensure all outputs match the user's language.

package/assets/init/root/.codex/skills/qfai-require/SKILL.md

@@ -0,0 +1,18 @@
+---
+name: qfai-require
+description: QFAI: Create requirements artifacts
+---
+
+This skill is a thin wrapper that forwards to the canonical QFAI prompt in this repository:
+
+- .qfai/assistant/prompts/qfai-require.md
+
+How to invoke (Codex CLI):
+
+- Select the `qfai-require` skill, or reference it by name and provide your request.
+
+Instructions:
+
+1. Read the prompt above and follow it precisely.
+2. Use the repository as the source of truth (tools, frameworks, directory structure).
+3. Ensure all outputs match the user's language.

package/assets/init/root/.codex/skills/qfai-scenario-test/SKILL.md

@@ -0,0 +1,18 @@
+---
+name: qfai-scenario-test
+description: QFAI: Implement acceptance tests from scenarios
+---
+
+This skill is a thin wrapper that forwards to the canonical QFAI prompt in this repository:
+
+- .qfai/assistant/prompts/qfai-scenario-test.md
+
+How to invoke (Codex CLI):
+
+- Select the `qfai-scenario-test` skill, or reference it by name and provide your request.
+
+Instructions:
+
+1. Read the prompt above and follow it precisely.
+2. Use the repository as the source of truth (tools, frameworks, directory structure).
+3. Ensure all outputs match the user's language.

package/assets/init/root/.codex/skills/qfai-spec/SKILL.md

@@ -0,0 +1,18 @@
+---
+name: qfai-spec
+description: QFAI: Create specs, contracts, and scenarios
+---
+
+This skill is a thin wrapper that forwards to the canonical QFAI prompt in this repository:
+
+- .qfai/assistant/prompts/qfai-spec.md
+
+How to invoke (Codex CLI):
+
+- Select the `qfai-spec` skill, or reference it by name and provide your request.
+
+Instructions:
+
+1. Read the prompt above and follow it precisely.
+2. Use the repository as the source of truth (tools, frameworks, directory structure).
+3. Ensure all outputs match the user's language.

package/assets/init/root/.codex/skills/qfai-unit-test/SKILL.md

@@ -0,0 +1,18 @@
+---
+name: qfai-unit-test
+description: QFAI: Implement unit tests from specs/scenarios
+---
+
+This skill is a thin wrapper that forwards to the canonical QFAI prompt in this repository:
+
+- .qfai/assistant/prompts/qfai-unit-test.md
+
+How to invoke (Codex CLI):
+
+- Select the `qfai-unit-test` skill, or reference it by name and provide your request.
+
+Instructions:
+
+1. Read the prompt above and follow it precisely.
+2. Use the repository as the source of truth (tools, frameworks, directory structure).
+3. Ensure all outputs match the user's language.

package/assets/init/root/.codex/skills/qfai-verify/SKILL.md

@@ -0,0 +1,18 @@
+---
+name: qfai-verify
+description: QFAI: Run quality gates and produce evidence
+---
+
+This skill is a thin wrapper that forwards to the canonical QFAI prompt in this repository:
+
+- .qfai/assistant/prompts/qfai-verify.md
+
+How to invoke (Codex CLI):
+
+- Select the `qfai-verify` skill, or reference it by name and provide your request.
+
+Instructions:
+
+1. Read the prompt above and follow it precisely.
+2. Use the repository as the source of truth (tools, frameworks, directory structure).
+3. Ensure all outputs match the user's language.

package/assets/init/root/.github/copilot-instructions.md

@@ -0,0 +1,14 @@
+# QFAI repository instructions (Copilot)
+
+This repository uses QFAI (Quality-First AI) to improve the quality and consistency of AI-assisted development.
+
+## Golden rules
+
+- Always match the user’s language in your outputs.
+- Treat `.qfai/` as the canonical source of truth for the QFAI workflow:
+  - Prompts: `.qfai/assistant/prompts/`
+  - Instructions: `.qfai/assistant/instructions/`
+  - Project steering: `.qfai/assistant/steering/`
+- When asked to perform QFAI workflow tasks, prefer using the QFAI prompt wrappers in `.github/prompts/` (e.g., `/qfai-spec`) which forward to the canonical prompts.
+- Do not invent repository structure, tools, or frameworks. Inspect the repo first and align with what is already used.
+- Keep changes minimal and targeted. Update tests and docs when behavior changes.

package/assets/init/root/.github/prompts/qfai-configure.prompt.md

@@ -0,0 +1,17 @@
+---
+agent: "agent"
+description: "QFAI: Configure qfai.config.yaml based on the repository"
+---
+
+You are operating in a repository that uses QFAI.
+
+1. Open and follow the canonical QFAI prompt:
+
+- .qfai/assistant/prompts/qfai-configure.md
+
+2. Use the repository as the source of truth (tools, frameworks, directory structure).
+3. Ask the user for missing inputs only when necessary.
+4. Do not modify files not required by the canonical prompt.
+5. All outputs must match the user's language.
+
+User notes: ${input:notes:Optional}

package/assets/init/root/.github/prompts/qfai-discuss.prompt.md

@@ -0,0 +1,17 @@
+---
+agent: "agent"
+description: "QFAI: Discuss an idea and clarify requirements"
+---
+
+You are operating in a repository that uses QFAI.
+
+1. Open and follow the canonical QFAI prompt:
+
+- .qfai/assistant/prompts/qfai-discuss.md
+
+2. Use the repository as the source of truth (tools, frameworks, directory structure).
+3. Ask the user for missing inputs only when necessary.
+4. Do not modify files not required by the canonical prompt.
+5. All outputs must match the user's language.
+
+User notes: ${input:notes:Optional}

package/assets/init/root/.github/prompts/qfai-implement.prompt.md

@@ -0,0 +1,17 @@
+---
+agent: "agent"
+description: "QFAI: Implement code changes with tests"
+---
+
+You are operating in a repository that uses QFAI.
+
+1. Open and follow the canonical QFAI prompt:
+
+- .qfai/assistant/prompts/qfai-implement.md
+
+2. Use the repository as the source of truth (tools, frameworks, directory structure).
+3. Ask the user for missing inputs only when necessary.
+4. Do not modify files not required by the canonical prompt.
+5. All outputs must match the user's language.
+
+User notes: ${input:notes:Optional}

package/assets/init/root/.github/prompts/qfai-require.prompt.md

@@ -0,0 +1,17 @@
+---
+agent: "agent"
+description: "QFAI: Create requirements artifacts"
+---
+
+You are operating in a repository that uses QFAI.
+
+1. Open and follow the canonical QFAI prompt:
+
+- .qfai/assistant/prompts/qfai-require.md
+
+2. Use the repository as the source of truth (tools, frameworks, directory structure).
+3. Ask the user for missing inputs only when necessary.
+4. Do not modify files not required by the canonical prompt.
+5. All outputs must match the user's language.
+
+User notes: ${input:notes:Optional}

package/assets/init/root/.github/prompts/qfai-scenario-test.prompt.md

@@ -0,0 +1,17 @@
+---
+agent: "agent"
+description: "QFAI: Implement acceptance tests from scenarios"
+---
+
+You are operating in a repository that uses QFAI.
+
+1. Open and follow the canonical QFAI prompt:
+
+- .qfai/assistant/prompts/qfai-scenario-test.md
+
+2. Use the repository as the source of truth (tools, frameworks, directory structure).
+3. Ask the user for missing inputs only when necessary.
+4. Do not modify files not required by the canonical prompt.
+5. All outputs must match the user's language.
+
+User notes: ${input:notes:Optional}

package/assets/init/root/.github/prompts/qfai-spec.prompt.md

@@ -0,0 +1,17 @@
+---
+agent: "agent"
+description: "QFAI: Create specs, contracts, and scenarios"
+---
+
+You are operating in a repository that uses QFAI.
+
+1. Open and follow the canonical QFAI prompt:
+
+- .qfai/assistant/prompts/qfai-spec.md
+
+2. Use the repository as the source of truth (tools, frameworks, directory structure).
+3. Ask the user for missing inputs only when necessary.
+4. Do not modify files not required by the canonical prompt.
+5. All outputs must match the user's language.
+
+User notes: ${input:notes:Optional}

package/assets/init/root/.github/prompts/qfai-unit-test.prompt.md

@@ -0,0 +1,17 @@
+---
+agent: "agent"
+description: "QFAI: Implement unit tests from specs/scenarios"
+---
+
+You are operating in a repository that uses QFAI.
+
+1. Open and follow the canonical QFAI prompt:
+
+- .qfai/assistant/prompts/qfai-unit-test.md
+
+2. Use the repository as the source of truth (tools, frameworks, directory structure).
+3. Ask the user for missing inputs only when necessary.
+4. Do not modify files not required by the canonical prompt.
+5. All outputs must match the user's language.
+
+User notes: ${input:notes:Optional}

package/assets/init/root/.github/prompts/qfai-verify.prompt.md

@@ -0,0 +1,17 @@
+---
+agent: "agent"
+description: "QFAI: Run quality gates and produce evidence"
+---
+
+You are operating in a repository that uses QFAI.
+
+1. Open and follow the canonical QFAI prompt:
+
+- .qfai/assistant/prompts/qfai-verify.md
+
+2. Use the repository as the source of truth (tools, frameworks, directory structure).
+3. Ask the user for missing inputs only when necessary.
+4. Do not modify files not required by the canonical prompt.
+5. All outputs must match the user's language.
+
+User notes: ${input:notes:Optional}

package/dist/cli/index.cjs

@@ -1075,8 +1075,8 @@ var import_promises7 = require("fs/promises");
 var import_node_path9 = __toESM(require("path"), 1);
 var import_node_url2 = require("url");
 async function resolveToolVersion() {
-  if ("1.0.6".length > 0) {
-    return "1.0.6";
+  if ("1.0.7".length > 0) {
+    return "1.0.7";
   }
   try {
     const packagePath = resolvePackageJsonPath();
@@ -1658,16 +1658,22 @@ async function runInit(options) {
     [...rootResult.copied, ...qfaiResult.copied, ...promptsResult.copied],
     [...rootResult.skipped, ...qfaiResult.skipped, ...promptsResult.skipped],
     options.dryRun,
-    "init"
+    "init",
+    destRoot
   );
 }
-function report(copied, skipped, dryRun, label) {
+function report(copied, skipped, dryRun, label, baseDir) {
   info(`qfai ${label}: ${dryRun ? "dry-run" : "done"}`);
   if (copied.length > 0) {
     info(`  created: ${copied.length}`);
   }
   if (skipped.length > 0) {
     info(`  skipped: ${skipped.length}`);
+    info("  skipped paths:");
+    for (const skippedPath of skipped) {
+      const relative = import_node_path13.default.relative(baseDir, skippedPath);
+      info(`    - ${relative}`);
+    }
   }
 }