abelworkflow 0.9.2 → 1.0.0-rc.1

package/{commands → lib/templates/workflow/commands}/abel-diagnose.md

@@ -12,7 +12,7 @@ argument-hint: <problem-description>
 **Guardrails**
 - Root cause first; never fix symptoms only
 - Verify root cause hypothesis with evidence before fix
-- Confidence gate: ≥90% before applying fixes
+- Only fixes with evidence-verified root cause may be applied
 - Every fix must include a regression test
 - Keep changes minimal and scoped
 - If verification fails, rollback and iterate
@@ -32,9 +32,9 @@ argument-hint: <problem-description>
 **Steps**
 1. Parse input, infer scope, and split into issue list (single or multiple).
 2. For each issue in parallel: collect logs/traces and locate code via the configured codebase retrieval policy.
-3. For each issue in parallel: perform root cause analysis; use `/sequential-think` for multi-component chains.
+3. For each issue in parallel: perform root cause analysis; for multi-component chains, decompose the failure chain step by step with evidence.
 4. Build dependency/conflict graph across issues and compute safe fix order.
-5. Run `/confidence-check` per issue; only issues with score ≥90% can move to fix generation.
+5. Verify each issue's root cause against collected evidence; only issues with a verified root cause can move to fix generation.
 6. Spawn one subagent per READY issue to generate `unified diff patch` and regression test with minimal scoped context.
 7. Main agent reviews/merges subagent outputs by dependency order and outputs one batch report with all issue statuses and patches.
 8. Apply merged patches strictly sequentially by dependency order.
@@ -42,13 +42,13 @@ argument-hint: <problem-description>
 
 **Batch Output**
 ```text
-## /oc:diagnose Batch Report
+## /abel-diagnose Batch Report
 
 ### Batch Summary
 Total: {n} | ReadyToFix: {n_ready} | Blocked: {n_blocked}
 
 ### Issue Results
-- [{id}] Classification: {category}/{severity} | Root Cause: {summary} | Confidence: {score} | Subagent: {agent_id|none} | Status: {READY|BLOCKED}
+- [{id}] Classification: {category}/{severity} | Root Cause: {summary} | Verified: {yes|no} | Subagent: {agent_id|none} | Status: {READY|BLOCKED}
 
 ### Patch Queue (dependency order)
 1. [{id}] [subagent:{agent_id}] {file_list}

package/{commands → lib/templates/workflow/commands}/abel-implement.md

@@ -44,9 +44,6 @@ argument-hint: [change_name]
 
 ```
 ┌─────────────────────────────────────────────────────────┐
-│ Step 0: Pre-Check                                       │
-│   └─ /confidence-check → require ≥90% to proceed        │
-├─────────────────────────────────────────────────────────┤
 │ Step 1: 🔴 Red Phase - Generate Failing Test            │
 │   ├─ Analyze task → determine test type                 │
 │   │   ├─ Backend → pytest/jest                          │
@@ -101,17 +98,15 @@ argument-hint: [change_name]
 13. Run all tests → MUST ALL PASS.
 14. If any test fails → analyze root cause, fix or rollback.
 15. Perform final side-effect review.
-16. Run `openspec archive <change_name>` or `/opsx:archive`.
+16. Report that the change is ready for archive; do not archive until the user explicitly authorizes `/opsx:archive`.
 
 **TDD Output Format**
 
 ```
-## /oc:implementation (TDD Mode)
+## /abel-implement (TDD Mode)
 
 ### Task 1/N: {task_description}
 
-📋 Confidence Check: {score}% {status}
-
 🔴 Red Phase
 ├─ Generated: tests/{test_file}
 ├─ Run: {test_command}
@@ -150,7 +145,7 @@ Frontend Review
 ✓ Reviews complete
 ├─ Applied: {refactoring_summary}
 ├─ Tests: {count} passed ✓
-└─ Ready for archive
+└─ Ready for user-authorized archive
 
 ✓ Implementation complete
 ```

package/{commands → lib/templates/workflow/commands}/abel-init.md

@@ -18,7 +18,7 @@ tags: [openspec, init, setup]
 4. Run `openspec init` (or `openspec update` for existing projects).
 5. {{AUGMENT_CONTEXT_ENGINE_VALIDATION}}
 6. Verify required skills:
-   - Skills: `/dev-browser` `/sequential-think` `/context7-auto-research` `/grok-search` `/confidence-check`
+   - Skills: `/dev-browser` `/context7-auto-research` `/grok-search`
 7. Output summary with ✓/✗:
    - OpenSpec installation
    - Project initialization

package/{commands → lib/templates/workflow/commands}/abel-plan.md

@@ -25,14 +25,8 @@ argument-hint: [change_name]
    - Check `openspec status --change <change_name>` for artifact completion
    - Use `openspec instructions specs --change <change_name>` for specs guidance
 
-3. **Implementation Analysis**: Invoke skills to perform systematic analysis to derive a plan:
+3. **Implementation Analysis**: Perform systematic analysis to derive a plan. If the proposal has 3+ interconnected requirements, first break it down into components, identify dependencies, evaluate architectural trade-offs, and surface potential conflicts. Then invoke `/context7-auto-research` to validate framework/library choices:
    ```
-   # First, invoke /sequential-think skill for systematic analysis if proposal has 3+ interconnected requirements
-
-   /sequential-think: "Analyze change <change_name> systematically: Break down into components, identify dependencies, evaluate architectural trade-offs, and surface potential conflicts."
-   
-   # Then invoke /context7-auto-research skill to validate framework/library choices
-
    /context7-auto-research: "For each technology mentioned in change <change_name>, retrieve official documentation patterns and best practices."
    ```
    Produce a consolidated, constraint-complete plan and list any missing constraints as questions to the user.

package/{commands → lib/templates/workflow/commands}/abel-research.md

@@ -77,7 +77,7 @@ All explore subagents MUST return valid JSON using this schema:
   - Clear scope
   - self-contained with independent output
   - Required output template (from Phase 4)
-  - If boundary involves 3+ interconnected components, invoke `/sequential-think` skill
+  - If boundary involves 3+ interconnected components, require explicit step-by-step dependency analysis
   - Clear success criteria: complete analysis of assigned boundary
 
 

package/{.gitignore → lib/templates/workflow/gitignore.template}

@@ -14,5 +14,3 @@ skills/dev-browser/.cache/
 .claude/
 .codex/
 *pycache*/
-openspec/
-package-lock.json

package/lib/tools/cli-installer.mjs

@@ -0,0 +1,277 @@
+import { spawn, spawnSync } from "node:child_process";
+import { join } from "node:path";
+import * as p from "@clack/prompts";
+import c from "picocolors";
+import { defaultPaths, getPlatform, isWindows } from "../paths.mjs";
+
+const { homeDir: home } = defaultPaths;
+
+function getRunCommandSpawnOptions(platform = getPlatform()) {
+  return { stdio: "inherit", shell: platform === "win32" };
+}
+
+function getCommandPath(command) {
+  const checker = isWindows() ? "where" : "which";
+  const result = spawnSync(checker, [command], { encoding: "utf8" });
+  if (result.status !== 0) {
+    return undefined;
+  }
+  return result.stdout
+    .split(/\r?\n/u)
+    .map((line) => line.trim())
+    .find(Boolean);
+}
+
+function commandExists(command) {
+  return Boolean(getCommandPath(command));
+}
+
+function readCommandOutput(command, args) {
+  const result = spawnSync(command, args, {
+    encoding: "utf8",
+    shell: isWindows(),
+    stdio: ["ignore", "pipe", "ignore"]
+  });
+  if (result.status !== 0) {
+    return undefined;
+  }
+  const outputValue = result.stdout.trim();
+  return outputValue || undefined;
+}
+
+async function runCommand(command, args) {
+  await new Promise((resolvePromise, rejectPromise) => {
+    const child = spawn(command, args, getRunCommandSpawnOptions(getPlatform()));
+    child.on("error", rejectPromise);
+    child.on("close", (code) => {
+      if (code === 0) {
+        resolvePromise();
+        return;
+      }
+      rejectPromise(new Error(`${command} ${args.join(" ")} exited with code ${code}`));
+    });
+  });
+}
+
+function normalizeInstallPath(value) {
+  if (!value) {
+    return "";
+  }
+  return value.replace(/\\/gu, "/").replace(/\/+$/u, "").toLowerCase();
+}
+
+function installPathIsWithin(path, parentPath) {
+  const normalizedPath = normalizeInstallPath(path);
+  const normalizedParent = normalizeInstallPath(parentPath);
+  return Boolean(normalizedPath && normalizedParent)
+    && (normalizedPath === normalizedParent || normalizedPath.startsWith(`${normalizedParent}/`));
+}
+
+function getNpmGlobalBinDirs(npmGlobalPrefix, platform = getPlatform()) {
+  if (!npmGlobalPrefix) {
+    return [];
+  }
+  return platform === "win32" ? [npmGlobalPrefix] : [join(npmGlobalPrefix, "bin")];
+}
+
+function inferPackageManagerFromCommandPath(commandPath, {
+  bunGlobalBinDir,
+  npmGlobalPrefix,
+  platform = getPlatform()
+} = {}) {
+  if (installPathIsWithin(commandPath, bunGlobalBinDir)) {
+    return "bun";
+  }
+  if (getNpmGlobalBinDirs(npmGlobalPrefix, platform)
+    .some((binDir) => installPathIsWithin(commandPath, binDir))) {
+    return "npm";
+  }
+  return null;
+}
+
+function chooseCliInstallPackageManager({
+  commandPath,
+  availablePackageManagers = [],
+  bunGlobalBinDir,
+  npmGlobalPrefix,
+  platform = getPlatform(),
+  nodeAvailable = true,
+  supportedPackageManagers = ["bun", "npm"]
+} = {}) {
+  const supported = new Set(supportedPackageManagers);
+  const available = new Set(availablePackageManagers.filter((packageManager) => {
+    if (!supported.has(packageManager)) {
+      return false;
+    }
+    return packageManager !== "bun" || nodeAvailable;
+  }));
+  const bunBlockedByMissingNode = !nodeAvailable
+    && supported.has("bun")
+    && availablePackageManagers.includes("bun");
+  const existingPackageManager = inferPackageManagerFromCommandPath(commandPath, {
+    bunGlobalBinDir,
+    npmGlobalPrefix,
+    platform
+  });
+
+  if (existingPackageManager && available.has(existingPackageManager)) {
+    return { packageManager: existingPackageManager, source: "existing" };
+  }
+  for (const packageManager of ["bun", "npm"]) {
+    if (available.has(packageManager)) {
+      return { packageManager, source: "available" };
+    }
+  }
+  return {
+    packageManager: null,
+    source: bunBlockedByMissingNode ? "missing-node" : (availablePackageManagers.length > 0 ? "unsupported" : "missing")
+  };
+}
+
+function buildCliToolInstallCommand(packageManager, { packageName, skipScripts = false }) {
+  if (packageManager === "npm") {
+    return {
+      command: "npm",
+      args: [
+        "install",
+        "-g",
+        ...(skipScripts ? ["--ignore-scripts"] : []),
+        packageName,
+        "--force"
+      ]
+    };
+  }
+  if (packageManager === "bun") {
+    return {
+      command: "bun",
+      args: [
+        "install",
+        "-g",
+        ...(skipScripts ? ["--ignore-scripts"] : []),
+        packageName
+      ]
+    };
+  }
+  throw new Error(`Unsupported package manager: ${packageManager}`);
+}
+
+function getPackageManagerInstallHelp(platform = getPlatform()) {
+  const platformLabel = {
+    darwin: "macOS",
+    win32: "Windows",
+    linux: "Linux"
+  }[platform] || platform;
+  return {
+    platformLabel,
+    mainlandUrl: "https://npmmirror.com/mirrors/node/",
+    officialUrl: "https://nodejs.org/en/download/"
+  };
+}
+
+function getAvailablePackageManagers() {
+  return ["bun", "npm"].filter((packageManager) => commandExists(packageManager));
+}
+
+function getBunGlobalBinDir(availablePackageManagers = getAvailablePackageManagers()) {
+  if (!availablePackageManagers.includes("bun")) {
+    return undefined;
+  }
+  return readCommandOutput("bun", ["pm", "bin", "-g"]) || join(home, ".bun", "bin");
+}
+
+function getNpmGlobalPrefix(availablePackageManagers = getAvailablePackageManagers()) {
+  if (!availablePackageManagers.includes("npm")) {
+    return undefined;
+  }
+  return readCommandOutput("npm", ["prefix", "-g"]);
+}
+
+async function installCliTool(tool, { confirmOrCancel }) {
+  const toolConfig = {
+    claude: {
+      label: "Claude Code",
+      command: "claude",
+      packageName: "@anthropic-ai/claude-code",
+      supportedPackageManagers: ["npm"],
+      installRequirement: "Claude Code 安装需要执行 postinstall；Bun 默认会阻止该脚本，因此需使用 npm。"
+    },
+    codex: {
+      label: "Codex",
+      command: "codex",
+      packageName: "@openai/codex"
+    },
+    pi: {
+      label: "Pi",
+      command: "pi",
+      packageName: "@earendil-works/pi-coding-agent",
+      skipScripts: true
+    }
+  }[tool];
+
+  if (!toolConfig) {
+    throw new Error(`Unsupported tool: ${tool}`);
+  }
+
+  const commandPath = getCommandPath(toolConfig.command);
+  const installed = Boolean(commandPath);
+  const availablePackageManagers = getAvailablePackageManagers();
+  const packageManagerChoice = chooseCliInstallPackageManager({
+    commandPath,
+    availablePackageManagers,
+    bunGlobalBinDir: getBunGlobalBinDir(availablePackageManagers),
+    npmGlobalPrefix: getNpmGlobalPrefix(availablePackageManagers),
+    platform: getPlatform(),
+    nodeAvailable: commandExists("node"),
+    supportedPackageManagers: toolConfig.supportedPackageManagers
+  });
+
+  if (!packageManagerChoice.packageManager) {
+    const help = getPackageManagerInstallHelp();
+    p.log.warn(`未检测到可用于安装 ${toolConfig.label} 的包管理器。`);
+    if (packageManagerChoice.source === "missing-node") {
+      p.log.message(`${toolConfig.label} 是 Node CLI；使用 Bun 安装前也需要先安装 Node.js。`);
+    }
+    if (toolConfig.installRequirement) {
+      p.log.message(toolConfig.installRequirement);
+    }
+    p.log.message(`${help.platformLabel} 可先安装 Node.js/npm，再重新运行安装。`);
+    p.log.message(`中国大陆镜像: ${help.mainlandUrl}`);
+    p.log.message(`官方下载页: ${help.officialUrl}`);
+    return;
+  }
+
+  if (installed) {
+    const managerMessage = packageManagerChoice.source === "existing"
+      ? `检测到原安装方式为 ${packageManagerChoice.packageManager}`
+      : `未识别原安装方式，将使用 ${packageManagerChoice.packageManager}`;
+    const shouldUpdate = await confirmOrCancel({
+      message: `${toolConfig.label} 已检测到（${managerMessage}），是否继续安装/更新？`,
+      initialValue: false
+    });
+    if (!shouldUpdate) {
+      p.log.message(`跳过 ${toolConfig.label} 安装。`);
+      return;
+    }
+  }
+
+  const installCommand = buildCliToolInstallCommand(packageManagerChoice.packageManager, toolConfig);
+  const s = p.spinner();
+  s.start(`正在使用 ${packageManagerChoice.packageManager} 安装 ${toolConfig.label}...`);
+  try {
+    await runCommand(installCommand.command, installCommand.args);
+    s.stop(`${toolConfig.label} 安装完成`);
+  } catch (e) {
+    s.cancel(c.red(`${toolConfig.label} 安装失败: ${e.message}`));
+    throw e;
+  }
+}
+
+export {
+  buildCliToolInstallCommand,
+  chooseCliInstallPackageManager,
+  getPackageManagerInstallHelp,
+  getRunCommandSpawnOptions,
+  inferPackageManagerFromCommandPath,
+  installCliTool,
+  commandExists
+};

package/package.json

@@ -1,11 +1,20 @@
 {
   "name": "abelworkflow",
-  "version": "0.9.2",
+  "version": "1.0.0-rc.1",
   "description": "Install AbelWorkflow into ~/.agents and create Claude/Codex symlinks.",
   "type": "module",
   "scripts": {
-    "test": "node --test test/runtime-doc-contracts.test.mjs test/cli-contracts.test.mjs test/codex-config.test.mjs test/pi-auth-precedence.test.mjs test/pi-auth-write.test.mjs test/pi-provider-tls.test.mjs",
-    "test:contracts": "node --test test/runtime-doc-contracts.test.mjs test/cli-contracts.test.mjs"
+    "test": "npm run test:node",
+    "test:node": "node --test test/*.test.mjs",
+    "test:python": "python -m unittest discover -s test",
+    "test:dev-browser": "npm test --prefix skills/dev-browser",
+    "test:contracts": "node --test test/runtime-doc-contracts.test.mjs test/cli-args.test.mjs",
+    "typecheck": "npm run typecheck --prefix skills/dev-browser",
+    "build": "npm run build --prefix skills/dev-browser",
+    "prepack": "npm run build",
+    "check:docs": "node --test test/docs-contracts.test.mjs test/runtime-doc-contracts.test.mjs",
+    "check:package": "node --test test/package-contents.test.mjs",
+    "check": "npm run build && npm run test:node && npm run test:python && npm run test:dev-browser && npm run typecheck && npm run check:docs && npm run check:package"
   },
   "bin": {
     "abelworkflow": "bin/abelworkflow.mjs"
@@ -13,21 +22,45 @@
   "files": [
     "bin",
     "lib",
-    "AGENTS.md",
     "README.md",
-    "commands",
-    "skills",
     "extensions",
-    ".skill-lock.json",
-    ".gitignore"
+    "skills/context7-auto-research/.env.example",
+    "skills/context7-auto-research/SKILL.md",
+    "skills/context7-auto-research/context7-api.cjs",
+    "skills/dev-browser/SKILL.md",
+    "skills/dev-browser/dist",
+    "skills/dev-browser/package-lock.json",
+    "skills/dev-browser/package.json",
+    "skills/dev-browser/references",
+    "skills/git-commit/SKILL.md",
+    "skills/grok-search/.env.example",
+    "skills/grok-search/SKILL.md",
+    "skills/grok-search/defaults.json",
+    "skills/grok-search/gitignore.template",
+    "skills/grok-search/requirements.txt",
+    "skills/grok-search/scripts/_dotenv.py",
+    "skills/grok-search/scripts/groksearch_cli.py",
+    "skills/grok-search/scripts/groksearch_entry.py",
+    "skills/prompt-enhancer/.env.example",
+    "skills/prompt-enhancer/ADVANCED.md",
+    "skills/prompt-enhancer/SKILL.md",
+    "skills/prompt-enhancer/TEMPLATE.md",
+    "skills/prompt-enhancer/requirements.txt",
+    "skills/prompt-enhancer/scripts/_dotenv.py",
+    "skills/prompt-enhancer/scripts/enhance.py",
+    "skills/prompt-enhancer/scripts/prompt_enhancer_entry.py",
+    "skills/time/SKILL.md",
+    "skills/time/scripts/time_cli.py"
   ],
   "engines": {
-    "node": ">=18"
+    "node": ">=22"
   },
+  "packageManager": "npm@10.9.2",
   "license": "MIT",
   "dependencies": {
     "@clack/prompts": "^1.2.0",
     "picocolors": "^1.1.1",
-    "proper-lockfile": "4.1.2"
+    "proper-lockfile": "4.1.2",
+    "smol-toml": "1.7.0"
   }
 }

package/skills/context7-auto-research/SKILL.md

@@ -30,13 +30,13 @@ Common cues:
 
 ## Workflow
 
-1. Run from this skill directory and use `./context7-api.js`.
+1. Run from this skill directory and use `./context7-api.cjs`.
 2. Search with the full user query:
 
 ```bash
 cd skills/context7-auto-research
-node ./context7-api.js --help
-node ./context7-api.js search '<library-name>' - <<'__C7_QUERY__'
+node ./context7-api.cjs --help
+node ./context7-api.cjs search '<library-name>' - <<'__C7_QUERY__'
 <full user query>
 __C7_QUERY__
 ```
@@ -50,7 +50,7 @@ __C7_QUERY__
 4. Fetch focused documentation:
 
 ```bash
-node ./context7-api.js context '<library-id>' - <<'__C7_QUERY__'
+node ./context7-api.cjs context '<library-id>' - <<'__C7_QUERY__'
 <feature name or focused question>
 __C7_QUERY__
 ```
@@ -72,7 +72,7 @@ __C7_QUERY__
 
 - Preferred: `CONTEXT7_API_KEY` environment variable
 - Also supported: `<skill-dir>/.env`
-- CLI help: `node ./context7-api.js --help`
+- CLI help: `node ./context7-api.cjs --help`
 
 ## Notes
 

package/skills/context7-auto-research/{context7-api.js → context7-api.cjs}

@@ -44,12 +44,12 @@ function printErrorResult(commandName, error, exitCode = 1) {
 
 function printUsage() {
   console.error(`Usage:
-  context7-api.js search <libraryName> <query|->
-  context7-api.js context <libraryId> <query|->
+  context7-api.cjs search <libraryName> <query|->
+  context7-api.cjs context <libraryId> <query|->
 
 Examples:
-  node context7-api.js search react "useEffect cleanup"
-  node context7-api.js context /facebook/react -
+  node context7-api.cjs search react "useEffect cleanup"
+  node context7-api.cjs context /facebook/react -
 
 Config:
   CONTEXT7_API_KEY from environment, or .env in the script directory`);
@@ -83,10 +83,7 @@ function loadApiKey() {
     if (key !== 'CONTEXT7_API_KEY') {
       continue;
     }
-    const value = trimmed.slice(separatorIndex + 1).trim();
-    if (value) {
-      return value.replace(/^["']|["']$/g, '');
-    }
+    return trimmed.slice(separatorIndex + 1).trim().replace(/^["']|["']$/g, '');
   }
 
   return null;