levante 0.3.1 → 0.3.4

package/README.md

@@ -173,17 +173,17 @@ Add to your MCP client config (e.g., `claude_desktop_config.json`):
 
 | Tool | Description |
 |------|-------------|
-| `e2e_ai_plan_workflow` | Get ordered step list with prerequisite checks |
-| `e2e_ai_execute_step` | Execute a single pipeline step |
-| `e2e_ai_get_workflow_guide` | Get the full workflow guide |
-| `e2e_ai_scan_codebase` | Scan project for test infrastructure |
-| `e2e_ai_validate_context` | Validate context.md completeness |
-| `e2e_ai_read_agent` | Load an agent prompt by name |
-| `e2e_ai_get_example` | Get example context.md template |
-| `e2e_ai_scan_ast` | Run AST scanner |
-| `e2e_ai_scan_ast_detail` | Drill into routes/components/hooks |
-| `e2e_ai_build_qa_map` | Build and validate QA map |
-| `e2e_ai_read_qa_map` | Load existing QA map |
+| `levante_plan_workflow` | Get ordered step list with prerequisite checks |
+| `levante_execute_step` | Execute a single pipeline step |
+| `levante_get_workflow_guide` | Get the full workflow guide |
+| `levante_scan_codebase` | Scan project for test infrastructure |
+| `levante_validate_context` | Validate context.md completeness |
+| `levante_read_agent` | Load an agent prompt by name |
+| `levante_get_example` | Get example context.md template |
+| `levante_scan_ast` | Run AST scanner |
+| `levante_scan_ast_detail` | Drill into routes/components/hooks |
+| `levante_build_qa_map` | Build and validate QA map |
+| `levante_read_qa_map` | Load existing QA map |
 
 ## Configuration
 

package/agents/0.init-agent.md

@@ -10,7 +10,7 @@ You are a codebase analysis assistant for the levante test automation tool. Your
 
 This agent is designed to be used directly in your AI tool (Claude Code, Cursor, Gemini CLI, etc.). Start a conversation and ask it to generate your project context.
 
-**If the levante MCP server is configured**, call `e2e_ai_scan_codebase` to get scan results, then follow this agent's instructions to produce the context file.
+**If the levante MCP server is configured**, call `levante_scan_codebase` to get scan results, then follow this agent's instructions to produce the context file.
 
 **If no MCP server**, manually explore the codebase: look at test files, fixtures, playwright config, tsconfig paths, and helper modules.
 

package/dist/cli.js

@@ -75308,7 +75308,7 @@ function registerInit(program2) {
     if (!isReInit) {
       console.log(import_picocolors5.default.bold("Next steps:"));
       console.log(`  1. Use the ${import_picocolors5.default.cyan("init-agent")} in your AI tool to generate ${import_picocolors5.default.cyan(`${CONFIG_DIR}/context.md`)}`);
-      console.log(`     (or use the MCP server: ${import_picocolors5.default.cyan("e2e_ai_scan_codebase")} + ${import_picocolors5.default.cyan("e2e_ai_read_agent")})`);
+      console.log(`     (or use the MCP server: ${import_picocolors5.default.cyan("levante_scan_codebase")} + ${import_picocolors5.default.cyan("levante_read_agent")})`);
       console.log(`  2. Review the generated ${import_picocolors5.default.cyan(`${CONFIG_DIR}/context.md`)}`);
       console.log(`  3. Run: ${import_picocolors5.default.cyan("levante run --key PROJ-101")}`);
     } else {

package/dist/mcp.js

@@ -32900,18 +32900,18 @@ NEVER run multiple pipeline steps at once. Each step is a separate job with its
 
 ## Protocol
 
-1. **Plan first.** Call \`e2e_ai_plan_workflow\` with the user's goal. This returns a structured todo list of steps.
+1. **Plan first.** Call \`levante_plan_workflow\` with the user's goal. This returns a structured todo list of steps.
 2. **Check prerequisites.** The plan includes a \`ready\` boolean and \`missingPrerequisites\` array. If \`ready\` is false, show the user what's missing (API keys, config, etc.) and **wait for them to fix it** before proceeding. Do NOT attempt to execute any step while prerequisites are missing.
 3. **Present the plan.** Show the user the ordered step list with descriptions. Ask for confirmation or adjustments before proceeding.
 4. **Execute one step at a time.** For each step in the approved plan:
    a. Tell the user which step you're about to run and why.
-   b. Call \`e2e_ai_execute_step\` with the step name and parameters.
+   b. Call \`levante_execute_step\` with the step name and parameters.
    c. Report the result to the user (success, key output, any warnings).
    d. If the step fails, stop and discuss with the user before continuing.
    e. Move to the next step only after the current one succeeds.
 5. **Use subagents when available.** If your AI platform supports subagents (e.g., Claude Code Agent tool), dispatch each step as a dedicated subagent to preserve context. Each subagent should:
    - Receive only the context it needs (step name, key, relevant file paths)
-   - Call \`e2e_ai_execute_step\` to do its work
+   - Call \`levante_execute_step\` to do its work
    - Return the result to the orchestrator
 
 ## Step Dependencies
@@ -32941,19 +32941,19 @@ The \`record\` step opens a browser and requires user interaction. When the plan
 - **Scanner pipeline**: scan → analyze → push
 - **Single step**: any individual command
 
-Always use \`e2e_ai_plan_workflow\` to determine the right steps — don't guess.
+Always use \`levante_plan_workflow\` to determine the right steps — don't guess.
 
 ## Scanner Analysis (Interactive QA Map)
 
 For deep codebase analysis and QA map generation, use the interactive scanner workflow instead of the CLI pipeline:
 
-1. **Load the protocol.** Call \`e2e_ai_read_agent("scanner-agent")\` — this returns the full interactive protocol.
-2. **Scan.** Call \`e2e_ai_scan_ast()\` to run the AST scanner and get a compact summary.
-3. **Explore.** Use \`e2e_ai_scan_ast_detail()\` to drill into routes, components, hooks, or files.
+1. **Load the protocol.** Call \`levante_read_agent("scanner-agent")\` — this returns the full interactive protocol.
+2. **Scan.** Call \`levante_scan_ast()\` to run the AST scanner and get a compact summary.
+3. **Explore.** Use \`levante_scan_ast_detail()\` to drill into routes, components, hooks, or files.
 4. **Propose & discuss.** Present candidate features to the user, ask clarifying questions.
-5. **Build.** Construct the QA map payload and validate with \`e2e_ai_build_qa_map({ dryRun: true })\`.
-6. **Write.** Once validated and approved, call \`e2e_ai_build_qa_map({ dryRun: false })\` to save.
-7. **Read existing.** Use \`e2e_ai_read_qa_map()\` to load a previously generated QA map for incremental updates.
+5. **Build.** Construct the QA map payload and validate with \`levante_build_qa_map({ dryRun: true })\`.
+6. **Write.** Once validated and approved, call \`levante_build_qa_map({ dryRun: false })\` to save.
+7. **Read existing.** Use \`levante_read_qa_map()\` to load a previously generated QA map for incremental updates.
 
 This approach is preferred over \`scan → analyze\` CLI steps because it allows interactive refinement with the user.
 `.trim();
@@ -33258,7 +33258,7 @@ ${stderr}`,
   }
 }
 var server = new McpServer({ name: "levante", version: "1.5.1" }, { instructions: SERVER_INSTRUCTIONS });
-server.registerTool("e2e_ai_scan_codebase", {
+server.registerTool("levante_scan_codebase", {
   title: "Scan Codebase",
   description: "Scan a project directory for test files, configs, fixtures, path aliases, and sample test content. Use this during project setup or to understand test infrastructure.",
   inputSchema: exports_external.object({
@@ -33271,7 +33271,7 @@ server.registerTool("e2e_ai_scan_codebase", {
     content: [{ type: "text", text: JSON.stringify(scan, null, 2) }]
   };
 });
-server.registerTool("e2e_ai_validate_context", {
+server.registerTool("levante_validate_context", {
   title: "Validate Context",
   description: "Validate that a context markdown file contains all required sections (Application, Test Infrastructure, Feature Methods, Import Conventions, Selector Conventions, Test Structure Template, Utility Patterns).",
   inputSchema: exports_external.object({
@@ -33283,7 +33283,7 @@ server.registerTool("e2e_ai_validate_context", {
     content: [{ type: "text", text: JSON.stringify(result, null, 2) }]
   };
 });
-server.registerTool("e2e_ai_read_agent", {
+server.registerTool("levante_read_agent", {
   title: "Read Agent",
   description: "Read an agent prompt definition by name. Returns the agent system prompt and config. Agents: transcript-agent, scenario-agent, playwright-generator-agent, refactor-agent, self-healing-agent, qa-testcase-agent, feature-analyzer-agent, scenario-planner-agent, scanner-agent, init-agent.",
   inputSchema: exports_external.object({
@@ -33309,7 +33309,7 @@ server.registerTool("e2e_ai_read_agent", {
     };
   }
 });
-server.registerTool("e2e_ai_get_example", {
+server.registerTool("levante_get_example", {
   title: "Get Example Context",
   description: `Returns the full example context markdown file that shows the expected format for ${CONFIG_DIR}/context.md.`,
   inputSchema: exports_external.object({})
@@ -33327,7 +33327,7 @@ server.registerTool("e2e_ai_get_example", {
     };
   }
 });
-server.registerTool("e2e_ai_plan_workflow", {
+server.registerTool("levante_plan_workflow", {
   title: "Plan Workflow",
   description: "Plan a levante automation workflow. Call this FIRST when the user asks to run any automation. " + "Returns an ordered list of steps (todo list) that should be executed one at a time. " + "Present the plan to the user for approval before executing any step.",
   inputSchema: exports_external.object({
@@ -33348,7 +33348,7 @@ server.registerTool("e2e_ai_plan_workflow", {
     }]
   };
 });
-server.registerTool("e2e_ai_execute_step", {
+server.registerTool("levante_execute_step", {
   title: "Execute Pipeline Step",
   description: "Execute a single levante pipeline step. Call this ONE STEP AT A TIME from an approved plan. " + "Each step produces artifacts consumed by later steps. " + "If your AI platform supports subagents, run each step in a dedicated subagent to preserve context. " + 'The "record" step is interactive and will open a browser window — the user must interact with it.',
   inputSchema: exports_external.object({
@@ -33405,7 +33405,7 @@ Ask the user to provide these before retrying.`
     }]
   };
 });
-server.registerTool("e2e_ai_get_workflow_guide", {
+server.registerTool("levante_get_workflow_guide", {
   title: "Get Workflow Guide",
   description: "Returns the levante workflow guide explaining how the pipeline works, step by step. Useful for understanding what each step does and how they connect.",
   inputSchema: exports_external.object({})
@@ -33429,9 +33429,9 @@ server.registerTool("e2e_ai_get_workflow_guide", {
     };
   }
 });
-server.registerTool("e2e_ai_scan_ast", {
+server.registerTool("levante_scan_ast", {
   title: "Scan AST",
-  description: "Run the deep AST scanner on the codebase. Returns a compact summary (stats, routes, components, hooks, directory groups). " + `The full AST is saved to ${CONFIG_DIR}/ast-scan.json for follow-up queries via e2e_ai_scan_ast_detail.`,
+  description: "Run the deep AST scanner on the codebase. Returns a compact summary (stats, routes, components, hooks, directory groups). " + `The full AST is saved to ${CONFIG_DIR}/ast-scan.json for follow-up queries via levante_scan_ast_detail.`,
   inputSchema: exports_external.object({
     scanDir: exports_external.string().optional().describe('Directory to scan (defaults to "src")'),
     include: exports_external.array(exports_external.string()).optional().describe('Glob patterns to include (defaults to ["**/*.ts", "**/*.tsx", "**/*.js", "**/*.jsx"])'),
@@ -33463,9 +33463,9 @@ server.registerTool("e2e_ai_scan_ast", {
     };
   }
 });
-server.registerTool("e2e_ai_scan_ast_detail", {
+server.registerTool("levante_scan_ast_detail", {
   title: "Scan AST Detail",
-  description: "Retrieve a filtered slice of the AST scan. Requires a prior e2e_ai_scan_ast call. " + "Use to drill into routes, components, hooks, dependencies, or files.",
+  description: "Retrieve a filtered slice of the AST scan. Requires a prior levante_scan_ast call. " + "Use to drill into routes, components, hooks, dependencies, or files.",
   inputSchema: exports_external.object({
     category: exports_external.enum(["routes", "components", "hooks", "dependencies", "files"]).describe("Which AST category to retrieve"),
     filter: exports_external.string().optional().describe('Glob pattern to filter results (e.g. "src/app/**", "Dashboard*")'),
@@ -33476,7 +33476,7 @@ server.registerTool("e2e_ai_scan_ast_detail", {
     const astPath = join5(process.cwd(), CONFIG_DIR, "ast-scan.json");
     if (!existsSync5(astPath)) {
       return {
-        content: [{ type: "text", text: "Error: No AST scan found. Run e2e_ai_scan_ast first." }],
+        content: [{ type: "text", text: "Error: No AST scan found. Run levante_scan_ast first." }],
         isError: true
       };
     }
@@ -33492,7 +33492,7 @@ server.registerTool("e2e_ai_scan_ast_detail", {
     };
   }
 });
-server.registerTool("e2e_ai_build_qa_map", {
+server.registerTool("levante_build_qa_map", {
   title: "Build QA Map",
   description: "Validate and optionally write a QAMapV2Payload. Use dryRun: true to validate without writing. " + "Returns validation result with errors, warnings, and stats.",
   inputSchema: exports_external.object({
@@ -33545,7 +33545,7 @@ server.registerTool("e2e_ai_build_qa_map", {
     };
   }
 });
-server.registerTool("e2e_ai_read_qa_map", {
+server.registerTool("levante_read_qa_map", {
   title: "Read QA Map",
   description: "Read an existing QA map file. Returns the parsed QAMapV2Payload or null if not found.",
   inputSchema: exports_external.object({

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "levante",
-  "version": "0.3.1",
+  "version": "0.3.4",
   "type": "module",
   "bin": {
     "levante": "./dist/cli.js",
@@ -24,6 +24,10 @@
   "peerDependencies": {
     "@playwright/test": ">=1.40.0"
   },
+  "dependencies": {
+    "picocolors": "^1.1.1",
+    "ws": "^8.19.0"
+  },
   "devDependencies": {
     "@inquirer/prompts": "^8.3.0",
     "@modelcontextprotocol/sdk": "^1.27.1",
@@ -36,11 +40,9 @@
     "ink": "^5",
     "ink-text-input": "^6",
     "ora": "^9.3.0",
-    "picocolors": "^1.1.1",
     "react": "^18",
     "react-devtools-core": "^7.0.1",
     "typescript": "^5.8.3",
-    "ws": "^8.19.0",
     "yaml": "^2.7.1",
     "zod": "^4.0.5"
   }

package/templates/workflow.md

@@ -24,7 +24,7 @@ record → transcribe → scenario → generate → refine → test → heal →
 
 After running `levante init`, you need a **context file** (`.qai/levante/context.md`) that teaches the AI about your project's test conventions — fixtures, helpers, selectors, login flows, etc.
 
-**How to create it:** Use the `init-agent` in your AI tool (Claude Code, Cursor, etc.). If you have the MCP server configured, the AI can scan your codebase automatically with `e2e_ai_scan_codebase`.
+**How to create it:** Use the `init-agent` in your AI tool (Claude Code, Cursor, etc.). If you have the MCP server configured, the AI can scan your codebase automatically with `levante_scan_codebase`.
 
 ---
 
@@ -207,10 +207,10 @@ This is independent from the test pipeline — use it to get an overview of your
 If you have the levante MCP server configured, you can ask your AI assistant to run the pipeline for you. The MCP server teaches the AI how to orchestrate the workflow:
 
 1. **You say:** "Run the full test pipeline for PROJ-101" (or any variation)
-2. **AI plans:** Calls `e2e_ai_plan_workflow` → gets an ordered step list
+2. **AI plans:** Calls `levante_plan_workflow` → gets an ordered step list
 3. **AI shows plan:** Presents the steps and asks for your approval
 4. **You adjust:** "Skip voice" / "Start from generate" / "Looks good, go"
-5. **AI executes:** Runs each step one at a time via `e2e_ai_execute_step`, reporting results between steps
+5. **AI executes:** Runs each step one at a time via `levante_execute_step`, reporting results between steps
 
 Each step runs as a separate subagent (when supported by the AI platform) to keep context clean and focused. If a step fails, the AI stops and asks you what to do.