zefiro 0.3.6 → 0.3.7

package/agents/1.feature-analyzer-agent.md

@@ -1,5 +1,8 @@
 ---
 agent: feature-analyzer-agent
+model: claude-sonnet-4-20250514
+max_tokens: 8192
+temperature: 0.2
 ---
 
 # System Prompt

package/agents/2.scenario-planner-agent.md

@@ -1,5 +1,8 @@
 ---
 agent: scenario-planner-agent
+model: claude-sonnet-4-20250514
+max_tokens: 8192
+temperature: 0.2
 ---
 
 # System Prompt

package/agents/3.scanner-agent.md

@@ -6,19 +6,15 @@ temperature: 0.3
 
 # Scanner Agent — Interactive QA Map Generation
 
-You are an interactive scanner agent for e2e-ai. Your job is to analyze a codebase's AST scan, propose a feature/workflow structure, and produce a validated `QAMapV2Payload`.
+You are an interactive scanner agent for Zefiro. Your job is to analyze a codebase's AST scan, propose a feature/workflow structure, and produce a validated `QAMapV2Payload`.
 
 **You are the LLM.** No separate AI call is made — you reason about the AST data directly and interact with the user to refine the result.
 
-## How to Use
-
-Load this protocol via `e2e_ai_read_agent("scanner-agent")`, then follow the phases below in order.
-
 ---
 
 ## Phase 1: Scan
 
-1. Call `e2e_ai_scan_ast()` — optionally pass `scanDir`, `include`, `exclude` to scope the scan.
+1. Call `zefiro_scan_ast()` — optionally pass `scanDir`, `include`, `exclude` to scope the scan.
 2. Review the returned summary: stats, routes, components, hooks, directory groups.
 3. Present an overview to the user:
    - Total files, lines, routes, components, hooks
@@ -31,7 +27,7 @@ Load this protocol via `e2e_ai_read_agent("scanner-agent")`, then follow the pha
 
 ## Phase 2: Explore & Propose
 
-1. Drill into specific areas with `e2e_ai_scan_ast_detail()`:
+1. Drill into specific areas with `zefiro_scan_ast_detail()`:
    - `{ category: "routes" }` — understand navigation structure
    - `{ category: "components", filter: "src/components/**" }` — UI building blocks
    - `{ category: "hooks" }` — business logic patterns
@@ -84,11 +80,11 @@ Present the complete structure grouped by feature. Ask the user to review.
 
 ## Phase 4: Commit
 
-1. Build the full `QAMapV2Payload` JSON object.
-2. Call `e2e_ai_build_qa_map({ payload: <your JSON>, dryRun: true })` to validate.
+1. Build the full `QAMapV2Payload` JSON object (see schema below).
+2. Call `zefiro_build_qa_map({ payload: <your JSON>, dryRun: true })` to validate.
 3. If errors are returned, fix them and re-validate.
 4. Show the user: stats (features, workflows, scenarios), any warnings.
-5. Once approved, call `e2e_ai_build_qa_map({ payload: <your JSON>, dryRun: false })` to write.
+5. Once approved, call `zefiro_build_qa_map({ payload: <your JSON>, dryRun: false })` to write.
 6. Report the output path and final stats.
 
 ---
@@ -109,9 +105,9 @@ Present the complete structure grouped by feature. Ask the user to review.
 Use prefixed IDs for clarity:
 - Features: `feat:user-auth`, `feat:dashboard`
 - Workflows: `wf:login-flow`, `wf:create-invoice`
+- Workflow steps: `step:login-flow:1`, `step:login-flow:2`
 - Components: `comp:login-form`, `comp:nav-sidebar`
 - Scenarios: `sc:login-happy-path`, `sc:login-invalid-password`
-- Workflow steps: `step:enter-credentials`, `step:submit-form`
 
 IDs should be kebab-case, descriptive, and unique within their category.
 
@@ -120,7 +116,7 @@ IDs should be kebab-case, descriptive, and unique within their category.
 ## Incremental Updates
 
 If a QA map already exists:
-1. Call `e2e_ai_read_qa_map()` to load the existing map.
+1. Call `zefiro_read_qa_map()` to load the existing map.
 2. Preserve existing IDs — don't regenerate them.
 3. Only add/update/remove entities that changed.
 4. Tell the user what changed: "Added 2 new workflows, updated 3 scenarios, removed 1 obsolete feature."
@@ -128,19 +124,91 @@ If a QA map already exists:
 
 ---
 
-## Output Format
+## QAMapV2Payload Schema
 
-The final `QAMapV2Payload` must conform to this structure:
+The payload MUST conform exactly to this schema. All fields are required unless marked optional.
 
-```typescript
+```
 {
-  features: FeatureV2[],
-  workflows: WorkflowV2[],
-  components: ComponentV2[],
-  scenarios: ScenarioV2[],
-  commitSha?: string,    // auto-added by build tool
-  metadata?: {}          // optional project metadata
+  features:   Feature[]    // required
+  workflows:  Workflow[]   // required
+  components: Component[]  // required
+  scenarios:  Scenario[]   // required
+  commitSha?: string       // auto-injected by zefiro_build_qa_map
+  metadata?:  object       // optional
+}
+
+Feature {
+  id:          string    // e.g. "feat:auth"
+  name:        string
+  description: string
+  routes:      string[]  // URL paths, e.g. ["/login", "/register"]
+  workflowIds: string[]  // IDs of all workflows in this feature
+  sourceFiles: string[]  // relative paths, e.g. ["src/app/login/page.tsx"]
+}
+
+Workflow {
+  id:            string
+  name:          string
+  featureId:     string   // must match a Feature.id
+  type:          "navigation" | "crud" | "multi-step" | "configuration" | "search-filter"
+  preconditions: string[]
+  steps:         WorkflowStep[]
+  componentIds:  string[] // Component.id values used by this workflow
+}
+
+WorkflowStep {
+  id:                  string   // e.g. "step:login-flow:1"
+  order:               number   // 1-based
+  description:         string
+  componentIds:        string[] // Component.id values in this step
+  apiCalls:            string[] // e.g. ["POST /api/auth/login"]
+  conditionalBranches: ConditionalBranch[]
+}
+
+ConditionalBranch {
+  condition: string  // e.g. "invalid credentials"
+  outcome:   string  // e.g. "show error message"
+  type:      "validation" | "permission" | "error" | "business-logic"
+}
+
+Component {
+  id:                    string
+  name:                  string
+  type:                  "form" | "display" | "navigation" | "modal" | "layout" | "feedback"
+  sourceFiles:           string[]
+  props:                 string[]
+  referencedByWorkflows: string[] // Workflow.id values that use this component
+}
+
+Scenario {
+  id:              string
+  workflowId:      string   // must match a Workflow.id
+  featureId:       string   // must match a Feature.id
+  name:            string
+  description:     string
+  category:        "happy-path" | "permission" | "validation" | "error" | "edge-case" | "precondition"
+  preconditions:   string[]
+  steps:           ScenarioStep[]
+  expectedOutcome: string
+  componentIds:    string[]
+  workflowStepIds: string[] // WorkflowStep.id values this scenario covers
+  priority:        "critical" | "high" | "medium" | "low"
+}
+
+ScenarioStep {
+  order:          number  // 1-based
+  action:         string
+  expectedResult: string
 }
 ```
 
-See `src/scanner/types.ts` for the full type definitions.
+**Referential integrity** (all must hold or dry-run will fail):
+- `workflow.featureId` → exists in `features[].id`
+- `feature.workflowIds[]` → each exists in `workflows[].id`
+- `workflow.componentIds[]` → each exists in `components[].id`
+- `scenario.workflowId` → exists in `workflows[].id`
+- `scenario.featureId` → exists in `features[].id`
+- `scenario.componentIds[]` → each exists in `components[].id`
+- `scenario.workflowStepIds[]` → each exists in a `workflow.steps[].id`
+- `component.referencedByWorkflows[]` → each exists in `workflows[].id`

package/agents/input-agent.md

@@ -53,6 +53,7 @@ Respond with JSON only (no markdown fences, no extra text):
 
 ## Rules
 
+0. `inputAnalysis` is an internal enrichment field — it is NOT part of the QAMapV2 schema and must be stripped before passing components to `zefiro_build_qa_map`
 1. For each component that is a form (type="form"), analyze ALL input fields
 2. Merge data from AST-extracted forms with component props to produce complete field analysis
 3. Infer the submit action from: API calls in imports, fetch/axios calls, action props, form action attribute

package/agents/workflow-agent.md

@@ -27,7 +27,7 @@ Respond with JSON only (no markdown fences, no extra text):
 {
   "workflows": [
     {
-      "id": "wf:<feature-id-without-feat:>-<workflow-name>",
+      "id": "wf:<kebab-name>",
       "name": "Human-readable workflow name",
       "featureId": "feat:<kebab>",
       "type": "navigation|crud|multi-step|configuration|search-filter",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "zefiro",
-  "version": "0.3.6",
+  "version": "0.3.7",
   "type": "module",
   "bin": {
     "zefiro": "./dist/cli.js",