@jenga-ai/agent 4.0.0 → 4.1.1

package/README.md

@@ -1,5 +1,5 @@
 # Jenga AI
-### No agent merges its own code.
+### The AI framework for serious projects.
 
 Jenga AI is an agentic software engineering framework for AI-assisted development: it splits work across three role-bounded agents — a Scrum Master that plans, a Developer that implements in an isolated git worktree, and a Tester that runs your test suite and owns the board status. Work survives session boundaries as Epics, Stories, and Tasks on a Markdown board your agent reads at the start of every session.
 
@@ -29,6 +29,37 @@ You've had this happen: Claude wrote the feature, said it worked, and the sessio
 
 Jenga AI solves each of these with structure: persistent engineering context maintained via board state, strict agent roles, typed inter-agent contracts, and session-end hooks that carry that context between sessions.
 
+### Documentation
+
+Start here, then go deeper as you need it:
+
+| Guide | What it covers |
+|---|---|
+| [Intro Guide](project/.wiki/intro-guide.md) | Start here. The philosophy, how to think about the system, and a first-15-minutes walkthrough for a new project or an existing codebase. Also on the [docs site](https://samwelmunga.github.io/jenga-npm/getting-started.html). |
+
+**Core concepts** — the three pillars, in the order they build on each other:
+
+| Concept | What it covers |
+|---|---|
+| [Role Separation](project/.wiki/concepts/role-separation.md) | Why Jenga AI uses three distinct agents instead of one. |
+| [Board Hierarchy](project/.wiki/concepts/board-hierarchy.md) | Why work is structured as Epics → Stories → Tasks, and how to use that hierarchy well. |
+| [Session Continuity](project/.wiki/concepts/session-continuity.md) | Why AI sessions losing context is the core problem — and how Jenga AI solves it structurally. |
+
+**How-to guides** — day-to-day working patterns:
+
+| Guide | What it covers |
+|---|---|
+| [Your First Feature](project/.wiki/concepts/first-feature.md) | Building a feature end-to-end, from idea to verified, committed code. |
+| [Capturing Mid-Flow Ideas](project/.wiki/concepts/mid-flow-capture.md) | Handling a new thought, tangent, or feature idea without derailing your current work. |
+| [Working Across Sessions](project/.wiki/concepts/multi-session-work.md) | Picking up a project after a break — without losing momentum or context. |
+| [Parallel Tasks](project/.wiki/concepts/parallel-tasks.md) | Running multiple tasks simultaneously with `j.dooo`, or automating board-wide parallel execution with `j.jenga`. |
+
+**Full reference:**
+
+| Reference | What it covers |
+|---|---|
+| [Documentation Reference](project/.wiki/documentation.md) | Every skill, every agent, MCP tools, hooks, and the inter-agent communication contract. Also on the [docs site](https://samwelmunga.github.io/jenga-npm/reference.html). |
+
 ---
 
 ## How Jenga AI's Agentic Workflow Works

package/lib/skill-allow-list.json

@@ -1,5 +1,5 @@
 {
-  "generated_at": "2026-09-26T13:22:56.631Z",
+  "generated_at": "2026-09-29T00:40:38.878Z",
   "skill_count": 41,
   "skills": [
     "brainstorm",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@jenga-ai/agent",
-  "version": "4.0.0",
+  "version": "4.1.1",
   "description": "An agentic development workflow for Claude Code, Copilot, and Codex — with a persistent Epic/Story/Task board, an isolated git worktree per task, and a separate tester agent that runs your test suite before anything is marked done.",
   "type": "module",
   "publishConfig": {

package/project/app/api/scripts/capture-snapshot.js

@@ -4,8 +4,9 @@
  *
  * E47_S04_T02 — capture step for `j.dashboard --snapshot`.
  *
- * Calls the dashboard API's `/v1/board`, `/v1/history`, `/v1/architecture`, and `/v1/health` routes
- * exactly once each and writes their combined JSON to a single artifact, consumable by the
+ * Calls the dashboard API's `/v1/board`, `/v1/history`, `/v1/architecture`, `/v1/health`,
+ * `/v1/documentation`, and `/v1/rapports` routes exactly once each and writes their combined JSON
+ * to a single artifact, consumable by the
  * bundling/inlining step in `E47_S04_T03` (implemented) and, for `/v1/health` specifically, by
  * `E47_S06_T02`'s snapshot `<title>` rewrite in `../../ui/scripts/build-snapshot-html.cjs`, which
  * needs the captured project name to bake into the exported HTML's title at build time.
@@ -44,10 +45,12 @@
  *   "captured_at": "<ISO 8601 UTC timestamp>",
  *   "project_root": "<absolute, realpath'd project root this snapshot was captured against>",
  *   "routes": {
- *     "board":        <full API envelope from GET /v1/board,        i.e. { data, meta, error }>,
- *     "history":       <full API envelope from GET /v1/history,      i.e. { data, meta, error }>,
- *     "architecture":  <full API envelope from GET /v1/architecture, i.e. { data, meta, error }>,
- *     "health":        <full API envelope from GET /v1/health,       i.e. { data, meta, error }>
+ *     "board":         <full API envelope from GET /v1/board,         i.e. { data, meta, error }>,
+ *     "history":       <full API envelope from GET /v1/history,       i.e. { data, meta, error }>,
+ *     "architecture":  <full API envelope from GET /v1/architecture,  i.e. { data, meta, error }>,
+ *     "health":        <full API envelope from GET /v1/health,        i.e. { data, meta, error }>,
+ *     "documentation": <full API envelope from GET /v1/documentation, i.e. { data, meta, error }>,
+ *     "rapports":      <full API envelope from GET /v1/rapports,      i.e. { data, meta, error }>
  *   }
  * }
  * Each `routes.<name>` value is the *full* envelope exactly as the route returned it (see
@@ -92,12 +95,14 @@ const path = require('path');
 const http = require('http');
 const fs = require('fs');
 
-const ROUTES = ['/v1/board', '/v1/history', '/v1/architecture', '/v1/health'];
+const ROUTES = ['/v1/board', '/v1/history', '/v1/architecture', '/v1/health', '/v1/documentation', '/v1/rapports'];
 const ROUTE_KEYS = {
   '/v1/board': 'board',
   '/v1/history': 'history',
   '/v1/architecture': 'architecture',
   '/v1/health': 'health',
+  '/v1/documentation': 'documentation',
+  '/v1/rapports': 'rapports',
 };
 
 function printUsage() {