@inventeer.tech/apex 0.2.34 → 0.2.36

package/README.md

@@ -82,46 +82,6 @@ Every time you run a command in APEX, a curated framework of specialized agents,
 
 None of this requires configuration. It's part of every session, for every developer in your organization.
 
-<!-- ---
-
-### Multi-repo by design
-
-A workspace groups all your repositories. One task can plan, write, test, and open PRs across your backend, frontend, and shared types simultaneously. The AI knows your full stack — not just the file you have open.
-
-### Five layers of always-active context
-
-Every LLM call carries five layers injected automatically — you never paste context manually:
-
-- **Codebase RAG** — every file across all repos, chunked and semantically indexed. The AI knows your schema when writing the endpoint, and your types when writing the frontend.
-- **Episodic memory** — when you close the terminal, APEX saves a structured summary (completed, pending, files changed, decisions made, next steps). The next session resumes in under 500 tokens. After months of work, APEX still knows why things were built the way they were.
-- **Org knowledge base** — ADRs, runbooks, API specs, onboarding docs uploaded with `apex knowledge add` are permanently searchable. The AI cites your actual documentation instead of inventing conventions.
-- **Working context** — the full active session state, preserved mid-task.
-- **Framework intelligence** — curated engineering agents, quality guardrails, and delivery workflows loaded at startup. No configuration required.
-
-### Plan before code — you stay in control
-
-APEX never writes a line of code without showing you a phased plan first. You approve, edit, or cancel before any file is touched. Every run of `/eng.work` is a deliberate, reviewed commitment.
-
-### Built-in quality gates
-
-`/eng.pre-pr` runs tests, type checks, and lint across all repos before any PR is opened. Failures are auto-fixed up to 3 times. You see a scored quality report before anything goes to review.
-
-### Self-correcting execution loop
-
-The AI doesn't stop on the first test failure. It diagnoses the error, tries a different strategy, and escalates through recovery hints before surfacing a report. Sessions run until real progress stops — not until a fixed step count is hit.
-
-### Architectural decisions, not just code
-
-Every decision the AI makes — why it chose an approach, what it considered — is recorded automatically and stored. Run `apex decisions` to see the full log. New team members can understand why the code was written the way it was.
-
-### Always-fresh codebase context
-
-Push webhooks trigger incremental re-indexing automatically on every commit. The TUI shows an amber warning when the index is stale. The AI is never working from outdated code.
-
-### Token visibility, per model
-
-Every LLM call is metered. Run `apex usage` to see token consumption broken down by model and provider. No surprise bills, no silent runaway sessions. -->
-
 ---
 
 ## The Workspace Concept

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@inventeer.tech/apex",
-  "version": "0.2.34",
+  "version": "0.2.36",
   "description": "AI-powered software delivery agent",
   "bin": {
     "apex": "./bin/apex"
@@ -36,5 +36,9 @@
   "repository": {
     "type": "git",
     "url": "https://github.com/Inventeer/apex.git"
-  }
+  },
+  "files": [
+    "README.md",
+    "install.js"
+  ]
 }