@echomem/mcp 1.4.44 → 1.4.46

package/README.md

@@ -35,36 +35,22 @@ Unencrypted accounts are unaffected. `search_memories` returns retrieved memorie
 your MCP client does the final answer generation; pass `includeAnswer: true` only if you need the
 legacy EchoMem-synthesized recall answer.
 
-## Quick start
+## Quick start (recommended)
 
-The standalone package installs and manages its own durable per-user MCP runtime. It configures
-detected Codex and Claude hosts, connects this device, imports selected local coding history, and
-keeps compatible runtime updates ready for the next agent session.
+Install Echo Desktop, sign in once, then open **Connect MCP** and choose **Connect Echo**. The app
+ships and installs the MCP runtime, configures the detected Codex and Claude hosts, mirrors the same
+device credential used by the desktop app, and verifies the MCP handshake. No terminal login is
+required.
 
-Prerequisite: **Node.js 18 or newer**. Run the command in the same environment as the agent you
-want to configure. Native Windows and WSL have separate home directories and client configs, so a
-WSL install does not configure native Windows apps.
+The standalone HUD has been retired; Echo Desktop is the persistent setup and status surface. The
+bridge still reads local agent logs for on-demand context-health tools, but it no longer publishes or
+auto-launches an Electron overlay.
 
-macOS, Linux, or WSL:
-
-```bash
-npx -y @echomem/mcp@latest init
-```
-
-Windows PowerShell:
-
-```powershell
-npx.cmd -y @echomem/mcp@latest init
-```
-
-The one-off `npx` command is the recommended install path; it stages a durable per-user runtime
-and does not require a global npm install. On Windows, use a new PowerShell window after installing
-Node if `npx.cmd` is not found.
+For headless systems and development, the granular CLI commands remain available:
 
 | Command | What it does |
 |---|---|
-| `npx -y @echomem/mcp@latest init` | One-command setup for installed agents + login (use `npx.cmd` in Windows PowerShell) |
-| `npm i -g @echomem/mcp@latest`, then `echomem-mcp init` | Optional global install for a persistent CLI command |
+| `npm i -g @echomem/mcp@latest && echomem-mcp init` | Legacy/headless setup for installed agents + login |
 | `npm i -g @echomem/mcp@latest && echomem-mcp setup` | Install the CLI globally and configure just the detected editor |
 | `npx -y @echomem/mcp@latest setup` | One-off setup without keeping a global CLI command |
 | `echomem-mcp setup [--client cursor\|windsurf\|claude-desktop\|claude-code\|codex]` | Write client config + log in |
@@ -109,6 +95,23 @@ Both hook entries are merged idempotently into `~/.codex/hooks.json` and
 `~/.claude/settings.json`; unrelated user hooks and settings are preserved. Hooks fail open when
 their local input is missing so they cannot prevent a conversation from starting or finishing.
 
+## Agent Doctor — local workspace forensics (new in 1.4.9)
+
+`echomem-mcp init` / `setup` now ends with an **Agent Doctor report**: a local scan of your
+Codex and Claude Code session logs that shows what your AI coding actually cost and where the
+context went dirty — rendered as an interactive 3D "repo city" plus a full forensic breakdown.
+
+- **Unified cost ledger.** Every provider request is priced individually from official API list
+  rates (model, cache write/read, long-context premiums, intro-pricing windows), so the headline
+  TOTAL SPENT, per-repo costs, per-model costs, and cost components all come from one path and
+  reconcile exactly. It is an **API-equivalent estimate of volume, not a bill you paid**.
+- **Fail-closed validation.** The report refuses to render unless every ledger reconciles
+  (tokens, costs, canonical waste analysis). Stale or preview data can never appear as your data.
+- **Wasteful-context analysis.** Canonical context windows label input tokens useful vs wasteful
+  (re-reads of unchanged files, re-finding, dead work) and project the waste over your billed input.
+- **Fully local, zero upload.** The scan reads local JSONL logs only: no transcripts are uploaded
+  and no LLM calls are made to build the report.
+
 ### Manual / headless (SSH, containers, CI)
 
 No browser? Provide secrets directly — this is the documented headless path:
@@ -137,7 +140,7 @@ npm test   # crypto compat + encrypted-local integration tests
 
 ### Add to your IDE (Cursor or Windsurf)
 
-> Prefer `npx -y @echomem/mcp@latest init` above (`npx.cmd` in Windows PowerShell) — it writes these files for you and keeps secrets out of
+> Prefer `npm i -g @echomem/mcp@latest && echomem-mcp init` above — it writes these files for you and keeps secrets out of
 > the client config. The manual steps below are the fallback.
 
 #### For Cursor

package/dist/city/README.md

@@ -0,0 +1,9 @@
+# Runtime City Assets
+
+Only these files are part of setup runtime:
+
+- `echo-ai-city-only.html` - pre-auth Agent Doctor City.
+- `echo-extraction-plate.html` - post-auth extraction progress plate.
+- `vendor/`, `personality_stickers/`, and `echo-face-cutout.png` - assets loaded by those pages.
+
+Everything under `archive/` is historical reference. It is excluded from the published package and rejected by the localhost City asset server.