Feat/hardening ci and tap

.github/dependabot.yml

@@ -0,0 +1,21 @@
+version: 2
+updates:
+  # Grouped and monthly on purpose: this is a small team, and a wall of open PRs
+  # gets ignored, which is worse than a slightly older lockfile. Security
+  # advisories still arrive immediately, separately from this schedule.
+  - package-ecosystem: npm
+    directory: "/"
+    schedule:
+      interval: monthly
+    open-pull-requests-limit: 5
+    groups:
+      dev-dependencies:
+        dependency-type: development
+  - package-ecosystem: github-actions
+    directory: "/"
+    schedule:
+      interval: monthly
+  - package-ecosystem: pip
+    directory: "/"
+    schedule:
+      interval: monthly

.github/workflows/ci.yml

@@ -0,0 +1,108 @@
+name: CI
+
+# Aide moves real money and is driven by a model, for users who cannot see the
+# screen to notice something went wrong. Every push runs the same gates a
+# reviewer would run by hand, in parallel, so a red check is visible before a
+# merge rather than after a withdrawal.
+on:
+  push:
+    branches: [main]
+  pull_request:
+  workflow_dispatch:
+
+# A second push to the same branch makes the first run irrelevant.
+concurrency:
+  group: ci-${{ github.ref }}
+  cancel-in-progress: true
+
+permissions:
+  contents: read
+
+env:
+  # lib/env.ts refuses to load without these, so `next build` cannot even import
+  # the payment routes unless they are present. CI never reaches a real
+  # provider — placeholders are the point: they prove the wiring, not the keys.
+  MONNIFY_API_KEY: ci-placeholder
+  MONNIFY_SECRET_KEY: ci-placeholder
+  MONNIFY_CONTRACT_CODE: "0000000000"
+  DEEPSEEK_API_KEY: ci-placeholder
+  NEXT_PUBLIC_CONVEX_URL: https://ci-placeholder.convex.cloud
+
+jobs:
+  typecheck:
+    name: Types
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-node@v4
+        with:
+          node-version: 22
+          cache: npm
+      - run: npm ci
+      - run: npm run typecheck
+
+  test:
+    name: Tests
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-node@v4
+        with:
+          node-version: 22
+          cache: npm
+      - run: npm ci
+      # Two vitest projects run here: plain Node for the money, agent and speech
+      # suites, and an edge-runtime VM for the Convex functions, which is the
+      # only environment convex-test can drive.
+      - run: npm test
+
+  build:
+    name: Production build
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-node@v4
+        with:
+          node-version: 22
+          cache: npm
+      - run: npm ci
+      - run: npm run build
+
+  speech:
+    name: Speech worker
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+          cache: pip
+      # The neural voice is not a nice-to-have here — it is the entire
+      # interface. Both speech entry points guard their entry behind
+      # __main__, so importing them is safe and proves more than a syntax
+      # check: that edge-tts still installs and that the names these files
+      # reach for still exist. A break here would otherwise reach the user as
+      # the robotic browser fallback voice, with nothing on screen to explain it.
+      - run: pip install -r requirements.txt
+      - name: Import both speech entry points
+        run: |
+          python -c "import sys; sys.path[:0] = ['scripts', 'api']; import tts_worker, speak"
+
+  secrets:
+    name: No secrets committed
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Refuse tracked env files and local Convex state
+        run: |
+          bad=$(git ls-files | grep -E '^(\.env($|\..*)|\.convex/)' | grep -v '^\.env\.example$' || true)
+          if [ -n "$bad" ]; then
+            echo "::error::These must never be committed:"; echo "$bad"; exit 1
+          fi
+      - name: Refuse live-looking credentials
+        run: |
+          # .env.example carries placeholders only (MK_TEST_xxx, sk-xxxxxxxx),
+          # so these patterns match real keys and nothing else.
+          if git grep -nIE 'MK_PROD_[A-Za-z0-9]{6,}|sk-[A-Za-z0-9]{24,}|-----BEGIN [A-Z ]*PRIVATE KEY-----' -- . ':!.github/workflows/ci.yml'; then
+            echo "::error::A live-looking credential is committed."; exit 1
+          fi

.gitignore

@@ -27,3 +27,10 @@ tts-env/
 venv/
 .venv/
 .vercel
+
+# Throwaway build dirs used by side-by-side test servers (see AIDE_DIST_DIR)
+.next-*/
+
+# Python bytecode from the TTS worker / speak function
+__pycache__/
+*.pyc

README.md

@@ -7,6 +7,8 @@ A worker talks; Aide does the rest — finds jobs, runs a spoken skill assessmen
 real bank account, confirms incoming pay, and reads the balance back aloud. No screen
 required.
 
+[![CI](https://github.com/David-Pjs/Aide/actions/workflows/ci.yml/badge.svg)](https://github.com/David-Pjs/Aide/actions/workflows/ci.yml)
+
 [**Live demo →** aide-ng.vercel.app](https://aide-ng.vercel.app) · Open in Chrome and just talk.
 
 ---
@@ -268,6 +270,26 @@ npm run balance    # wallet balance check
 
 `npm run proof` prints `SUCCESS` or the documented `PENDING_AUTHORIZATION` sandbox state
 
+### Continuous integration
+
+Every push and pull request runs five checks in parallel
+([`.github/workflows/ci.yml`](.github/workflows/ci.yml)). They run against placeholder
+credentials, never a real provider — what they prove is the wiring, not the keys.
+
+| Check | What it protects |
+|---|---|
+| **Types** | `tsc --noEmit` across app, Convex functions, and tests. |
+| **Tests** | 267 tests over two vitest projects — plain Node for money, agent, and speech; an edge-runtime VM for the Convex functions, which is the only environment `convex-test` can drive. |
+| **Production build** | A full `next build`, so a route that only breaks when compiled cannot reach a deploy. |
+| **Speech worker** | Installs `edge-tts` and imports both speech entry points. A break here would otherwise reach a blind user as the robotic fallback voice, with nothing on screen to explain it. |
+| **No secrets committed** | Fails on a tracked `.env`, on local Convex state (it holds an admin key), or on anything shaped like a live credential. |
+
+Run the same gates locally:
+
+```bash
+npm run typecheck && npm test && npm run build
+```
+
 ### Troubleshooting
 
 | Symptom | Fix |
@@ -358,6 +380,24 @@ contrast.
   speech and incoming messages are announced automatically, `role="alert"` on errors,
   properly associated `<label>`s on every control, and a skip-to-content link.
 
+### Controls with no target to find
+
+A mute button is only a control if you can find it. These three do the same job without
+one, and each announces itself aloud, because a state change a user cannot see or hear is
+a state change they have to guess at.
+
+| Gesture | What happens |
+|---|---|
+| **Tap anywhere, or press any key** | Cuts Aide off mid-sentence. Nothing to aim at — a blind user should not have to hunt for a stop button while being talked over. |
+| **Tap three times** | Closes the microphone and keeps it closed. Aide says so, and says how to come back, since that sentence is the last thing heard before it goes quiet. Three more taps reopen it. Two would be too easy to do by accident; three is not. |
+| **Say nothing for 90 seconds** | Aide closes the mic itself and says it is doing so, rather than streaming an empty room indefinitely. Any tap or key wakes it. |
+
+The held state is enforced at the single function that can open the microphone, not at each
+of its callers, so a tab regaining focus, a reply finishing, or a recognizer restarting
+cannot quietly undo it. The input-level meter releases its own capture stream at the same
+time — otherwise the browser's recording indicator stays lit and "I've stopped listening"
+is a lie.
+
 The throughline: **redundancy**. Text, shape, contrast, and voice each carry the meaning on
 their own, so no single sensory channel is load-bearing — which is what lets one interface
 serve blind, low-vision, and colorblind users at the same time.

app/aide/index.tsx

@@ -20,6 +20,7 @@ type AideContextValue = {
   listening: boolean;
   speaking: boolean;
   dormant: boolean;
+  muted: boolean;
   thinking: boolean;
   capturing: boolean;
   supported: boolean;
@@ -77,6 +78,7 @@ export function AideProvider({ children }: { children: React.ReactNode }) {
     listening: false,
     speaking: false,
     dormant: false,
+    muted: false,
     interim: "",
     micStatus: "starting…",
     error: null,
@@ -237,7 +239,9 @@ export function AideProvider({ children }: { children: React.ReactNode }) {
             .catch(() => null)
             .then((data) => {
               const base = data?.greeting || "Hello, I'm Aide. I'm listening — just talk to me.";
-              const greeting = `${base} By the way, you can stop me any time — just tap the screen or press any key.`;
+              // The gesture has no visual affordance at all, so the only place a
+          // user can learn it is here. Kept to one clause, said once a session.
+          const greeting = `${base} By the way, you can stop me any time — just tap the screen or press any key. Tap three times if you'd like me to stop listening altogether.`;
               setMessages((m) => [...m, { role: "assistant", content: greeting }]);
               engine.speak(greeting);
             });
@@ -287,6 +291,7 @@ export function AideProvider({ children }: { children: React.ReactNode }) {
         listening: voice.listening,
         speaking: voice.speaking,
         dormant: voice.dormant,
+        muted: voice.muted,
         thinking,
         capturing,
         supported,
@@ -338,17 +343,21 @@ function PaymentAlerts({
 // The small Aide that follows the user onto every other screen. It glows
 // while talking and pulses while listening; tapping it interrupts Aide.
 function MiniAide() {
-  const { listening, speaking, thinking, capturing, interim, messages, interrupt } = useAide();
+  const { listening, speaking, thinking, capturing, muted, interim, messages, interrupt } = useAide();
   const lastAide = [...messages].reverse().find((m) => m.role === "assistant")?.content;
-  const status = speaking
-    ? "Aide is speaking"
-    : thinking
-      ? "Aide is thinking"
-      : capturing
-        ? "Aide is writing down what you say"
-        : listening
-          ? "Aide is listening"
-          : "Aide is paused";
+  // Held beats everything below it. Announcing "Aide is listening" while the
+  // user has deliberately closed the mic is the one lie that matters here.
+  const status = muted
+    ? "Aide is not listening — tap three times to start again"
+    : speaking
+      ? "Aide is speaking"
+      : thinking
+        ? "Aide is thinking"
+        : capturing
+          ? "Aide is writing down what you say"
+          : listening
+            ? "Aide is listening"
+            : "Aide is paused";
 
   return (
     <div className="fixed bottom-5 right-5 z-40 flex flex-col items-end gap-2">