feat: add setup-ai bootstrap

.gitignore

@@ -65,3 +65,4 @@ certs/
 memory-bank/epoch/*
 !memory-bank/epoch/.gitkeep
 models/*.bin
+whisper.cpp/

CHANGELOG.md

@@ -5,6 +5,12 @@ All notable changes to OpenStudio will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [Unreleased]
+
+### Added
+
+- **`setup-ai.sh`** one-shot bootstrap script for the AI pipeline. It clones and builds `whisper.cpp`, downloads the default Whisper model into `models/`, and prompts for LLM provider settings in `.env`.
+
 ## [0.3.2] - 2026-05-25
 
 ### Added

QUICKSTART.md

@@ -9,6 +9,8 @@ cp .env.example .env
 cd server && npm install && cd ..
 cd web && npm install && cd ..
 cp station-manifest.sample.json station-manifest.json
+# Optional: bootstrap the AI pipeline (whisper.cpp, model, LLM config)
+./setup-ai.sh
 ```
 
 ## Daily Development Workflow

README.md

@@ -132,18 +132,18 @@ OpenStudio includes a complete post-production pipeline — transcription, show
 
 ### Prerequisites
 - `ffmpeg` and `ffprobe` on your `PATH` (most package managers ship both: `brew install ffmpeg`, `apt install ffmpeg`)
+- `cmake` on your `PATH` for the `whisper.cpp` build
 - ~1.5 GB free disk space for the default Whisper model
 
-### whisper.cpp setup (one-time)
+### One-shot AI setup
 
 ```bash
-git clone https://github.com/ggerganov/whisper.cpp
-cd whisper.cpp && make -j$(nproc)
-cd .. && mkdir -p models
-wget -O models/ggml-medium.bin https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-medium.bin
+./setup-ai.sh
 ```
 
-You can swap the model — `ggml-tiny.bin` (~75 MB) is faster but less accurate; `ggml-large.bin` is the other direction. The server looks for `models/ggml-medium.bin` by default.
+The script clones and builds `whisper.cpp`, downloads `models/ggml-medium.bin`, and prompts for your LLM provider so `.env` is ready for show notes.
+
+You can swap the model manually if you want — `ggml-tiny.bin` (~75 MB) is faster but less accurate; `ggml-large.bin` is the other direction. The server looks for `models/ggml-medium.bin` by default.
 
 ### LLM Provider Examples
 
@@ -240,8 +240,6 @@ See [docs/vision.md](docs/vision.md) for the full project vision and philosophy.
 Honest about what's there and what isn't:
 
 - **Invite-link UI** — the server can mint scoped invite tokens (host / ops / guest, 4 h TTL), but the host UI doesn't expose a button yet. For now, hosts share the room URL manually. Coming in 0.4.
-- **AI pipeline setup is manual** — the whisper.cpp build, model download, and LLM configuration aren't scripted. A `setup-ai.sh` would be a great PR.
-- **whisper.cpp gitlink** — the repo references whisper.cpp as a gitlink without a `.gitmodules` entry. Use the manual `git clone` in the AI setup section above; `git submodule update` will fail.
 - **Mesh scale ceiling** — WebRTC mesh tops out around 15 participants. Larger rooms need an SFU (planned for 0.5).
 
 ## Contributing

package.json

@@ -7,6 +7,7 @@
     "start": "node server/server.js",
     "dev": "node --watch server/server.js",
     "test": "node server/test-signaling.js && node server/test-rooms.js",
+    "test:setup-ai": "bash tests/test-setup-ai.sh",
     "install": "cd server && npm install"
   },
   "engines": {

run-pre-validation.sh

@@ -18,6 +18,7 @@ echo "  3. test-gain-controls.mjs   - Per-participant gain controls"
 echo "  4. test-program-bus.mjs     - Program bus mixing"
 echo "  5. test-mix-minus.mjs       - Mix-minus calculation (3 peers)"
 echo "  6. test-return-feed.mjs     - Return feed routing (2 peers)"
+echo "  7. test-setup-ai.sh         - AI bootstrap script smoke test"
 echo ""
 echo "================================================================================"
 echo ""
@@ -32,13 +33,18 @@ run_test() {
     local test_name=$1
     local test_file=$2
     local timeout_seconds=${3:-60}
+    local runner="node"
+
+    case "$test_file" in
+        *.sh) runner="bash" ;;
+    esac
 
     echo "--- Running: $test_name ---"
     echo "File: $test_file"
     echo "Timeout: ${timeout_seconds}s"
     echo ""
 
-    if timeout ${timeout_seconds} node "$test_file"; then
+    if timeout ${timeout_seconds} "$runner" "$test_file"; then
         echo ""
         echo "✅ PASSED: $test_name"
         echo ""
@@ -64,6 +70,7 @@ run_test "Gain Controls" "tests/test-gain-controls.mjs" 60
 run_test "Program Bus Mixing" "tests/test-program-bus.mjs" 60
 run_test "Mix-Minus Calculation" "tests/test-mix-minus.mjs" 60
 run_test "Return Feed Routing" "tests/test-return-feed.mjs" 60
+run_test "AI Bootstrap Script" "tests/test-setup-ai.sh" 120
 
 # Summary
 echo "================================================================================"
@@ -76,7 +83,7 @@ for test in "${TESTS[@]}"; do
 done
 
 echo ""
-echo "Results: $PASSED passed, $FAILED failed (out of 6 total)"
+echo "Results: $PASSED passed, $FAILED failed (out of 7 total)"
 echo ""
 
 # Decision

server/lib/whisper-transcriber.js

@@ -175,12 +175,41 @@ async function downloadModel(model = 'medium') {
  */
 async function buildWhisperCpp() {
   const whisperDir = path.join(process.cwd(), 'whisper.cpp');
+  const whisperBin = WHISPER_BIN;
+  const cmakeLists = path.join(whisperDir, 'CMakeLists.txt');
+  const makefile = path.join(whisperDir, 'Makefile');
+
+  if (!fs.existsSync(whisperDir)) {
+    logger.info('Cloning whisper.cpp...');
+    await execAsync(`git clone --depth 1 --recursive https://github.com/ggerganov/whisper.cpp.git ${whisperDir}`);
+  } else if (!fs.existsSync(cmakeLists) && !fs.existsSync(makefile)) {
+    const entries = fs.readdirSync(whisperDir);
+    if (entries.length === 0) {
+      logger.warn('Found empty whisper.cpp directory, re-cloning...');
+      fs.rmSync(whisperDir, { recursive: true, force: true });
+      await execAsync(`git clone --depth 1 --recursive https://github.com/ggerganov/whisper.cpp.git ${whisperDir}`);
+    } else {
+      throw new Error('whisper.cpp checkout exists but has no supported build files');
+    }
+  }
 
-  logger.info('Cloning whisper.cpp...');
-  await execAsync(`git clone --depth 1 https://github.com/ggerganov/whisper.cpp.git ${whisperDir}`);
+  if (fs.existsSync(whisperBin)) {
+    logger.info('whisper.cpp already built');
+    return;
+  }
 
-  logger.info('Building whisper.cpp...');
-  await execAsync(`cd ${whisperDir} && make -j$(nproc) 2>&1 | tail -5`);
+  if (fs.existsSync(cmakeLists)) {
+    logger.info('Configuring whisper.cpp with CMake...');
+    await execAsync(`cmake -S ${whisperDir} -B ${whisperDir}/build -DWHISPER_BUILD_TESTS=OFF -DWHISPER_BUILD_EXAMPLES=ON -DWHISPER_BUILD_SERVER=OFF`);
+
+    logger.info('Building whisper.cpp...');
+    await execAsync(`cmake --build ${whisperDir}/build --config Release --target whisper-cli -j$(nproc)`);
+  } else if (fs.existsSync(makefile)) {
+    logger.info('Building whisper.cpp...');
+    await execAsync(`cd ${whisperDir} && make -j$(nproc) 2>&1 | tail -5`);
+  } else {
+    throw new Error('whisper.cpp checkout does not contain a supported build system');
+  }
 
   logger.info('whisper.cpp built successfully');
 }