Fix container crash on startup: onnxruntime-node requires glibc (switch Alpine → Debian slim) (#97)

* docker fixes

* fix(worker): default COMPUTE_PREWARM_MODELS to false and update docs, env, and compose

Set COMPUTE_PREWARM_MODELS to false by default in runtime, docker-compose,
and .env.example to avoid pre-downloading ONNX models during worker startup.
Update Dockerfile and deployment documentation to reflect this change and
clarify configuration for model prewarming.

* fix(docker): downgrade pnpm version to 10.33.4 for compatibility

---------

Co-authored-by: Richard R <me@richardr.dev>

Dockerfile

@@ -11,10 +11,10 @@ RUN cp "$(command -v nats-server)" /tmp/nats-server
 
 
 # Stage 2: build the Next.js app
-FROM node:lts-alpine AS app-builder
+FROM node:lts-slim AS app-builder
 
 # Install pnpm globally
-RUN npm install -g pnpm@11.1.2
+RUN npm install -g pnpm@10.33.4
 
 # Create app directory
 WORKDIR /app
@@ -44,12 +44,14 @@ RUN mkdir -p /app/THIRD_PARTY_LICENSES && \
 
 
 # Stage 3: minimal runtime image
-FROM node:lts-alpine AS runner
+FROM node:lts-slim AS runner
 
 # Add runtime OS dependencies:
 # - libreoffice-writer: required for DOCX → PDF conversion
 # ffmpeg is provided by ffmpeg-static from node_modules.
-RUN apk add --no-cache ca-certificates libreoffice-writer
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends ca-certificates libreoffice-writer && \
+    rm -rf /var/lib/apt/lists/*
 
 # Install pnpm for runtime process commands.
 RUN npm install -g pnpm@10.33.4

compute/worker/.env.example

@@ -39,7 +39,7 @@ S3_ENDPOINT=http://host.docker.internal:8333
 S3_FORCE_PATH_STYLE=true
 
 # Optional tuning
-# COMPUTE_PREWARM_MODELS=true
+# COMPUTE_PREWARM_MODELS=false
 # COMPUTE_JOB_CONCURRENCY=1
 # COMPUTE_WHISPER_TIMEOUT_MS=30000
 # COMPUTE_PDF_TIMEOUT_MS=300000

compute/worker/docker-compose.yml

@@ -24,7 +24,7 @@ services:
       PORT: ${PORT:-8081}
       COMPUTE_WORKER_TOKEN: ${COMPUTE_WORKER_TOKEN:-local-compute-token}
       S3_PREFIX: ${S3_PREFIX:-openreader}
-      COMPUTE_PREWARM_MODELS: ${COMPUTE_PREWARM_MODELS:-true}
+      COMPUTE_PREWARM_MODELS: ${COMPUTE_PREWARM_MODELS:-false}
     ports:
       - "8081:8081"
     develop:

compute/worker/src/runtime.ts

@@ -510,7 +510,7 @@ export async function createComputeWorkerApp(options: CreateComputeWorkerAppOpti
   const pdfTimeoutMs = timeoutConfig.pdfTimeoutMs;
   const pdfHardCapMs = timeoutConfig.pdfHardCapMs;
   const pdfAttempts = readIntEnv('COMPUTE_PDF_JOB_ATTEMPTS', 1);
-  const prewarmModels = parseBoolEnv('COMPUTE_PREWARM_MODELS', true);
+  const prewarmModels = parseBoolEnv('COMPUTE_PREWARM_MODELS', false);
   const jobsStreamMaxBytes = readIntEnv('COMPUTE_JOBS_STREAM_MAX_BYTES', 256 * 1024 * 1024);
   const eventsStreamMaxBytes = readIntEnv('COMPUTE_EVENTS_STREAM_MAX_BYTES', 128 * 1024 * 1024);
   const jobStatesMaxBytes = readIntEnv('COMPUTE_JOB_STATES_MAX_BYTES', 64 * 1024 * 1024);

docs-site/docs/deploy/compute-worker.md

@@ -51,7 +51,7 @@ Common optional variables:
 - `COMPUTE_WORKER_HOST=0.0.0.0`
 - `PORT=8081` for local/manual runs. Platforms like Railway usually inject `PORT`.
 - `LOG_FORMAT=json` and `COMPUTE_LOG_LEVEL=info`
-- `COMPUTE_PREWARM_MODELS=true`
+- `COMPUTE_PREWARM_MODELS=false` by default. Set it to `true` to pre-download ONNX models during worker startup.
 - `COMPUTE_JOB_CONCURRENCY=1`
 - `COMPUTE_WHISPER_TIMEOUT_MS=30000`
 - `COMPUTE_PDF_TIMEOUT_MS=300000`