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.

Dockerfile

@@ -78,11 +78,6 @@ RUN chmod +x /usr/local/bin/nats-server
 # Include OpenAI Whisper license text for runtime-downloaded ONNX artifacts.
 COPY --from=app-builder /app/compute/core/src/whisper/assets/LICENSE.txt /licenses/openai-whisper-LICENSE.txt
 
-# Bind the worker's health endpoint before downloading ONNX models, so cold
-# starts don't exceed the entrypoint's 30s /health/ready gate. Models load
-# lazily on first job instead.
-ENV COMPUTE_PREWARM_MODELS=false
-
 # Expose the port the app runs on
 EXPOSE 3003
 

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`