Migrate backend jobs to Redis Streams

backend/.env.example

@@ -15,12 +15,42 @@ VLM_MODEL=qwen3-vl:30b
 # API key for the FastAPI app (change in production)
 API_KEY=your-secret-key-here
 
-# PRO completion timeout (seconds)
-PRO_COMPLETION_TIMEOUT=1200
+# Job backend
+JOB_BACKEND=redis
+REDIS_URL=redis://localhost:6379/0
+JOB_REDIS_PREFIX=llmtext:jobs
+JOB_CONSUMER_NAME=
+JOB_SHARED_TEMP_DIR=/tmp/llm-in-text-jobs
+JOB_STATE_TTL_SECONDS=600
+JOB_EVENT_TTL_SECONDS=600
+JOB_EVENT_STREAM_MAXLEN=512
+JOB_CANCEL_POLL_SECONDS=0.5
+JOB_BUSY_NORMAL_THRESHOLD=0.25
+JOB_BUSY_HIGH_THRESHOLD=0.75
+JOB_BUSY_FULL_THRESHOLD=1.0
 
-# Concurrency limits
-STANDARD_CONCURRENCY_LIMIT=5
-PRO_CONCURRENCY_LIMIT=20
+# Per-queue concurrency and capacity
+JOB_COMPLETION_CONCURRENCY=2
+JOB_COMPLETION_MAX_QUEUE=16
+JOB_PRO_COMPLETION_CONCURRENCY=1
+JOB_PRO_COMPLETION_MAX_QUEUE=8
+JOB_COMPRESS_CONCURRENCY=1
+JOB_COMPRESS_MAX_QUEUE=8
+JOB_OCR_CONCURRENCY=1
+JOB_OCR_MAX_QUEUE=8
+JOB_CONVERT_CONCURRENCY=1
+JOB_CONVERT_MAX_QUEUE=8
+JOB_TTS_CONCURRENCY=1
+JOB_TTS_MAX_QUEUE=4
+JOB_ASR_CONCURRENCY=1
+JOB_ASR_MAX_QUEUE=4
+
+# Timeouts (seconds)
+LLM_COMPLETION_TIMEOUT=600
+LLM_OCR_TIMEOUT=600
+
+# Compression limit
+DOC_COMPRESS_CONTEXT_LIMIT=128000
 
 # Legacy fallback: if LLM_BASE_URL is not set, OLLAMA_HOST will be auto-converted to /v1/ path
 #OLLAMA_HOST=http://localhost:11434