feat: expand ai retry policy

README.md

@@ -85,6 +85,8 @@ scheduling.
   returning secrets.
 - `GET /api/v1/infra/status` returns AI-server sidecar telemetry
   (GPU, containers and vLLM live metrics) when configured.
+- `GET /health/detail` returns PostgreSQL, provider, queue, error, throughput
+  and infra components for Portal `admin/health`.
 - `GET /healthz` returns process health.
 - `GET /readyz` checks PostgreSQL readiness.
 - Built-in workers expose open Kubernetes endpoints on `WORKER_HTTP_PORT`:
@@ -94,6 +96,20 @@ All `/api/v1/*` endpoints require `Authorization: Bearer <AI_SERVICE_TOKEN>`
 when `AI_SERVICE_TOKEN` is configured. Health and readiness endpoints stay open
 for Kubernetes probes.
 
+## Retry policy
+
+Workers store a normalized `error_code` on failed jobs. AI Service requeues only
+explicitly retryable categories while attempts remain.
+
+| Category | Retry | Delay |
+| --- | --- | --- |
+| `provider_unavailable`, `model_unavailable`, `provider_error`, `dependency_error`, `timeout`, `storage_error`, `stale_worker` | yes | 30s |
+| `bad_response`, `transcript_hallucination`, `transcript_incomplete`, `internal_error`, `unknown` | yes | 2m |
+| `bad_audio`, `bad_input`, `context_length`, `unsupported_task`, `cancelled` | no | - |
+
+Domain services may still expose manual retry for terminal errors after the
+underlying data or prompt is corrected.
+
 ## Configuration
 
 - `HTTP_HOST`, default `0.0.0.0`