Add Prometheus metrics to expose request success/failure counts and
error types so operators can monitor and alert on API communication
issues.

New metrics:
- coder_logstream_requests_total{status} - tracks success/failure counts
- coder_logstream_errors_total{type} - tracks errors by type (network)

New flag:
- --metrics-addr / CODER_LOGSTREAM_METRICS_ADDR (default :9100)
  Starts an HTTP server serving /metrics for Prometheus scraping.

Instrumented paths:
- PostLogSource failures
- ConnectRPC28WithRole / ConnectRPC20 failures
- Log Send failures
- All success paths

Resolves #173, partially addresses #146

…Total

Address review feedback from @deansheather:
- Replace scattered metric calls with an instrumentedClient wrapper
  around agentsdk.Client that records metrics in one place
- Remove redundant errorsTotal metric (was always incremented alongside
  requestsTotal failure)
- Add method label to requestsTotal for better granularity:
  PostLogSource, ConnectRPC, SendLog

Address review feedback:
- Replace global prometheus metrics with a metricsCollector struct
  holding a custom prometheus.Registry, passed to all components
- Use requestMethod enum (methodPostLogSource, methodConnectRPC,
  methodSendLog) instead of raw strings
- Tests create fresh metricsCollector instances, avoiding flakes
  from shared global state in parallel test execution