feat: reorder first/latency in seconds, add effort column

- logs columns are now Key | Account | Model | Effort | Type | Tokens |
  Cost | First | Latency | Tok/s | Time
- First and Latency render in seconds (5.3s) instead of milliseconds
- Effort shows the request reasoning_effort (- when absent) and is
  filterable; the detail line appends it to the model as model (effort)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

README.md

@@ -83,7 +83,7 @@ Sub2API admin usage API and refreshes every 60 seconds by default
 (`--logs-refresh-seconds` / `SHUSUB2_LOGS_REFRESH_SECONDS`). Columns:
 
 ```text
-Key | Account | Model | Type | Tokens | Cost | Latency | First | Tok/s | Time
+Key | Account | Model | Effort | Type | Tokens | Cost | First | Latency | Tok/s | Time
 ```
 
 `Type` is the Sub2API `request_type` (`sync` / `stream` / `ws_v2` / `cyber`).
@@ -91,8 +91,10 @@ Key | Account | Model | Type | Tokens | Cost | Latency | First | Tok/s | Time
 the table shows the per-bucket breakdown, actual cost, first-token latency,
 decode speed, upstream model mapping, user, and request id.
 
-`First` is the first-token latency (`first_token_ms`). `Tok/s` is the decode
-throughput computed as `output_tokens / (latency - first_token)`; it shows
+`Effort` is the request's `reasoning_effort` (`-` when absent). `First` is the
+first-token latency and `Latency` the total duration, both shown in seconds.
+`Tok/s` is the decode throughput computed as
+`output_tokens / (latency - first_token)`; it shows
 `-` when there is no output or no positive decode window. In the TUI each
 API key name is rendered in a stable per-key color so rows from the same
 key are easy to group visually (`--once --logs` output stays plain text).