Make poll intervals and operational timeouts configurable

New env vars: UNLOAD_POLL_INTERVAL, HISTORY_POLL_INTERVAL, PROBE_TIMEOUT,
FREE_TIMEOUT, WARM_TIMEOUT, SHUTDOWN_TIMEOUT, PROMPT_CAPTURE_LIMIT.
Defaults unchanged; invalid values fail fast at startup.

SPEC.md

@@ -81,12 +81,14 @@ ComfyUI listener (`:8188` → `COMFY_URL`):
 2. Unload Ollama: `GET /api/ps`; for each model `POST /api/generate
    {"model":M,"keep_alive":0}`; if that returns non-2xx (embedding-only
    models), `POST /api/embed {"model":M,"input":"x","keep_alive":0}`. Poll
-   `/api/ps` every 500 ms until empty or `UNLOAD_TIMEOUT`. On timeout: log and
+   `/api/ps` every `UNLOAD_POLL_INTERVAL` (default 500 ms) until empty or
+   `UNLOAD_TIMEOUT`. On timeout: log and
    continue (degrade, don't fail the user's request).
 3. Forward the original request body to ComfyUI `/prompt`, return status,
    headers and body to the caller unchanged, flush.
 4. If the response is 200 and contains `prompt_id`: in a goroutine, poll
-   `GET /history/<prompt_id>` every 1 s until the entry has
+   `GET /history/<prompt_id>` every `HISTORY_POLL_INTERVAL` (default 1 s)
+   until the entry has
    `status.completed == true`, `status.status_str == "error"`, or
    `JOB_TIMEOUT`. Then `POST /free {"unload_models":true,"free_memory":true}`.
    Then release the image lock.
@@ -111,6 +113,13 @@ load time. Off by default.
 | `LLM_WAIT_TIMEOUT` | `10m` | max time an LLM request waits for the lock before 503 |
 | `WARM_MODEL` | `` | optional model to reload after an image job |
 | `LOG_LEVEL` | `info` | `debug` logs every lock transition |
+| `UNLOAD_POLL_INTERVAL` | `500ms` | `/api/ps` poll interval while unloading |
+| `HISTORY_POLL_INTERVAL` | `1s` | `/history/<id>` poll interval while a job runs |
+| `PROBE_TIMEOUT` | `5s` | startup probe of both upstreams |
+| `FREE_TIMEOUT` | `30s` | `POST /free` call after an image job |
+| `WARM_TIMEOUT` | `2m` | warm-model reload after an image job |
+| `SHUTDOWN_TIMEOUT` | `10s` | graceful shutdown on SIGINT/SIGTERM |
+| `PROMPT_CAPTURE_LIMIT` | `65536` | bytes of the `/prompt` response buffered to find `prompt_id` (pass-through is unaffected) |
 
 Startup fails fast on unparsable values. Both upstreams are probed once at
 start (`/api/version`, `/system_stats`); failure is logged, not fatal.