Documentation & Readme updates

Author: piotrekno1

README.md

@@ -84,30 +84,19 @@ Pass `hubs=` to track model download provenance. Hubs are framework-agnostic and
 | `huggingface` | Downloads via `huggingface_hub` |
 | `torchhub` | Downloads via `torch.hub` |
 
-For `torch` and `keras`, models are user-defined subclasses so there's no constructor to patch. Use `client.load()` to get load/unload tracking alongside inference:
-
-```python
-model = client.load(MyModel)
-output = model(x)  # tracked automatically
-```
-
 For unsupported frameworks, see [Manual tracking](docs/manual-tracking.md).
 
 ## Configuration
 
-| Parameter | Default | Env var | Description |
-|---|---|---|---|
-| `dsn` | - | `WILDEDGE_DSN` | `https://<secret>@ingest.wildedge.dev/<key>` |
-| `app_version` | `None` | - | Your app's version string |
-| `app_identity` | `<project_key>` | `WILDEDGE_APP_IDENTITY` | Namespace for offline persistence. Set per-app in multi-process workloads |
-| `debug` | `false` | `WILDEDGE_DEBUG` | Log events to console |
-| `batch_size` | `10` | - | Events per transmission (1-100) |
-| `flush_interval_sec` | `60` | - | Max seconds between flushes (1-3600) |
-| `max_queue_size` | `200` | - | In-memory buffer limit (10-10000) |
-| `enable_offline_persistence` | `true` | - | Persist unsent events to disk and replay on restart |
-| `max_event_age_sec` | `900` | - | Max age before dead-lettering |
-| `enable_dead_letter_persistence` | `false` | - | Persist dropped batches to disk |
-| `sampling_interval_s` | `30.0` | `WILDEDGE_SAMPLING_INTERVAL_S` | Seconds between background hardware snapshots. Set to `0` or `None` to disable |
+| Parameter | Default | Description |
+|---|---|---|
+| `dsn` | - | `https://<secret>@ingest.wildedge.dev/<key>` (or `WILDEDGE_DSN`) |
+| `app_version` | `None` | Your app's version string |
+| `app_identity` | `<project_key>` | Namespace for offline persistence. Set per-app in multi-process workloads (or `WILDEDGE_APP_IDENTITY`) |
+| `enable_offline_persistence` | `true` | Persist unsent events to disk and replay on restart |
+| `sampling_interval_s` | `30.0` | Seconds between background hardware snapshots. Set to `0` or `None` to disable (or `WILDEDGE_SAMPLING_INTERVAL_S`) |
+
+For advanced options (batching, queue tuning, dead-letter storage), see [Configuration](docs/configuration.md).
 
 ## Privacy
 

docs/configuration.md

@@ -0,0 +1,24 @@
+# Configuration
+
+Full reference for all `WildEdge` client parameters.
+
+## Core
+
+| Parameter | Default | Env var | Description |
+|---|---|---|---|
+| `dsn` | - | `WILDEDGE_DSN` | `https://<secret>@ingest.wildedge.dev/<key>` |
+| `app_version` | `None` | - | Your app's version string |
+| `app_identity` | `<project_key>` | `WILDEDGE_APP_IDENTITY` | Namespace for offline persistence. Set per-app in multi-process workloads |
+| `enable_offline_persistence` | `true` | - | Persist unsent events to disk and replay on restart |
+| `sampling_interval_s` | `30.0` | `WILDEDGE_SAMPLING_INTERVAL_S` | Seconds between background hardware snapshots. Set to `0` or `None` to disable |
+
+## Advanced
+
+| Parameter | Default | Env var | Description |
+|---|---|---|---|
+| `batch_size` | `10` | - | Events per transmission (1-100) |
+| `flush_interval_sec` | `60` | - | Max seconds between flushes (1-3600) |
+| `max_queue_size` | `200` | - | In-memory buffer limit (10-10000) |
+| `max_event_age_sec` | `900` | - | Max age in seconds before an event is dropped |
+| `enable_dead_letter_persistence` | `false` | - | Persist dropped batches to disk for later inspection |
+| `debug` | `false` | `WILDEDGE_DEBUG` | Log SDK internals to console |

docs/manual-tracking.md

@@ -9,6 +9,15 @@ Use manual tracking when your framework is not covered by a WildEdge integration
 - You want to attach input/output metadata (token counts, image dimensions, confidence scores, etc.)
 - You want to record user feedback tied to a specific inference
 
+## torch and keras
+
+For `torch` and `keras`, models are user-defined subclasses with no constructor to patch. Use `client.load()` to get load, unload, and inference tracking automatically:
+
+```python
+model = client.load(MyModel)
+output = model(x)  # tracked automatically
+```
+
 ## Register your model
 
 Every model needs a handle before you can track events against it. Pass the model object and an explicit `model_id`: