opencode-cache-coach 0.2.0 → 0.2.1

package/README.md

@@ -13,7 +13,10 @@ The cache indicator and `/cache` details show where you stand. Tips and expiry m
 decide what to do next, such as compacting while the cache is warm or using a cheaper model when
 the context must be written again.
 
-Requires OpenCode 2.2 or later.
+![Cache Coach expiry notice estimating the cost of rewriting a large context and suggesting cheaper compaction.](https://raw.githubusercontent.com/pedropombeiro/opencode-plugins/main/packages/cache-coach/images/cache-expiry-notice.png)
+
+Requires OpenCode 2.2 or later. See the [source repository](https://github.com/pedropombeiro/opencode-plugins/tree/main/packages/cache-coach)
+for local builds and the [MIT license](https://github.com/pedropombeiro/opencode-plugins/blob/main/LICENSE).
 
 ## Installation
 
@@ -37,6 +40,8 @@ messages out of model requests.
 
 The prompt footer shows the cache state of the session on screen:
 
+![Animated Cache Coach footer showing the cache countdown and state indicators.](https://raw.githubusercontent.com/pedropombeiro/opencode-plugins/main/packages/cache-coach/images/cache-countdown.gif)
+
 | Footer                                 | Meaning                                                                  |
 | -------------------------------------- | ------------------------------------------------------------------------ |
 | `● cache 3:42`                         | Warm. The next message reads the context from the cache.                 |
@@ -81,6 +86,11 @@ A compaction after the cache expires writes the whole context again, so compacti
 model saves most of that cost. Set `compactionModel` to name the model. Without it, the message
 only says that a cheaper model costs less.
 
+This recording shows the expiry advice and footer as the user switches to GPT-6.1 Sol and
+starts compaction. The plugin suggests the change; it doesn't switch models or compact automatically.
+
+![Animated expiry notice and footer during a user-initiated model switch and compaction.](https://raw.githubusercontent.com/pedropombeiro/opencode-plugins/main/packages/cache-coach/images/compaction.gif)
+
 The message appears once each time the session goes idle, in top-level sessions whose last request
 the TUI saw finish, and only when the next message writes at least `minTokens` and costs at least
 `minCost`. The server part removes these messages from every model request, so the model never

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "opencode-cache-coach",
-  "version": "0.2.0",
+  "version": "0.2.1",
   "description": "OpenCode plugin that shows whether a session's prompt cache is still warm and suggests cheaper habits when a costly pattern shows up",
   "author": {
     "name": "Pedro Pombeiro",