refactor: rename the commands after what they do

Slugs and titles now say what each command does, and every command is
described the same way.

- `sessions` "Chat Sessions" -> `chat-history` "Chat History"
- `models` "Ollama Models" -> `manage-models` "Manage Models"
- `setup` "Set Up Lam Agent" -> "Setup & Status", which no longer repeats
  the extension name
- Drop the redundant "Lam Agent" subtitle from chat, snip and models: the
  extension name is already shown next to the command

`chat` and `snip` keep their slugs, so the deeplinks and hotkeys the README
documents still work, and the two cross-launches (`snip` -> `chat`,
chat -> `snip`) are untouched. The other two slugs change, so a deeplink or
a shortcut bound to `sessions` or `models` needs rebinding.

In-view navigation titles are aligned with the new titles (the setup view
was "Lam Agent Setup"), and the README's command table, architecture tree
and prose follow.

package.json

@@ -11,34 +11,31 @@
     {
       "name": "chat",
       "title": "Chat with Lam",
-      "subtitle": "Lam Agent",
       "description": "Ask Lam anything. Answers stream in as they are generated, your session history is kept, and Lam can search the web when it needs current information.",
       "mode": "view"
     },
     {
       "name": "snip",
       "title": "Snip to Lam",
-      "subtitle": "Lam Agent",
       "description": "Capture a region of the screen and start a new chat about it. The launcher window closes first so it cannot end up in the shot. Offered only when the model in preferences supports image input.",
       "mode": "no-view"
     },
     {
-      "name": "sessions",
-      "title": "Chat Sessions",
+      "name": "chat-history",
+      "title": "Chat History",
       "description": "Browse, reopen, and clean up your past conversations with Lam.",
       "mode": "view"
     },
     {
-      "name": "models",
-      "title": "Ollama Models",
-      "subtitle": "Lam Agent",
+      "name": "manage-models",
+      "title": "Manage Models",
       "description": "Browse the models your Ollama host can reach, pick the one Lam should use, unload one that is holding memory, and pull or delete models on a server you run. A pick takes effect immediately; a pull keeps downloading until it finishes, so leave the launcher open.",
       "mode": "view"
     },
     {
       "name": "setup",
-      "title": "Set Up Lam Agent",
-      "description": "Check your Ollama connection, pick the model Lam should use, and tune how Lam answers.",
+      "title": "Setup & Status",
+      "description": "Check your Ollama connection, pick the model Lam should use, tune how Lam answers, and clear out old chats or screenshots you never sent.",
       "mode": "view"
     }
   ],
@@ -53,7 +50,7 @@
     {
       "name": "model",
       "title": "Model",
-      "description": "The model Lam should use, for example deepseek-v4.1-flash:cloud or gpt-oss:120b. Run \"Set Up Lam Agent\" to pick from the models your key can access.",
+      "description": "The model Lam should use, for example deepseek-v4.1-flash:cloud or gpt-oss:120b. Run \"Setup & Status\" to pick from the models your key can access.",
       "type": "textfield",
       "required": true
     },