Implemented vibecoding functionality for llmchat

README.md

@@ -206,6 +206,9 @@ The instance exposes the following methods (all returning a `(status, result)` t
 - `reset_context()`: clear the conversation history and re-add the system prompt
 - `get_completion(prompt)`: prompt the LLM and return the response message
 - `list_models()`: list available model IDs from the current active provider
+- `get_last_response()`: get the most recent assistant's response as a plain string
+- `add_file(fname)`: read a text file and add it to the context (within the message limit)
+- `export()`: export the entire current conversation (within the message limit) as a plain string
 
 ## Applets (`app.*`)
 
@@ -241,7 +244,7 @@ The editor mode supports the following subset of POSIX ed commands in the standa
 
 ### `app.llmchat`
 
-A simple interactive chat with remote LLMs. Configured via `llmcfg.json` (see the `deck.llm` module reference) placed into the storage root.
+A simple interactive chat with remote LLMs. Configured via `llmcfg.json` (see the `deck.llm` module reference) placed into the storage root. Run with the single `llmchat()` method it exports.
 
 Supported chat commands:
 
@@ -253,6 +256,11 @@ Supported chat commands:
 - `/model`: display or set the current model selection
 - `/provlist`: list provider IDs in the config
 - `/modellist`: list model IDs available for current provider
+- `/add`: add a (text) file to the context
+- `/saveconv`: save the entire conversation log (within the current limits) into a file
+- `/savelast`: save the most recent message into a file
+- `/savecode`: extract code blocks from the most recent message and save them into a file
+- `/edcode`: extract code blocks from the most recent message and open `app.ed.edbuf()` on the contents
 - `/exit` or `/quit`: exit the chat applet
 
 ### `app.blog`