README.md

@@ -1,128 +1,59 @@
-# lmcli - Large Language Model CLI
+# lmcli
 
-`lmcli` is a versatile command-line interface for interacting with LLMs and LMMs.
+`lmcli` is a (Large) Language Model CLI.
 
-## Features
+Current features:
+- Perform one-shot prompts with `lmcli prompt <message>`
+- Manage persistent conversations with the `new`, `reply`, `view`, `rm`,
+  `edit`, `retry`, `continue` sub-commands.
+- Syntax highlighted output
+- Tool calling, see the [Tools](#tools) section.
 
-- Multiple model backends (Ollama, OpenAI, Anthropic, Google)
+Maybe features:
-- Customizable agents with tool calling
+- Chat-like interface (`lmcli chat`) for rapid back-and-forth conversations
-- Persistent conversation management
+- Support for additional models/APIs besides just OpenAI
-- Interactive terminal interface for seamless chat experiences
-- Syntax highlighting!
 
-## Screenshots
+## Tools
+Tools must be explicitly enabled by adding the tool's name to the
+`openai.enabledTools` array in `config.yaml`.
 
-[TODO: Add screenshots of the TUI in action, showing different views and features]
+Note: all filesystem related tools operate relative to the current directory
+only. They do not accept absolute paths, and efforts are made to ensure they
+cannot escape above the working directory). **Close attention must be paid to
+where you are running `lmcli`, as the model could at any time decide to use one
+of these tools to discover and read potentially sensitive information from your
+filesystem.**
 
-## Installation
+It's best to only have tools enabled in `config.yaml` when you intend to be
+using them, since their descriptions (see `pkg/cli/functions.go`) count towards
+context usage.
 
-To install `lmcli`, make sure you have Go installed on your system, then run:
+Available tools:
 
-```sh
+- `read_dir` - Read the contents of a directory.
-go install git.mlow.ca/mlow/lmcli@latest
+- `read_file` - Read the contents of a file.
+- `write_file` - Write contents to a file.
+- `file_insert_lines` - Insert lines at a position within a file. Tricky for
+  the model to use, but can potentially save tokens.
+- `file_replace_lines` - Remove or replace a range of lines within a file. Even
+  trickier for the model to use.
+
+## Install
+
+```shell
+$ go install git.mlow.ca/mlow/lmcli@latest
 ```
 
-## Configuration
-
-`lmcli` uses a YAML configuration file located at `~/.config/lmcli/config.yaml`. Here's a sample configuration:
-
-```yaml
-defaults:
-  model: claude-3-5-sonnet-20240620
-  maxTokens: 3072
-  temperature: 0.2
-conversations:
-  titleGenerationModel: claude-3-haiku-20240307
-chroma:
-  style: onedark
-  formatter: terminal16m
-agents:
-  - name: code-helper
-    tools:
-      - dir_tree
-      - read_file
-      #- write_file
-    systemPrompt: |
-      You are an experienced software engineer...
-  # ...
-providers:
-  - kind: ollama
-    models:
-      - phi3:instruct
-      - llama3:8b
-  - kind: anthropic
-    apiKey: your-api-key-here
-    models:
-      - claude-3-5-sonnet-20240620
-      - claude-3-opus-20240229
-      - claude-3-haiku-20240307
-  - kind: openai
-    apiKey: your-api-key-here
-    models:
-      - gpt-4o
-      - gpt-4-turbo
-  - name: openrouter
-    kind: openai
-    apiKey: your-api-key-here
-    baseUrl: https://openrouter.ai/api/
-    models:
-      - qwen/qwen-2-72b-instruct
-  # ...
-```
-
-Customize this file to add your own providers, agents, and models.
-
 ## Usage
 
-Here's the default help output for `lmcli`:
+Invoke `lmcli` at least once:
 
-```
+```shell
-[TODO: Insert the output of `lmcli help` here]
+$ lmcli help
 ```
 
-### Examples
+Edit `~/.config/lmcli/config.yaml` and set `openai.apiKey` to your API key.
 
-Start a new chat:
+Refer back to the output of `lmcli help` for usage.
-```sh
-lmcli chat --agent code-helper
-```
 
-Send a one-shot prompt:
+Enjoy!
-```sh
-lmcli prompt "Explain the theory of everything"
-```
-
-## Agents
-
-Agents in `lmcli` are configurations that combine a system prompt with a set of available tools. You can define agents in the `config.yaml` file and switch between them using the `--agent` or `-a` flag.
-
-Example:
-```sh
-lmcli chat -a financier
-```
-
-## Tools
-
-`lmcli` supports various tool calling. Currently built-in tools are:
-
-- `dir_tree`: Display a directory structure
-- `read_file`: Read the contents of a file
-- `write_file`: Write content to a file
-- `file_insert_lines`: Insert lines at a specific position in a file
-- `file_replace_lines`: Replace a range of lines in a file
-
-Obviously, some of these tools carry significant risk. Use wisely :)
-
-## Contributing
-
-Contributions to `lmcli` are welcome! Feel free to open issues or submit pull requests on the project repository.
-
-For a full list of planned features and improvements, check out the [TODO.md](TODO.md) file.
-
-## License
-
-MIT
-
-## Acknowledgements
-
-`lmcli` is just a hobby project. Special thanks to the Go community and the creators of the libraries used in this project.

TODO.md

@@ -19,8 +19,6 @@
   the conversation we had six months ago about X")
 - [ ] Conversation categorization - model driven category creation and
   conversation classification
-- [ ] Image input
-- [ ] Image output (sixel support?)
 
 ## UI
 - [x] Prettify/normalize tool_call and tool_result outputs so they can be