xonecas.io
64875
Mc

mini-coder / commit 9d9012e

docs: address spec notes — branding, /effort command, remove MCP plugin section

xonecas2026-04-05 9d9012e084bfc89df3eb18742e6596baf8a92ed8 parent 499bbe6

2 files changed

TODO.md+0−4
@@ -40,7 +40,3 @@
4040 - [ ] `index.ts` — entry point, provider discovery, startup sequence, command routing
4141 - [ ] Commands — `/model`, `/session`, `/new`, `/fork`, `/undo`, `/reasoning`, `/verbose`, `/login`, `/logout`, `/help`, `/effort`
4242 - [ ] Input handling — `/skill:name` parsing, image path detection, Tab file autocomplete
43-
44-## Open questions
45-
46-- **`/effort` command**: we need a command to control model reasoning effort at runtime (similar to `/model` for model switching). This is missing from `spec.md` — update the spec before implementing. Consider: should it cycle through levels (`low` → `med` → `high` → `xhigh`), show a selector, or accept an argument (`/effort high`)? How does it interact with the session's `effort` field? Status bar already shows effort — just needs the command wired up.
spec.md+6−23
@@ -1,6 +1,6 @@
11 # mini-coder — spec
22
3-A CLI coding agent. Small, fast, focused.
3+👾 Lightning fast coding agent for your terminal.
44
55 ## Motivation for rewrite
66
@@ -186,23 +186,10 @@ Plugins are declared in a config file (`~/.config/mini-coder/plugins.json` or si
186186 }
187187 ```
188188
189-Built-in plugins (like MCP) can ship with mini-coder and be enabled by default.
190-
191-### MCP as a plugin
192-
193-MCP support is implemented as a plugin, not baked into the core. The MCP plugin:
194-
195-- Connects to configured MCP servers (stdio or HTTP).
196-- Converts MCP tools into mini-coder tools, prefixed with the server name.
197-- Adds server descriptions to the system prompt.
198-- Manages server lifecycle (connect on init, disconnect on destroy).
199-
200-This keeps the core agent loop clean — it only knows about `Tool[]`, regardless of where tools come from.
201-
202189 ### Why plugins
203190
204-- **Separation of concerns**: the agent loop doesn't know about MCP, OAuth flows, or any specific integration.
205-- **Optional complexity**: users who don't need MCP don't pay for it in startup time or code complexity.
191+- **Separation of concerns**: the agent loop doesn't know about specific integrations — it only sees `Tool[]`.
192+- **Optional complexity**: capabilities are opt-in. Users only pay for what they use.
206193 - **Extensibility without bloat**: third-party tools, custom integrations, project-specific helpers — all through the same interface.
207194
208195 ## Agent loop
@@ -405,7 +392,7 @@ Three zones, top to bottom:
405392 │ ▷ Agent: I'll check the test suite... │
406393 │ ┌─────────────────────────────┐ │
407394 │ │ $ bun test │ │
408-│ │ 3 passed, 1 failed │ │
395+│ │ 3 passed, 1 failed │ │
409396 │ └─────────────────────────────┘ │
410397 │ Fixed the assertion in... │
411398 │ │
@@ -479,11 +466,6 @@ While the agent is working, an inline spinner with an activity label ("thinking"
479466
480467 Multi-line text input. Intrinsic height (1 line when empty, grows with content) up to `maxHeight: 10`, then scrolls internally. cel-tui's `TextInput` with `submitKey: "enter"` (Enter submits, Shift+Enter adds newlines).
481468
482-The `>` prompt glyph is styled to indicate state:
483-
484-- Ready for input (normal)
485-- Agent is working (dimmed/different color, input is not focused)
486-
487469 Supports:
488470
489471 - `Tab` for file path autocomplete.
@@ -518,9 +500,10 @@ Supports:
518500 | `/verbose` | Toggle full output display (disables truncation in the UI). |
519501 | `/login` | Interactive OAuth login. Shows a selector with available OAuth providers and their login status (logged in / not logged in). Selecting a provider starts the browser-based OAuth flow. Uses pi-ai's OAuth registry. Credentials are persisted to the app data directory and used for provider discovery on subsequent launches. |
520502 | `/logout` | Interactive OAuth logout. Shows a selector with logged-in OAuth providers. Selecting one clears its saved credentials. |
503+| `/effort` | Interactive effort selector. Shows the four reasoning levels (`low`, `med`, `high`, `xhigh`) with the current level highlighted. Updates the status bar immediately. Does not update the session record's `effort` field (it reflects the initial choice, like `/model`). |
521504 | `/help` | List available commands, loaded AGENTS.md files, discovered skills, and active plugins. |
522505
523-Commands are discoverable via `/` + Tab autocomplete in the input area.
506+Commands are discoverable via `/` + Tab to interactively select/filter in the input area.
524507
525508 ### Startup