xonecas.io
64875
Mc

mini-coder / commit f3346d1

fix: More idea alignment work

xonecas2026-03-14 f3346d16993176e8c88946d31aa93d24ffc32e4d parent d9f67cf

6 files changed

README.md+2−2
@@ -50,7 +50,7 @@ Need more firepower? I connect to **MCP servers** over HTTP or stdio — bolt on
5050 - **Slash commands** — `/model` or `/models` to list/switch models, `/model effort <low|medium|high|xhigh|off>` for reasoning effort, `/reasoning [on|off]` to toggle reasoning display, `/context` to inspect or tune pruning/tool-result caps, `/cache` to configure prompt caching, `/review` for a code review (global custom command, auto-created at `~/.agents/commands/review.md`), `/agent [name]` to set or clear an active primary agent, `/undo` to roll back a turn, `/new` for a clean session, `/mc …
5151
5252 - **Custom commands** — drop a `.md` file in `.agents/commands/` and it becomes a `/command`. Claude-compatible `.claude/commands/` works too. Supports argument placeholders (`$ARGUMENTS`, `$1`…`$9`) and shell interpolation (`` !`cmd` ``). Global commands live in `~/.agents/commands/` and `~/.claude/commands/`. Custom commands take precedence over built-ins. → [docs/custom-commands.md](docs/custom-commands.md)
53-- **Custom agents** — drop a `.md` file in `.agents/agents/` or `.claude/agents/` (or `~/.agents/agents/` / `~/.claude/agents/` globally) and activate it with `/agent [name]`. Agent definitions are also exposed to subagent delegation unless `mode: primary`. `@agent-name` is supported for completion and is a useful prompt convention. → [docs/custom-agents.md](docs/custom-agents.md)
53+- **Custom agents** — drop a `.md` file in `.agents/agents/` or `.claude/agents/` (or `~/.agents/agents/` / `~/.claude/agents/` globally) and activate it with `/agent [name]`. Agent definitions are also exposed to subagent delegation unless `mode: primary`. → [docs/custom-agents.md](docs/custom-agents.md)
5454 - **Skills** — place a `SKILL.md` in `.agents/skills/<name>/` and inject it into any prompt with `@skill-name`. Claude-compatible `.claude/skills/<name>/SKILL.md` works too. Skills are _never_ auto-loaded — always explicit. → [docs/skills.md](docs/skills.md)
5555 - **Post-tool hooks** — drop an executable at `.agents/hooks/post-<tool>` (or `~/.agents/hooks/post-<tool>` globally) and I'll run it after matching built-in tool calls. → [docs/tool-hooks.md](docs/tool-hooks.md)
5656 - **Beautiful, minimal output** — diffs for edits, formatted trees for file searches, a live status bar with model, git branch, and token counts.
@@ -117,7 +117,7 @@ export EXA_API_KEY=your-exa-key # enables webSearch/webContent
117117 mc
118118 ```
119119
120-Or drop me a prompt straight away and stay in the session:
120+Or drop me a prompt straight away for one-shot mode (runs once, then exits):
121121
122122 ```bash
123123 mc "Refactor the auth module to use async/await"
TODO.md+5−4
@@ -1,11 +1,12 @@
11 # TODO
22
3-- Tool hooks output prints inline with spinner
4-- Review our markdown renderer. Let's make it render the raw markdown, but syntax highlited
3+- Most models hang for long periods during turns. Sometines needing the user to interrupt to continue
4+- Our output is not responsive. The user experience is poor right now, with long period of waiting for output. I've compared the same priovider and model with pi and opencode and their output is responsive and fast. This is critical to fix, it's part of our core idea and philosophy
5+
6+- Tool hooks output prints inline with spinner when they should output in a new line and indented like the tool calls output.
7+- Review our markdown renderer. Let's make it render the raw markdown, but syntax highlited.
58 - add a spinner state showing the user when the undo snapshotting is happening
69 - Structuted output when a skill is auto loaded for the agent
7-
8-- Kimi-k2.5 and other models that use the same sdk hang for long periods during turns.
910 - Kimi-k2.5, GLM-5 and other models that use the same sdk produce these errors:
1011
1112 Error 1:
docs/mini-coder.1.md+3−3
@@ -29,7 +29,7 @@
2929 : Display help information.
3030
3131 **[prompt]**
32-: Optional one-shot prompt text before entering interactive mode.
32+: Optional one-shot prompt text. Runs once, then exits.
3333
3434 ## INTERACTIVE COMMANDS
3535 Inside the interactive session, the following slash commands are available:
@@ -96,8 +96,8 @@ Inside the interactive session, the following slash commands are available:
9696 **Shell Integration**
9797 : Prefix user prompts with `!` to run shell commands inline directly into the context.
9898
99-**File & Agent Referencing**
100-: Prefix words with `@` to reference files, custom agents, or skills within prompts (supports tab completion).
99+**File & Skill Referencing**
100+: Prefix words with `@` to reference files or skills within prompts (supports tab completion).
101101
102102 ## BUILT-IN TOOLS
103103 The agent has access to the following tools:
mini-coder-idea.md+1−1
@@ -43,7 +43,7 @@ conventions and not introduce more specs. (`.agents` / `AGENTS.md`, while also s
4343 - `/reasoning` toggles display of model reasoning output.
4444 - `/context` configures context pruning and tool-result caps.
4545 - `/cache` toggles prompt caching globally; sub-commands configure provider-specific caching (`/cache openai <in_memory|24h>`, `/cache gemini <off|cachedContents/...>`).
46- - `/review` reviews recent changes via a global command installed at app start (`~/.agents/commands/review.md`), and can be customized or shadowed locally.
46+ - `/review` reviews recent changes via a global custom command installed at app start (`~/.agents/commands/review.md`), and can be customized or shadowed locally.
4747 - `/agent` sets or clears the active primary agent.
4848 - `/mcp` list/add/remove mcp servers. servers are stored in sqlite
4949 - `/new` starts a new session with clean context. Clean UI and fresh session display
src/cli/commands.ts+2−2
@@ -590,7 +590,7 @@ function handleHelp(
590590 const tag =
591591 agent.source === "local" ? c.dim(" (local)") : c.dim(" (global)");
592592 writeln(
593- ` ${c.magenta(`@${agent.name}`.padEnd(26))} ${c.dim(agent.description)}${modeTag}${tag}`,
593+ ` ${c.magenta(agent.name.padEnd(26))} ${c.dim(agent.description)}${modeTag}${tag}`,
594594 );
595595 }
596596 }
@@ -615,7 +615,7 @@ function handleHelp(
615615
616616 writeln();
617617 writeln(
618- ` ${c.green("@agent".padEnd(26))} ${c.dim("run prompt through a custom agent (Tab to complete)")}`,
618+ ` ${c.green("/agent <name>".padEnd(26))} ${c.dim("activate a custom agent by name")}`,
619619 );
620620 writeln(
621621 ` ${c.green("@skill".padEnd(26))} ${c.dim("load a skill body on demand into the prompt (Tab to complete)")}`,
src/tools/subagent.ts+1−1
@@ -38,7 +38,7 @@ export function createSubagentTool(
3838 ): ToolDef<SubagentInput, SubagentOutput> {
3939 const agentSection =
4040 availableAgents.size > 0
41- ? `\n\nWhen the user's message contains @<agent-name>, delegate to that agent by setting agentName to the exact agent name. Available custom agents: ${[...availableAgents.entries()].map(([name, cfg]) => `"${name}" (${cfg.description})`).join(", ")}.`
41+ ? `\n\nIf a specific custom agent should be used, set agentName to the exact agent name. Available custom agents: ${[...availableAgents.entries()].map(([name, cfg]) => `"${name}" (${cfg.description})`).join(", ")}.`
4242 : "";
4343 return {
4444 name: "subagent",