kodenique-agent 0.3.0 → 0.6.0

package/README.md

@@ -14,7 +14,7 @@ kodenique-agent
 ```
 
 Update with `npm install -g kodenique-agent@latest`.
-A release archive can also be installed with `npm install -g ./kodenique-agent-0.3.0.tgz`.
+A release archive can also be installed with `npm install -g ./kodenique-agent-0.6.0.tgz`.
 
 The wizard asks for their API key (hidden while typing), optional Anthropic workspace ID, model from the live Claude API list, and whether to enable thinking summaries. Use a separate key per teammate; don't include your personal key in the package.
 
@@ -60,13 +60,21 @@ Thinking is optional. Enable with `/thinking on`, disable with `/thinking off`.
 | Command | Action |
 | --- | --- |
 | `/model` or `/models` | Fetch available models and select one; saves default and clears conversation on change |
+| `/approval ask` | Ask before writes and commands (default) |
+| `/approval auto-edit` | Automatically approve file edits; ask for shell commands |
+| `/approval auto-all` | Automatically approve file edits and shell commands |
+| `/status` | Show model, project, thinking and approval mode |
+| `/` | Show available commands (menu also opens as you type `/`; Tab completes commands) |
+| `/project /path/to/folder` | Switch local project and clear conversation |
+| `/project` | Prompt for a local project path |
+| `/files` | List the current project directory locally |
 | `/help` | Show help |
 | `/clear` | Reset conversation context |
 | `/thinking on` or `/thinking off` | Toggle thinking for this session |
 | `/usage` | Show reported session input/output tokens |
 | `/exit` or Ctrl+C | Exit |
 
-The agent lists and reads files, proposes full-file edits, and runs commands such as searches and tests. Every write shows existing/proposed contents and requires `y`; every command shows its exact text and requires `y`. Tool activity is visible. It never runs an incomplete streamed tool request.
+The agent lists and reads files, proposes full-file edits, and runs commands such as searches and tests. In Ask mode, every write shows a colored change preview and requires `y`; every command shows its exact text and requires `y`. Use `/full` at an approval prompt to see the complete change. Tool activity is visible. It never runs an incomplete streamed tool request.
 
 ## Boundaries
 
@@ -74,7 +82,7 @@ Approved shell commands have your full local permissions; they are **not sandbox
 
 File tools reject traversal outside the project, symlinks, `.git`, `.ssh`, `.aws`, `.env*`, `node_modules`, `.pem` and `.key` files. This is not a complete secret detector or protection against malicious concurrent filesystem changes. Prompts and tool results are sent directly to Anthropic. File and command output limits are 100 KB; directory listings stop at 500 entries.
 
-Conversations live in memory only. There is no saved history, context compaction, dollar spending cap, or auto-approval mode. `/clear` reduces growing context. The loop stops after 15 model calls per user turn. Shell commands time out after 60 seconds; API calls after 120 seconds. Ctrl+C exits the agent; already started shell descendants may require separate cleanup.
+Conversations live in memory only. There is no saved history, context compaction, dollar spending cap. `/clear` reduces growing context. The loop stops after 15 model calls per user turn. Shell commands time out after 60 seconds; API calls after 120 seconds. Ctrl+C exits the agent; already started shell descendants may require separate cleanup.
 
 ## Build a team release
 
@@ -90,7 +98,7 @@ The package allowlist contains only the CLI, agent, stream parser, config and mo
 
 ## Validation and protocol
 
-Nine tests cover file restrictions and approvals, concurrent edits, real local HTTP request/response and errors, workspace headers, fragmented streamed thinking/text/tool JSON, signature preservation, interrupted streams, private config/environment overrides, and paginated model discovery/selection. They do not establish live model availability or account billing. No live Claude request was made for this release.
+Twelve tests cover file restrictions and approvals, concurrent edits, real local HTTP request/response and errors, workspace headers, fragmented streamed thinking/text/tool JSON, signature preservation, interrupted streams, private config/environment overrides, paginated model discovery/selection, approval mode enforcement, UI previews, and local project selection/completion. They do not establish live model availability or account billing. No live Claude request was made for this release.
 
 API contract: POST `https://api.anthropic.com/v1/messages`, `x-api-key`, `anthropic-version: 2023-06-01`, optional `anthropic-workspace-id`. Streaming uses SSE. Thinking blocks/signatures are preserved in conversation history, followed by all matching tool results.
 
@@ -100,3 +108,25 @@ Official references:
 - https://platform.claude.com/docs/en/manage-claude/authentication
 
 Model discovery uses GET `/v1/models` with your API key and workspace header, following all pagination cursors. Opus, Sonnet, and Haiku appear when returned by the API; no hardcoded catalogue is used. Discovery failures keep the current model. See https://platform.claude.com/docs/en/api/models/list.
+
+## Automatic approvals
+
+```sh
+kodenique-agent --approval auto-edit
+kodenique-agent --auto
+```
+
+`--auto` is shorthand for `--approval auto-all`. Modes apply only to the current session and are visible in every prompt. `/approval` opens a mode prompt; `/approval ask` immediately restores manual approvals. Auto-all executes requested shell commands with your full user permissions, without a confirmation prompt. File path restrictions still apply to file tools. No command safety classifier or sandbox is claimed.
+
+The terminal UI uses color when supported; set `NO_COLOR=1` for plain text. Changes are presented as compact previews, with complete edits available via `/full` before manual approval.
+
+## Open projects on your laptop
+
+```sh
+kodenique-agent /Users/you/development/my-project
+kodenique-agent "/Users/you/My Project" --auto
+```
+
+Inside chat, type `/` to display the command menu immediately, then finish typing a command or use Tab completion. `/project` prompts for a folder; you can paste or drag a folder path into that prompt. `/project ~/development/another-project` switches directly. Relative paths resolve from the active project; quotes and escaped spaces are accepted. A failed folder switch keeps the current project. A successful switch clears chat context and preserves the session's visible approval mode. `/files` lists the active folder without an API call.
+
+The selected folder is the root for file tools and the working directory for shell commands. File content reaches Claude when the agent reads it; opening a folder does not upload the whole project. Your existing approval mode controls edits and commands.

package/agent.mjs

@@ -30,7 +30,7 @@ export async function executeTool(root, tool, approve) {
   const input = tool.input ?? {};
   if(tool.name==='run_command') {
     if(typeof input.command!=='string' || !input.command.trim()) throw Error('Command required');
-    if(!await approve(`Run shell command (full local permissions):\n${input.command}`)) throw Error('User denied command');
+    if(!await approve(`Run shell command (full local permissions):\n${input.command}`,{tool:'run_command',command:input.command})) throw Error('User denied command');
     const env = Object.fromEntries(['PATH','HOME','TMPDIR','LANG','SHELL'].filter(k=>process.env[k]).map(k=>[k,process.env[k]]));
     return await new Promise(resolve=>exec(input.command,{cwd:root,env,timeout:60000,maxBuffer:100000,shell:'/bin/sh'},(error,stdout,stderr)=>resolve(JSON.stringify({exitCode:error?.code??0,stdout,stderr,error:error?.message}))));
   }
@@ -50,7 +50,7 @@ export async function executeTool(root, tool, approve) {
   if(typeof input.content!=='string' || Buffer.byteLength(input.content)>100000) throw Error('Content must be text under 100 KB');
   let old=null;
   try { old=await fs.readFile(target,'utf8'); } catch(e) { if(e.code!=='ENOENT') throw e; }
-  if(!await approve(`Write ${input.path}\n--- existing ---\n${old??'(new file)'}\n--- proposed ---\n${input.content}`)) throw Error('User denied write');
+  if(!await approve(`Write ${input.path}\n--- existing ---\n${old??'(new file)'}\n--- proposed ---\n${input.content}`,{tool:'write_file',path:input.path,before:old,after:input.content})) throw Error('User denied write');
   await safePath(root,input.path);
   let now=null;
   try { now=await fs.readFile(target,'utf8'); } catch(e) { if(e.code!=='ENOENT') throw e; }
@@ -74,7 +74,10 @@ export async function apiRequest({key,workspaceId,baseUrl='https://api.anthropic
     if(key) detail=detail.split(key).join('[REDACTED]');
     detail=printable(detail.replace(/sk-ant-[A-Za-z0-9_-]+/g,'[REDACTED]')).slice(0,1500);
     const hint=response.status===401?'Check your API key.':response.status===429?'Rate limited; wait before trying again.':'Check credits, model access, and request size.';
-    throw Error(`Claude API HTTP ${response.status}: ${detail || hint}`);
+    const error=new Error(`Claude API HTTP ${response.status}: ${detail || hint}`);
+    error.status=response.status;
+    if(response.status===429) error.code='ANTHROPIC_RATE_LIMIT';
+    throw error;
   }
   return response;
 }
@@ -97,7 +100,10 @@ export async function runTurn({messages,request,execute,output=()=>{},onUsage=()
     const results=[];
     for(const call of calls) {
       try { results.push({type:'tool_result',tool_use_id:call.id,content:String(await execute(call))}); }
-      catch(e) { results.push({type:'tool_result',tool_use_id:call.id,content:e.message,is_error:true}); }
+      catch(e) {
+        if(e.code==='ANTHROPIC_RATE_LIMIT') throw e;
+        results.push({type:'tool_result',tool_use_id:call.id,content:e.message,is_error:true});
+      }
     }
     messages.push({role:'user',content:results});
   }

package/cli.mjs

@@ -1,21 +1,24 @@
 #!/usr/bin/env node
 import { createInterface } from 'node:readline/promises';
 import { Writable } from 'node:stream';
-import fs from 'node:fs/promises';
+import {commands,completeCommand,resolveProject} from './commands.mjs';
 import { executeTool, printable, requestMessage, runTurn } from './agent.mjs';
+import {createUI,parseArgs,autoApproves,approvalModes,editPreview} from './ui.mjs';
 import { pickModel } from './models.mjs';
 import { configPath, loadConfig, saveConfig, resolveConfig } from './config.mjs';
 
 const args=process.argv.slice(2);
-const help=`kodenique-agent [project-folder]\nkodenique-agent setup       Configure your own API key and workspace\nkodenique-agent --version\n\nChat: /model /models /help /clear /thinking on|off /usage /exit\nEnvironment overrides: ANTHROPIC_API_KEY, ANTHROPIC_WORKSPACE_ID,\nANTHROPIC_MODEL, ANTHROPIC_THINKING=on|off\nRequires Node.js 22+, macOS or Linux. Writes and commands require approval.`;
+const help=`kodenique-agent [project-folder] [--approval ask|auto-edit|auto-all]\nkodenique-agent --auto      Auto-approve edits and commands for this session\nkodenique-agent setup       Configure your own API key and workspace\nkodenique-agent --version\n\nChat: / /project [folder] /files /approval /status /model /models /help /clear /thinking on|off /usage /exit\nEnvironment overrides: ANTHROPIC_API_KEY, ANTHROPIC_WORKSPACE_ID,\nANTHROPIC_MODEL, ANTHROPIC_THINKING=on|off\nRequires Node.js 22+, macOS or Linux. Ask is the default. Auto-all runs shell commands with your full permissions.`;
 if(args.includes('--help')) { console.log(help); process.exit(0); }
-if(args.includes('--version')) { console.log('kodenique-agent 0.3.0'); process.exit(0); }
-if(args.length>1 || args.some(a=>a.startsWith('-'))) { console.error(help); process.exit(1); }
+if(args.includes('--version')) { console.log('kodenique-agent 0.6.0'); process.exit(0); }
+let options;
+try { options=parseArgs(args); } catch(e) {console.error(e.message);process.exit(1);}
+let approval=options.mode;
 if(!process.stdin.isTTY) { console.error('Run in an interactive terminal.'); process.exit(1); }
 let muted=false;
 const terminalOutput=new Writable({write(chunk,encoding,done){ if(!muted) process.stdout.write(chunk); done(); }});
 terminalOutput.isTTY=true;
-const rl=createInterface({input:process.stdin,output:terminalOutput,terminal:true});
+const rl=createInterface({input:process.stdin,output:terminalOutput,terminal:true,completer:completeCommand});
 rl.on('SIGINT',()=>{ muted=false; console.log('\nExited.'); rl.close(); process.exit(130); });
 const ask=async(prompt,secret=false)=>{
   if(!secret) return (await rl.question(prompt)).trim();
@@ -26,9 +29,17 @@ const ask=async(prompt,secret=false)=>{
 let config;
 const clean=value=>printable(config?.key ? String(value).split(config.key).join('[REDACTED]') : value);
 const show=value=>console.log(clean(value));
+const ui=createUI(clean);
+const commandMenu=()=>{ui.label('Commands · type a command, Tab completes');for(const [command,description] of commands) show(`  ${command.padEnd(16)} ${description}`);};
+let chatPrompt=false;
+process.stdin.on('keypress',(text)=>{
+  if(chatPrompt && text==='/' && rl.line==='/') {
+    process.stdout.write('\n'); commandMenu(); rl.prompt(true);
+  }
+});
 try {
   const saved=await loadConfig(); config=resolveConfig(saved);
-  if(args[0]==='setup' || !config.key) {
+  if(options.workspace==='setup' || !config.key) {
     show('kodenique-agent · Setup\nUse your own Anthropic API key. It will be stored locally with owner-only file permissions.');
     const key=await ask(`API key${config.key?' (Enter keeps current)':''}: `,true) || config.key;
     if(!key) throw Error('API key required.');
@@ -39,17 +50,35 @@ try {
     const next={key,workspaceId:selectedWorkspace,model:model||config.model,thinking:thinking?thinking.toLowerCase()==='y':config.thinking};
     await saveConfig(next); config=resolveConfig(next);
     show(`Saved to ${configPath}. Environment variables override saved settings.`);
-    if(args[0]==='setup') { show('Ready. Open a project folder and run kodenique-agent.'); process.exitCode=0; }
+    if(options.workspace==='setup') { show('Ready. Open a project folder and run kodenique-agent.'); process.exitCode=0; }
   }
-  if(args[0]!=='setup') {
-    const root=await fs.realpath(args[0]||process.cwd());
-    if(!(await fs.stat(root)).isDirectory()) throw Error('Project must be an existing directory.');
-    show(`\nkodenique-agent · ${config.model}\nProject: ${root}\nThinking summaries: ${config.thinking?'on':'off'} · /help for commands\nWrites and shell commands require approval. Approved commands have full local permissions.`);
+  if(options.workspace!=='setup') {
+    let root=await resolveProject(options.workspace||process.cwd());
+    ui.header({model:config.model,root,mode:approval,thinking:config.thinking});
+    if(approval==='auto-all') ui.note('Auto-all: edits and shell commands run without prompts, with full local permissions.');
     let messages=[]; let usage={input:0,output:0};
     while(!rl.closed) {
-      const prompt=await ask('\nYou › ');
+      chatPrompt=true;
+      const prompt=await ask(ui.prompt(approval));
+      chatPrompt=false;
       if(!prompt) continue;
       if(prompt==='/exit') break;
+      if(prompt==='/') {commandMenu();continue;}
+      if(prompt==='/project' || prompt.startsWith('/project ')) {
+        const input=prompt==='/project'?await ask(`Project folder (current: ${root}; Enter keeps it): `):prompt.slice(9).trim();
+        if(!input) continue;
+        try {
+          const next=await resolveProject(input,root);
+          if(next!==root) {root=next;messages=[];ui.success('Project opened. Conversation cleared.');}
+          ui.header({model:config.model,root,mode:approval,thinking:config.thinking});
+        } catch(e) {ui.error(`Cannot open project: ${e.message}. Current project unchanged.`);}
+        continue;
+      }
+      if(prompt==='/files') {
+        try {ui.label(root);show(await executeTool(root,{name:'list_files',input:{path:'.'}},async()=>false));}
+        catch(e) {ui.error(e.message);}
+        continue;
+      }
       if(prompt==='/help') { show(help); continue; }
       if(prompt==='/clear') { messages=[]; show('Conversation cleared.'); continue; }
       if(prompt==='/model' || prompt==='/models') {
@@ -63,6 +92,15 @@ try {
         }
         continue;
       }
+      if(prompt==='/status') {ui.header({model:config.model,root,mode:approval,thinking:config.thinking});continue;}
+      if(prompt==='/approval' || prompt.startsWith('/approval ')) {
+        const next=prompt==='/approval'?await ask(`Approval mode: ask / auto-edit / auto-all [${approval}]: `):prompt.slice(10).trim();
+        if(!next) continue;
+        if(!approvalModes.includes(next)) {ui.error('Choose ask, auto-edit, or auto-all.');continue;}
+        approval=next;ui.success(`Approval mode: ${approval} (this session only)`);
+        if(approval==='auto-all') ui.note('Edits and shell commands run without prompts, with full local permissions.');
+        continue;
+      }
       if(prompt==='/usage') { show(`Session usage: ${usage.input} input / ${usage.output} output tokens (reported by API).`); continue; }
       if(prompt==='/thinking on' || prompt==='/thinking off') { config.thinking=prompt.endsWith(' on'); show(`Thinking summaries ${config.thinking?'on':'off'} for this session.`); continue; }
       if(prompt.startsWith('/')) { show('Unknown command. Use /help.'); continue; }
@@ -91,9 +129,9 @@ try {
               if(event.type==='block_start') {
                 finish();
                 const type=event.block.type;
-                if(type==='thinking') {show('Thinking summary ›');line=true;}
+                if(type==='thinking') {ui.label('◌ Thinking summary');line=true;}
                 if(type==='redacted_thinking') show('Thinking… (content not provided by API)');
-                if(type==='text') {show('Claude ›');line=true;}
+                if(type==='text') {ui.label('◇ Claude');line=true;}
                 if(type==='tool_use') show(`Preparing ${event.block.name}…`);
               }
               if(event.type==='text' || event.type==='thinking') flush(event.text);
@@ -101,14 +139,29 @@ try {
             }});
           } finally {clearInterval(timer);stopWait();finish();}
         },execute:async call=>{
-          show(`→ ${call.name}${call.input?.path?' · '+call.input.path:''}`);
+          ui.label(`› ${call.name}${call.input?.path?' · '+call.input.path:''}`);
           try {
-            const result=await executeTool(root,call,async description=>{show(`\n${description}`);return (await ask('Allow? [y/N] ')).toLowerCase()==='y';});
-            show('✓ Tool completed'); return result;
-          } catch(e) {show(`✗ ${e.message}`);throw e;}
+            const result=await executeTool(root,call,async (description,action)=>{
+              if(action.tool==='write_file') {ui.note(`Edit · ${action.path}`);ui.diff(editPreview(action.before,action.after));}
+              else ui.note(`$ ${action.command}`);
+              if(autoApproves(approval,action.tool)) {ui.note(`Auto-approved · ${approval}`);return true;}
+              while(true) {
+                const answer=(await ask('Allow? [y/N] · /full shows complete change: ')).toLowerCase();
+                if(answer==='/full') {show(description);continue;}
+                return answer==='y';
+              }
+            });
+            ui.success('✓ Completed'); return result;
+          } catch(e) {ui.error(`✗ ${e.message}`);throw e;}
         }});
-        show(`Done · ${((Date.now()-start)/1000).toFixed(1)}s · session tokens ${usage.input} in / ${usage.output} out`);
-      } catch(e) { show(`Error: ${e.message}\nUse /clear to reset, or try again. For unsupported thinking, use /thinking off.`); }
+        ui.note(`Done · ${((Date.now()-start)/1000).toFixed(1)}s · session tokens ${usage.input} in / ${usage.output} out`);
+      } catch(e) {
+        if(e.code==='ANTHROPIC_RATE_LIMIT') {
+          ui.error('Claude API limit reached. This request stopped; kodenique-agent will not retry or send the failed tool back to Claude.');
+          show(e.message);
+          if(messages.at(-1)?.role==='user') messages.pop();
+        } else show(`Error: ${e.message}\nUse /clear to reset, or try again. For unsupported thinking, use /thinking off.`);
+      }
     }
   }
 } catch(e) { show(`Error: ${e.message}`); process.exitCode=1; }

package/commands.mjs

@@ -0,0 +1,33 @@
+import fs from 'node:fs/promises';
+import path from 'node:path';
+import os from 'node:os';
+
+export const commands=[
+ ['/project','Open a local project folder'],
+ ['/files','List files in the current project'],
+ ['/model','Fetch and choose a Claude model'],
+ ['/approval','Choose ask, auto-edit, or auto-all'],
+ ['/thinking on','Enable thinking summaries'],
+ ['/thinking off','Disable thinking summaries'],
+ ['/status','Show project, model, and approval mode'],
+ ['/usage','Show session token usage'],
+ ['/clear','Start a fresh conversation'],
+ ['/help','Show startup options and commands'],
+ ['/exit','Close kodenique-agent'],
+];
+export function completeCommand(line) {
+ const matches=commands.map(([name])=>name).filter(name=>name.startsWith(line));
+ return [line.startsWith('/')?matches:[],line];
+}
+export async function resolveProject(input,base=process.cwd()) {
+ let name=input.trim();
+ if((name.startsWith('"')&&name.endsWith('"'))||(name.startsWith("'")&&name.endsWith("'"))) name=name.slice(1,-1);
+ // Accept Finder/terminal drag-and-drop paths without executing shell expansions.
+ name=name.replace(/\\([ ()'"&])/g,'$1');
+ if(name==='~') name=os.homedir();
+ else if(name.startsWith('~/')) name=path.join(os.homedir(),name.slice(2));
+ if(!name) throw Error('Enter a project folder path.');
+ const root=await fs.realpath(path.resolve(base,name));
+ if(!(await fs.stat(root)).isDirectory()) throw Error('Project must be an existing directory.');
+ return root;
+}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "kodenique-agent",
-  "version": "0.3.0",
+  "version": "0.6.0",
   "description": "Your team's terminal coding agent, powered directly by the Claude API",
   "type": "module",
   "engines": {
@@ -19,6 +19,8 @@
     "stream.mjs",
     "config.mjs",
     "models.mjs",
+    "ui.mjs",
+    "commands.mjs",
     "README.md"
   ],
   "scripts": {

package/ui.mjs

@@ -0,0 +1,45 @@
+export const approvalModes=['ask','auto-edit','auto-all'];
+export function autoApproves(mode,tool) {
+  return mode==='auto-all' && ['write_file','run_command'].includes(tool) || mode==='auto-edit' && tool==='write_file';
+}
+export function parseArgs(args) {
+  let mode='ask'; const positional=[];
+  for(let i=0;i<args.length;i++) {
+    if(args[i]==='--approval') { mode=args[++i]; if(!approvalModes.includes(mode)) throw Error('--approval must be ask, auto-edit, or auto-all'); }
+    else if(args[i]==='--auto') mode='auto-all';
+    else if(args[i].startsWith('-')) throw Error(`Unknown option: ${args[i]}`);
+    else positional.push(args[i]);
+  }
+  if(positional.length>1) throw Error('Provide one project folder.');
+  return {mode,workspace:positional[0]};
+}
+export function editPreview(oldText,newText,maxLines=60) {
+  const before=(oldText??'').split('\n'),after=newText.split('\n');
+  let prefix=0,suffix=0;
+  while(prefix<before.length && prefix<after.length && before[prefix]===after[prefix]) prefix++;
+  while(suffix<before.length-prefix && suffix<after.length-prefix && before.at(-1-suffix)===after.at(-1-suffix)) suffix++;
+  const changed=[...before.slice(prefix,before.length-suffix).map(s=>'- '+s),...after.slice(prefix,after.length-suffix).map(s=>'+ '+s)];
+  if(!changed.length) return '(no changes)';
+  const lines=[`@@ line ${prefix+1} @@`,...changed];
+  return lines.length>maxLines?lines.slice(0,maxLines).join('\n')+`\n… ${lines.length-maxLines} more lines (/full shows all)`:lines.join('\n');
+}
+export function createUI(clean,output=process.stdout) {
+  const color=output.isTTY && !process.env.NO_COLOR && process.env.TERM!=='dumb';
+  const paint=(code,text)=>color?`\x1b[${code}m${clean(text)}\x1b[0m`:clean(text);
+  const line=text=>output.write(text+'\n');
+  return {
+    label:text=>line(paint('1;36',text)),
+    note:text=>line(paint('2',text)),
+    success:text=>line(paint('32',text)),
+    error:text=>line(paint('31',text)),
+    prompt:mode=>`\n\x01${paint(mode==='auto-all'?'33':'36',`${mode} ❯ `)}\x02`,
+    header:({model,root,mode,thinking})=>{
+      line('');line(paint('1;36','  ◇ KODENIQUE')+paint('2','  /  terminal agent · 0.5.0'));
+      line(paint('2','  ─────────────────────────────────────────────'));
+      line('  '+paint('1',model));line('  '+paint('2',root));
+      line('  '+paint(mode==='auto-all'?'33':'36',`approval: ${mode}`)+paint('2',`  ·  thinking: ${thinking?'on':'off'}`));
+      line('');line(paint('2','  Type / for commands · Tab to complete · /project to open a folder'));
+    },
+    diff:text=>{for(const row of text.split('\n')) line(paint(row.startsWith('+ ')?'32':row.startsWith('- ')?'31':'2',row));},
+  };
+}