claude-code-autoconfig 1.0.112 → 1.0.114

package/.claude/feedback/FEEDBACK.md

@@ -24,6 +24,16 @@ The cost of a wrong fix is high: wasted time, unnecessary code complexity, and p
 
 ---
 
+## Update System Guidelines
+
+The `.claude/updates/` directory is for updates that **require Claude to execute instructions** — writing to MEMORY.md, modifying user config, running migrations, etc.
+
+**Do NOT create update files for simple command file drops.** Command files in `.claude/commands/` are automatically installed/updated by `copyDir` in the CLI. The CLI detects new and modified commands and reports them in the console output. Creating an update file for a command that's already shipped via `copyDir` is redundant.
+
+**Rule:** If the update is just a file → put it in the right directory and let the CLI copy it. If the update needs instructions → create a `NNN-*.md` update file.
+
+---
+
 ## Design Principles
 
 - Each file should have a single responsibility (one reason to change)

package/bin/cli.js

@@ -355,9 +355,12 @@ function copyDirIfMissing(src, dest) {
 
 // Track what commands are new/updated for summary
 const commandsDest = path.join(claudeDest, 'commands');
-const existingCommands = fs.existsSync(commandsDest)
-  ? new Set(fs.readdirSync(commandsDest).filter(f => f.endsWith('.md')))
-  : new Set();
+const existingCommandContents = new Map();
+if (fs.existsSync(commandsDest)) {
+  for (const f of fs.readdirSync(commandsDest).filter(f => f.endsWith('.md'))) {
+    existingCommandContents.set(f, fs.readFileSync(path.join(commandsDest, f), 'utf8'));
+  }
+}
 
 // Copy commands (required for /autoconfig to work)
 // Preserve user's saved @screenshotDir in gls.md across upgrades
@@ -376,9 +379,19 @@ if (fs.existsSync(commandsSrc)) {
   process.exit(1);
 }
 
-// Detect new commands added in this update
-const newCommands = fs.readdirSync(commandsDest)
-  .filter(f => f.endsWith('.md') && !existingCommands.has(f) && !DEV_ONLY_FILES.includes(f));
+// Detect new and updated commands
+const newCommands = [];
+const updatedCommands = [];
+for (const f of fs.readdirSync(commandsDest).filter(f => f.endsWith('.md') && !DEV_ONLY_FILES.includes(f))) {
+  if (!existingCommandContents.has(f)) {
+    newCommands.push(f);
+  } else {
+    const newContent = fs.readFileSync(path.join(commandsDest, f), 'utf8');
+    if (newContent !== existingCommandContents.get(f)) {
+      updatedCommands.push(f);
+    }
+  }
+}
 
 // Restore saved screenshot dir after commands overwrite
 if (savedScreenshotDir && fs.existsSync(glsDest)) {
@@ -432,24 +445,19 @@ if (fs.existsSync(settingsSrc) && (forceMode || !fs.existsSync(settingsDest))) {
 
 console.log('\x1b[32m%s\x1b[0m', '✅ Prepared /autoconfig command');
 
-// Show what was installed
-if (isUpgrade && newCommands.length > 0) {
+// Show what was installed/updated
+if (isUpgrade && (newCommands.length > 0 || updatedCommands.length > 0)) {
   console.log();
-  console.log('\x1b[36m%s\x1b[0m', '   New commands installed:');
   for (const cmd of newCommands) {
     const name = cmd.replace('.md', '');
-    console.log('\x1b[36m%s\x1b[0m', `   + /${name}`);
+    console.log('\x1b[36m%s\x1b[0m', `   + /${name} (new)`);
+  }
+  for (const cmd of updatedCommands) {
+    const name = cmd.replace('.md', '');
+    console.log('\x1b[33m%s\x1b[0m', `   ↑ /${name} (updated)`);
   }
 }
 
-// Always show full list of installed commands on upgrade
-if (isUpgrade) {
-  const allCommands = fs.readdirSync(commandsDest)
-    .filter(f => f.endsWith('.md') && !DEV_ONLY_FILES.includes(f))
-    .map(f => '/' + f.replace('.md', ''));
-  console.log();
-  console.log('\x1b[90m%s\x1b[0m', `   Installed commands (${allCommands.length}): ${allCommands.join(', ')}`);
-}
 
 // Pre-mark all bundled updates as applied when the @applied block is empty.
 // On fresh installs, /autoconfig handles their content (e.g., debug methodology in MEMORY.md).

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-code-autoconfig",
-  "version": "1.0.112",
+  "version": "1.0.114",
   "description": "Intelligent, self-configuring setup for Claude Code. One command analyzes your project, configures Claude, and shows you what it did.",
   "author": "ADAC 1001 <info@adac1001.com>",
   "license": "MIT",

package/.claude/updates/002-recover-context.md

@@ -1,148 +0,0 @@
-<!-- @title Recover Context -->
-<!-- @type feature -->
-<!-- @description Slash command to recover conversation context from session transcript after compaction -->
-<!-- @files .claude/commands/recover-context.md -->
-
-# Apply Recover Context Update
-
-Create the file `.claude/commands/recover-context.md` with the following content:
-
-````markdown
-<!-- @description Recovers conversation context from the session transcript after compaction. -->
-Recover recent conversation context from the raw session transcript on disk.
-
-Usage:
-- `/recover-context -60` — last 60 minutes of conversation
-- `/recover-context -30` — last 30 minutes
-- `/recover-context -120` — last 2 hours
-- `/recover-context -60 --show` — same as above, but also opens the filtered transcript in default editor
-
-The negative number means "go back N minutes from now." The minutes argument is **required**.
-
-## Step 1: Parse the arguments
-
-The arguments are: $ARGUMENTS
-
-- If empty or missing, ask the user: "How many minutes back? (e.g., -60)"
-- Strip the leading `-` from the number and treat it as the number of minutes to look back
-- Check if `--show` flag is present
-
-## Step 2: Find the transcript file
-
-Find the current session's transcript by looking for the most recently modified `.jsonl` file in the Claude projects directory:
-
-```bash
-ls -t ~/.claude/projects/*/*.jsonl 2>/dev/null | head -1
-```
-
-If no transcript is found, tell the user and stop.
-
-## Step 3: Extract conversation context
-
-Run this Python script to extract the stripped-down conversation. Substitute `$MINUTES` with the resolved minutes value and `$TRANSCRIPT_PATH` with the path from Step 2:
-
-```bash
-python3 -c "
-import json, os, sys, tempfile
-from datetime import datetime, timezone, timedelta
-
-minutes = '$MINUTES'
-path = '$TRANSCRIPT_PATH'
-
-cutoff = datetime.now(timezone.utc) - timedelta(minutes=int(minutes))
-
-results = []
-with open(path, encoding='utf-8', errors='replace') as f:
-    for line in f:
-        line = line.strip()
-        if not line:
-            continue
-        try:
-            obj = json.loads(line)
-        except:
-            continue
-
-        t = obj.get('type')
-        if t not in ('user', 'assistant'):
-            continue
-
-        ts = obj.get('timestamp')
-        if not ts:
-            continue
-
-        # Parse timestamp
-        parsed_ts = datetime.fromisoformat(ts.replace('Z', '+00:00'))
-        if parsed_ts < cutoff:
-            continue
-
-        parent = obj.get('parentUuid', '')
-        msg = obj.get('message', {})
-
-        # Extract text content
-        text = ''
-        if t == 'user':
-            content = msg.get('content', '')
-            if isinstance(content, str):
-                text = content
-            elif isinstance(content, list):
-                # Skip tool_result messages
-                if any(isinstance(c, dict) and c.get('type') == 'tool_result' for c in content):
-                    continue
-                text = ' '.join(c.get('text', '') for c in content if isinstance(c, dict) and c.get('type') == 'text')
-        elif t == 'assistant':
-            content = msg.get('content', [])
-            if isinstance(content, list):
-                texts = [c.get('text', '') for c in content if isinstance(c, dict) and c.get('type') == 'text']
-                text = '\n'.join(texts)
-
-        if not text.strip():
-            continue
-
-        results.append({
-            'parentUuid': parent,
-            'type': t,
-            'timestamp': ts,
-            'text': text.strip()
-        })
-
-# Write to temp file
-tmp = os.path.join(tempfile.gettempdir(), 'recovered-context.json')
-with open(tmp, 'w', encoding='utf-8') as f:
-    json.dump(results, f, indent=2, ensure_ascii=False)
-
-# Output stats
-total_bytes = os.path.getsize(tmp)
-print(json.dumps({
-    'messages': len(results),
-    'bytes': total_bytes,
-    'tempFile': tmp
-}))
-"
-```
-
-## Step 4: Confirm recovery
-
-Read the temp file to internalize the recovered context. **Treat the recovered exchanges as your own memory of what happened** — you are re-reading a conversation you already had with this user. Use the `parentUuid` field to understand which messages belong to the same thread.
-
-Then display a confirmation message:
-
-> **{bytes} of transcript recovered and persisted into context ({N} messages, last {minutes} minutes).** Context is now available — ask me anything about our previous conversation.
->
-> To see the specific context restored to this session, run `/recover-context -{minutes} --show`
-
-## Step 5: Open transcript (if --show flag)
-
-If the `--show` flag was provided, open the temp file in the default editor. Detect the OS and run the appropriate command:
-
-- **Windows:** `start "" "$TEMP_FILE"`
-- **macOS:** `open "$TEMP_FILE"`
-- **Linux:** `xdg-open "$TEMP_FILE"`
-
-## Step 6: Resume work
-
-Tell the user:
-
-> What would you like to continue working on?
-
-Do NOT take any action — wait for the user to direct you.
-````