glm-coding - npm Package Compare versions

Comparing version 0.6.0 to 0.7.0

dist/cli.js

@@ -54,3 +54,4 @@ #!/usr/bin/env node
                 break;
-            case 'stats': {
+            case 'stats':
+            case 'usage': {
                 const { showStats } = await import('./commands/stats.js');
@@ -57,0 +58,0 @@ const period = flags.includes('--monthly') ? 'monthly' : 'daily';

dist/commands/generate.js

@@ -61,2 +61,8 @@ /**
         }
+        else if (arg === '-m' || arg === '--max-tokens') {
+            const value = parseInt(args[++i], 10);
+            if (!isNaN(value) && value > 0) {
+                options.maxTokens = value;
+            }
+        }
         else if (arg === '-x' || arg === '--exec') {
@@ -117,14 +123,34 @@ options.execute = true;
         ];
-        // Stream response (to stdout only if not saving to file and not executing)
+        // Use non-streaming for file output (to get token usage)
+        // Use streaming for interactive output (real-time feedback)
         let fullContent = '';
+        let usage = null;
         const suppressOutput = !!options.output || !!options.execute;
+        const useStreaming = !options.output; // Disable streaming when writing to file
         // Lower temperature for execution mode (more deterministic)
         const temperature = options.execute ? 0.3 : undefined;
         try {
-            for await (const chunk of client.generateCompletionStream({ messages, temperature })) {
-                if (!suppressOutput) {
-                    process.stdout.write(chunk);
+            if (useStreaming) {
+                // Streaming mode (interactive, no token usage)
+                for await (const chunk of client.generateCompletionStream({
+                    messages,
+                    temperature,
+                    maxTokens: options.maxTokens,
+                })) {
+                    if (!suppressOutput) {
+                        process.stdout.write(chunk);
+                    }
+                    fullContent += chunk;
                 }
-                fullContent += chunk;
             }
+            else {
+                // Non-streaming mode (file output, includes token usage)
+                const response = await client.generateCompletion({
+                    messages,
+                    temperature,
+                    maxTokens: options.maxTokens,
+                });
+                fullContent = response.choices[0].message.content;
+                usage = response.usage || null;
+            }
         }
@@ -139,3 +165,3 @@ catch (error) {
                 model: config.apiModel,
-                stream: true,
+                stream: useStreaming,
                 error: errorMessage,
@@ -145,4 +171,4 @@ });
         }
-        // Ensure newline at end (only when outputting to stdout)
-        if (!suppressOutput && !fullContent.endsWith('\n')) {
+        // Ensure newline at end (only when outputting to stdout in streaming mode)
+        if (useStreaming && !suppressOutput && !fullContent.endsWith('\n')) {
             process.stdout.write('\n');
@@ -219,3 +245,3 @@ }
         }
-        // Log usage (streaming doesn't return token counts)
+        // Log usage (non-streaming mode includes token counts)
         await logUsage({
@@ -226,4 +252,4 @@ profile: options.profile || null,
             model: config.apiModel,
-            stream: true,
-            usage: null,
+            stream: useStreaming,
+            usage: usage,
         });
@@ -230,0 +256,0 @@ }

dist/commands/help.js

@@ -19,2 +19,3 @@ /**
   -l, --language <lang>     Language for execution (python, node, bash)
+  -m, --max-tokens <num>    Maximum tokens (default: 20000, GLM max: 20K)
   -x, --exec                Execute generated code after security check
@@ -27,3 +28,4 @@ --force                   Bypass security check (not recommended)
   init [-g]                 Initialize configuration (local or global)
-  stats [--monthly]         Show usage statistics
+  stats [--monthly]         Show usage statistics (daily by default)
+  usage [--monthly]         Alias for stats command
   version                   Show version
@@ -30,0 +32,0 @@ help                      Show this help

dist/commands/stats.js

@@ -58,12 +58,14 @@ /**
 /**
- * Format date for grouping
+ * Format date for grouping (using local timezone)
  */
 function formatDateKey(date, period) {
+    // Use local timezone instead of UTC
+    const year = date.getFullYear();
+    const month = String(date.getMonth() + 1).padStart(2, '0');
+    const day = String(date.getDate()).padStart(2, '0');
     if (period === 'daily') {
-        return date.toISOString().split('T')[0]; // YYYY-MM-DD
+        return `${year}-${month}-${day}`; // YYYY-MM-DD in local timezone
     }
     else {
-        const year = date.getFullYear();
-        const month = String(date.getMonth() + 1).padStart(2, '0');
-        return `${year}-${month}`; // YYYY-MM
+        return `${year}-${month}`; // YYYY-MM in local timezone
     }
@@ -70,0 +72,0 @@ }

dist/core/constants.d.ts

@@ -10,3 +10,3 @@ /**
 export declare const DEFAULT_TEMPERATURE = 0.7;
-export declare const DEFAULT_MAX_TOKENS = 4096;
+export declare const DEFAULT_MAX_TOKENS = 20000;
 /**
@@ -13,0 +13,0 @@ * Timeout values (milliseconds)

dist/core/constants.js

@@ -11,3 +11,3 @@ /**
 export const DEFAULT_TEMPERATURE = 0.7;
-export const DEFAULT_MAX_TOKENS = 4096;
+export const DEFAULT_MAX_TOKENS = 20000; // GLM supports up to 20K tokens
 /**
@@ -14,0 +14,0 @@ * Timeout values (milliseconds)

dist/core/types.d.ts

@@ -101,2 +101,3 @@ /**
     dryRun?: boolean;
+    maxTokens?: number;
 }
@@ -103,0 +104,0 @@ /**

package.json

 {
   "name": "glm-coding",
-  "version": "0.6.0",
+  "version": "0.7.0",
   "description": "GLM CLI - AI Code Generator with streaming output",
@@ -5,0 +5,0 @@ "type": "module",

README.md

@@ -150,5 +150,6 @@ # GLM CLI - AI Code Generator
 -q, --query <prompt>      Query prompt (required if no pipe)
--o, --output <file>       Save output to file (suppresses code output)
+-o, --output <file>       Save output to file (enables token tracking)
 -p, --profile <name>      Use specific profile
 -l, --language <lang>     Language for execution (python, node, bash)
+-m, --max-tokens <num>    Maximum tokens (default: 20000, GLM max: 20K)
 -x, --exec                Execute generated code after security check
@@ -167,2 +168,4 @@ --force                   Bypass security check (not recommended)
 glm stats --monthly       Show monthly statistics
+glm usage                 Alias for stats command
+glm usage --monthly       Monthly statistics (alias)
 glm version               Show version
@@ -332,7 +335,9 @@ glm help                  Show help
 ```bash
-# View 5-hour usage + daily stats
+# View 5-hour usage + daily stats (both commands work)
 glm stats
+glm usage
 
 # View monthly stats
 glm stats --monthly
+glm usage --monthly
 ```
@@ -342,6 +347,6 @@
 - **5-Hour Usage Window**: Current usage vs plan limit with progress bar
-- **Historical Stats**: Daily/monthly aggregated data
+- **Historical Stats**: Daily/monthly aggregated data (in your local timezone)
 - **Profile breakdown**: Top 5 profiles used
 - Request counts (total, successful, failed)
-- Token usage (prompt, completion, total)
+- **Token usage** (prompt, completion, total) - **NEW in v0.7.0**
 
@@ -352,2 +357,46 @@ **Log locations:**
 
+### Token Usage Tracking (NEW in v0.7.0)
+
+**Automatic token tracking when using `-o` flag:**
+
+```bash
+# This captures token usage statistics
+glm -q "create API client" -o api.py
+
+# Check usage
+glm stats
+```
+
+**Output example:**
+```
+Date          Requests  Success  Failed  Total Tokens    Prompt  Completion
+────────────────────────────────────────────────────────────────────────────────
[phone]          10        10       0         45,231    32,148      13,083
+```
+
+**How it works:**
+- **Interactive mode** (`glm -q "prompt"`): Streaming output, no token tracking
+- **File output mode** (`glm -q "prompt" -o file.py`): Non-streaming, **captures token usage**
+- No configuration needed - automatically optimizes for each use case
+
+### Controlling Output Length (NEW in v0.7.0)
+
+**Use `--max-tokens` to control output size and costs:**
+
+```bash
+# Limit to 1000 tokens (good for simple functions)
+glm -q "simple validation function" -o validator.py -m 1000
+
+# Use full capacity for complex files (default: 20000)
+glm -q "comprehensive REST API" -o api.py -m 20000
+
+# Default is 20K, so no flag needed for complex tasks
+glm -q "large application" -o app.py
+```
+
+**Benefits:**
+- **Cost control**: Limit tokens for simple tasks
+- **No truncation**: Default 20K handles complex files (increased from 4K)
+- **Flexible**: Override per-request based on complexity
+
 ## Project Structure
@@ -354,0 +403,0 @@

templates/claude-code/CLAUDE.md

 # GLM Code Generation
 - `@glm`, `-glm`, `--glm` in prompt → Auto-triggers GLM mode (hook)
-- `/glm TASK` → Explicit GLM command
-- Always use `-o` for direct file save
+- 'GLM -q {CODE GENERATION TASK}' returns the entire code as stdout
+- USE '-l {python|node|bash}' to specify the language
+- Use '-o {path/filename}' for direct file save
+- GLM can only generate codes, no documents

New alerts

Long strings

Supply chain risk

Contains long string literals, which may be a sign of obfuscated or packed code.

Found 1 instance in 1 package

Fixed alerts

Long strings

Supply chain risk

Contains long string literals, which may be a sign of obfuscated or packed code.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

143413

2.43%

Lines of code

3051

1.06%

Number of lines in readme file

567

9.46%

No dependency changes