glance-cli 0.13.1 → 0.15.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +33 -0
- package/README.md +22 -1
- package/dist/cli.js +182 -119
- package/package.json +2 -1
- package/src/cli/commands.ts +28 -6
- package/src/cli/config.ts +1 -1
- package/src/cli/display.ts +1 -0
- package/src/cli/index.ts +2 -0
- package/src/core/summarizer.ts +106 -51
package/CHANGELOG.md
CHANGED
|
@@ -5,6 +5,39 @@ All notable changes to glance-cli will be documented in this file.
|
|
|
5
5
|
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
|
|
6
6
|
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
|
|
7
7
|
|
|
8
|
+
## [0.15.0] - 2026-01-06
|
|
9
|
+
|
|
10
|
+
### 🚀 Added: Comprehensive Local Model Support
|
|
11
|
+
- **Fixed gpt-oss model compatibility**: Added special handling for gpt-oss models that use "thinking" field in responses
|
|
12
|
+
- **Tested and verified 7 Ollama models**:
|
|
13
|
+
- ✅ llama3:latest - Fast, reliable general-purpose model
|
|
14
|
+
- ✅ gemma3:4b - Lightweight, efficient for quick summaries
|
|
15
|
+
- ✅ mistral:7b / mistral:latest - Excellent quality responses
|
|
16
|
+
- ✅ gpt-oss:20b - Advanced local model with reasoning capabilities
|
|
17
|
+
- ✅ gpt-oss:120b-cloud - Largest model for complex tasks
|
|
18
|
+
- ✅ deepseek-r1:latest - Strong reasoning and analysis
|
|
19
|
+
- **100% test success rate**: All models work with --tldr, --key-points, and --eli5 modes
|
|
20
|
+
- **Improved response parsing**: Better extraction of meaningful content from various model response formats
|
|
21
|
+
|
|
22
|
+
### 🐛 Fixed
|
|
23
|
+
- **gpt-oss models now properly route to Ollama**: Previously failing gpt-oss models now correctly use local Ollama endpoint
|
|
24
|
+
- **Response extraction for thinking-based models**: Models that output reasoning in "thinking" field now have their responses properly extracted
|
|
25
|
+
- **Consistent model detection**: Enhanced provider detection to correctly identify local vs cloud models
|
|
26
|
+
|
|
27
|
+
### 📝 Documentation
|
|
28
|
+
- Added comprehensive list of tested and supported local models in README
|
|
29
|
+
- Included model-specific notes for optimal usage
|
|
30
|
+
- Updated examples with various model options
|
|
31
|
+
|
|
32
|
+
## [0.14.0] - 2026-01-06
|
|
33
|
+
|
|
34
|
+
### ✨ Added: Clipboard Copy Feature
|
|
35
|
+
- **New --copy/-c flag**: Copy summaries directly to clipboard
|
|
36
|
+
- **Cross-platform support**: Works on macOS, Windows, and Linux via clipboardy package
|
|
37
|
+
- **Smart formatting**: Copies raw text for terminal output, formatted for JSON/markdown
|
|
38
|
+
- **Updated documentation**: Added examples and help text for copy feature
|
|
39
|
+
- **Fixed metadata display**: Now shows actual extracted values instead of placeholders
|
|
40
|
+
|
|
8
41
|
## [0.13.1] - 2026-01-05
|
|
9
42
|
|
|
10
43
|
### 📦 Optimized: Package Size (Breaking: Major Size Reduction)
|
package/README.md
CHANGED
|
@@ -27,6 +27,7 @@ bun install -g glance-cli # Or: npm install -g glance-cli
|
|
|
27
27
|
glance https://www.ayiti.ai # AI summary
|
|
28
28
|
glance https://www.ayiti.ai/fr --read # Auto-detects French + voice
|
|
29
29
|
glance https://news.com --output summary.md # Save as markdown
|
|
30
|
+
glance https://news.com --copy # Copy to clipboard
|
|
30
31
|
```
|
|
31
32
|
|
|
32
33
|
**For 100% free local AI:**
|
|
@@ -51,6 +52,7 @@ glance <url> --key-points # Bullet points
|
|
|
51
52
|
glance <url> --eli5 # Simple explanation
|
|
52
53
|
glance <url> --full # Full content (no summary)
|
|
53
54
|
glance <url> --ask "..." # Ask specific question
|
|
55
|
+
glance <url> --copy # Copy summary to clipboard
|
|
54
56
|
```
|
|
55
57
|
|
|
56
58
|
### 🎤 **Voice & Audio**
|
|
@@ -79,9 +81,21 @@ glance <url> --full -l es --voice isabella --read # Override to Spanish + voic
|
|
|
79
81
|
```
|
|
80
82
|
|
|
81
83
|
### 🤖 **AI Models**
|
|
84
|
+
|
|
85
|
+
#### Tested & Supported Local Models (via Ollama)
|
|
86
|
+
- ✅ **llama3:latest** - Fast, reliable, great for general use
|
|
87
|
+
- ✅ **gemma3:4b** - Lightweight, efficient for quick summaries
|
|
88
|
+
- ✅ **mistral:7b** / **mistral:latest** - Excellent quality responses
|
|
89
|
+
- ✅ **gpt-oss:20b** - Advanced local model with reasoning capabilities
|
|
90
|
+
- ✅ **gpt-oss:120b-cloud** - Largest model for complex tasks
|
|
91
|
+
- ✅ **deepseek-r1:latest** - Strong reasoning and analysis
|
|
92
|
+
|
|
82
93
|
```bash
|
|
83
94
|
# Free local AI (recommended)
|
|
84
|
-
glance <url> --model llama3
|
|
95
|
+
glance <url> --model llama3:latest
|
|
96
|
+
glance <url> --model gemma3:4b
|
|
97
|
+
glance <url> --model mistral:7b
|
|
98
|
+
glance <url> --model gpt-oss:20b
|
|
85
99
|
|
|
86
100
|
# Premium cloud AI (optional, requires API keys)
|
|
87
101
|
glance <url> --model gpt-4o-mini # OpenAI
|
|
@@ -101,6 +115,9 @@ glance <url> --free-only # Never use paid APIs
|
|
|
101
115
|
# Morning news with audio
|
|
102
116
|
glance https://news.ycombinator.com --tldr --read
|
|
103
117
|
|
|
118
|
+
# Quick copy for sharing
|
|
119
|
+
glance https://techcrunch.com/article --tldr --copy
|
|
120
|
+
|
|
104
121
|
# Documentation lookup
|
|
105
122
|
glance https://nextjs.org/docs --ask "What's the App Router?"
|
|
106
123
|
|
|
@@ -159,6 +176,7 @@ done
|
|
|
159
176
|
```bash
|
|
160
177
|
--format <type> # Output format: md, json, plain (default: terminal)
|
|
161
178
|
--output, -o <file> # Save to file (auto-detects format from extension)
|
|
179
|
+
--copy, -c # Copy summary to clipboard
|
|
162
180
|
--stream # Live streaming output
|
|
163
181
|
```
|
|
164
182
|
|
|
@@ -197,6 +215,9 @@ export OLLAMA_ENDPOINT=http://localhost:11434
|
|
|
197
215
|
# 1. Auto language detection + file saving
|
|
198
216
|
glance https://lemonde.fr --output french-article.md # Auto-detects French format
|
|
199
217
|
|
|
218
|
+
# 2. Quick sharing workflow
|
|
219
|
+
glance https://article.com --tldr --copy # Copy summary for instant sharing
|
|
220
|
+
|
|
200
221
|
# 2. Format override for different use cases
|
|
201
222
|
glance https://news.com --format json --output backup.md # JSON content in .md file
|
|
202
223
|
|