a2zusage 1.0.9 → 1.0.11
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/README.md +4 -23
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -28,8 +28,9 @@
|
|
|
28
28
|
├────────────────┼──────────┼───────────────┼─────────────┼─────────────┼───────────────┤
|
|
29
29
|
│ Claude Code │ ✓ Active │ 321K tokens │ 1.4M tokens │ 6.1M tokens │ 24.2M tokens │
|
|
30
30
|
│ Cursor │ ✓ Active │ - │ - │ - │ 32.5K tokens │
|
|
31
|
-
│ Windsurf │ ✓ Active │
|
|
31
|
+
│ Windsurf │ ✓ Active │ 1 req │ 1 req │ 1 req │ 21 reqs │
|
|
32
32
|
│ Warp AI │ ✓ Active │ - │ - │ 8.2M tokens │ 167.1M tokens │
|
|
33
|
+
│ Gemini CLI │ ✓ Active │ - │ 72K tokens │ 101K tokens │ 48.1M tokens │
|
|
33
34
|
│ GitHub Copilot │ ○ N/A │ - │ - │ - │ - │
|
|
34
35
|
│ ... │ ... │ ... │ ... │ ... │ ... │
|
|
35
36
|
╰────────────────┴──────────┴───────────────┴─────────────┴─────────────┴───────────────╯
|
|
@@ -73,12 +74,12 @@ a2zusage supports **14+ AI coding tools** out of the box:
|
|
|
73
74
|
| **Claude Code** | Local JSONL (`~/.claude/projects/`) | ✅ Exact token counts (input/output + cache tokens when present) |
|
|
74
75
|
| **Cursor** | SQLite database | ✅ Exact token counts (when present in DB) |
|
|
75
76
|
| **GitHub Copilot** | GitHub API + Local logs | ⚠️ Usage count / requests only (GitHub does not expose reliable token totals here) |
|
|
76
|
-
|
|
77
|
+
|| **Windsurf** | Cascade sessions (`~/.codeium/`) | ℹ️ Session count only (token data encrypted). Visit windsurf.ai for detailed usage. |
|
|
77
78
|
| **Warp AI** | SQLite database | ✅ Total tokens (Warp does not expose a reliable input/output split) |
|
|
78
79
|
| **Cline / Roo Code** | VS Code extension storage | ✅ Exact token counts (when stored by the extension) |
|
|
79
80
|
| **OpenCode** | Local JSON files | ✅ Exact token counts (when present in session/message usage fields) |
|
|
80
81
|
| **OpenAI Codex** | OpenAI Usage API | ✅ Exact token counts (requires API key + org access) |
|
|
81
|
-
|| **Gemini CLI** |
|
|
82
|
+
|| **Gemini CLI** | Native sessions (`~/.gemini/tmp/`) | ✅ Exact token counts from native session files (no setup required) |
|
|
82
83
|
| **Amazon Q Developer** | Local logs | ⚠️ Best-effort: logs may not contain token totals |
|
|
83
84
|
| **Tabnine** | Local logs | ⚠️ Partial: uses explicit token fields when present; no invented prompt/context tokens |
|
|
84
85
|
| **Gemini Code Assist** | Google Cloud | ⚠️ Not implemented in this repo yet |
|
|
@@ -141,26 +142,6 @@ a2zusage -v # Verbose mode with data sources
|
|
|
141
142
|
]
|
|
142
143
|
```
|
|
143
144
|
|
|
144
|
-
## Tool-Specific Setup
|
|
145
|
-
|
|
146
|
-
### Gemini CLI Setup
|
|
147
|
-
|
|
148
|
-
Gemini CLI stores conversation data in encrypted protobuf files. To get accurate token tracking, use our wrapper script that captures the `usageMetadata` from the `--output-format stream-json` output:
|
|
149
|
-
|
|
150
|
-
```bash
|
|
151
|
-
# 1. Copy the wrapper script
|
|
152
|
-
curl -o ~/.local/bin/gemini-wrapper https://raw.githubusercontent.com/aezizhu/a2zaiusage/main/scripts/gemini-wrapper.sh
|
|
153
|
-
chmod +x ~/.local/bin/gemini-wrapper
|
|
154
|
-
|
|
155
|
-
# 2. Create an alias (add to your .bashrc or .zshrc)
|
|
156
|
-
alias gemini="~/.local/bin/gemini-wrapper"
|
|
157
|
-
|
|
158
|
-
# 3. Use gemini as normal - token data is now tracked!
|
|
159
|
-
gemini "Your prompt here"
|
|
160
|
-
```
|
|
161
|
-
|
|
162
|
-
The wrapper creates `~/.gemini/a2zusage-telemetry.jsonl` with exact token counts for each request.
|
|
163
|
-
|
|
164
145
|
## Why This Tool?
|
|
165
146
|
|
|
166
147
|
### 🎯 Built for Hiring AI-Native Developers
|
package/package.json
CHANGED