llm-usage-metrics 0.4.0 → 0.4.1
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 +9 -0
- package/dist/index.js +676 -38
- package/dist/index.js.map +1 -1
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -92,6 +92,9 @@ llm-usage daily --markdown
|
|
|
92
92
|
|
|
93
93
|
# Detailed per-model breakdown
|
|
94
94
|
llm-usage monthly --per-model-columns
|
|
95
|
+
|
|
96
|
+
# Write a share SVG image
|
|
97
|
+
llm-usage monthly --share
|
|
95
98
|
```
|
|
96
99
|
|
|
97
100
|
### Efficiency Reports
|
|
@@ -105,6 +108,9 @@ llm-usage efficiency weekly --repo-dir /path/to/repo
|
|
|
105
108
|
|
|
106
109
|
# Include merge commits and export JSON
|
|
107
110
|
llm-usage efficiency monthly --include-merge-commits --json
|
|
111
|
+
|
|
112
|
+
# Write a monthly share SVG
|
|
113
|
+
llm-usage efficiency monthly --share
|
|
108
114
|
```
|
|
109
115
|
|
|
110
116
|
Efficiency reports are repo-attributed: usage events are mapped to a Git repository root using source metadata (`cwd`/path info), and only events attributed to the selected repo are included in efficiency totals.
|
|
@@ -143,6 +149,9 @@ llm-usage optimize monthly --provider openai --candidate-model gpt-4.1 --candida
|
|
|
143
149
|
|
|
144
150
|
# Keep only the cheapest candidate in JSON output
|
|
145
151
|
llm-usage optimize weekly --provider openai --candidate-model gpt-4.1,gpt-5-codex --top 1 --json
|
|
152
|
+
|
|
153
|
+
# Write a monthly share SVG
|
|
154
|
+
llm-usage optimize monthly --provider openai --candidate-model gpt-4.1 --candidate-model gpt-5-codex --share
|
|
146
155
|
```
|
|
147
156
|
|
|
148
157
|
`--provider` filters by billing entity. Provider aliases are normalized to billing roots (for example, `openai-codex` is treated as `openai`).
|