llm-usage-metrics 0.1.4 → 0.1.6

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 CHANGED
@@ -43,6 +43,23 @@ To force-skip startup update checks:
43
43
  LLM_USAGE_SKIP_UPDATE_CHECK=1 llm-usage daily
44
44
  ```
45
45
 
46
+ ### Runtime environment overrides
47
+
48
+ You can tune runtime behavior with environment variables:
49
+
50
+ - `LLM_USAGE_SKIP_UPDATE_CHECK`: skip startup update check when set to `1`
51
+ - `LLM_USAGE_UPDATE_CACHE_TTL_MS`: update-check cache TTL in milliseconds (clamped: `60000..2592000000`)
52
+ - `LLM_USAGE_UPDATE_FETCH_TIMEOUT_MS`: update-check network timeout in milliseconds (clamped: `200..30000`)
53
+ - `LLM_USAGE_PRICING_CACHE_TTL_MS`: pricing cache TTL in milliseconds (clamped: `60000..2592000000`)
54
+ - `LLM_USAGE_PRICING_FETCH_TIMEOUT_MS`: pricing fetch timeout in milliseconds (clamped: `200..30000`)
55
+ - `LLM_USAGE_PARSE_MAX_PARALLEL`: max concurrent file parses per source adapter (clamped: `1..64`)
56
+
57
+ Example:
58
+
59
+ ```bash
60
+ LLM_USAGE_PARSE_MAX_PARALLEL=16 LLM_USAGE_PRICING_FETCH_TIMEOUT_MS=8000 llm-usage monthly
61
+ ```
62
+
46
63
  ## Usage
47
64
 
48
65
  ### Daily report (default terminal table)
@@ -114,7 +131,40 @@ llm-usage monthly --source pi --source codex
114
131
  llm-usage monthly --source pi,codex
115
132
  ```
116
133
 
117
- ## Output semantics
134
+ ## Output features
135
+
136
+ ### Terminal UI
137
+
138
+ The CLI provides an enhanced terminal output with:
139
+
140
+ - **Boxed report header** showing the report type and timezone
141
+ - **Session summary** displayed at startup (session files and event counts per source)
142
+ - **Pricing source info** indicating whether data was loaded from cache or fetched remotely
143
+ - **Environment variable overrides** displayed when active
144
+ - **Models displayed as bullet points** for better readability
145
+ - **Rounded table borders** and improved color scheme
146
+
147
+ Example output:
148
+
149
+ ```text
150
+ ℹ Found 12 session file(s) with 45 event(s)
151
+ • pi: 8 file(s), 32 events
152
+ • codex: 4 file(s), 13 events
153
+ ℹ Loaded pricing from cache
154
+
155
+ ┌──────────────────────────────────────────────────────────┐
156
+ │ Monthly Token Usage Report (Timezone: Africa/Casablanca) │
157
+ └──────────────────────────────────────────────────────────┘
158
+
159
+ ╭────────────┬──────────┬──────────────────────╮
160
+ │ Period │ Source │ Models │
161
+ ├────────────┼──────────┼──────────────────────┤
162
+ │ Feb 2026 │ pi │ • gpt-5.2 │
163
+ │ │ │ • gpt-5.2-codex │
164
+ ╰────────────┴──────────┴──────────────────────╯
165
+ ```
166
+
167
+ ### Report structure
118
168
 
119
169
  Each report includes:
120
170
 
@@ -132,8 +182,8 @@ Columns:
132
182
  - Reasoning
133
183
  - Cache Read
134
184
  - Cache Write
135
- - Total Tokens
136
- - Cost (USD)
185
+ - Total
186
+ - Cost
137
187
 
138
188
  ## Development
139
189