@xerg/cli 0.1.10 → 0.2.0
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/README.md +5 -4
- package/dist/index.js +1524 -255
- package/dist/index.js.map +1 -1
- package/package.json +3 -3
package/README.md
CHANGED
|
@@ -1,8 +1,8 @@
|
|
|
1
1
|
# xerg
|
|
2
2
|
|
|
3
|
-
Audit OpenClaw workflows in dollars, compare fixes, and
|
|
3
|
+
Audit OpenClaw workflows in dollars, compare fixes, and export daily spend and waste trends.
|
|
4
4
|
|
|
5
|
-
Xerg audits OpenClaw workflows in dollars, not tokens. It reads your gateway logs and session transcripts, surfaces
|
|
5
|
+
Xerg audits OpenClaw workflows in dollars, not tokens. It reads your gateway logs and session transcripts, surfaces daily spend and waste rollups plus the highest-leverage findings, and lets you re-run the same audit with `--compare` so you can see exactly what changed after a fix.
|
|
6
6
|
|
|
7
7
|
Everything runs locally by default. No account is required for local audits. No data leaves your machine unless you explicitly `--push` results to the Xerg API for a team dashboard.
|
|
8
8
|
|
|
@@ -149,9 +149,10 @@ Example `~/.xerg/config.json`:
|
|
|
149
149
|
## What the audit shows
|
|
150
150
|
|
|
151
151
|
- Total spend by workflow and model, in dollars
|
|
152
|
+
- Daily spend and confirmed waste rollups in UTC
|
|
152
153
|
- Observed vs. estimated cost (always labeled)
|
|
153
|
-
- Confirmed waste: retry, loop
|
|
154
|
-
- Savings opportunities: context bloat, downgrade candidates, idle
|
|
154
|
+
- Confirmed waste: retry, loop, cache carryover where applicable
|
|
155
|
+
- Savings opportunities: context bloat, downgrade candidates, idle, max mode concentration where applicable
|
|
155
156
|
- Savings recommendations with suggested A/B tests
|
|
156
157
|
- Before/after deltas on re-audit
|
|
157
158
|
|