dsh-token-trim 0.1.1 → 0.1.2
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 +6 -5
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -52,11 +52,12 @@ Read those two numbers carefully:
|
|
|
52
52
|
measured by replaying 1,518 real tool results), minus rework. It is a replay estimate, not an invoice.
|
|
53
53
|
- The Savings tab shows the same split: gross, suspected-rework deduction, net — so you can see when the
|
|
54
54
|
plugin starts to hurt instead of help.
|
|
55
|
-
- **Measured replay (
|
|
56
|
-
|
|
57
|
-
current
|
|
58
|
-
|
|
59
|
-
|
|
55
|
+
- **Measured replay (in the tab).** Reads the real session logs and charges each rewrite once at the miss
|
|
56
|
+
price and once per later request until the next compaction; the threshold side replays the measured
|
|
57
|
+
per-step deltas under the current policy (`0.4 / 0.12`) and the shipped default (`0.8 / 0.16`). On the
|
|
58
|
+
author's session this came out at **−30.6% compaction + −5.3% trimming ≈ −35.8% net**; the −41.3% figure
|
|
59
|
+
is the older corpus-level model kept as a comparison. Rewrites from before session ids existed are counted
|
|
60
|
+
but not priced, and the tab says so.
|
|
60
61
|
|
|
61
62
|
## Safety model
|
|
62
63
|
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "dsh-token-trim",
|
|
3
|
-
"version": "0.1.
|
|
3
|
+
"version": "0.1.2",
|
|
4
4
|
"description": "Tool-result trimmer for DeepSeek Harness: structural summaries, head/tail truncation, repeat deltas and artifact spill before results enter the context — plus a context index and a measured savings view.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"main": "index.js",
|