@tokmizer/plugin 0.9.51 → 0.9.52
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/.claude-plugin/plugin.json +1 -1
- package/README.md +5 -1
- package/codex-plugin/plugin.json +1 -1
- package/dist/bin/tkr-codex-hook.js +33 -29
- package/dist/bin/tkr-exec.js +35 -31
- package/dist/bin/tkr-shim.js +32 -28
- package/dist/hooks-host/post-tool-use.js +40 -36
- package/dist/index.js +34 -30
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -83,7 +83,9 @@ From any terminal (after the shell-shim install, or `npm install -g @tokmizer/pl
|
|
|
83
83
|
|
|
84
84
|
## Choosing a compression mode
|
|
85
85
|
|
|
86
|
-
Choose `light` for gentle reduction, `balanced` (the default) for more compact output, or `max` for the strongest standard reduction. The aliases `normal`, `compact`, and `minimal` map to these levels respectively. Short or exact output can be identical across levels.
|
|
86
|
+
Choose `light` for gentle reduction, `balanced` (the default) for more compact output, or `max` for the strongest standard reduction. The aliases `normal`, `compact`, and `minimal` map to these levels respectively. Short or exact output can be identical across levels.
|
|
87
|
+
|
|
88
|
+
Since 0.9.52, short code reads and small explicit excerpts stay complete by default in all three standard modes. Larger reads can still be shortened. Recognized failures retain their diagnostics; Max can summarize repeated log lines with an occurrence count. Distinct diagnostic messages and command exit codes are preserved.
|
|
87
89
|
|
|
88
90
|
Without a linked account, standard settings stay on this machine and work offline after initial activation. With a linked account, changes require a connection and sync across machines. Linking an account restores its server settings.
|
|
89
91
|
|
|
@@ -123,6 +125,8 @@ The result also depends on the output. In a separate set of five JSON examples,
|
|
|
123
125
|
|
|
124
126
|
In one real failed test, `max` kept 302 tokens and YOLO kept 77. Both retained the actual and expected values. YOLO removed the explanation about invoice 42 and the location `payment.test.mjs:4:10`, which were retained by `max`. That missing context can matter when fixing the failure.
|
|
125
127
|
|
|
128
|
+
In a separate controlled test for 0.9.52, a repetitive failure log went from 1,094 to 84 tokens in Max (92.3% fewer, counted with cl100k). Every distinct diagnostic and the repetition counts were retained. This result applies to that example, not to typical usage.
|
|
129
|
+
|
|
126
130
|
These tokenizer counts are separate from the byte-based estimates in `tkr gain`. They measure output volume, not your bill, an agent's task success, or execution speed. See the [mode guide](https://tokmizer.com/en/docs#configuration) for usage and limits.
|
|
127
131
|
|
|
128
132
|
## Distribution
|