@lmctl-ai/lmctl 0.2.75 → 0.2.77
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/CHANGELOG.md +1 -0
- package/build-info.json +1 -1
- package/dist/cli/index.js +319 -319
- package/dist/cli/lmscript.js +141 -141
- package/package.json +1 -1
package/CHANGELOG.md
CHANGED
|
@@ -4,6 +4,7 @@ All notable public-preview changes for `@lmctl-ai/lmctl` are recorded here.
|
|
|
4
4
|
|
|
5
5
|
## Unreleased
|
|
6
6
|
|
|
7
|
+
- **`lmctl cost` no longer over-counts Claude and Codex sessions.** Claude writes one session record per content block of a message, each repeating that message's usage; every record was added, so token totals were typically twice the real ones. The cost then priced cached input a second time at the full input rate, for Claude and for Codex. Each message is now counted once and each token priced once: uncached input, cache reads, and Claude cache writes at their own rates, with 1-hour cache writes at the catalog's 1-hour rate. Expect Claude token totals to drop by about half and Claude and Codex costs several-fold; on a checked session the result equals the provider's own reported cost. The displayed input total still includes cached tokens. Not covered yet: Claude subagent transcripts are not part of a session's cost, and Gemini and Qwen sessions still price cached input twice.
|
|
7
8
|
- **Hello model selection.** `lmctl hello <provider> --model <name>` sets the model of the Lead in the downloaded hello teamfile. For codex and agy the name is checked against the provider's own live catalog (`codex debug models`, `agy models`) before anything is started: a name that is not in it is refused with the list of valid models, and no teamfile is left behind. For other providers, and when the catalog cannot be read, the usual lint warning is shown and the seed proceeds. A name may contain spaces (`--model "Gemini 3.8 Flash (High)"`) but not quotes or line breaks. Without the flag nothing changes: the provider default is used.
|
|
8
9
|
|
|
9
10
|
- **First external LMScript module.** modules/git.lms wraps git with argv execution and NUL-delimited parsing: root, branch, status, log, diff_stat, is_clean, remote_url and rev_parse. Imports have no command effects; failures name the command, exit and stderr tail. The source module and relative-import git_summary example ship in the package, without a module registry. Queries require trusted repository configuration/attributes and Git environment; clean filters may execute during status/diff. Error diagnostics mask recognized URL credentials; log requests UTF-8 and avoids a worktree scan.
|
package/build-info.json
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"sha": "
|
|
1
|
+
{"sha": "9221d09bec27c72bfaf4a95b76d0ccb9d27ad9bd", "dirty": false, "builtAt": "2026-10-05T17:15:33.000Z"}
|