zames_pro 2.82.139 → 2.82.141
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 +57 -0
- package/README.md +68 -42
- package/SECURITY.md +6 -3
- package/dist/browser.js +8 -2
- package/dist/commands.js +5 -1
- package/dist/compact.js +6 -1
- package/dist/config-command.js +17 -1
- package/dist/config.js +63 -10
- package/dist/context.js +27 -9
- package/dist/i18n/common.js +16 -11
- package/dist/i18n/config.js +9 -2
- package/dist/i18n/deepseek.js +2 -2
- package/dist/i18n/doctor.js +9 -5
- package/dist/i18n/glm.js +2 -2
- package/dist/i18n/help.js +126 -117
- package/dist/i18n/mcp.js +11 -5
- package/dist/i18n/prompt.js +9 -3
- package/dist/i18n/qwen.js +2 -2
- package/dist/i18n/self-review.js +4 -0
- package/dist/i18n/spinner.js +13 -8
- package/dist/index.js +41 -7
- package/dist/mcp.js +4 -1
- package/dist/prompt.js +16 -1
- package/dist/status-command.js +6 -2
- package/dist/system-prompt.js +8 -0
- package/dist/tui/AskQuestion.js +1 -1
- package/dist/tui/TuiEditor.js +7 -0
- package/dist/tui/widgets.js +4 -2
- package/llms-full.txt +35 -22
- package/llms.txt +4 -2
- package/package.json +2 -2
- package/skills/systematic-debugging/SKILL.md +7 -0
- package/skills/test-driven-development/SKILL.md +5 -0
- package/skills/verification-before-completion/SKILL.md +5 -0
- package/skills/writing-plans/SKILL.md +12 -0
|
@@ -38,3 +38,15 @@ Because there is no separate plan file unless the operator asks for one, the
|
|
|
38
38
|
plan lives in your reasoning and, for a long task, in a TodoWrite list — one
|
|
39
39
|
entry per step, status updated as you go. Do not narrate the plan to the
|
|
40
40
|
operator between tool calls; the todo list IS the visible plan.
|
|
41
|
+
|
|
42
|
+
Two more constraints follow from the same design:
|
|
43
|
+
|
|
44
|
+
- **A plan is not a report.** The operator sees ONLY the last `respond`
|
|
45
|
+
before the run stops, so the plan and the per-step evidence must not be
|
|
46
|
+
split across intermediate messages — put the final evidence in that one
|
|
47
|
+
`respond`.
|
|
48
|
+
- **Subagents do not parallelise the plan.** A `Task` call runs in a FRESH
|
|
49
|
+
isolated chat and returns only a report; zames has ONE browser and ONE send
|
|
50
|
+
slot, so subagents are SEQUENTIAL. Use them to keep a broad read-only
|
|
51
|
+
investigation out of the main context — never to "go faster", and never for
|
|
52
|
+
a step that must be applied in order with the main chat.
|