codewhale.history 2.8.9 → 2.8.11

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "codewhale.history",
-  "version": "2.8.9",
+  "version": "2.8.11",
   "description": "CodeWhale utility commands: session history, tool listing, file snapshot, interactive code quiz — global install",
   "bin": {
     "codewhale-history": "./_list_sessions.js",

package/skills/teach-me/SKILL.md

@@ -154,6 +154,8 @@ explanation. The model removes lines from the file and the user restores them.
 
 #### Interactive Mode Per-Round Flow
 
+0. **Snapshot git state.** Run `git status --porcelain <file>` before touching
+   it. Note whether the file was clean or already had uncommitted changes.
 1. **Select** a snippet using the standard rules (section 2).
 2. **Save** the original lines in memory.
 3. **Remove** 1–3 lines from the actual file on disk using `edit_file`.
@@ -165,17 +167,22 @@ explanation. The model removes lines from the file and the user restores them.
    completion.
 7. **Re-read** the file. Diff the user's restored lines against the saved
    original.
-8. **Feedback** (see Interactive Evaluation below). Offer to restore the
-    original if the user wants to undo.
+8. **Feedback** (see Interactive Evaluation below). After feedback, restore
+   the file with `git checkout -- <file>` for a byte-perfect reset. If the
+   file had pre-existing uncommitted changes (from step 0), restore the
+   original lines manually via `edit_file` instead and warn the user.
 
 #### Thinking Suppression (Interactive Mode)
 
-During steps 1–4 (selection through presentation), **suppress thinking
-entirely**. Do not include the selected snippet, the original lines, or
-which lines are being removed in your reasoning. The user can see the
-thinking block and it spoils the exercise. Use light thinking only for
-mechanical coordination (e.g., "reading file, selecting lines 42-55,
-removing 2 lines, presenting") — never the actual code.
+During steps 1–4 (selection through presentation), use **Skip** thinking
+depth — emit no reasoning_content at all. Do not include the selected
+snippet, the original lines, or which lines are being removed. The
+thinking block is visible to the user and spoils the exercise before it
+begins. Resume normal thinking depth at step 5 (after presentation).
+
+The `edit_file` diff output is unavoidably visible in the transcript
+(CodeWhale transparency), but thinking control keeps the primary leak
+closed.
 
 #### Interactive Mode Presentation Format
 
@@ -448,11 +455,16 @@ criteria for the Mechanics axis:
   teaching session unless the user explicitly asks to switch modes.
 - **Interactive mode file edits.** The model MAY remove lines from files to set
   up reconstruction exercises. The model MUST NOT add or modify lines — only
-  the user restores code. After the session ends, offer to restore any
-  remaining gapped files.
+  the user restores code.
+- **Restore after each round.** After feedback in interactive mode, restore
+  each touched file with `git checkout -- <file>` for a byte-perfect reset
+  that leaves no git diff. If the file had pre-existing uncommitted changes
+  (noted in step 0), restore the original lines manually via `edit_file`
+  instead and warn the user.
 - **Restore on session end.** When the session ends, check whether any files
-  still contain `# ... N lines removed ...` placeholders from interactive mode.
-  If so, offer to restore the original lines.
+  still contain `# ... N lines removed ...` placeholders. If so, restore
+  them with `git checkout -- <file>` (or `edit_file` if pre-existing
+  changes were present).
 
 ## Verification