From dd6f5ade2729de98b1084fe059860ab5b0aa8eb3 Mon Sep 17 00:00:00 2001
From: Yurii Bakurov <45154988+Yurii201811@users.noreply.github.com>
Date: Wed, 23 Sep 2026 08:17:25 +0200
Subject: [PATCH] fix: classify notebooks as trimmable data

---
 CHANGELOG.md           |  7 +++++++
 README.md              |  2 ++
 package-lock.json      | 12 ++----------
 package.json           |  2 +-
 src/classify.js        |  2 +-
 test/notebooks.test.js | 37 +++++++++++++++++++++++++++++++++++++
 6 files changed, 50 insertions(+), 12 deletions(-)
 create mode 100644 test/notebooks.test.js

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 966d236..ea73774 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -3,6 +3,13 @@
 All notable changes to this project are documented here, following
 [Keep a Changelog](https://keepachangelog.com/) and semantic versioning.
 
+## [0.1.17] - 2026-09-23
+
+### Fixed
+
+- Classify `.ipynb` notebooks as data trim candidates, including notebooks below the large-data threshold.
+- Repair unresolved merge markers in the package lockfile while updating release metadata.
+
 ## [0.1.16] - 2026-09-17
 
 ### Fixed
diff --git a/README.md b/README.md
index 89e3050..f81cd0e 100644
--- a/README.md
+++ b/README.md
@@ -65,6 +65,8 @@ ctxtrim  ·  my-repo  ·  412 files
   ✓ .cursorignore (created, 34 patterns), .aiexclude (created, 34 patterns)
 ```
 
+Jupyter notebooks (`.ipynb`) are treated as data and suggested for trimming regardless of size. This excludes the whole notebook, including its source cells, not only its outputs; review these suggestions before using `--write`.
+
 Estimates use the widely-cited ~4-chars-per-token rule (great for ranking and relative savings; pass `--price` to match your model).
 
 Vendored dependency and build output directories (`node_modules`, `dist`, `build`, ...) are reported as a single entry keyed by directory name — sized from a cheap stat walk without reading the files inside. Directory-level categories are decided by the directory name, not by reading its contents.
diff --git a/package-lock.json b/package-lock.json
index 20a1a7d..4f11004 100644
--- a/package-lock.json
+++ b/package-lock.json
@@ -1,20 +1,12 @@
 {
   "name": "ctxtrim",
-<<<<<<< HEAD
-  "version": "0.1.16",
-=======
-  "version": "0.1.15",
->>>>>>> origin/main
+  "version": "0.1.17",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "ctxtrim",
-<<<<<<< HEAD
-      "version": "0.1.16",
-=======
-      "version": "0.1.15",
->>>>>>> origin/main
+      "version": "0.1.17",
       "license": "MIT",
       "bin": {
         "ctxtrim": "bin/ctxtrim.js"
diff --git a/package.json b/package.json
index 8f855ca..726111b 100644
--- a/package.json
+++ b/package.json
@@ -1,6 +1,6 @@
 {
   "name": "ctxtrim",
-  "version": "0.1.16",
+  "version": "0.1.17",
   "description": "Trim what bloats your AI coding context. Scan a repo, find the high-cost/low-value files ballooning your Claude Code / Cursor / Codex context, and write ignore files to cut token cost. Zero dependencies.",
   "type": "module",
   "bin": {
diff --git a/src/classify.js b/src/classify.js
index 8a1bc2b..e9230fd 100644
--- a/src/classify.js
+++ b/src/classify.js
@@ -21,7 +21,7 @@ const LOCKFILES = new Set([
 ]);
 
 const DATA_EXT = new Set([
-  ".csv", ".tsv", ".parquet", ".ndjson", ".jsonl", ".sqlite", ".sqlite3",
+  ".ipynb", ".csv", ".tsv", ".parquet", ".ndjson", ".jsonl", ".sqlite", ".sqlite3",
   ".db", ".dump", ".log", ".pkl", ".npy", ".npz", ".arrow", ".feather", ".geojson",
 ]);
 
diff --git a/test/notebooks.test.js b/test/notebooks.test.js
new file mode 100644
index 0000000..1fdcec3
--- /dev/null
+++ b/test/notebooks.test.js
@@ -0,0 +1,37 @@
+import { mkdtempSync, rmSync, writeFileSync } from "node:fs";
+import { tmpdir } from "node:os";
+import { join } from "node:path";
+import { test } from "node:test";
+import assert from "node:assert/strict";
+import { classify } from "../src/classify.js";
+import { scanRepo } from "../src/scan.js";
+
+test("notebooks are data trim candidates below the large-data threshold", () => {
+  for (const name of ["analysis.ipynb", "analysis.IPYNB"]) {
+    const result = classify(name, { tokens: 1510, maxTokens: 2000 });
+    assert.equal(result.category, "data", name);
+    assert.equal(result.trim, true, name);
+    assert.equal(result.binary, false, name);
+  }
+  assert.equal(classify("analysis.py", { tokens: 1510 }).trim, false);
+});
+
+test("scan accounts for output-heavy notebooks and suggests their ignore pattern", (t) => {
+  const root = mkdtempSync(join(tmpdir(), "ctxtrim-notebook-"));
+  t.after(() => rmSync(root, { recursive: true, force: true }));
+  const notebook = {
+    cells: [{ cell_type: "code", execution_count: 1, metadata: {}, source: ["print('x')"],
+      outputs: [{ output_type: "stream", name: "stdout", text: ["x".repeat(6000)] }] }],
+    metadata: {}, nbformat: 4, nbformat_minor: 5,
+  };
+  writeFileSync(join(root, "analysis.ipynb"), JSON.stringify(notebook));
+  writeFileSync(join(root, "analysis.py"), "print('x')\n");
+  const result = scanRepo(root);
+  const file = result.files.find((entry) => entry.rel === "analysis.ipynb");
+  assert.ok(file.tokens > 1500 && file.tokens < 2000);
+  assert.equal(file.category, "data");
+  assert.equal(file.trim, true);
+  assert.equal(result.totals.trimTokens, file.tokens);
+  assert.deepEqual(result.patterns, ["analysis.ipynb"]);
+  assert.equal(result.files.find((entry) => entry.rel === "analysis.py").trim, false);
+});