feat!: remove the deep-research feature

The harness ships browser tools; orchestrating a multi-agent research
workflow on top of them is the agent's job, not this extension's. Drops
the skill, the /deep-research command, and the web-search-researcher
subagent config.

browser_web_search and browser_read_page are untouched — the two tests
that covered their pure parsers move to test/domains/, where the test
glob still picks them up.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

1 files changed, 60 insertions, 0 deletions

diff --git a/test/domains/readability-test.ts b/test/domains/readability-test.ts
new file mode 100644
index 0000000..211229d
--- /dev/null
+++ b/test/domains/readability-test.ts
@@ -0,0 +1,60 @@
+import { test, describe } from "node:test";
+import assert from "node:assert/strict";
+import { readFileSync } from "node:fs";
+import { join } from "node:path";
+import { extractReadable, type PageCapture } from "../../src/domains/readpage/readability";
+
+const fixture = (name: string): PageCapture =>
+  JSON.parse(readFileSync(join(import.meta.dirname, "fixtures", name), "utf8")) as PageCapture;
+
+describe("pure readability extractor", () => {
+  test("S10: article body text is present", () => {
+    const page = extractReadable(fixture("article-capture.json"));
+    assert.ok(page.text.includes("Chrome DevTools Protocol lets tools instrument"));
+  });
+
+  test("S10: article headings are preserved", () => {
+    const page = extractReadable(fixture("article-capture.json"));
+    assert.ok(page.text.includes("Sessions and Targets"));
+  });
+
+  test("S10: nav boilerplate is dropped", () => {
+    const page = extractReadable(fixture("article-capture.json"));
+    assert.ok(!page.text.includes("Home Products Blog"));
+  });
+
+  test("S10: footer boilerplate is dropped", () => {
+    const page = extractReadable(fixture("article-capture.json"));
+    assert.ok(!page.text.includes("Copyright 2026"));
+  });
+
+  test("S10: high-link-density promo block is dropped", () => {
+    const page = extractReadable(fixture("article-capture.json"));
+    assert.ok(!page.text.includes("Subscribe here for our newsletter"));
+  });
+
+  test("S10: paragraph/heading structure preserved as markdown", () => {
+    const page = extractReadable(fixture("article-capture.json"));
+    assert.ok(page.text.includes("## Sessions and Targets"));
+  });
+
+  test("S10: title and url passed through", () => {
+    const page = extractReadable(fixture("article-capture.json"));
+    assert.ok(page.title === "How the Chrome DevTools Protocol Works" && page.url.startsWith("https://"));
+  });
+
+  test("S10: word count reflects the article body", () => {
+    const page = extractReadable(fixture("article-capture.json"));
+    assert.ok(page.wordCount > 40);
+  });
+
+  test("S11: structure-less page falls back to non-empty body text", () => {
+    const page = extractReadable(fixture("no-article-capture.json"));
+    assert.ok(page.text.length > 0);
+  });
+
+  test("S11: fallback body text carries the real content", () => {
+    const page = extractReadable(fixture("no-article-capture.json"));
+    assert.ok(page.text.includes("Your account is active"));
+  });
+});