From b77c1923c81ec7dd6d3b0dc66f5b47b3f47c6744 Mon Sep 17 00:00:00 2001
From: schienbiz <274676847+schienbiz@users.noreply.github.com>
Date: Sat, 29 Aug 2026 23:37:24 +0800
Subject: [PATCH] feat(redact): add Groq, Tavily and Notion API key patterns

---
 lib/redact-patterns.ts     | 27 +++++++++++++++++++++++++++
 test/redact-engine.test.ts | 10 ++++++++++
 2 files changed, 37 insertions(+)

diff --git a/lib/redact-patterns.ts b/lib/redact-patterns.ts
index 29bd14921..322fc696b 100644
--- a/lib/redact-patterns.ts
+++ b/lib/redact-patterns.ts
@@ -438,6 +438,33 @@ export const PATTERNS: RedactPattern[] = [
     // gstack drives glab first-class — these were a coverage gap (#1946).
     regex: /\b(gl(?:pat|ptt|dt)-[A-Za-z0-9_-]{20,})\b/,
   },
+  {
+    id: "groq.key",
+    tier: "HIGH",
+    category: "secret",
+    description: "Groq API key",
+    regex: /\b(gsk_[A-Za-z0-9]{20,})\b/,
+  },
+  {
+    id: "tavily.key",
+    tier: "HIGH",
+    category: "secret",
+    description: "Tavily API key (incl. tvly-dev-/tvly-prod-)",
+    // Explicit environment infixes rather than a globally-optional segment,
+    // which would also match separator-less tvly-devabc… (same reasoning as
+    // openai.key above).
+    regex: /\b(tvly-(?:dev-|prod-)?[A-Za-z0-9]{16,})\b/,
+  },
+  {
+    id: "notion.token",
+    tier: "HIGH",
+    category: "secret",
+    description: "Notion integration token (ntn_ current, secret_ legacy)",
+    // Two explicit shapes. The legacy `secret_` form keeps a high {40,} floor
+    // because the prefix is an ordinary English word — the length is what makes
+    // it a credential rather than prose.
+    regex: /\b(ntn_[A-Za-z0-9]{40,}|secret_[A-Za-z0-9]{40,})\b/,
+  },
   {
     id: "huggingface.token",
     tier: "HIGH",
diff --git a/test/redact-engine.test.ts b/test/redact-engine.test.ts
index fe6a1f46a..8b86c471f 100644
--- a/test/redact-engine.test.ts
+++ b/test/redact-engine.test.ts
@@ -48,6 +48,11 @@ describe("HIGH credential patterns", () => {
     ["gitlab.token", "remote: glpat-" + "Ab12Cd34Ef56Gh78Ij90"],
     ["gitlab.token", "trigger glptt-" + "a1b2c3d4e5f6a7b8c9d0e1f2"],
     ["gitlab.token", "deploy gldt-" + "Zy98Xw76Vu54Ts32Rq10"],
+    ["groq.key", "gsk_" + "AbCdEfGhIjKlMnOpQrStUvWxYz0123456789AbCdEfGhIjKlMn"],
+    ["tavily.key", "tvly-" + "AbCdEfGhIjKlMnOpQrStUvWx"],
+    ["tavily.key", "tvly-dev-" + "AbCdEfGhIjKlMnOpQrStUvWx"],
+    ["notion.token", "ntn_" + "AbCdEfGhIjKlMnOpQrStUvWxYz0123456789AbCdEfGh"],
+    ["notion.token", "secret_" + "AbCdEfGhIjKlMnOpQrStUvWxYz0123456789AbCdEfGh"],
     ["huggingface.token", "hf_" + "AbCdEfGhIjKlMnOpQrStUvWxYz012345"],
     ["npm.token", "npm_" + "a1B2c3D4e5F6g7H8i9J0k1L2m3N4o5P6q7R8"],
     ["digitalocean.token", "dop_v1_" + "0123456789abcdef".repeat(4)],
@@ -261,6 +266,11 @@ describe("#1946 pattern negatives (placeholders never fire)", () => {
   test("short or placeholder shapes don't trip the new HIGH patterns", () => {
     expect(ids("glpat-xxxx")).not.toContain("gitlab.token");
     expect(ids("hf_token")).not.toContain("huggingface.token");
+    expect(ids("gsk_key")).not.toContain("groq.key");
+    expect(ids("tvly-key")).not.toContain("tavily.key");
+    expect(ids("ntn_token")).not.toContain("notion.token");
+    // `secret_` is an ordinary word; only the length makes it a credential.
+    expect(ids("secret_value")).not.toContain("notion.token");
     expect(ids("npm_install")).not.toContain("npm.token");
     expect(ids("dop_v1_short")).not.toContain("digitalocean.token");
     // pem header WITHOUT the GCP JSON shape stays pem.private_key only.