fix(media): decode remote URL fallback filenames (#84108)

clawsweeper[bot] · jbetala7 · Takhoffman · web-flow · commit 4e60ad721209 · 2026-05-19T11:42:16.000Z
Summary: - This replacement PR decodes valid percent escapes in remote media URL fallback basenames, replaces decoded s ... scores, preserves malformed escapes, adds `saveRemoteMedia` regression coverage, and updates the changelog. - Reproducibility: yes. Source inspection plus a Node check on current main show the URL path basename remains `My%20Report.pdf`, and the linked source PR supplies after-fix runtime proof through `saveRemoteMedia`. Automerge notes: - PR branch already contained follow-up commit before automerge: fix(media): decode remote URL fallback filenames Validation: - ClawSweeper review passed for head 8cbac43. - Required merge gates passed before the squash merge. Prepared head SHA: 8cbac43 Review: #84108 (comment) Co-authored-by: Jayesh Betala <jayesh.betala7@gmail.com> Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com> Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com> Approved-by: takhoffman Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -18,6 +18,7 @@ Docs: https://docs.openclaw.ai
 - Agents/subagents: recover stale completion announces by retrying unsupported transcript-wait wakes without transcript waiting and forcing a message-tool handoff when the requester run is already stale. Fixes #83699. (#83700) Thanks @galiniliev.
 - Agents/subagents: skip stale embedded-run wake probes for dormant completion requesters, so late subagent completions go straight to requester-agent/direct handoff instead of producing `reason=no_active_run` queue noise. (#82964) Thanks @galiniliev.
 - CLI: retry config snapshot reads after a transient failure so one rejected read no longer poisons later commands in the same process. (#83931) Thanks @honor2030.
+- Media: decode URL path basenames before using them as remote media fallback filenames, so files like `My%20Report.pdf` are surfaced as `My Report.pdf`. Fixes #84050. (#84052) Thanks @jbetala7.
 - WhatsApp: clarify inbound group diagnostics so observed but unregistered groups point to `channels.whatsapp.groups` without changing routing or sender authorization. (#83846) Thanks @neeravmakwana.
 - WhatsApp: drain pending outbound deliveries on a 30s periodic timer in addition to the reconnect handler, so messages enqueued while the provider is already connected no longer wait for the next reconnect to send. (#79083) Thanks @Oviemudiaga.
 - CLI/TUI: include gateway plugin slash commands in TUI autocomplete, so connected sessions can suggest plugin-owned commands exposed by the running Gateway. (#83640) Thanks @se7en-agent.
diff --git a/src/media/fetch.test.ts b/src/media/fetch.test.ts
@@ -583,6 +583,70 @@ describe("readRemoteMediaBuffer", () => {
     await expect(fs.readFile(saved.path)).resolves.toStrictEqual(Buffer.from([1, 2, 3, 4]));
   });
 
+  it("decodes URL path basenames when deriving remote media filenames", async () => {
+    const fetchImpl = vi.fn(
+      async () =>
+        new Response(makeStream([new Uint8Array([1, 2, 3])]), {
+          status: 200,
+          headers: { "content-type": "application/pdf" },
+        }),
+    );
+
+    const saved = await saveRemoteMedia({
+      url: "https://example.com/files/My%20Report.pdf",
+      fetchImpl,
+      lookupFn: makeLookupFn(),
+      maxBytes: 8,
+    });
+
+    expect(saved.fileName).toBe("My Report.pdf");
+  });
+
+  it("keeps raw URL path basenames when percent escapes are malformed", async () => {
+    const fetchImpl = vi.fn(
+      async () =>
+        new Response(makeStream([new Uint8Array([1, 2, 3])]), {
+          status: 200,
+          headers: { "content-type": "application/pdf" },
+        }),
+    );
+
+    const saved = await saveRemoteMedia({
+      url: "https://example.com/files/bad%E0%A4%A.pdf",
+      fetchImpl,
+      lookupFn: makeLookupFn(),
+      maxBytes: 8,
+    });
+
+    expect(saved.fileName).toBe("bad%E0%A4%A.pdf");
+  });
+
+  it.each([
+    ["https://example.com/files/reports%2FQ1.pdf", "reports_Q1.pdf"],
+    ["https://example.com/files/reports%5CQ1.pdf", "reports_Q1.pdf"],
+    ["https://example.com/files/reports%2F%2FQ1.pdf", "reports__Q1.pdf"],
+  ])(
+    "keeps decoded URL fallback separators inside the selected basename",
+    async (url, fileName) => {
+      const fetchImpl = vi.fn(
+        async () =>
+          new Response(makeStream([new Uint8Array([1, 2, 3])]), {
+            status: 200,
+            headers: { "content-type": "application/pdf" },
+          }),
+      );
+
+      const saved = await saveRemoteMedia({
+        url,
+        fetchImpl,
+        lookupFn: makeLookupFn(),
+        maxBytes: 8,
+      });
+
+      expect(saved.fileName).toBe(fileName);
+    },
+  );
+
   it("saves bodyless successful responses without unbounded buffering", async () => {
     const saved = await saveResponseMedia(new Response(null, { status: 204 }), {
       sourceUrl: "https://example.com/empty",
diff --git a/src/media/fetch.ts b/src/media/fetch.ts
@@ -129,6 +129,18 @@ function parseContentDispositionFileName(header?: string | null): string | undef
   return undefined;
 }
 
+function basenameFromUrlPathname(pathname: string): string {
+  const base = basenameFromAnyPath(pathname);
+  if (!base) {
+    return "";
+  }
+  try {
+    return decodeURIComponent(base).replace(/[\\/]/g, "_");
+  } catch {
+    return base;
+  }
+}
+
 async function readErrorBodySnippet(
   res: Response,
   opts?: {
@@ -295,7 +307,7 @@ function resolveRemoteFileName(params: {
   let fileNameFromUrl: string | undefined;
   try {
     const parsed = new URL(params.finalUrl);
-    const base = basenameFromAnyPath(parsed.pathname);
+    const base = basenameFromUrlPathname(parsed.pathname);
     fileNameFromUrl = base || undefined;
   } catch {
     // ignore parse errors; leave undefined
