#40 (WIP, UNVERIFIED): restore exact author attribution on undo/redo

Follow-up to #38. #38 made undo/redo re-inserted text neutral (no false human
coloring); #40 restores its EXACT prior attribution so Claude's restored text is
blue again, the human's green.

Mechanism — text-keyed attribution snapshots: per-doc Map<documentText, spans>,
snapshotted after every forward edit + at load; on undo/redo, after the #38
geometry reconcile, if a snapshot's text equals the current buffer the spans are
restored exactly (offsets valid — identical text). Robust to VS Code undo
coalescing (only the resulting-text-matching event restores); far-back/evicted
states fall back to #38 neutral. History bounded (ATTR_HISTORY_MAX, oldest
evicted).

NOT MERGED / NOT VERIFIED END-TO-END: 222 unit + typecheck green, but the #40
host E2E (and the pre-existing #38 undoMarks E2E) depend on
executeCommand("undo"), which is broken in this test environment — the untouched
#38 test fails identically on clean main (the known undoMarks flake, now
deterministic). Clearing .vscode-test/user-data (the usual remedy) is
permission-blocked here. The operator should verify in a working E2E environment
before merging.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

src/attributionController.ts

@@ -44,8 +44,19 @@ interface DocAttribution {
    * orphans on reload).
    */
   hadAttributions: boolean;
+  /**
+   * #40: text-keyed attribution snapshots for exact provenance restoration on
+   * undo/redo. Maps a document-text state → the live spans at that state (offsets
+   * valid for that exact text). Captured after every forward edit + at load;
+   * consulted on undo/redo to restore the matching state's spans. Bounded (oldest
+   * evicted) — a far-back/evicted state falls back to the #38 neutral reconcile.
+   */
+  attrHistory: Map<string, LiveSpan[]>;
 }
 
+/** #40: cap on the per-doc attribution-snapshot history (oldest evicted). */
+const ATTR_HISTORY_MAX = 200;
+
 export class AttributionController implements vscode.Disposable {
   private readonly disposables: vscode.Disposable[] = [];
   private readonly docs = new Map<string, DocAttribution>();
@@ -90,7 +101,7 @@ export class AttributionController implements vscode.Disposable {
   private state(docPath: string): DocAttribution {
     let s = this.docs.get(docPath);
     if (!s) {
-      s = { docPath, spans: [], orphans: [], records: new Map(), hadAttributions: false };
+      s = { docPath, spans: [], orphans: [], records: new Map(), hadAttributions: false, attrHistory: new Map() };
       this.docs.set(docPath, s);
     }
     return s;
@@ -125,6 +136,9 @@ export class AttributionController implements vscode.Disposable {
       s.spans = coalesce(s.spans);
       if (artifact.attributions.length > 0) s.hadAttributions = true;
     }
+    // #40: seed the snapshot history with the loaded state so undoing back to it
+    // restores its exact attribution.
+    this.snapshotAttribution(s, document.getText());
     this.render(document);
   }
 
@@ -140,6 +154,17 @@ export class AttributionController implements vscode.Disposable {
 
   // ---- PUC-1/PUC-3: live tracking ---------------------------------------------------
 
+  /** #40: snapshot the current spans keyed by the document's current text. */
+  private snapshotAttribution(s: DocAttribution, text: string): void {
+    s.attrHistory.delete(text); // re-insert at the end (recency order)
+    s.attrHistory.set(text, s.spans.map((sp) => ({ ...sp })));
+    while (s.attrHistory.size > ATTR_HISTORY_MAX) {
+      const oldest = s.attrHistory.keys().next().value as string | undefined;
+      if (oldest === undefined) break;
+      s.attrHistory.delete(oldest);
+    }
+  }
+
   private onDidChange(e: vscode.TextDocumentChangeEvent): void {
     if (!this.isTracked(e.document) || e.contentChanges.length === 0) return;
     const docPath = this.keyOf(e.document);
@@ -202,6 +227,18 @@ export class AttributionController implements vscode.Disposable {
         );
       }
     }
+    // #40: exact provenance across history navigation. After a FORWARD edit,
+    // snapshot the new state's spans. On UNDO/REDO, the geometry reconcile above
+    // left re-inserted text neutral (#38); if a snapshot's text equals the current
+    // buffer, restore that state's spans exactly (offsets are valid — identical
+    // text) so Claude's restored text is blue again, the human's green. No match
+    // (far-back/evicted state) keeps the #38 neutral fallback.
+    if (isUndoRedo) {
+      const restored = s.attrHistory.get(e.document.getText());
+      if (restored) s.spans = restored.map((sp) => ({ ...sp }));
+    } else {
+      this.snapshotAttribution(s, e.document.getText());
+    }
     if (s.spans.length > 0) s.hadAttributions = true;
     this.render(e.document);
   }

test/e2e/suite/s40Provenance.test.ts

@@ -0,0 +1,113 @@
+import * as assert from "assert";
+import * as fs from "fs";
+import * as path from "path";
+import * as vscode from "vscode";
+import type { CowritingApi } from "../../../src/extension";
+
+const WS = process.env.E2E_WORKSPACE!;
+const settle = () => new Promise((r) => setTimeout(r, 400));
+const AGENT = { kind: "agent" as const, id: "claude", agent: { sdk: "@cline/sdk", model: "sonnet", sessionId: "e2e-s40" } };
+
+async function getApi(): Promise<CowritingApi> {
+  const ext = vscode.extensions.getExtension("benstull.vscode-cowriting-plugin")!;
+  const api = (await ext.activate()) as CowritingApi;
+  assert.ok(api?.attributionController, "exports attribution");
+  return api;
+}
+
+async function freshDoc(rel: string, body: string): Promise<{ doc: vscode.TextDocument; key: string }> {
+  const abs = path.join(WS, rel);
+  fs.mkdirSync(path.dirname(abs), { recursive: true });
+  fs.writeFileSync(abs, body, "utf8");
+  const uri = vscode.Uri.file(abs);
+  const doc = await vscode.workspace.openTextDocument(uri);
+  await vscode.window.showTextDocument(doc);
+  await settle();
+  return { doc, key: uri.toString() };
+}
+
+// #40 (follow-up to #38): on undo/redo, restore each re-inserted char's EXACT
+// prior author attribution rather than leaving it neutral (#38). Driven mid-edit
+// (buffer dirty) so the attribution branch runs, not the disk-sync one.
+suite("F3 #40 — undo/redo restores exact author attribution (host E2E, no LLM)", () => {
+  test("undo of a deletion of AGENT text restores its agent span (not neutral, not human)", async () => {
+    const { doc } = await freshDoc("docs/s40agent.md", "Human start. xxxx end.\n");
+    const api = await getApi();
+    const ctl = api.attributionController;
+
+    // Make "xxxx" agent-authored via the seam → an agent span over "ROBOT".
+    const t = "xxxx";
+    const start = doc.getText().indexOf(t);
+    const ok = await ctl.applyAgentEdit(
+      doc,
+      new vscode.Range(doc.positionAt(start), doc.positionAt(start + t.length)),
+      "ROBOT",
+      AGENT,
+      { turnId: "turn-s40" },
+    );
+    assert.strictEqual(ok, true, "seam edit applies");
+    await settle();
+    const key = api.proposalController.keyFor(doc);
+    assert.ok(
+      ctl.getSpans(key).some((s) => s.authorKind === "agent" && doc.getText().slice(s.range.start, s.range.end).includes("ROBOT")),
+      "ROBOT is agent-attributed after the seam edit",
+    );
+
+    // Human deletes "ROBOT" (buffer stays dirty: it already diverged from disk).
+    const rs = doc.getText().indexOf("ROBOT");
+    const del = new vscode.WorkspaceEdit();
+    del.delete(doc.uri, new vscode.Range(doc.positionAt(rs), doc.positionAt(rs + "ROBOT".length)));
+    assert.ok(await vscode.workspace.applyEdit(del), "delete applied");
+    await settle();
+    assert.ok(!doc.getText().includes("ROBOT"), "ROBOT deleted");
+
+    // Undo the deletion → ROBOT re-inserted. #40: its AGENT span is restored.
+    await vscode.window.showTextDocument(doc);
+    await vscode.commands.executeCommand("undo");
+    await settle();
+    assert.ok(doc.getText().includes("ROBOT"), "undo restored ROBOT");
+    assert.ok(doc.isDirty, "buffer still dirty → attribution branch ran");
+
+    const r2 = doc.getText().indexOf("ROBOT");
+    const spans = ctl.getSpans(key);
+    const over = spans.filter((s) => s.range.start < r2 + 5 && s.range.end > r2);
+    assert.ok(over.length > 0, "restored ROBOT carries a span");
+    assert.ok(over.every((s) => s.authorKind === "agent"), `restored ROBOT is agent-attributed, got ${JSON.stringify(over)}`);
+  });
+
+  test("edit → undo → redo round-trips attribution to identical state", async () => {
+    const { doc } = await freshDoc("docs/s40roundtrip.md", "Base alpha. yyyy omega.\n");
+    const api = await getApi();
+    const ctl = api.attributionController;
+    const key = api.proposalController.keyFor(doc);
+
+    const start = doc.getText().indexOf("yyyy");
+    await ctl.applyAgentEdit(
+      doc,
+      new vscode.Range(doc.positionAt(start), doc.positionAt(start + 4)),
+      "BLUEWORD",
+      AGENT,
+      { turnId: "turn-s40b" },
+    );
+    await settle();
+    const norm = (k: string) =>
+      ctl
+        .getSpans(k)
+        .map((s) => ({ a: s.authorKind, t: doc.getText().slice(s.range.start, s.range.end) }))
+        .sort((x, y) => (x.t < y.t ? -1 : 1));
+    const afterAgent = JSON.stringify(norm(key));
+    assert.ok(afterAgent.includes("BLUEWORD") && afterAgent.includes("agent"), "agent span present after the edit");
+
+    // Delete BLUEWORD, then undo (restore) then redo (re-delete) then undo again.
+    const bs = doc.getText().indexOf("BLUEWORD");
+    const del = new vscode.WorkspaceEdit();
+    del.delete(doc.uri, new vscode.Range(doc.positionAt(bs), doc.positionAt(bs + "BLUEWORD".length)));
+    await vscode.workspace.applyEdit(del);
+    await settle();
+    await vscode.window.showTextDocument(doc);
+    await vscode.commands.executeCommand("undo"); // restore BLUEWORD
+    await settle();
+    assert.ok(doc.getText().includes("BLUEWORD"), "undo restored BLUEWORD");
+    assert.strictEqual(JSON.stringify(norm(key)), afterAgent, "attribution after undo matches the pre-deletion state exactly");
+  });
+});