#47 (SLICE-2, review): per-block document proposals + word-precise accept

Document-edit flow SLICE-2 (specs/coauthoring-document-edit-flow.md §7.2,
INV-39/40/41 — P1 "too much to review"). A whole-document rewrite now proposes
ONE F4 proposal per CHANGED BLOCK (the unit a human reviews), but accepting a
block reconciles attribution at WORD granularity (the unit F3 records). Block =
decision unit; word = attribution unit. Supersedes INV-37's per-word cut for
document edits; selection edits unchanged.

- trackChangesModel.ts: new pure diffToBlockHunks(current, rewritten) — block-key
  alignment (reusing diffArrays/diffBlocks keying): an isolated changed block →
  one block-aligned hunk → the rewritten block raw (a code/mermaid fence is one
  atomic whole-fence hunk, INV-23); insert/delete runs → one gap-span hunk over
  the inter-anchor region (separators included) so reconstruction stays exact; a
  zero-width gap-span is anchored (INV-41). Also split diffToHunks into the raw,
  un-anchored wordEditHunks + the anchoring wrapper (the anchoring could grow an
  insertion to overlap an adjacent hunk, corrupting a batch apply — a latent bug
  that only surfaced once hunks are applied as a batch).
- trackChangesPreview.ts: runEditAndPropose document branch uses diffToBlockHunks
  and tags each proposal granularity:"block".
- model.ts / proposalModel.ts: additive optional Proposal.granularity
  ("block"|"single"; absent ⇒ single, back-compat — no migration).
- proposalController.ts: accept of a block proposal runs an intra-block word
  sub-diff (wordEditHunks, disjoint) and applies one applyAgentEdit per changed
  run, descending offset — only the words Claude changed land Claude-attributed;
  unchanged spans keep prior authorship (INV-40).
- Tests: diffToBlockHunks unit (reconstruction + fence atomic + add/remove);
  f12Review host E2E (M blocks→M proposals, unchanged→none, fence atomic, INV-40
  attribution, INV-41 insertion accept); updated the f11 document-path E2E to
  per-block (INV-39 supersedes INV-37); MANUAL-SMOKE-F12 §2.

Seam note: pendingEdits.matchEvent resolves one registration per change event, so
INV-40's per-run attribution is sequential applyAgentEdit calls (N undo steps),
not one multi-replace WorkspaceEdit — see transcript Deferred decisions.

214 unit + 69/5 host E2E green.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Ben Stull
2026-06-13 08:01:16 -07:00
parent 6e944ab4cc
commit 2f6008ba2b
9 changed files with 456 additions and 26 deletions
+11 -8
View File
@@ -67,8 +67,10 @@ suite("F11 preview toolbar (host E2E — message → seam wiring, no LLM)", () =
assert.match(entry!.when ?? "", /editorLangId == markdown/, "guarded on markdown");
});
// SLICE-3: Edit Document → a whole-document rewrite diffed into N F4 proposals.
test("runEditAndPropose(document) with a stubbed multi-hunk rewrite → N proposals matching the hunks (PUC-4, INV-37)", async () => {
// #47 (was INV-37): Edit Document now cuts at BLOCK granularity — two word
// changes in ONE paragraph are ONE block proposal (INV-39 supersedes INV-37's
// per-word cut). Full block coverage lives in f12Review.test.ts.
test("runEditAndPropose(document) — two word edits in one paragraph → ONE block proposal (PUC-4, INV-39)", async () => {
const { doc, key } = await freshDoc(
"docs/f11doc.md",
"# F11 doc\n\nThe quick brown fox jumps over the lazy dog.\n",
@@ -87,15 +89,16 @@ suite("F11 preview toolbar (host E2E — message → seam wiring, no LLM)", () =
const ids = await ctl.runEditAndPropose(doc, { kind: "document" }, "swap brown→RED and dog→CAT");
await settle();
assert.strictEqual(ids.length, 2, "two changed words → two independent proposals");
assert.strictEqual(ids.length, 1, "two changed words in one block → ONE block proposal (INV-39)");
const views = api.proposalController.listProposals(doc);
assert.ok(
ids.every((id) => views.some((v) => v.id === id)),
"every returned proposal id is a live pending proposal",
const view = views.find((v) => v.id === ids[0]);
assert.ok(view, "the returned proposal id is a live pending proposal");
assert.strictEqual(
view!.replacement,
"The quick RED fox jumps over the lazy CAT.",
"the block proposal carries the whole rewritten paragraph",
);
const replacements = views.map((v) => v.replacement);
assert.ok(replacements.includes("RED") && replacements.includes("CAT"), "proposals carry the per-hunk replacements");
// INV-10: proposing never mutates the document.
assert.ok(doc.getText().includes("brown fox") && doc.getText().includes("lazy dog"), "document unchanged by propose");
void key;
+134
View File
@@ -0,0 +1,134 @@
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));
async function getApi(): Promise<CowritingApi> {
const ext = vscode.extensions.getExtension("benstull.vscode-cowriting-plugin")!;
const api = (await ext.activate()) as CowritingApi;
assert.ok(api?.trackChangesPreviewController && api?.proposalController, "exports controllers");
return api;
}
async function freshDoc(rel: string, body: string): Promise<vscode.TextDocument> {
const abs = path.join(WS, rel);
fs.mkdirSync(path.dirname(abs), { recursive: true });
fs.writeFileSync(abs, body, "utf8");
const doc = await vscode.workspace.openTextDocument(vscode.Uri.file(abs));
await vscode.window.showTextDocument(doc);
await settle();
return doc;
}
// #47 SLICE-2 (review, P1): a document rewrite proposes ONE F4 proposal per
// CHANGED BLOCK (INV-39 supersedes INV-37's per-word cut), but accepting a block
// reconciles attribution at WORD granularity (INV-40 — block = decision unit,
// word = attribution unit). Host E2E, no LLM (the edit turn is stubbed).
suite("F12 SLICE-2 — block-granularity document proposals (#47, INV-39/40/41)", () => {
// PUC-4: M changed blocks → M proposals; unchanged blocks → none.
test("edits across two paragraphs → two proposals; the untouched paragraph yields none (INV-39)", async () => {
const doc = await freshDoc(
"docs/f12-multi.md",
"# Doc\n\nFirst paragraph alpha.\n\nSecond paragraph beta.\n\nThird paragraph gamma.\n",
);
const api = await getApi();
const ctl = api.trackChangesPreviewController;
ctl.setEditTurnForTest(async () => ({
replacement: "# Doc\n\nFirst paragraph ALPHA.\n\nSecond paragraph beta.\n\nThird paragraph GAMMA.\n",
model: "sonnet",
sessionId: "e2e-f12-multi",
}));
const ids = await ctl.runEditAndPropose(doc, { kind: "document" }, "uppercase the first/last nouns");
await settle();
assert.strictEqual(ids.length, 2, "two changed blocks → two proposals; the unchanged middle block → none");
// each proposal's anchor spans a whole block, and the replacement is that block's rewrite
const views = api.proposalController.listProposals(doc);
const replacements = views.map((v) => v.replacement).sort();
assert.deepStrictEqual(replacements, ["First paragraph ALPHA.", "Third paragraph GAMMA."]);
});
// PUC-4 + INV-23: a changed code fence is ONE atomic whole-fence proposal.
test("a changed code fence → one atomic proposal over the whole fence (INV-23)", async () => {
const doc = await freshDoc(
"docs/f12-fence.md",
"# Code\n\n```js\nconst a = 1;\nconst b = 2;\n```\n",
);
const api = await getApi();
const ctl = api.trackChangesPreviewController;
ctl.setEditTurnForTest(async () => ({
replacement: "# Code\n\n```js\nconst a = 10;\nconst b = 2;\n```\n",
model: "sonnet",
sessionId: "e2e-f12-fence",
}));
const ids = await ctl.runEditAndPropose(doc, { kind: "document" }, "bump a to 10");
await settle();
assert.strictEqual(ids.length, 1, "a changed fence is one atomic proposal");
const view = api.proposalController.listProposals(doc).find((v) => v.id === ids[0])!;
assert.strictEqual(view.replacement, "```js\nconst a = 10;\nconst b = 2;\n```", "whole-fence replacement");
});
// PUC-5 / INV-40: accepting a block attributes ONLY the words Claude changed —
// unchanged words in the block are NOT swept into Claude's authorship.
test("accepting a block proposal attributes only the changed words to Claude (INV-40)", async () => {
const doc = await freshDoc("docs/f12-attr.md", "# T\n\nThe quick brown fox jumps lazily.\n");
const api = await getApi();
const ctl = api.trackChangesPreviewController;
const key = api.proposalController.keyFor(doc);
ctl.setEditTurnForTest(async () => ({
replacement: "# T\n\nThe quick RED fox jumps SLOWLY.\n",
model: "sonnet",
sessionId: "e2e-f12-attr",
}));
const ids = await ctl.runEditAndPropose(doc, { kind: "document" }, "change two words");
await settle();
assert.strictEqual(ids.length, 1, "one changed paragraph → one block proposal");
const ok = await api.proposalController.acceptById(key, ids[0]);
assert.ok(ok, "the block proposal accepts");
await settle();
assert.strictEqual(doc.getText(), "# T\n\nThe quick RED fox jumps SLOWLY.\n", "the whole block landed");
const agentTexts = api.attributionController
.getSpans(key)
.filter((s) => s.authorKind === "agent")
.map((s) => doc.getText().slice(s.range.start, s.range.end).trim())
.filter((t) => t.length > 0);
// Only the two words Claude actually changed are Claude-attributed.
const joined = agentTexts.join(" ");
assert.ok(joined.includes("RED"), "the changed word RED is Claude-attributed");
assert.ok(joined.includes("SLOWLY"), "the changed word SLOWLY is Claude-attributed");
assert.ok(!/\bquick\b/.test(joined), "the unchanged word 'quick' is NOT swept into Claude's authorship");
assert.ok(!/\bfox\b/.test(joined), "the unchanged word 'fox' is NOT swept into Claude's authorship");
});
// PUC-4 / INV-41: a block-insertion rewrite produces acceptable proposals and
// accepting them all reconstructs the intended document (no born-orphaned hunk).
test("a rewrite that inserts a paragraph → acceptable proposals; accept-all reaches the rewrite (INV-41)", async () => {
const original = "# Ins\n\nAlpha block.\n\nBeta block.\n";
const rewrite = "# Ins\n\nAlpha block.\n\nBrand new middle block.\n\nBeta block.\n";
const doc = await freshDoc("docs/f12-insert.md", original);
const api = await getApi();
const ctl = api.trackChangesPreviewController;
const key = api.proposalController.keyFor(doc);
ctl.setEditTurnForTest(async () => ({ replacement: rewrite, model: "sonnet", sessionId: "e2e-f12-insert" }));
const ids = await ctl.runEditAndPropose(doc, { kind: "document" }, "insert a paragraph");
await settle();
assert.ok(ids.length >= 1, "the insertion produced at least one proposal");
for (const id of ids) {
const ok = await api.proposalController.acceptById(key, id);
assert.ok(ok, `proposal ${id} is acceptable (not born-orphaned, INV-41)`);
await settle();
}
assert.strictEqual(doc.getText(), rewrite, "accepting all proposals reconstructs the intended rewrite");
assert.strictEqual(api.proposalController.listProposals(doc).length, 0, "no proposals left pending");
});
});
+85 -1
View File
@@ -1,5 +1,5 @@
import { describe, it, test, expect } from "vitest";
import { splitBlocks, splitBlocksWithRanges, diffBlocks, diffToHunks, renderTrackChanges, colorByAuthor, type AuthorSpan } from "../src/trackChangesModel";
import { splitBlocks, splitBlocksWithRanges, diffBlocks, diffToHunks, diffToBlockHunks, renderTrackChanges, colorByAuthor, type AuthorSpan } from "../src/trackChangesModel";
describe("splitBlocks", () => {
it("splits prose paragraphs on blank lines, dropping empties", () => {
@@ -402,6 +402,90 @@ describe("F11 diffToHunks (INV-37)", () => {
});
});
// #47 SLICE-2 (INV-39): a whole-document rewrite is diffed into ONE EditHunk per
// CHANGED BLOCK (the unit a human reviews), superseding INV-37's per-word hunks.
// Built by coarsening diffToHunks to block boundaries; fences stay atomic
// (INV-23); inserted/deleted blocks keep their anchored gap hunks (INV-41).
// Applying all hunks right→left must still reconstruct the rewrite exactly.
describe("#47 diffToBlockHunks (INV-39/41)", () => {
const applyHunks = (current: string, hunks: ReturnType<typeof diffToBlockHunks>): string => {
let out = current;
for (const h of [...hunks].sort((a, b) => b.start - a.start)) {
out = out.slice(0, h.start) + h.replacement + out.slice(h.end);
}
return out;
};
test("an identical rewrite → zero hunks", () => {
expect(diffToBlockHunks("# H\n\nSame body.\n", "# H\n\nSame body.\n")).toEqual([]);
});
test("two word edits in ONE paragraph → ONE block hunk (supersedes INV-37's two)", () => {
const current = "# Doc\n\nThe quick brown fox jumps over the lazy dog.\n";
const rewrite = "# Doc\n\nThe quick RED fox jumps over the lazy CAT.\n";
const hunks = diffToBlockHunks(current, rewrite);
expect(hunks).toHaveLength(1);
// the hunk spans the whole changed paragraph block
const para = "The quick brown fox jumps over the lazy dog.";
const start = current.indexOf(para);
expect(hunks[0].start).toBe(start);
expect(hunks[0].end).toBe(start + para.length);
expect(hunks[0].replacement).toBe("The quick RED fox jumps over the lazy CAT.");
expect(applyHunks(current, hunks)).toBe(rewrite);
});
test("edits across two paragraphs → two block hunks, one per changed block; unchanged → none", () => {
const current = "First para alpha.\n\nSecond para beta.\n\nThird para gamma.\n";
const rewrite = "First para ALPHA.\n\nSecond para beta.\n\nThird para GAMMA.\n";
const hunks = diffToBlockHunks(current, rewrite);
expect(hunks).toHaveLength(2);
// each hunk lands on a real block boundary in current
const blocks = splitBlocksWithRanges(current);
for (const h of hunks) {
expect(blocks.some((b) => b.start === h.start && b.end === h.end)).toBe(true);
}
expect(applyHunks(current, hunks)).toBe(rewrite);
});
test("a changed code fence → ONE atomic whole-fence hunk (INV-23)", () => {
const current = "# Code\n\n```js\nconst a = 1;\nconst b = 2;\n```\n";
const rewrite = "# Code\n\n```js\nconst a = 10;\nconst b = 2;\n```\n";
const hunks = diffToBlockHunks(current, rewrite);
expect(hunks).toHaveLength(1);
const fence = "```js\nconst a = 1;\nconst b = 2;\n```";
const start = current.indexOf(fence);
expect(hunks[0].start).toBe(start);
expect(hunks[0].end).toBe(start + fence.length);
expect(hunks[0].replacement).toBe("```js\nconst a = 10;\nconst b = 2;\n```");
expect(applyHunks(current, hunks)).toBe(rewrite);
});
test("every hunk is resolvable (non-zero-width, real source text) and reconstructs", () => {
const cases: Array<[string, string]> = [
["# H\n\nThe brown fox sleeps.\n", "# H\n\nThe brown fox QUIETLY sleeps today.\n"], // insert words mid-block
["A para.\n\nB para.\n\nC para.\n", "A para.\n\nC para.\n"], // delete a whole block
["A para.\n\nB para.\n", "A para.\n\nNEW para.\n\nB para.\n"], // insert a whole block
["Only one block here.\n", "A totally different single block.\n"], // wholesale
["Keep me.\n\nDrop this one.\n", "Keep me.\n"], // delete trailing block
["unchanged body\n", "unchanged body\n"], // no-op
];
for (const [current, rewrite] of cases) {
const hunks = diffToBlockHunks(current, rewrite);
for (const h of hunks) {
expect(h.end).toBeGreaterThan(h.start); // non-zero-width → F4 fp resolves
expect(current.slice(h.start, h.end).length).toBeGreaterThan(0);
}
expect(applyHunks(current, hunks)).toBe(rewrite);
}
});
test("is deterministic — same inputs → identical hunks", () => {
const c = "P one.\n\nP two.\n";
const r = "P ONE.\n\nP two.\n";
expect(diffToBlockHunks(c, r)).toEqual(diffToBlockHunks(c, r));
});
});
// F11 SLICE-2 (INV-36): the pure render layer emits data-src-start/data-src-end
// (source char offsets from BlockWithRange) on every LIVE-source rendered block,
// in BOTH modes. The webview's selection→source mapping walks the DOM to the