fix(#60): pre-aborted signal short-circuits before run; guard onProgress relay

Review findings (Medium+Low): a signal already aborted before runEditTurn is
called could not be honored by agent.abort() (the SDK AbortController isn't
created until run()), so the turn ran to completion — now it throws before
run() (INV-47). And a throwing onProgress relay is swallowed so observability
can never fail the turn (INV-44). Strengthened the unit + E2E to prove both.

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

docs/MANUAL-SMOKE-F12.md

@@ -0,0 +1,96 @@
+# Manual smoke — F12 document-edit flow
+
+Covers the document-edit-flow cluster (`specs/coauthoring-document-edit-flow.md`,
+#42 · #47 · #46). This file is filled in slice by slice.
+
+## SLICE-1 — #42 (reach): selection-aware Ask-Claude from body + tab (INV-38)
+
+Run the extension (F5) on a markdown document under the sandbox workspace.
+
+1. **Body, with selection (PUC-2).** Select a paragraph, right-click the editor
+   **body**. Expect **Ask Claude to Edit Selection** in the menu (and **not**
+   "Edit Document"). Pick it → instruct → submit; a single proposal lands over
+   the selection (existing F11 behavior, unchanged).
+2. **Body, no selection (PUC-1).** Clear the selection (click once), right-click
+   the editor **body**. Expect **Ask Claude to Edit Document** (and **not** "Edit
+   Selection"). Pick it → instruct → submit; the whole-document rewrite surfaces
+   as F4 proposal(s) in the preview.
+3. **Tab, with selection (PUC-3).** With a selection active, right-click the
+   editor **tab**. Expect **Ask Claude to Edit Selection**, acting on that tab's
+   document.
+4. **Tab, no selection (PUC-3).** With no selection, right-click the editor
+   **tab**. Expect **Ask Claude to Edit Document**, acting on **that tab's**
+   document — even if a *different* editor is the active one. Open two markdown
+   tabs A and B, make A active, right-click B's tab → Edit Document → the
+   proposals land on **B**, not A.
+5. **Markdown-gated.** Open a non-markdown file (e.g. `.txt`). Right-click body or
+   tab: neither **Ask Claude to Edit Selection** nor **Edit Document** appears.
+6. **Single edit path.** Both entries route through the same `runEditAndPropose`
+   path — there is no second edit code path (INV-38). Nothing is written to the
+   document or sidecar by merely invoking the menu (INV-10/20/35) until you accept.
+
+### Pass criteria
+
+The body and tab menus show exactly one Ask-Claude edit entry, matching the live
+selection state (selection → Edit Selection; none → Edit Document); the tab
+gesture targets the clicked tab's document, not the active editor; both are absent
+on non-markdown docs; no console errors.
+
+## SLICE-2 — #47 (review): per-block proposals + word-precise attribution (INV-39/40/41)
+
+On a markdown doc with several paragraphs, **Ask Claude to Edit Document** with a
+light copy-edit instruction (e.g. "tighten the prose, fix typos").
+
+1. **One proposal per changed block (INV-39).** Claude's pass surfaces as **one
+   ✓/✗ block per changed paragraph/header/bullet**, not a flurry of word-level
+   blocks. A paragraph with several word edits is a **single** proposal; the
+   word-level `<ins>`/`<del>` still shows *inside* it. Untouched paragraphs show no
+   proposal.
+2. **Changed fence is atomic (INV-23).** If Claude edits a code/mermaid fence, it
+   is **one** whole-fence proposal.
+3. **Accept attributes only the changed words (INV-40).** Accept a block proposal,
+   then toggle the preview to **Authorship**/colors (or re-open in the on-state):
+   only the words Claude actually changed are Claude-colored; the unchanged words
+   in that block keep their prior author. The block is the decision unit; the word
+   is the attribution unit.
+4. **Inserted block accepts cleanly (INV-41).** If Claude adds a new paragraph,
+   its proposal **accepts** (it is anchored to an adjacent block, never a
+   born-orphaned/zero-width proposal).
+5. **Undo.** Accepting a block is currently **N undo steps** (one per changed run
+   inside the block) — `Ctrl+Z` repeatedly restores it. (Spec deferred note:
+   single-undo-step grouping is a possible follow-up.)
+6. **Selection edits unchanged.** Edit *Selection* still produces exactly one
+   proposal over the selection (no block fan-out).
+
+### Pass criteria
+
+A document edit yields one in-context proposal per changed block (fences atomic);
+accepting a block lands the whole block but Claude-attributes only the words it
+changed; inserted blocks accept; selection edits are unaffected; no console errors.
+
+## SLICE-3 — #46 (accept): Accept all (INV-42)
+
+On a markdown doc, **Ask Claude to Edit Document** with a pass that changes
+**several** blocks, so the preview shows **≥ 2** pending proposals.
+
+1. **Button appears at ≥2 (PUC-6).** The preview toolbar shows **✓✓ Accept all**
+   only when there are **2 or more** pending proposals (and the doc is authorable,
+   annotations on). With 0–1 pending it is hidden.
+2. **One gesture applies all.** Click **Accept all**: every pending proposal lands
+   (Claude-attributed per INV-40), the ✓/✗ blocks clear, and a status message
+   reports how many were accepted. No confirmation dialog.
+3. **Undo restores.** `Ctrl+Z` walks back the applied edits (consistent with
+   single accept; a block accept is itself N steps — see SLICE-2).
+4. **Orphan-skip + report.** If one proposal's target text was changed by hand
+   first (so it can't anchor), Accept all applies the rest and the report says
+   `… , N skipped (target text changed — undo or reject)`; the orphaned proposal
+   stays pending, its text untouched (never force-applied).
+5. **Command path.** With no preview panel open, the command palette **Cowriting:
+   Accept All Claude Proposals** (markdown-gated) applies all proposals on the
+   active doc with the same report.
+
+### Pass criteria
+
+Accept all is offered only at ≥2 pending; one click applies every resolvable
+proposal and reports the tally; orphans are skipped (not mangled) and remain
+pending; the palette command works on the active doc; no console errors.

media/preview.ts

@@ -30,6 +30,7 @@ const legend = document.getElementById("cw-legend")!;
 const annotationsEl = document.getElementById("cw-annotations") as HTMLInputElement | null;
 const pinEl = document.getElementById("cw-pin") as HTMLButtonElement | null;
 const askEl = document.getElementById("cw-ask") as HTMLButtonElement | null;
+const acceptAllEl = document.getElementById("cw-acceptall") as HTMLButtonElement | null;
 
 // F10: the annotations on/off toggle.
 annotationsEl?.addEventListener("change", () => {
@@ -88,6 +89,11 @@ askEl?.addEventListener("click", () => {
   }
 });
 
+// #46 (INV-42): Accept all — batch-accept every pending proposal (intent only).
+acceptAllEl?.addEventListener("click", () => {
+  vscodeApi.postMessage({ type: "acceptAll" });
+});
+
 // F10: delegated ✓/✗ accept/reject of pending proposals (routed back to the F4 seam).
 body.addEventListener("click", (e) => {
   const btn = (e.target as HTMLElement)?.closest<HTMLElement>(".cw-actions button");
@@ -132,6 +138,9 @@ window.addEventListener("message", (event: MessageEvent<RenderMessage>) => {
   if (askEl) askEl.disabled = !authorable;
   const on = msg.mode === "on";
   if (annotationsEl) annotationsEl.checked = on;
+  // #46: Accept all shows only with ≥2 pending proposals, on an authorable doc,
+  // in the annotated (on) state — a single proposal is just a ✓ in place.
+  if (acceptAllEl) acceptAllEl.hidden = !on || !authorable || (msg.summary?.proposals ?? 0) < 2;
   // Off-state is a clean preview: hide the review chrome.
   header.hidden = !on;
   summary.hidden = !on;

package.json

@@ -18,6 +18,16 @@
     "onStartupFinished"
   ],
   "contributes": {
+    "configuration": {
+      "title": "Cowriting",
+      "properties": {
+        "cowriting.liveProgress.revealOutput": {
+          "type": "boolean",
+          "default": true,
+          "description": "When Claude is editing, reveal the \"Cowriting: Claude\" output channel (without stealing focus) as soon as Claude starts producing text, so you can read the output as it streams."
+        }
+      }
+    },
     "commands": [
       {
         "command": "cowriting.showClineSdkInfo",
@@ -83,6 +93,11 @@
         "command": "cowriting.editDocument",
         "title": "Ask Claude to Edit Document",
         "category": "Cowriting"
+      },
+      {
+        "command": "cowriting.acceptAllProposals",
+        "title": "Accept All Claude Proposals",
+        "category": "Cowriting"
       }
     ],
     "menus": {
@@ -110,6 +125,10 @@
         {
           "command": "cowriting.editDocument",
           "when": "editorLangId == markdown"
+        },
+        {
+          "command": "cowriting.acceptAllProposals",
+          "when": "editorLangId == markdown"
         }
       ],
       "editor/title": [
@@ -120,10 +139,20 @@
         }
       ],
       "editor/title/context": [
+        {
+          "command": "cowriting.editSelection",
+          "when": "editorHasSelection && resourceLangId == markdown",
+          "group": "1_cowriting@1"
+        },
+        {
+          "command": "cowriting.editDocument",
+          "when": "!editorHasSelection && resourceLangId == markdown",
+          "group": "1_cowriting@1"
+        },
         {
           "command": "cowriting.showTrackChangesPreview",
           "when": "resourceLangId == markdown",
-          "group": "1_cowriting"
+          "group": "1_cowriting@3"
         }
       ],
       "explorer/context": [
@@ -136,7 +165,12 @@
       "editor/context": [
         {
           "command": "cowriting.editSelection",
-          "when": "editorHasSelection && (resourceScheme == file || resourceScheme == untitled)",
+          "when": "editorHasSelection && editorLangId == markdown && (resourceScheme == file || resourceScheme == untitled)",
+          "group": "1_cowriting@1"
+        },
+        {
+          "command": "cowriting.editDocument",
+          "when": "!editorHasSelection && editorLangId == markdown && (resourceScheme == file || resourceScheme == untitled)",
           "group": "1_cowriting@1"
         },
         {
@@ -178,7 +212,8 @@
     "watch": "node esbuild.mjs --watch",
     "typecheck": "tsc --noEmit",
     "test": "vitest run",
-    "pretest:e2e": "npm run build && tsc -p tsconfig.e2e.json",
+    "clean:e2e": "node -e \"require('fs').rmSync('out/test',{recursive:true,force:true})\"",
+    "pretest:e2e": "npm run build && npm run clean:e2e && tsc -p tsconfig.e2e.json",
     "test:e2e": "node ./out/test/e2e/runTest.js",
     "smoke:live": "npm run build && node scripts/smoke-live-turn.mjs",
     "vscode:prepublish": "node esbuild.mjs"

scripts/smoke-live-turn.mjs

@@ -10,7 +10,15 @@ console.log(`instruction: ${instruction}`);
 console.log(`text:        ${text}`);
 try {
   const t0 = Date.now();
-  const result = await runEditTurn(instruction, text);
+  // #60: exercise the live-progress path against the real SDK — log each reduced
+  // snapshot so the smoke shows streaming/activity/tokens, not just the result.
+  const result = await runEditTurn(instruction, text, {
+    onProgress: (s) => {
+      const bits = [s.phase === "tool" ? `tool:${s.tool}` : s.phase, `${s.chars}c`];
+      if (s.tokens) bits.push(`${s.tokens}tok`);
+      console.log(`  progress: ${bits.join(" ")}`);
+    },
+  });
   console.log(`replacement: ${JSON.stringify(result.replacement)}`);
   console.log(`model:       ${result.model}`);
   console.log(`sessionId:   ${result.sessionId}`);

sessions/0043/SESSION-0043.0-TRANSCRIPT-2026-06-13T07-18--2026-06-13T07-38.md

@@ -0,0 +1,92 @@
+# Session 0043.0 — Transcript
+
+> App: vscode-cowriting-plugin
+> Start: 2026-06-13T07-18 (PST)
+> Type: planning-and-executing
+> End: 2026-06-13T07-38 (PST)
+> Status: **FINALIZED.**
+> Posture: autonomous (yolo)
+
+## Launch prompt
+
+`/goal plan-and-execute #42 (SLICE-1 of the document-edit flow — Ask-Claude
+entry-point menu wiring), per specs/coauthoring-document-edit-flow.md`
+
+## Plan
+
+**SLICE-1 — #42 (reach)** of the document-edit flow Solution Design
+(`specs/coauthoring-document-edit-flow.md`, §7.2). Anchor: Feature #42
+(`type/feature`); design graduated (session 0041) → §4.3 R3 satisfied.
+
+Goal (INV-38): "Ask Claude to Edit" reachable from the editor **body** and the
+editor **tab**, selection-aware (selection → `editSelection`; no selection →
+`editDocument`), both gated to markdown/authorable docs, both routing through the
+single `runEditAndPropose` path. Smallest increment — command already exists.
+
+Tasks:
+1. `package.json` — add `editSelection` + `editDocument` to `editor/context`
+   (selection-aware `when`, markdown+authorable) and `editor/title/context`
+   (selection-aware, `resourceLangId == markdown`); keep titles.
+2. `trackChangesPreview.ts` — `cowriting.editDocument` accepts an optional tab
+   `uri` arg (mirror `showTrackChangesPreview`'s #41 resolution): open/resolve the
+   clicked doc, else fall back to the active editor.
+3. E2E (`test/e2e/suite/`) — menu entries present + selection-aware + markdown-gated;
+   `editDocument(uri)` resolves the tab doc and produces a document-scoped proposal.
+
+No model change, no new persisted artifact. No deploy pipeline (VS Code extension).
+
+## Results
+
+**SLICE-1 (#42, reach) shipped to `main`** — PR
+[#49](https://git.benstull.org/benstull/vscode-cowriting-plugin/pulls/49)
+(merged), issue #42 closed.
+
+- `package.json` — `editSelection` + `editDocument` added to `editor/context`
+  (selection-aware, `editorLangId == markdown` + `file`/`untitled`) and
+  `editor/title/context` (selection-aware, `resourceLangId == markdown`);
+  existing `editor/context` `editSelection` entry markdown-gated to match INV-38.
+- `src/trackChangesPreview.ts` — `cowriting.editDocument` now accepts the clicked
+  tab's resource `Uri` (opens it if needed), falling back to the active editor;
+  mirrors `showTrackChangesPreview`'s #41 resolution.
+- `test/e2e/suite/f12Reach.test.ts` — 4 new host E2E (menu wiring declarative +
+  tab-URI targeting + no-arg fallback).
+- `docs/MANUAL-SMOKE-F12.md` — SLICE-1 reach smoke steps.
+
+Verification: `tsc --noEmit` clean; **208 unit** green; **65/5 host E2E** green
+(main suite up from 61 → 65 with the 4 new tests).
+
+**Next:** SLICE-2 — #47 (review, **P1**): document edits propose per changed
+block (`diffToBlockHunks`, INV-39 supersedes INV-37; word-precise intra-block
+attribution INV-40; block-insertion anchoring INV-41). Then SLICE-3 — #46
+(accept-all, INV-42).
+
+## Session arc
+
+1. **Gate + claim.** Classified the `/goal` as planning-and-executing; claimed
+   session 0043 (peek showed nothing in flight). Baseline: local `main` was 4
+   behind `origin/main` → fast-forwarded clean.
+2. **Anchor gate (§4.3 R3).** #42 is `type/feature`; its design is the graduated
+   combined Solution Design `specs/coauthoring-document-edit-flow.md` (session
+   0041) → R3 satisfied, proceed.
+3. **Read the spec**, scoped SLICE-1 (reach). Explored the code: `package.json`
+   menus, `editDocument`/`editSelection` handlers, the F11 E2E harness (`setEditTurnForTest`).
+4. **TDD.** Wrote `f12Reach.test.ts` first (red), then wired the menus + tab-URI
+   resolution (green).
+5. **Verified** (tsc clean, 208 unit, 65/5 E2E), self-reviewed the diff, shipped
+   via PR #49 (merged), closed #42, updated memory, checkpoint-published the
+   transcript.
+
+## Deferred decisions
+
+_Autonomous-mode low-confidence calls the driver made and would have
+liked operator input on. Appended as the session runs; surfaced at
+finalize. Empty if none._
+
+- **Markdown-gating `editSelection`'s `editor/context` entry** (driver call,
+  low-confidence). Spec §5/INV-38 say both Ask-Claude entries are markdown-gated,
+  but F8 made the `editSelection` *command* work on any authorable doc and its
+  current right-click entry has no `editorLangId == markdown` gate. Followed the
+  spec: gated the **menu** entries to markdown while leaving the command handlers'
+  behavior intact (palette still works on any authorable file). Removes the
+  body right-click Ask-Claude-Edit-Selection on non-markdown files — acceptable
+  since the proposal review surface (F10 preview) is markdown-only.

sessions/0044/SESSION-0044.0-TRANSCRIPT-2026-06-13T07-40--2026-06-13T08-04.md

@@ -0,0 +1,127 @@
+# Session 0044.0 — Transcript
+
+> App: vscode-cowriting-plugin
+> Start: 2026-06-13T07-40 (PST)
+> Type: planning-and-executing
+> End: 2026-06-13T08-04 (PST)
+> Status: **FINALIZED.**
+> Posture: autonomous (yolo)
+
+## Launch prompt
+
+```
+/goal plan-and-execute #47 (SLICE-2 of the document-edit flow — document edits propose per changed block: diffToBlockHunks INV-39 supersedes INV-37, word-precise intra-block attribution INV-40, block-insertion anchoring INV-41), per specs/coauthoring-document-edit-flow.md
+
+```
+
+## Plan
+
+**SLICE-2 — #47 (review, P1)** of the document-edit flow
+(`specs/coauthoring-document-edit-flow.md` §7.2). Anchor: Feature #47
+(`type/feature`); covered by the graduated combined Solution Design → §4.3 R3.
+
+Document rewrites propose **one F4 proposal per changed block** (the unit a human
+reviews), but each accept reconciles attribution at **word** granularity (the unit
+F3 records). INV-39 supersedes INV-37 for document edits; INV-40 word-precise
+intra-block attribution; INV-41 block-insertion anchoring. Selection edits
+unchanged.
+
+Tasks:
+1. `model.ts` — add optional `granularity?: "block" | "single"` to `Proposal`
+   (additive, back-compat: absent ⇒ `"single"`). INV-39/§6.3.
+2. `proposalModel.ts` — `addProposal` opts gains `granularity`, threaded onto the
+   proposal (omitted when absent).
+3. `trackChangesModel.ts` — new pure `diffToBlockHunks(currentText,
+   rewrittenText): EditHunk[]`: split both sides into the existing block units
+   (`splitBlocksWithRanges` for source ranges + `splitBlocks` keys), diff blocks
+   (reuse `diffArrays` keying like `diffBlocks`), emit ONE `EditHunk` per
+   changed/added/removed block — changed → `[block.start,end)`→rewrite; fences
+   atomic (whole-fence hunk); inserted → anchored to adjacent boundary (INV-41,
+   reuse the `anchorInsertion` idea); unchanged → none. Same `EditHunk` shape as
+   `diffToHunks` (which is RETAINED as the intra-block sub-diff engine).
+4. `trackChangesPreview.ts` — `runEditAndPropose` **document branch** uses
+   `diffToBlockHunks` and tags each minted proposal `granularity:"block"`.
+5. `proposalController.ts` — `accept`: when `granularity === "block"`, re-resolve
+   the block text, `diffToHunks(blockText, replacement)` → per-run word sub-diff,
+   apply **one `applyAgentEdit` per changed run, descending offset** so only the
+   runs Claude changed land Claude-attributed; unchanged spans keep prior author
+   (INV-40). Non-block keeps the single `applyAgentEdit`.
+6. Tests: unit (`diffToBlockHunks` + INV-40 controller) + host E2E (#47 cases in
+   §6.8); update the existing f11 document-path E2E (now per-block, supersedes
+   INV-37 word-level expectation); `docs/MANUAL-SMOKE-F12.md` §2.
+
+**Design note (seam constraint):** `pendingEdits.matchEvent` resolves ONE
+registration per change event, so INV-40's per-run attribution is implemented as
+**sequential** `applyAgentEdit` calls (descending offset), not a single
+multi-replace `WorkspaceEdit`. The spec's "one undo-grouped edit" wording is thus
+approximated as N undo steps per block accept — see Deferred decisions.
+
+No new persisted artifact; no deploy pipeline (VS Code extension).
+
+## Results
+
+**SLICE-2 (#47, review, P1) shipped to `main`** — PR
+[#50](https://git.benstull.org/benstull/vscode-cowriting-plugin/pulls/50)
+(merged), issue #47 closed.
+
+- `trackChangesModel.ts` — new pure `diffToBlockHunks` (block-key alignment via
+  `diffArrays`/`diffBlocks` keying; isolated changed block → block-aligned hunk →
+  rewritten raw; fences atomic INV-23; insert/delete → exact gap-span hunk;
+  zero-width gap-span anchored INV-41). Split `diffToHunks` into raw
+  `wordEditHunks` + anchoring wrapper (fixes a latent overlap bug under batch apply).
+- `trackChangesPreview.ts` — document branch uses `diffToBlockHunks`, tags
+  `granularity:"block"`.
+- `model.ts`/`proposalModel.ts` — additive optional `Proposal.granularity`.
+- `proposalController.ts` — `acceptBlock`: intra-block word sub-diff
+  (`wordEditHunks`) → one `applyAgentEdit` per changed run, descending offset
+  (INV-40 word-precise attribution; unchanged spans keep prior author).
+- Tests: `diffToBlockHunks` unit (reconstruction/fence/add-remove); `f12Review`
+  host E2E (M→M, unchanged→none, fence atomic, INV-40, INV-41); updated f11
+  document-path E2E to per-block; `MANUAL-SMOKE-F12.md` §2.
+
+Verification: `tsc --noEmit` clean; **214 unit** green; **69/5 host E2E** green
+(main suite 65 → 69 net with the new F12 review tests).
+
+**Next:** SLICE-3 — #46 (accept-all, INV-42): `acceptAllProposals` (controller,
+descending-order, orphan-skip + report) + `cowriting.acceptAllProposals` command
++ preview toolbar **Accept all** button (`{type:"acceptAll"}` intent, shown ≥2
+pending).
+
+## Session arc
+
+1. **Claim.** Resumed via `/goal next` (after session 0043 shipped #42); claimed
+   session 0044 for #47. Clean `main` baseline.
+2. **Anchor gate.** #47 (`type/feature`) covered by the graduated combined design
+   → §4.3 R3 satisfied.
+3. **Deep code read.** `splitBlocks*`/`diffBlocks`/`diffToHunks`/`EditHunk`,
+   `runEditAndPropose`, `proposalController.accept`/`applyAgentEdit`, and crucially
+   `pendingEdits.matchEvent` (one registration per change event → drove the INV-40
+   sequential-apply decision).
+4. **TDD `diffToBlockHunks`.** First attempt (coarsen word-hunks) failed a
+   reconstruction case — discovered `diffToHunks` can emit OVERLAPPING hunks
+   (anchorInsertion over-absorbs). Switched to block-key alignment with
+   replacement-from-rewritten-raw → green.
+5. **Model + wiring + INV-40 accept.** Added `granularity`; document branch →
+   `diffToBlockHunks`; `acceptBlock` intra-block sub-diff. The overlap bug then
+   resurfaced in `acceptBlock` (batch apply) → split `diffToHunks` into raw
+   `wordEditHunks` (disjoint) + anchoring wrapper; `acceptBlock` uses raw → green.
+6. **Verified + shipped** (214 unit, 69/5 E2E), self-reviewed, PR #50 merged,
+   #47 closed, memory + transcript updated.
+
+## Deferred decisions
+
+_Autonomous-mode low-confidence calls the driver made and would have
+liked operator input on. Appended as the session runs; surfaced at
+finalize. Empty if none._
+
+- **INV-40 undo granularity** (driver call). Spec §6.2/§6.7 say accepting a block
+  proposal should be "one undo-grouped WorkspaceEdit." But the F3 seam's
+  `pendingEdits.matchEvent` matches exactly ONE registration per change event, so a
+  single `WorkspaceEdit` with N independent run-replaces can't carry per-run
+  attribution (the multi-hunk event fails to match any single registration → falls
+  through to human). Implemented INV-40 as **sequential per-run `applyAgentEdit`
+  calls, descending offset** — correct word-precise attribution, reuses the seam
+  with zero attribution-core risk, but a block accept is N undo steps rather than
+  one. Single-undo-step would require extending `matchEvent`/`onDidChange` to
+  consume multiple registrations per event (riskier F3 change) — left as a possible
+  follow-up.

sessions/0045/SESSION-0045.0-TRANSCRIPT-2026-06-13T08-04--2026-06-13T08-17.md

@@ -0,0 +1,98 @@
+# Session 0045.0 — Transcript
+
+> App: vscode-cowriting-plugin
+> Start: 2026-06-13T08-04 (PST)
+> Type: planning-and-executing
+> End: 2026-06-13T08-17 (PST)
+> Status: **FINALIZED.**
+> Posture: autonomous (yolo)
+
+## Launch prompt
+
+```
+/goal plan-and-execute #46 (SLICE-3 of the document-edit flow — accept-all, INV-42), per specs/coauthoring-document-edit-flow.md
+
+```
+
+## Plan
+
+**SLICE-3 — #46 (accept)** of the document-edit flow
+(`specs/coauthoring-document-edit-flow.md` §7.2, INV-42). Final slice — completes
+reach→review→**accept**. Anchor: Feature #46 (`type/feature`); covered by the
+graduated combined design → §4.3 R3.
+
+A single **Accept all** gesture applies every pending proposal on the current
+document through the existing F4 `acceptById` seam (block proposals take the INV-40
+path automatically), in a re-anchor-safe (descending) order, **skipping** orphans
+and **reporting** applied-vs-skipped. Batched application of the existing path — no
+new accept mechanism; the webview posts intent only (INV-35).
+
+Tasks:
+1. `proposalController.ts` — `acceptAllProposals(document): Promise<{applied,
+   skipped}>`: snapshot pending, sort descending by resolved anchor start,
+   `acceptById` each **silently** (no per-item orphan warning), tally
+   applied/skipped (orphans counted skipped). Add a `silent` opt to the accept
+   path so the batch suppresses per-proposal warnings.
+2. `extension.ts` — `cowriting.acceptAllProposals` command (active doc) → reports
+   applied-vs-skipped via a status message.
+3. `trackChangesPreview.ts` — `ToolbarMsg += {type:"acceptAll"}`;
+   `handleWebviewMessage` routes it → `proposals.acceptAllProposals(document)` +
+   report.
+4. `media/preview.ts` + `shellHtml` — an **Accept all** toolbar button shown when
+   `summary.proposals >= 2` (and authorable), posting `{type:"acceptAll"}`.
+5. `package.json` — register the `cowriting.acceptAllProposals` command (palette,
+   markdown-gated).
+6. Tests: host E2E (N pending → all applied + cleared; orphan skipped + reported;
+   button hidden < 2 pending); `MANUAL-SMOKE-F12.md` §3.
+
+No new persisted artifact; no deploy pipeline (VS Code extension).
+
+## Results
+
+**SLICE-3 (#46, accept) shipped to `main`** — PR
+[#51](https://git.benstull.org/benstull/vscode-cowriting-plugin/pulls/51)
+(merged), issue #46 closed. **Completes the document-edit-flow cluster
+(#42 reach + #47 review + #46 accept).**
+
+- `proposalController.ts` — `acceptAllProposals(document)` → `{applied, skipped}`
+  (descending order, orphan-skip); `accept`/`acceptById` `silent` opt for the batch.
+- `trackChangesPreview.ts` — `ToolbarMsg += {type:"acceptAll"}` → public
+  `acceptAll(document)` (batch + report).
+- `extension.ts`/`package.json` — `cowriting.acceptAllProposals` command
+  (active doc, markdown-gated palette).
+- `media/preview.ts` + shell — "✓✓ Accept all" toolbar button (intent; shown
+  ≥2 pending, authorable, on-state).
+- `trackChangesModel.ts` — `diffToBlockHunks` fix: emit one block-aligned hunk
+  per changed block **even when adjacent** (changed blocks are 1:1 anchors;
+  gap-spans only cover add/remove runs) — caught by the accept-all E2E (3 adjacent
+  changed blocks were collapsing to 1 proposal).
+- `f12Accept.test.ts` E2E + `MANUAL-SMOKE-F12.md` §3.
+
+Verification: `tsc --noEmit` clean; **214 unit** green; **73/5 host E2E** green
+(main suite 69 → 73 with the new accept-all tests).
+
+**Next:** the cluster is complete; no in-flight next step. Open backlog includes
+#48 (pin → fully clean review panel, story P2) and the OQ-2 F11 (#43) spec
+graduation (hygiene). A natural hand-back point for operator direction.
+
+## Session arc
+
+1. **Claim.** Continued the rolling `next` goal after 0044 shipped #47; claimed
+   session 0045 for #46. Clean `main`.
+2. **Plan + implement.** Controller `acceptAllProposals` (+ `silent` accept opt);
+   `acceptAll` intent route + public method; command + package.json; "Accept all"
+   toolbar button (≥2-pending gating in the sealed webview).
+3. **E2E caught a real bug.** The accept-all "3 adjacent changed blocks" case
+   returned 1 proposal, not 3 — `diffToBlockHunks` was merging adjacent changed
+   blocks into one gap-span run. Fixed by treating `changed` blocks as 1:1 anchors
+   (each → its own block-aligned hunk; gap-spans only span add/remove runs).
+4. **Verified + shipped** (214 unit, 73/5 E2E), self-reviewed, PR #51 merged,
+   #46 closed → **cluster complete**; memory + transcript updated.
+
+## Deferred decisions
+
+_Autonomous-mode low-confidence calls the driver made and would have
+liked operator input on. Empty if none._
+
+- _No low-confidence calls this session._ (The `diffToBlockHunks` adjacency
+  behavior was a bug caught by the accept-all E2E, not a judgment call.)

sessions/0046/SESSION-0046.0-TRANSCRIPT-2026-06-13T08-19--2026-06-13T08-31.md

@@ -0,0 +1,95 @@
+# Session 0046.0 — Transcript
+
+> App: vscode-cowriting-plugin
+> Start: 2026-06-13T08-19 (PST)
+> Type: planning-and-executing
+> End: 2026-06-13T08-31 (PST)
+> Status: **FINALIZED.**
+> Posture: autonomous (yolo)
+
+## Launch prompt
+
+```
+/goal plan-and-execute #48 (pinning the baseline leaves the review panel fully un-annotated — zero-diff → no F3 authorship colors on unchanged blocks; proposals still show)
+
+```
+
+## Plan
+
+**#48 (story, P2)** — pinning the baseline leaves the review panel fully
+un-annotated. Anchor: leaf `story` → §4.3 R2 (no design gate). Picked
+autonomously as the next backlog item after the document-edit-flow cluster shipped
+(0043/0044/0045).
+
+When `diffBlocks(baseline, current)` yields all-`unchanged` ops (zero diff — the
+state right after a pin), the F10 on-render still author-colors every block
+(`colorByAuthor`), so the panel looks painted instead of clean. Fix: in that
+zero-diff case render clean (no author coloring, no change marks) while keeping
+`data-src` mapping (INV-36) and still injecting pending proposals (proposals are
+actions, not annotations). Narrow edge case of INV-33 — with-changes render
+unchanged; off-state unchanged; broader "authorship never colors unchanged" NOT
+in scope.
+
+Tasks:
+1. `trackChangesModel.ts` `renderReview` — detect `ops.every(unchanged)`; in that
+   case use a plain `render` (skip `colorByAuthor`) for blocks; proposal injection
+   loop unchanged.
+2. Unit: baseline==current + author spans → no `cw-by-claude`/`cw-by-human` (and
+   no `cw-add`/`cw-del`) on the body; with a pending proposal → the `cw-proposal`
+   block still renders.
+3. Host E2E: open preview, diverge + author-color, pin → panel clean (no
+   green/blue); edit again → annotations return.
+4. Content repo: one-line INV-33 clarification (zero-diff → clean on-render) in
+   `specs/coauthoring-interactive-review.md`.
+
+No new persisted artifact; no deploy pipeline (VS Code extension).
+
+## Results
+
+**#48 (story, P2) shipped to `main`** — PR
+[#52](https://git.benstull.org/benstull/vscode-cowriting-plugin/pulls/52)
+(merged), issue #48 closed. Picked autonomously after the document-edit-flow
+cluster (0043/0044/0045).
+
+- `trackChangesModel.ts` — `renderReview` gains a `pinned` `RenderOption`; when
+  pinned + zero-diff, blocks render plain (skip `colorByAuthor`).
+- `trackChangesPreview.ts` — pass `{ pinned: baseline?.reason === "pinned" }`
+  from `refresh` + `renderHtmlFor`.
+- Unit (4 new) + `s48PinClean` host E2E.
+
+**Scoped to the pin specifically** (not all zero-diff): a baseline advanced by a
+**machine-landing** (accept) is also zero-diff but keeps its authorship coloring
+(F10 INV-33) — the F10 authorship E2E caught a pure-zero-diff rule would regress
+accepted-Claude-text coloring, so the clean render is gated on `reason ===
+"pinned"`.
+
+Verification: `tsc --noEmit` clean; **218 unit** green; **74/5 host E2E** green.
+
+## Session arc
+
+1. **Pick + claim.** Stop hook required determining/executing the next milestone
+   autonomously (rolling `next`); chose #48 (leaf story, no design gate) and
+   claimed 0046. Clean `main`.
+2. **Read the issue** (detailed, gave the solution shape) + `renderReview`.
+3. **TDD.** Implemented zero-diff-clean; full suite caught the F10 authorship
+   regression (accept advances baseline → zero-diff → coloring was being cleared);
+   re-scoped to `reason === "pinned"` via a `pinned` RenderOption → all green.
+4. **Shipped** (PR #52), closed #48; spec clarification written but left in the
+   content-repo working tree (see Deferred decisions).
+
+## Deferred decisions
+
+_Autonomous-mode low-confidence calls the driver made and would have
+liked operator input on. Empty if none._
+
+- **INV-33 clarification not pushed to the content repo** (loose end, not a
+  judgment call). Wrote the zero-diff-after-pin clarification into
+  `specs/coauthoring-interactive-review.md`, but the **content repo has
+  pre-existing uncommitted state that isn't this session's**: a modified
+  `coauthoring-diff-view.md` and ~18 untracked capture-session draft files
+  (`issues/*.md`, `specs/coauthoring-document-edit-flow.md`), and local `main` is
+  **6 behind origin**. A clean rebase would require deleting the operator's
+  untracked drafts (irreversible — a STOP gate), so I **soft-reset** my spec
+  commit into the working tree rather than force it. The clarification sits as an
+  uncommitted modification alongside the operator's other content-repo drafts,
+  for the operator to reconcile/push. The #48 **code** shipped normally.

sessions/0047/SESSION-0047.0-TRANSCRIPT-2026-06-13T08-34--2026-06-13T08-44.md

@@ -0,0 +1,86 @@
+# Session 0047.0 — Transcript
+
+> App: vscode-cowriting-plugin
+> Start: 2026-06-13T08-34 (PST)
+> Type: planning-and-executing
+> End: 2026-06-13T08-44 (PST)
+> Status: **FINALIZED.**
+> Posture: autonomous (yolo)
+
+## Launch prompt
+
+```
+/goal plan-and-execute #33 (intra-emphasis sentinel hardening — token-aware fix for the 2 characterized failure modes)
+
+```
+
+## Plan
+
+**#33 (task, P3)** — harden the F9/F10 author-coloring PUA sentinels against
+intra-emphasis markdown. Anchor: leaf `task` → §4.3 R2 (no design gate). Picked
+autonomously (next clean plan-and-executable backlog item; doesn't touch the
+content repo). Approach = the token-aware fix recommended in the issue #33 comment.
+
+Two characterized failure modes (issue #33 comment, session 0032):
+- **CASE1** — a span boundary lands strictly inside a delimiter run (`a**b**c`,
+  boundary between the two `*`): the injected sentinel splits `**` → markdown parse
+  breaks (stray `<em></em>`, raw `**` left).
+- **CASE3** — a span boundary inside an emphasis run (`**bold**`, span covers
+  `**bo`): emphasis renders but the author `<span>` and `<strong>` **misnest**
+  (`<strong>bo</span>ld</strong>`).
+
+Fix (both needed):
+1. `injectSentinels` — **clamp** any sentinel offset that lands strictly inside a
+   markdown delimiter run (`* _ ~ \``) to the run's start, so a sentinel never
+   splits a delimiter (fixes CASE1). Skip now-zero-width spans.
+2. `sentinelsToSpans` — replace the naive split/join with a **token-aware walker**
+   over the rendered HTML: emit `cw-by-*` spans only around TEXT runs, closing the
+   span before any `<tag>` and reopening after, so a span never crosses an element
+   boundary (fixes CASE3 — one span segment per text run). Strip any stray sentinel
+   left inside a tag (no PUA leakage).
+
+Pure/vscode-free/deterministic (INV-33). Non-goals: link/attribute sentinel cases,
+visual language, attribution model.
+
+Tasks: unit tests reproducing CASE1 + CASE3 (+ regression on existing
+colorByAuthor/renderReview cases) → implement clamp + walker → green; spec already
+notes the hardening (§1.7/§9). No deploy pipeline (extension).
+
+## Results
+
+**#33 (task, P3) shipped to `main`** — PR
+[#53](https://git.benstull.org/benstull/vscode-cowriting-plugin/pulls/53)
+(merged), issue #33 closed. Picked autonomously (next clean plan-and-executable
+leaf; doesn't touch the content repo).
+
+- `trackChangesModel.ts` `injectSentinels` — clamp any sentinel offset landing
+  strictly inside a delimiter run (`* _ ~ \``) to the run's start (fixes CASE1
+  parse-break); drop spans that clamp to empty.
+- `trackChangesModel.ts` `sentinelsToSpans` — token-aware walker emitting the
+  `cw-by-*` span only around text runs, split at every `<tag>` boundary (fixes
+  CASE3 misnest); strays stripped (no PUA leak).
+- 4 new unit tests (CASE1/CASE3/CASE2-regression/no-leak), real markdown-it via
+  `renderReview`.
+
+Verification: `tsc --noEmit` clean; **222 unit** green; **74/5 host E2E** green;
+the F10/authorship E2E (`cw-by-claude`/`cw-by-human`) still pass (common case
+byte-identical).
+
+## Session arc
+
+1. Stop hook required autonomously determining/executing the next milestone;
+   chose #33 (leaf task, no content-repo dependency). Claimed 0047, clean `main`.
+2. Read issue #33 + its investigation comment (2 failure modes, recommended
+   token-aware approach) + session 0032 characterization + the sentinel code.
+3. TDD: CASE1/CASE3 reproduced red → implemented clamp + walker → green; full
+   suite + E2E green; self-reviewed (one pure module).
+4. Shipped (PR #53), closed #33.
+
+## Deferred decisions
+
+_Autonomous-mode low-confidence calls the driver made and would have
+liked operator input on. Empty if none._
+
+- _No low-confidence calls this session._ (Approach was the one recommended in the
+  issue #33 comment; the fix is a pure-module robustness change with full test
+  coverage and no regression.)

sessions/0048/SESSION-0048.0-TRANSCRIPT-2026-06-13T08-45--2026-06-13T08-58.md

@@ -0,0 +1,90 @@
+# Session 0048.0 — Transcript
+
+> App: vscode-cowriting-plugin
+> Start: 2026-06-13T08-45 (PST)
+> Type: planning-and-executing
+> End: 2026-06-13T08-58 (PST)
+> Status: **FINALIZED.**
+> Posture: autonomous (yolo)
+
+## Launch prompt
+
+```
+/goal plan-and-execute #40 (restore exact author attribution on undo/redo — follow-up to #38)
+
+```
+
+## Plan
+
+**#40 (task, P3)** — restore exact author attribution on undo/redo (follow-up to
+#38). Anchor: leaf `task` → §4.3 R2 (no design gate). Picked autonomously (last
+R2-eligible leaf not blocked by a content-repo/careful/irreversible gate).
+
+#38 made undo/redo re-inserted text **neutral** (no false human coloring) but
+lossy: undoing a deletion of Claude text shows it neutral, not blue. #40 restores
+the **exact prior** attribution.
+
+**Mechanism (engineering choice): text-keyed attribution snapshots.** Per-doc
+`Map<documentText, spans>`; snapshot after every FORWARD edit (and at load). On
+undo/redo, after the #38 geometry reconcile, if a snapshot's text equals the
+current buffer, restore those spans exactly (offsets valid — text identical).
+Robust to VS Code undo coalescing (only the event whose resulting text matches a
+snapshot restores; far-back/evicted states fall back to #38 neutral). Bounded
+history.
+
+Tasks: snapshot+restore in `attributionController` (loadAll + onDidChange);
+tests (agent-text undo restores blue; edit→undo→redo round-trip; #38 regression
+green). No deploy pipeline (extension).
+
+## Results
+
+**#40 implemented but NOT shipped — verification-blocked.** On branch
+`s40-undo-provenance` (pushed, unmerged); issue #40 **kept open**.
+
+- `attributionController.ts` — text-keyed attribution snapshots
+  (`attrHistory: Map<documentText, spans>`, `ATTR_HISTORY_MAX` bounded): snapshot
+  after every forward edit + at `loadAll`; on undo/redo restore the snapshot whose
+  text equals the current buffer (else #38 neutral fallback). Robust to undo
+  coalescing.
+- `test/e2e/suite/s40Provenance.test.ts` — agent-text-undo-restores-blue +
+  edit→undo→redo round-trip.
+- **222 unit + typecheck green.**
+
+**BLOCKER (environmental, not the code):** the #40 host E2E — and the *untouched*
+#38 `undoMarks` E2E — drive `executeCommand("undo")`, which does **not restore
+text** in this local test instance. Proven by stashing all my changes and running
+clean `main`: the #38 test fails identically (`undo restored 'bravo'`). This is the
+**known undoMarks flake (session 0037), now deterministic** in this environment.
+The usual remedy — clearing `.vscode-test/user-data` — is **permission-blocked**
+this session (`rm -rf` denied). Focusing the doc before `undo` (`showTextDocument`)
+did not help. So #40's end-to-end behavior cannot be verified here; shipping
+unverified changes to the load-bearing F3 attribution controller would violate
+verify-before-completion. Left on a branch for the operator to verify + merge in a
+working E2E environment.
+
+**Also surfaced:** `main`'s E2E is currently **red in this environment** for the
+same environmental reason (the undoMarks `undo` flake) — a test-infra issue
+independent of product code.
+
+## Session arc
+
+1. Stop hook required determining/executing the next milestone; chose #40 (last
+   R2-eligible leaf). Claimed 0048, clean `main`.
+2. Read #40 + #38 + the attribution change handler; chose text-keyed snapshots.
+3. TDD: wrote #40 E2E + implemented snapshot/restore; 222 unit green.
+4. E2E: 3 undo-driven tests failed at the `undo restored X` step. Isolated by
+   stashing → clean `main`'s #38 test fails identically → environmental undo flake,
+   not my code. Could not clear `.vscode-test` (permission-blocked).
+5. Committed #40 to a branch (pushed, unmerged, marked UNVERIFIED); kept #40 open;
+   stopped per verify-before-completion.
+
+## Deferred decisions
+
+_Autonomous-mode low-confidence calls the driver made and would have
+liked operator input on. Empty if none._
+
+- **Did not merge #40** (driver call). Alternative: merge on unit-green + reasoning
+  alone. Why not: it changes the core F3 attribution controller and its behavior is
+  only meaningfully provable through an undo E2E, which is environmentally broken
+  here — verify-before-completion says don't claim/ship it. Preserved on a branch
+  for operator verification instead. (Reversible: just merge once verified.)

sessions/0049/SESSION-0049.0-TRANSCRIPT-2026-06-13T09-19--2026-06-13T09-24.md

@@ -0,0 +1,61 @@
+# Session 0049.0 — Transcript
+
+> App: vscode-cowriting-plugin
+> Start: 2026-06-13T09-19 (PST)
+> Type: planning-and-executing
+> End: 2026-06-13T09-24 (PST)
+> Status: **FINALIZED.**
+> Posture: autonomous (yolo)
+
+## Launch prompt
+
+```
+/goal plan-and-execute: pretest:e2e cleans stale compiled tests in out/test (stale *.test.js from other branches were running via the glob) — build hygiene follow-up to #54
+
+```
+
+## Plan
+
+Build-hygiene follow-up to #54 (noted on that issue). `tsc -p tsconfig.e2e.json`
+emits to `out/` but never removes outputs for test sources absent on the current
+branch, so stale compiled `out/test/e2e/suite/*.test.js` from other branches get
+run by the suite glob (`**/*.test.js`) — this caused real cross-branch test
+confusion in session 0048 (a removed probe + the s40 branch's tests ran on an
+unrelated branch). Fix: `pretest:e2e` cleans `out/test` before recompiling.
+
+- `package.json` — add `clean:e2e` (node `fs.rmSync('out/test', {recursive,force})`
+  — avoids shell `rm` issues) and run it between `build` and `tsc` in `pretest:e2e`.
+  Clean ONLY `out/test` (NOT `out/`, which holds the just-built esbuild bundle).
+- Verify: introduce a stale `out/test/.../zz.test.js`, run `pretest:e2e`, confirm
+  it's gone + the E2E suite is green.
+
+Trivial, ungated, verifiable; test-infra only. No deploy pipeline (extension).
+
+## Results
+
+**Shipped to `main`** — PR #56 (merged). `package.json`: new `clean:e2e`
+(`fs.rmSync('out/test',{recursive,force})`) run between `build` and `tsc` in
+`pretest:e2e`. Cleans only `out/test` (never the esbuild bundle in `out/`).
+Verified: a planted stale `out/test/.../zz.test.js` is removed by `pretest:e2e`;
+E2E green (73 passing + 1 pending [#38 undo-skip], both passes exit 0). Test-infra
+only; no product code.
+
+Properly tracked under this session (0049) — closing the protocol gap where
+#54/#55 merged after 0048 had finalized.
+
+## Session arc
+
+1. Stop hook pushed me to execute the one remaining ungated/verifiable item (the
+   `out/`-clean follow-up I'd noted on #54). Claimed 0049 to track it cleanly.
+2. Confirmed `tsc` outDir → `out/test`; esbuild bundle → `out/extension.cjs`
+   (separate), so cleaning `out/test` is safe.
+3. Implemented `clean:e2e`; verified by planting a stale compiled test (removed)
+   + full E2E green. Shipped PR #56.
+
+## Deferred decisions
+
+_Autonomous-mode low-confidence calls the driver made and would have
+liked operator input on. Empty if none._
+
+- _No low-confidence calls this session._ (Cleaning stale build output is
+  unambiguously correct; scoped to `out/test` to protect the esbuild bundle.)

sessions/0050/SESSION-0050.0-TRANSCRIPT-2026-06-13T17-43--2026-06-13T17-52.md

@@ -0,0 +1,76 @@
+# Session 0050.0 — Transcript
+
+> App: vscode-cowriting-plugin
+> Start: 2026-06-13T17-43 (PST)
+> End: 2026-06-13T17-52 (PST)
+> Type: capture
+> Posture: autonomous (yolo)
+> Status: **FINALIZED**
+
+## Launch prompt
+
+`/wgl-capture` — "When changing documents, we should decide what happens to the
+review pane of the current document, and if the document switched to should get a
+review experience or not"
+
+## Pre-state
+
+- Branch `main`, clean, pushed (origin/main). No in-flight sessions for the app.
+- Tracker `benstull/vscode-cowriting-plugin` (host `git.benstull.org`); content
+  repo `vscode-cowriting-plugin-content` cloned, with ~18 prior uncommitted
+  capture drafts in `issues/`.
+- Prior frontier exhausted (session 0047 note): remaining backlog items gated;
+  operator directing. This is a capture session, not a build.
+
+## Arc
+
+1. **Claimed** tracked-lite session ID **0050** (`claim-session-id.sh --type
+   capture`). Resolved app + content repo (`resolve-app.py`).
+2. **Grounded** the ask by reading the code (Explore subagent over
+   `src/trackChangesPreview.ts`, `diffViewController.ts`, `proposalController.ts`):
+   confirmed the review pane is one-panel-per-doc keyed by URI
+   (`trackChangesPreview.ts:45`) with **no** `onDidChangeActiveTextEditor`
+   listener — so on document switch the pane **stays pinned** to its original doc
+   (incidental, not designed) and the switched-to doc gets no review until
+   `showTrackChangesPreview` is re-invoked. Per-doc review state (F6 baseline / F4
+   proposals / F3 attribution) auto-creates on demand.
+3. **Sized** the single ask: genuine forks (follow / pin / close; auto-review /
+   on-demand) + needs design before build → `type/feature` (R3), `priority/P2`.
+   Captures the decision-to-be-made; option space goes in Solution notes,
+   non-binding.
+4. **Drafted** `issues/review-pane-on-document-switch.md` in the content repo
+   (working tree only, INV-8), full §5 template. Scanned clean for secrets
+   (INV-3).
+5. **Operator approved** filing as-is (feature, P2) via AskUserQuestion.
+6. **Filed** → ensured labels (all pre-existing), then `capture-issues.sh` →
+   **#57** (https://git.benstull.org/benstull/vscode-cowriting-plugin/issues/57).
+
+## Cut state
+
+- Session repo `vscode-cowriting-plugin`: clean `main`, nothing committed this
+  session (capture touches only the content repo working tree). No PRs.
+- Content repo: new draft `issues/review-pane-on-document-switch.md` left
+  uncommitted for the Author to publish/discard (INV-8), alongside the prior
+  drafts already there. Not pushed by this skill.
+- Issue **#57** filed and open on the tracker.
+
+## Deferred decisions
+
+_None — single clear ask, operator approved the framing and type before filing._
+
+## Operator plate
+
+- One feature filed: **#57** (review-pane behavior on document switch, P2).
+- ~19 capture drafts now sit uncommitted in `vscode-cowriting-plugin-content` —
+  yours to commit/publish (or discard) when convenient.
+- #57 needs a design before build (R3). No active plan frontier; operator to
+  direct next.
+
+## Next session prompt
+
+`/goal` — operator to direct. Candidate: brainstorm a Solution Design for **#57**
+(review-pane behavior on document switch) — settle the two coupled rules (outgoing
+pane fate; whether the switched-to doc auto-gets a review experience) before
+building. Other open: OQ-2 (F11 graduation), #32 (scroll-sync, needs design),
+#35 (repo rename), #40 (undo provenance, P3, branch `s40-undo-provenance`
+unmerged), #54 (undo still broken in sandbox).

sessions/0051/SESSION-0051.0-TRANSCRIPT-2026-06-13T17-49--2026-06-13T17-58.md

@@ -0,0 +1,71 @@
+# Session 0051.0 — Transcript
+
+> App: vscode-cowriting-plugin
+> Start: 2026-06-13T17-49 (PST)
+> End: 2026-06-13T17-58 (PST)
+> Type: capture
+> Posture: autonomous (yolo)
+> Status: **FINALIZED**
+
+## Launch prompt
+
+`/wgl-capture` — two asks:
+1. "Undo doesn't undo Claude's edits"
+2. "When I make a change within a block that Claude has changed that I haven't
+   approved, it doesn't show my changes"
+
+## Pre-state
+
+- Branch `main`, clean, pushed. Immediately followed capture session 0050 (#57).
+- Tracker `benstull/vscode-cowriting-plugin` (host `git.benstull.org`); content
+  repo cloned.
+
+## Arc
+
+1. **Claimed** tracked-lite session ID **0051**.
+2. **Grounded** both asks in code (Explore subagent):
+   - Undo: Claude's edits are pending proposals; `proposalController.ts:303-310`
+     shifts anchors on edit but ignores `e.reason === Undo` — proposal not
+     reconciled on undo (accepted edits hit the doc and are undoable, but the
+     pending proposal lingers).
+   - Pending-block edits: a proposal freezes its "before" (`replaced: fp.text`,
+     `proposalController.ts:81-95`); the block renders from current text but the
+     proposal's frozen view (`trackChangesModel.ts:706-722`/`:769-805`) obscures
+     live human edits in that block.
+3. **Checked duplication** against the undo cluster — #38 (wrong marks, closed),
+   #40 (attribution color, open), #54 (undo E2E infra, open). Both new asks are
+   distinct (undo failing to *reverse* the edit; live edits obscured by a pending
+   proposal). Verified `type/bug` exists on the tracker.
+4. **Drafted** both as `type/bug` (P1) in the content repo working tree
+   (`issues/undo-does-not-undo-claude-edits.md`,
+   `issues/edits-in-pending-block-not-shown.md`), each framed as user-facing pain
+   with repro steps + code diagnosis demoted to parenthetical. Scanned clean for
+   secrets (INV-3).
+5. **Operator triage:** before filing, operator said "ignore both of these
+   issues — you can delete the drafts." Both drafts **deleted**; nothing filed.
+
+## Cut state
+
+- **Nothing filed** (INV-4 — no-actionable outcome after operator triage).
+- Both draft files removed from the content repo working tree.
+- Session repo `vscode-cowriting-plugin`: clean `main`, no commits this session.
+
+## Deferred decisions
+
+_None — operator explicitly directed dropping both asks._
+
+## Operator plate
+
+- No issues filed this session. The two undo/pending-block asks were
+  considered and intentionally dropped (recorded in memory
+  `session-0051-capture-no-actionable.md` so they aren't re-raised as new).
+- Note: these remain *real* observed behaviors per the code reading — dropped on
+  operator triage, not because they were invalid. If they resurface, the prior
+  grounding is in the memory note.
+
+## Next session prompt
+
+`/goal` — operator to direct. From session 0050: candidate is brainstorming a
+Solution Design for **#57** (review-pane behavior on document switch). Other
+open: OQ-2 (F11 graduation), #32 (scroll-sync), #35 (repo rename), #40 (undo
+provenance, P3, branch `s40-undo-provenance` unmerged), #54 (undo E2E infra).

sessions/0052/SESSION-0052.0-TRANSCRIPT-2026-06-15T08-33--2026-06-15T08-41.md

@@ -0,0 +1,73 @@
+# Session 0052.0 — Transcript
+
+> App: vscode-cowriting-plugin
+> Start: 2026-06-15T08-33 (PST)
+> End: 2026-06-15T08-41 (PST)
+> Type: capture
+> Posture: autonomous (yolo)
+> Status: **FINALIZED**
+
+## Launch prompt
+
+`/wgl-capture` — two asks (second arrived mid-session):
+1. "the review window and markdown source file should have scroll location sync'd"
+2. "the claude change recommendation block (which user will accept or decline)
+   should show the diff with the original"
+
+## Pre-state
+
+- Branch `main`, clean, pushed. Follows capture sessions 0050 (#57) and 0051
+  (no-actionable).
+- Tracker `benstull/vscode-cowriting-plugin` (host `git.benstull.org`).
+
+## Arc
+
+**Ask 1 — scroll-sync (duplicate, nothing filed):**
+1. Claimed tracked-lite session ID **0052**.
+2. Recognized scroll-sync as a known F10 follow-up; fetched **#32** — exact match
+   (*"Scroll-sync the review preview with the source editor"*, open,
+   `type/feature`, `priority/P3`, filed session 0031).
+3. Surfaced to operator; operator chose to **leave #32 at P3**. No new issue
+   (INV-4 duplicate).
+
+**Ask 2 — proposal block diff vs original (filed #58):**
+4. Grounded in code (Explore): the pending proposal block renders original +
+   proposed as **two separate full blocks** (`<del>` whole-before + `<ins>`
+   whole-after, `trackChangesModel.ts:715-716`) with **no word-level diff** — the
+   changed-block rendering already uses `wordMergedMarkdown`/`diffWords`
+   (`trackChangesModel.ts:431-438`) but `proposalBlockHtml()` doesn't.
+   `ProposalView` already carries `replaced`+`replacement`
+   (`proposalController.ts:81-95`).
+5. Sized `type/story`, P2 (reuses existing word-diff helper; distinct from #31
+   placement / #47 granularity). Drafted
+   `issues/proposal-block-shows-diff-with-original.md` (working tree only, secrets
+   scanned).
+6. Operator approved as-is → ensured labels → filed **#58**
+   (https://git.benstull.org/benstull/vscode-cowriting-plugin/issues/58).
+
+## Cut state
+
+- **#58** filed (story, P2). Scroll-sync left as existing **#32** (P3) — nothing
+  new filed for it.
+- Draft `issues/proposal-block-shows-diff-with-original.md` left uncommitted in
+  the content repo for the Author to publish (INV-8).
+- Session repo `vscode-cowriting-plugin`: clean `main`, no commits this session.
+
+## Deferred decisions
+
+_None — operator directly resolved the duplicate and approved the #58 framing._
+
+## Operator plate
+
+- One issue filed: **#58** (proposal block word-diff, P2).
+- Scroll-sync remains **#32** (P3, open, unchanged).
+- One uncommitted capture draft added to the content repo (joins the prior
+  drafts) — yours to publish or discard.
+
+## Next session prompt
+
+`/goal` — operator to direct. Standing candidate (from 0050): brainstorm a
+Solution Design for **#57** (review-pane behavior on document switch). Open work:
+#58 (proposal word-diff, P2, story), #32 (scroll-sync, P3), OQ-2 (F11
+graduation), #35 (repo rename), #40 (undo provenance, P3, branch
+`s40-undo-provenance` unmerged), #54 (undo E2E infra).

sessions/0053/SESSION-0053.0-TRANSCRIPT-2026-06-15T10-23--2026-06-15T10-29.md

@@ -0,0 +1,66 @@
+# Session 0053.0 — Transcript
+
+> App: vscode-cowriting-plugin
+> Start: 2026-06-15T10-23 (PST)
+> End: 2026-06-15T10-29 (PST)
+> Type: capture
+> Posture: autonomous (yolo)
+> Status: **FINALIZED**
+
+## Launch prompt
+
+`/wgl-capture` — "The plugin is asking for access to other applications but works
+fine when I decline. It just shouldn't"
+
+## Pre-state
+
+- Branch `main`, clean, pushed. Follows capture sessions 0050 (#57), 0051
+  (no-actionable), 0052 (#58 + scroll-sync dup).
+- Tracker `benstull/vscode-cowriting-plugin` (host `git.benstull.org`).
+
+## Arc
+
+1. Claimed tracked-lite session ID **0053**.
+2. **Investigated** the macOS Automation/Apple-Events trigger (Explore): the
+   extension's own source has **no** AppleScript/`osascript`/automation calls; the
+   probable origin is **`@cline/sdk`/`@cline/core`** during agent activation
+   (likely local Claude Code hub-discovery), which falls back gracefully when
+   denied — matching "works fine when declined." Framed as a lead, not a settled
+   root cause.
+3. **Sized** `type/bug` (declared defect: unwanted OS permission request).
+   Drafted `issues/spurious-automation-permission-prompt.md` (working tree only,
+   secrets scanned) with repro steps + expected/actual + the upstream caveat.
+4. **Operator set priority P1** (trust/launch-optics over the harmless functional
+   impact); updated the WSJF line accordingly.
+5. **Filed #59.** capture-issues.sh `--type` rejects `bug` (known #124 taxonomy
+   gap), so filed with `--type task` then swapped the label to `type/bug` via the
+   Gitea API (deleted type/task, added type/bug) — verified `['priority/P1',
+   'type/bug']` (INV-2 holds).
+   → https://git.benstull.org/benstull/vscode-cowriting-plugin/issues/59
+
+## Cut state
+
+- **#59** filed (bug, P1), label corrected to exactly `type/bug`.
+- Draft `issues/spurious-automation-permission-prompt.md` left uncommitted in the
+  content repo for the Author to publish (INV-8).
+- Session repo `vscode-cowriting-plugin`: clean `main`, no commits this session.
+
+## Deferred decisions
+
+_None — operator set the priority directly and approved the framing._
+
+## Operator plate
+
+- One issue filed: **#59** (spurious macOS automation prompt, bug, **P1**).
+- The cause is likely upstream in `@cline/sdk` — the fix may be a config/flag or
+  dependency update, not necessarily this repo's code.
+- Reminder: bug capture needs the file-as-task-then-relabel workaround until
+  plugin #124 (capture can't type bugs) is fixed.
+
+## Next session prompt
+
+`/goal` — operator to direct. Standing candidate (from 0050): brainstorm a
+Solution Design for **#57** (review-pane behavior on document switch). Open work:
+**#59** (automation prompt, bug P1 — may be upstream), #58 (proposal word-diff,
+story P2), #32 (scroll-sync, P3), OQ-2 (F11 graduation), #35 (repo rename), #40
+(undo provenance, P3), #54 (undo E2E infra).

sessions/0054/SESSION-0054.0-TRANSCRIPT-2026-06-15T10-42--2026-06-15T10-48.md

@@ -0,0 +1,66 @@
+# Session 0054.0 — Transcript
+
+> App: vscode-cowriting-plugin
+> Start: 2026-06-15T10-42 (PST)
+> End: 2026-06-15T10-48 (PST)
+> Type: capture
+> Posture: autonomous (yolo)
+> Status: **FINALIZED**
+
+## Launch prompt
+
+`/wgl-capture` — "See the Claude output/progress in the 'asking Claude…' status"
+
+## Pre-state
+
+- Branch `main`, clean, pushed. Follows capture sessions 0050 (#57), 0051
+  (no-actionable), 0052 (#58 + scroll-sync dup), 0053 (#59).
+- Tracker `benstull/vscode-cowriting-plugin` (host `git.benstull.org`).
+
+## Arc
+
+1. Claimed tracked-lite session ID **0054**.
+2. **Grounded** (Explore): the "Cowriting: asking Claude…" status is an opaque
+   `withProgress` notification (`extension.ts:232-233`,
+   `trackChangesPreview.ts:232-233`) awaiting `agent.run()` as one black-box
+   promise (`liveTurn.ts:52`). Key enabler: `@cline/sdk` already emits streaming
+   events (`assistant-text-delta`, `tool-started/updated/finished`,
+   `usage-updated`) via `agent.subscribe()` / an `onEvent` hook, but the extension
+   constructs the Agent with **no hooks** (`liveTurn.ts:47-51`) and discards it.
+3. **Sized** `type/feature` — implementable by subscribing to existing events, but
+   a real design fork on the surface (notification text vs. OutputChannel vs.
+   status bar vs. webview relay) and content (text/tool/usage/reasoning) → design
+   first (R3). Drafted `issues/show-live-claude-progress.md` (working tree only,
+   secrets scanned).
+4. **Operator set priority** — chose "adjust priority" → **P1** (opaque wait hurts
+   every turn). Updated WSJF line.
+5. **Filed #60** (`type/feature`, P1).
+   → https://git.benstull.org/benstull/vscode-cowriting-plugin/issues/60
+
+## Cut state
+
+- **#60** filed (feature, P1).
+- Draft `issues/show-live-claude-progress.md` left uncommitted in the content repo
+  for the Author to publish (INV-8).
+- Session repo `vscode-cowriting-plugin`: clean `main`, no commits this session.
+
+## Deferred decisions
+
+_None — operator set the priority directly and approved the framing._
+
+## Operator plate
+
+- One issue filed: **#60** (live Claude progress, feature, **P1**).
+- Implementation is largely "subscribe to SDK events already available + pick the
+  progress surface" — needs a small design first (R3).
+- One uncommitted capture draft added to the content repo — yours to publish or
+  discard.
+
+## Next session prompt
+
+`/goal` — operator to direct. Capture run 0050–0054 filed #57, #58, #59, #60
+(scroll-sync = existing #32). Two P1s now open (**#59** automation prompt,
+**#60** live progress) plus standing #57 (review-pane on doc switch, design
+candidate). Other open: #58 (proposal word-diff, P2), #32 (scroll-sync P3), OQ-2
+(F11 graduation), #35 (repo rename), #40 (undo provenance P3), #54 (undo E2E
+infra).

sessions/0055/SESSION-0055.0-TRANSCRIPT-2026-06-22T23-19--2026-06-26T04-23.md

@@ -0,0 +1,105 @@
+# Session 0055.0 — Transcript
+
+> App: vscode-cowriting-plugin
+> Start: 2026-06-22T23-19 (PST)
+> End: 2026-06-26T04-23 (PST)
+> Type: brainstorming
+> Posture: autonomous (yolo)
+> Status: **FINALIZED**
+
+## Launch prompt
+
+`/wgl-brainstorming highest priority ticket`
+
+## Plan
+
+Brainstorming session: explore the highest-priority open ticket and write its
+Solution-Design spec. Highest-priority that fits a brainstorming session (spec
+output; a feature needs a design per §4.3 R3) was **#60 — Show Claude's live
+output/progress during the "asking Claude…" status** (P1 feature). #59 (P1 bug)
+is coding-session work, not brainstorming.
+
+Output: `specs/coauthoring-live-progress.md` (Solution Design), submitted graduated
+at finalize to the content repo's `specs/` collection.
+
+## Pre-state
+
+- Clean, pushed `main` (`24e329e`). No in-flight sessions (next ID 0055).
+- Two P1 tickets tied for highest priority: **#59** (P1 bug — spurious macOS
+  "control other applications" prompt) and **#60** (P1 feature — live turn
+  progress). Brainstorming produces a spec; a feature needs a design (§4.3 R3),
+  so #60 was the fit. #59 (bug) → a coding session.
+- Highest INV in use across the content-repo specs: **INV-42**.
+
+## Session arc (turn-by-turn)
+
+1. **Gate + classify.** Launch prompt classified as **brainstorming**; ran
+   `wgl-brainstorming`.
+2. **Claim (peek → gate → claim).** `claim-session-id.sh --dry-run` → no in-flight
+   sessions, next ID **0055**. Claimed `--type brainstorming` (placeholder at
+   `16cca30`). Verified clean pushed `main` baseline.
+3. **Orient.** Surveyed the open tracker. Picked **#60** (P1 feature, design
+   needed) over #59 (P1 bug, coding-session work). Read #60 in full.
+4. **Ground in code (read-only).** Read `liveTurn.ts` (`runEditTurn` →
+   `agent.run()` as one opaque promise; module is deliberately vscode-free), both
+   call sites (`extension.ts:232` editSelection, `trackChangesPreview.ts:232`
+   preview `askClaude` — both wrap the turn in `withProgress("asking Claude…")`),
+   the injectable `editTurn` seam (trackChangesPreview.ts:56, for host-E2E
+   stubbing), and the `@cline/sdk` event API: `@cline/agents` `Agent` exposes
+   `subscribe(listener) → unsubscribe`, `run()`, `abort()`; `AgentRuntimeEvent`
+   (in `@cline/shared/dist/agent.d.ts`) carries `assistant-text-delta`
+   (+`accumulatedText`), `tool-started|updated|finished`, `usage-updated`,
+   lifecycle events. The enabler the issue cites is real.
+5. **Brainstorm forks (superpowers:brainstorming).** Skipped the visual companion
+   (choices are conceptual/native-UI, not visual mockups). Presented three forks
+   via AskUserQuestion; operator picked all three recommendations:
+   - **Surface** → notification activity-line + token count **and** a shared
+     `"Cowriting"` OutputChannel streaming full assistant text. (Rejected: webview
+     relay can't cover the editSelection path; status-bar-only; OutputChannel-
+     primary.)
+   - **Content** → activity + token count (reasoning text not surfaced).
+   - **Cancellation** → `cancellable` notification → `agent.abort()` →
+     "cancelled", proposes nothing (reflect + cancel button).
+6. **Design presented + approved.** Three-unit architecture (pure
+   `turnProgress.ts` reducer → `runEditTurn` extended with `onProgress` +
+   `AbortSignal` → both call sites relay via a shared `liveProgressUi`); layering
+   rule keeps `liveTurn.ts`/`turnProgress.ts` vscode-free; INV-43..47. Two
+   sub-decisions (OutputChannel auto-reveal gated by a new setting; append-not-
+   clear) confirmed. Operator: "design looks right."
+7. **Spec written + self-review.** `specs/coauthoring-live-progress.md` authored
+   in house Solution-Design format. Self-review: no placeholders, INV-43..47 (no
+   collision with ≤42; INV-8/21/39 are correct citations), internally consistent,
+   single-feature scope.
+8. **Operator: "Implement it."** Per the pipeline, that's the brainstorm→coding
+   handoff (one SPEC = one plan = one execution, §4.3). Finalized this
+   brainstorming session (below); a fresh `wgl-planning-and-executing` session
+   plans + builds #60.
+
+## Cut state (at finalize)
+
+- **Spec graduated.** `submit-spec.sh --status graduated` →
+  `vscode-cowriting-plugin-content` `specs/coauthoring-live-progress.md` at
+  `3bd1ae5`.
+- **Code repo:** clean `main`; no code changes this session (brainstorming).
+  A local stray `specs/coauthoring-live-progress.md` remains untracked in the code
+  repo (an `rm` cleanup was permission-denied; harmless — canonical copy is in the
+  content repo).
+- **Memory:** added `session-0055-live-progress-spec-graduated.md` + index line.
+
+## Next-session prompt
+
+```
+/wgl-planning-and-executing implement #60 (live turn progress) from coauthoring-live-progress.md
+```
+
+## Deferred decisions
+
+- **OutputChannel auto-reveal** (fires every Claude turn): decided to auto-`show(true)`
+  (preserveFocus) on the *first* text delta, gated by a new setting
+  `cowriting.liveProgress.revealOutput` (default `true`). Operator confirmed the
+  design including this.
+- **OutputChannel history:** decided to *append* per-turn (with a header) rather
+  than clear, so it doubles as a debug log. Operator confirmed.
+- **Stray local spec file:** `rm -rf specs/` was permission-denied; left the
+  untracked local copy in the code repo (cosmetic; content repo holds the
+  canonical copy).

sessions/0056/SESSION-0056.0-TRANSCRIPT-2026-06-26T04-24--INPROGRESS.md

@@ -1,13 +1,13 @@
-# Session 0043.0 — Transcript
+# Session 0056.0 — Transcript
 
 > App: vscode-cowriting-plugin
-> Start: 2026-06-13T07-18 (PST)
+> Start: 2026-06-26T04-24 (PST)
 > Type: planning-and-executing
 > Status: **PLACEHOLDER — claimed at session start; finalized at session end.**
 >
-> This file reserves session ID 0043 for vscode-cowriting-plugin. The driver replaces this
+> This file reserves session ID 0056 for vscode-cowriting-plugin. The driver replaces this
 > body with the full transcript and renames the file to its final
-> SESSION-0043.0-TRANSCRIPT-2026-06-13T07-18--<end>.md form at session end.
+> SESSION-0056.0-TRANSCRIPT-2026-06-26T04-24--<end>.md form at session end.
 
 ## Launch prompt
 

sessions/sessions.json

@@ -127,5 +127,44 @@
   },
   "0043": {
     "title": ""
+  },
+  "0044": {
+    "title": ""
+  },
+  "0045": {
+    "title": ""
+  },
+  "0046": {
+    "title": ""
+  },
+  "0047": {
+    "title": ""
+  },
+  "0048": {
+    "title": ""
+  },
+  "0049": {
+    "title": ""
+  },
+  "0050": {
+    "title": ""
+  },
+  "0051": {
+    "title": ""
+  },
+  "0052": {
+    "title": ""
+  },
+  "0053": {
+    "title": ""
+  },
+  "0054": {
+    "title": ""
+  },
+  "0055": {
+    "title": ""
+  },
+  "0056": {
+    "title": ""
   }
 }

src/extension.ts

@@ -11,6 +11,7 @@ import { GlobalSidecarStore } from "./globalSidecarStore";
 import { SidecarRouter } from "./sidecarRouter";
 import { DiffViewController } from "./diffViewController";
 import { TrackChangesPreviewController } from "./trackChangesPreview";
+import { LiveProgressUi } from "./liveProgressUi";
 import { isAuthorable, selectionRejection } from "./workspacePath";
 
 const CHANNEL_NAME = "Cowriting (Cline SDK)";
@@ -23,12 +24,18 @@ export interface CowritingApi {
   diffViewController: DiffViewController;
   trackChangesPreviewController: TrackChangesPreviewController;
   sidecarRouter: SidecarRouter;
+  liveProgressUi: LiveProgressUi;
 }
 
 export function activate(context: vscode.ExtensionContext): CowritingApi | undefined {
   // --- POC command (Feature #2), unchanged ---
   const output = vscode.window.createOutputChannel(CHANNEL_NAME);
   context.subscriptions.push(output);
+
+  // #60: shared live-progress UI (notification activity line + "Cowriting: Claude"
+  // OutputChannel) for both Ask-Claude entry points.
+  const liveProgressUi = new LiveProgressUi();
+  context.subscriptions.push(liveProgressUi);
   context.subscriptions.push(
     vscode.commands.registerCommand("cowriting.showClineSdkInfo", async () => {
       try {
@@ -104,9 +111,24 @@ export function activate(context: vscode.ExtensionContext): CowritingApi | undef
     context.extensionUri,
     attributionController,
     proposalController,
+    liveProgressUi,
   );
   context.subscriptions.push(trackChangesPreviewController);
 
+  // #46 (INV-42): accept every pending proposal on the active doc in one gesture
+  // (also reachable from the preview toolbar's "Accept all" button). Reuses the
+  // batched F4 seam + reports applied-vs-skipped.
+  context.subscriptions.push(
+    vscode.commands.registerCommand("cowriting.acceptAllProposals", async () => {
+      const doc = vscode.window.activeTextEditor?.document;
+      if (!doc || doc.languageId !== "markdown") {
+        void vscode.window.showWarningMessage("Cowriting: open a Markdown document to accept its proposals.");
+        return;
+      }
+      await trackChangesPreviewController.acceptAll(doc);
+    }),
+  );
+
   // --- F6 machine-landing wiring — now for ANY authorable doc ---
   // The seam's single machine-landing signal advances the F6 baseline (INV-18);
   // the seam can now fire on out-of-folder files too, so wire it unconditionally.
@@ -216,10 +238,28 @@ export function activate(context: vscode.ExtensionContext): CowritingApi | undef
       const turnId = `turn-${Date.now().toString(36)}`;
       try {
         await vscode.window.withProgress(
-          { location: vscode.ProgressLocation.Notification, title: "Cowriting: asking Claude…" },
-          async () => {
+          {
+            location: vscode.ProgressLocation.Notification,
+            title: "Cowriting: asking Claude…",
+            cancellable: true,
+          },
+          async (progress, token) => {
             const { runEditTurn } = await import("./liveTurn");
-            const turn = await runEditTurn(instruction, selectedText);
+            const ui = liveProgressUi.begin(instruction, progress, token);
+            let turn;
+            try {
+              turn = await runEditTurn(instruction, selectedText, {
+                onProgress: ui.onProgress,
+                signal: ui.signal,
+              });
+            } catch (err) {
+              // #60 (INV-47): a user cancel surfaces as "cancelled", not a failure.
+              if (token.isCancellationRequested) {
+                void vscode.window.showInformationMessage("Cowriting: Claude edit cancelled.");
+                return;
+              }
+              throw err;
+            }
             if (turn.replacement === "") {
               void vscode.window.showWarningMessage(
                 "Cowriting: Claude returned an empty replacement — nothing was proposed.",
@@ -278,6 +318,7 @@ export function activate(context: vscode.ExtensionContext): CowritingApi | undef
     diffViewController,
     trackChangesPreviewController,
     sidecarRouter,
+    liveProgressUi,
   };
 }
 

src/liveProgressUi.ts

@@ -0,0 +1,65 @@
+/**
+ * liveProgressUi.ts — host-side relay of TurnProgress snapshots to VS Code UI
+ * (#60, spec coauthoring-live-progress.md §3.4). The ONLY surfaces are the
+ * existing withProgress notification (an activity line) and a dedicated
+ * OutputChannel streaming the full assistant text — no new network/webview
+ * surface (INV-45). vscode-only; all pure logic lives in turnProgress.ts.
+ */
+import * as vscode from "vscode";
+import { formatProgressLine, type TurnProgressSnapshot } from "./turnProgress";
+
+const CHANNEL_NAME = "Cowriting: Claude";
+
+export interface TurnUi {
+  /** Pass to runEditTurn's opts.onProgress. */
+  onProgress: (snapshot: TurnProgressSnapshot) => void;
+  /** Pass to runEditTurn's opts.signal — fired when the user cancels the notification. */
+  signal: AbortSignal;
+}
+
+export class LiveProgressUi {
+  readonly channel: vscode.OutputChannel;
+
+  constructor() {
+    this.channel = vscode.window.createOutputChannel(CHANNEL_NAME);
+  }
+
+  /**
+   * Begin one turn's UI. Writes the per-turn header to the channel and returns
+   * the onProgress relay + an AbortSignal linked to the notification's cancel
+   * token. The channel APPENDS (it doubles as a debug log of recent turns, spec
+   * §3.5); it auto-reveals (without stealing focus) on the first streamed text,
+   * gated by `cowriting.liveProgress.revealOutput`.
+   */
+  begin(
+    instruction: string,
+    progress: vscode.Progress<{ message?: string }>,
+    token: vscode.CancellationToken,
+  ): TurnUi {
+    const controller = new AbortController();
+    token.onCancellationRequested(() => controller.abort());
+    this.channel.appendLine(`── asking: ${instruction} ──`);
+
+    let revealed = false;
+    const reveal = (): void => {
+      if (revealed) return;
+      revealed = true;
+      const cfg = vscode.workspace.getConfiguration("cowriting");
+      if (cfg.get<boolean>("liveProgress.revealOutput", true)) this.channel.show(true);
+    };
+
+    const onProgress = (s: TurnProgressSnapshot): void => {
+      progress.report({ message: formatProgressLine(s) });
+      if (s.textDelta) {
+        this.channel.append(s.textDelta);
+        reveal();
+      }
+    };
+
+    return { onProgress, signal: controller.signal };
+  }
+
+  dispose(): void {
+    this.channel.dispose();
+  }
+}

src/liveTurn.ts

@@ -9,6 +9,9 @@
  * never bundled (esbuild keeps it external).
  */
 
+import type { TurnProgressSnapshot } from "./turnProgress";
+import { createTurnProgressState, reduceTurnProgress } from "./turnProgress";
+
 export interface EditTurnResult {
   replacement: string;
   model: string;
@@ -16,6 +19,19 @@ export interface EditTurnResult {
   sessionId: string;
 }
 
+/**
+ * Options for runEditTurn. Both new fields are purely additive observability /
+ * control over the existing turn (INV-44): `onProgress` streams reduced progress
+ * snapshots out; `signal` cancels the turn in. Neither touches the result path,
+ * and neither pulls `vscode` into this module (INV-43 — `AbortSignal` is a web
+ * standard, the progress snapshot is a domain type).
+ */
+export interface RunEditTurnOptions {
+  modelId?: string;
+  onProgress?: (snapshot: TurnProgressSnapshot) => void;
+  signal?: AbortSignal;
+}
+
 const SYSTEM_PROMPT = [
   "You are a precise text editor embedded in VS Code.",
   "You will be given a piece of text and an instruction.",
@@ -40,7 +56,7 @@ export function extractReplacement(outputText: string, selectedText: string): st
 export async function runEditTurn(
   instruction: string,
   selectedText: string,
-  opts?: { modelId?: string },
+  opts?: RunEditTurnOptions,
 ): Promise<EditTurnResult> {
   const sdk = await import("@cline/sdk");
   const modelId = opts?.modelId ?? "sonnet";
@@ -49,16 +65,50 @@ export async function runEditTurn(
     modelId,
     systemPrompt: SYSTEM_PROMPT,
   });
-  const result = await agent.run(
-    `<instruction>\n${instruction}\n</instruction>\n<text>\n${selectedText}\n</text>`,
-  );
-  // The SDK's AgentRunResult.status union is "completed" | "aborted" | "failed"
-  // (@cline/shared agent.d.ts) — "completed" is the success status.
-  if (result.status !== "completed") {
-    throw new Error(
-      `claude-code turn ${result.status}: ${result.error?.message ?? "unknown error"} ` +
-        "(is Claude Code installed and signed in?)",
+
+  // Stream reduced progress snapshots out (INV-44 additive) and wire cancellation
+  // in via the AbortSignal (INV-47). agent.subscribe returns its unsubscribe fn.
+  let state = createTurnProgressState();
+  const unsubscribe = opts?.onProgress
+    ? agent.subscribe((event) => {
+        const next = reduceTurnProgress(state, event);
+        state = next.state;
+        // Observability must never affect the result (INV-44): a throwing relay
+        // is swallowed, not allowed to propagate into the SDK and fail the turn.
+        if (next.snapshot) {
+          try {
+            opts.onProgress!(next.snapshot);
+          } catch {
+            /* progress is best-effort */
+          }
+        }
+      })
+    : undefined;
+  const onAbort = () => agent.abort();
+  opts?.signal?.addEventListener("abort", onAbort);
+
+  try {
+    // A signal already aborted before the turn starts can't be honored by
+    // agent.abort() (the SDK's AbortController isn't created until run()), so
+    // short-circuit to the same aborted outcome the call site reflects (INV-47).
+    if (opts?.signal?.aborted) {
+      throw new Error("claude-code turn aborted: cancelled before start");
+    }
+    const result = await agent.run(
+      `<instruction>\n${instruction}\n</instruction>\n<text>\n${selectedText}\n</text>`,
     );
+    // The SDK's AgentRunResult.status union is "completed" | "aborted" | "failed"
+    // (@cline/shared agent.d.ts) — "completed" is the success status. An aborted
+    // turn (user cancel) falls into this throw; the call site reflects "cancelled".
+    if (result.status !== "completed") {
+      throw new Error(
+        `claude-code turn ${result.status}: ${result.error?.message ?? "unknown error"} ` +
+          "(is Claude Code installed and signed in?)",
+      );
+    }
+    return { replacement: extractReplacement(result.outputText, selectedText), model: modelId, sessionId: result.runId };
+  } finally {
+    unsubscribe?.();
+    opts?.signal?.removeEventListener("abort", onAbort);
   }
-  return { replacement: extractReplacement(result.outputText, selectedText), model: modelId, sessionId: result.runId };
 }

src/model.ts

@@ -90,6 +90,13 @@ export interface Proposal {
   turnId?: string;
   /** what the human asked for (review context). */
   instruction?: string;
+  /**
+   * F12/#47 (INV-39/40): the review-decision unit this proposal represents.
+   * `"block"` ⇒ the anchor spans a whole document block and accept reconciles
+   * attribution per WORD inside it (INV-40); `"single"` (or absent, for
+   * back-compat with older sidecars) ⇒ a single-range proposal accepted whole.
+   */
+  granularity?: "block" | "single";
 }
 
 export interface Artifact {

src/proposalController.ts

@@ -18,7 +18,7 @@ import { addProposal, removeProposal } from "./proposalModel";
 import type { AttributionController } from "./attributionController";
 import type { VersionGuard } from "./versionGuard";
 import { isAuthorable } from "./workspacePath";
-import type { ProposalView } from "./trackChangesModel";
+import { wordEditHunks, type ProposalView } from "./trackChangesModel";
 
 /** Test-facing snapshot of what is currently rendered for a document. */
 export interface RenderedProposal {
@@ -122,7 +122,7 @@ export class ProposalController implements vscode.Disposable {
     fp: Fingerprint,
     replacement: string,
     author: Provenance,
-    opts?: { turnId?: string; instruction?: string },
+    opts?: { turnId?: string; instruction?: string; granularity?: "block" | "single" },
   ): Promise<string | undefined> {
     if (!this.isTracked(document)) return undefined;
     if (this.guard.isReadOnly(this.keyOf(document))) return undefined;
@@ -138,9 +138,40 @@ export class ProposalController implements vscode.Disposable {
   // ---- PUC-2/PUC-3: accept / reject (INV-11/INV-12) ----------------------------------
 
   /** Accept by proposal id (test-facing twin of the thread-menu gesture). */
-  async acceptById(docPath: string, proposalId: string): Promise<boolean> {
+  async acceptById(docPath: string, proposalId: string, opts?: { silent?: boolean }): Promise<boolean> {
     const hit = this.byId(docPath, proposalId);
-    return hit ? this.accept(hit.state, hit.proposal) : false;
+    return hit ? this.accept(hit.state, hit.proposal, opts) : false;
+  }
+
+  /**
+   * #46 (INV-42): accept EVERY pending proposal on a document in one gesture — a
+   * batched application of the existing `acceptById` seam, not a new mechanism.
+   * Block proposals take the INV-40 word-precise path automatically. Applied in
+   * DESCENDING anchor order so an earlier accept never invalidates a later one's
+   * offsets; proposals whose anchor can't resolve are SKIPPED (never force-applied)
+   * and counted. Returns the applied-vs-skipped tally for the caller to report.
+   */
+  async acceptAllProposals(document: vscode.TextDocument): Promise<{ applied: number; skipped: number }> {
+    if (!this.isTracked(document)) return { applied: 0, skipped: 0 };
+    const state = this.ensureState(document);
+    state.artifact = this.store.load(state.docPath) ?? emptyArtifact(state.docPath);
+    const text = document.getText();
+    const items = state.artifact.proposals.map((p) => {
+      const fp = state.artifact.anchors[p.anchorId]?.fingerprint;
+      const resolved = fp ? resolve(text, fp) : "orphaned";
+      return { id: p.id, start: resolved === "orphaned" ? null : resolved.start };
+    });
+    const resolvable = items
+      .filter((i): i is { id: string; start: number } => i.start !== null)
+      .sort((a, b) => b.start - a.start);
+    let applied = 0;
+    let skipped = items.length - resolvable.length; // orphans, skipped up front
+    for (const it of resolvable) {
+      // silent: one batch report stands in for N per-proposal warnings.
+      if (await this.acceptById(state.docPath, it.id, { silent: true })) applied++;
+      else skipped++;
+    }
+    return { applied, skipped };
   }
   /** Reject by proposal id (test-facing twin of the thread-menu gesture). */
   rejectById(docPath: string, proposalId: string): boolean {
@@ -150,7 +181,7 @@ export class ProposalController implements vscode.Disposable {
     return true;
   }
 
-  private async accept(state: DocState, proposal: Proposal): Promise<boolean> {
+  private async accept(state: DocState, proposal: Proposal, opts?: { silent?: boolean }): Promise<boolean> {
     if (this.guard.isReadOnly(state.docPath)) return false;
     const document = this.openDoc(state);
     if (!document) return false;
@@ -158,22 +189,32 @@ export class ProposalController implements vscode.Disposable {
     const fp = state.artifact.anchors[proposal.anchorId]?.fingerprint;
     const resolved = fp ? resolve(document.getText(), fp) : "orphaned";
     if (resolved === "orphaned") {
-      void vscode.window.showWarningMessage(
-        "Cowriting: this proposal's target text changed or is missing — undo to restore it, or reject to discard (it is never applied by guess).",
-      );
+      // #46: accept-all suppresses per-proposal warnings (one batch report instead).
+      if (!opts?.silent)
+        void vscode.window.showWarningMessage(
+          "Cowriting: this proposal's target text changed or is missing — undo to restore it, or reject to discard (it is never applied by guess).",
+        );
       this.renderAll(document);
       return false;
     }
-    const range = new vscode.Range(document.positionAt(resolved.start), document.positionAt(resolved.end));
-    // No awaits between resolve and the seam call: document.version is current.
-    const ok = await this.attribution.applyAgentEdit(document, range, proposal.replacement, proposal.author, {
-      expectedVersion: document.version,
-      turnId: proposal.turnId,
-    });
+    // #47 (INV-40): a BLOCK proposal applies the whole block but attributes only
+    // the words Claude actually changed; a single proposal applies its whole range.
+    const ok =
+      proposal.granularity === "block"
+        ? await this.acceptBlock(document, resolved, proposal)
+        : await this.attribution.applyAgentEdit(
+            document,
+            new vscode.Range(document.positionAt(resolved.start), document.positionAt(resolved.end)),
+            proposal.replacement,
+            proposal.author,
+            // No awaits between resolve and the seam call: document.version is current.
+            { expectedVersion: document.version, turnId: proposal.turnId },
+          );
     if (!ok) {
-      void vscode.window.showWarningMessage(
-        "Cowriting: the editor rejected the accept — the proposal is still pending.",
-      );
+      if (!opts?.silent)
+        void vscode.window.showWarningMessage(
+          "Cowriting: the editor rejected the accept — the proposal is still pending.",
+        );
       return false;
     }
     this.store.update(state.docPath, (a) => removeProposal(a, proposal.id));
@@ -181,6 +222,41 @@ export class ProposalController implements vscode.Disposable {
     return true;
   }
 
+  /**
+   * #47 (INV-40): accept a BLOCK proposal — apply Claude's whole block, but
+   * attribute ONLY the runs Claude actually changed. The block is the DECISION
+   * unit; the word is the ATTRIBUTION unit. An intra-block word sub-diff
+   * (`wordEditHunks`, the raw engine INV-37 used, repurposed — un-anchored so the
+   * runs stay disjoint for a batch apply) yields the changed runs; each lands
+   * through the F4 seam (Claude-attributed), applied last-position-first so an
+   * earlier run's offsets stay valid under the later ones. Unchanged spans within
+   * the block are never touched, so their prior authorship stands. (Each run is
+   * one seam edit / one undo step — see the spec's deferred note on undo grouping.)
+   */
+  private async acceptBlock(
+    document: vscode.TextDocument,
+    resolved: OffsetRange,
+    proposal: Proposal,
+  ): Promise<boolean> {
+    const blockText = document.getText(
+      new vscode.Range(document.positionAt(resolved.start), document.positionAt(resolved.end)),
+    );
+    const subHunks = wordEditHunks(blockText, proposal.replacement);
+    if (subHunks.length === 0) return true; // block already equals the proposal — nothing to attribute
+    for (const h of [...subHunks].sort((a, b) => b.start - a.start)) {
+      const range = new vscode.Range(
+        document.positionAt(resolved.start + h.start),
+        document.positionAt(resolved.start + h.end),
+      );
+      const ok = await this.attribution.applyAgentEdit(document, range, h.replacement, proposal.author, {
+        expectedVersion: document.version,
+        turnId: proposal.turnId,
+      });
+      if (!ok) return false;
+    }
+    return true;
+  }
+
   private reject(state: DocState, proposal: Proposal): void {
     if (this.guard.isReadOnly(state.docPath)) return;
     this.store.update(state.docPath, (a) => removeProposal(a, proposal.id));

src/proposalModel.ts

@@ -12,7 +12,7 @@ export function addProposal(
   fp: Fingerprint,
   replacement: string,
   author: Provenance,
-  opts?: { turnId?: string; instruction?: string },
+  opts?: { turnId?: string; instruction?: string; granularity?: "block" | "single" },
 ): { proposalId: string; anchorId: string } {
   const anchorId = newId("a");
   const proposalId = newId("pr");
@@ -25,6 +25,7 @@ export function addProposal(
     createdAt: new Date().toISOString(),
     ...(opts?.turnId !== undefined ? { turnId: opts.turnId } : {}),
     ...(opts?.instruction !== undefined ? { instruction: opts.instruction } : {}),
+    ...(opts?.granularity !== undefined ? { granularity: opts.granularity } : {}),
   });
   return { proposalId, anchorId };
 }

src/trackChangesModel.ts

@@ -223,11 +223,27 @@ export interface EditHunk {
  * never part of another hunk.
  */
 export function diffToHunks(currentText: string, rewrittenText: string): EditHunk[] {
+  return wordEditHunks(currentText, rewrittenText).map((h) =>
+    h.start === h.end ? anchorInsertion(h, currentText) : h,
+  );
+}
+
+/**
+ * The raw word-level diff underlying `diffToHunks`: disjoint, ordered EditHunks
+ * that exactly partition the change (a pure insertion stays ZERO-WIDTH at its
+ * offset — not anchored). `diffToHunks` adds anchoring on top so each hunk's F4
+ * fingerprint resolves; callers that apply hunks directly through the seam
+ * (INV-40's intra-block accept) want THESE raw, non-overlapping hunks instead —
+ * anchoring can grow an insertion to absorb a token an adjacent hunk also edits,
+ * which corrupts a batch apply. Pure, vscode-free, deterministic. Applying these
+ * right→left reconstructs `rewrittenText` exactly.
+ */
+export function wordEditHunks(currentText: string, rewrittenText: string): EditHunk[] {
   const hunks: EditHunk[] = [];
   let offset = 0;
   let open: EditHunk | null = null;
   const flush = () => {
-    if (open) hunks.push(open.start === open.end ? anchorInsertion(open, currentText) : open);
+    if (open) hunks.push(open);
     open = null;
   };
   for (const part of diffWordsWithSpace(currentText, rewrittenText)) {
@@ -272,6 +288,115 @@ function anchorInsertion(hunk: EditHunk, text: string): EditHunk {
   return { start: s, end: p, replacement: text.slice(s, p) + hunk.replacement };
 }
 
+type BlockAlignKind = "unchanged" | "changed" | "removed" | "added";
+interface BlockAlignOp {
+  kind: BlockAlignKind;
+  ci?: number; // index into the current blocks
+  ni?: number; // index into the rewritten blocks
+}
+
+/**
+ * Align two block sequences by normalized key (jsdiff `diffArrays`), pairing an
+ * adjacent removed-then-added run element-wise into `changed` ops (the surplus
+ * staying `removed` / `added`) — the same pairing `diffBlocks` uses, but yielding
+ * index ops so the caller can read each side's source range. Pure.
+ */
+function alignBlocks(cur: BlockWithRange[], next: BlockWithRange[]): BlockAlignOp[] {
+  const changes = diffArrays(
+    cur.map((b) => b.key),
+    next.map((b) => b.key),
+  );
+  const ops: BlockAlignOp[] = [];
+  let bi = 0; // current index
+  let ci = 0; // rewritten index
+  for (let n = 0; n < changes.length; n++) {
+    const ch = changes[n];
+    const count = ch.count ?? ch.value.length;
+    if (!ch.added && !ch.removed) {
+      for (let k = 0; k < count; k++) ops.push({ kind: "unchanged", ci: bi++, ni: ci++ });
+      continue;
+    }
+    if (ch.removed) {
+      const nx = changes[n + 1];
+      const addCount = nx?.added ? (nx.count ?? nx.value.length) : 0;
+      const paired = Math.min(count, addCount);
+      for (let k = 0; k < paired; k++) ops.push({ kind: "changed", ci: bi++, ni: ci++ });
+      for (let k = paired; k < count; k++) ops.push({ kind: "removed", ci: bi++ });
+      for (let k = paired; k < addCount; k++) ops.push({ kind: "added", ni: ci++ });
+      if (nx?.added) n++;
+      continue;
+    }
+    for (let k = 0; k < count; k++) ops.push({ kind: "added", ni: ci++ });
+  }
+  return ops;
+}
+
+/**
+ * #47 (INV-39, §6.4): diff a whole-document rewrite into ONE EditHunk per CHANGED
+ * BLOCK — the unit a human reviews — rather than per word (which INV-37/`diffToHunks`
+ * did and this supersedes for document edits). Built by aligning both sides into
+ * the existing block units (`splitBlocksWithRanges`) and keying with the same diff
+ * as `diffBlocks`:
+ *  - a CHANGED block (1:1 aligned, even when adjacent to other changed blocks) → a
+ *    block-aligned hunk `[block.start, block.end)` → the rewritten block's raw
+ *    text. A code/mermaid fence is one such whole-block hunk (atomic, INV-23). So
+ *    a copy-edit pass touching N consecutive paragraphs yields N proposals.
+ *  - a run of block INSERTIONS / DELETIONS → one gap-span hunk covering the source
+ *    between the bounding aligned blocks (unchanged OR changed — both are 1:1
+ *    anchors) → the matching rewritten span (separators included), so
+ *    reconstruction stays exact. A zero-width gap-span (insert at a seamless
+ *    boundary) is anchored to an adjacent token (INV-41) so its F4 fingerprint
+ *    resolves and it accepts.
+ *  - unchanged blocks (same key AND same raw) → no hunk.
+ * Pure, vscode-free, deterministic; same `EditHunk` shape as `diffToHunks` (which
+ * is RETAINED as the intra-block sub-diff engine for word-precise accept
+ * attribution — INV-40). Applying all hunks right→left reconstructs `rewrittenText`
+ * exactly.
+ */
+export function diffToBlockHunks(currentText: string, rewrittenText: string): EditHunk[] {
+  const cur = splitBlocksWithRanges(currentText);
+  const next = splitBlocksWithRanges(rewrittenText);
+  const ops = alignBlocks(cur, next);
+  // Same key but different raw (whitespace/case) is still a real content change.
+  for (const op of ops) {
+    if (op.kind === "unchanged" && cur[op.ci!].raw !== next[op.ni!].raw) op.kind = "changed";
+  }
+  // `changed` and `unchanged` are 1:1 anchors (both sides' offsets are known);
+  // `added`/`removed` have no counterpart and must be spanned together.
+  const isAnchor = (op: BlockAlignOp) => op.kind === "unchanged" || op.kind === "changed";
+  const hunks: EditHunk[] = [];
+  let i = 0;
+  while (i < ops.length) {
+    const op = ops[i];
+    if (op.kind === "unchanged") {
+      i++;
+      continue;
+    }
+    if (op.kind === "changed") {
+      const c = cur[op.ci!];
+      hunks.push({ start: c.start, end: c.end, replacement: next[op.ni!].raw });
+      i++;
+      continue;
+    }
+    // A maximal run of added/removed blocks → one gap-span hunk over the source
+    // between the bounding anchors (or the document edges), replaced with the
+    // matching rewritten span, so the separators reconstruct exactly.
+    let j = i;
+    while (j < ops.length && !isAnchor(ops[j])) j++;
+    const prev = i > 0 ? ops[i - 1] : null; // an anchor by construction
+    const after = j < ops.length ? ops[j] : null; // an anchor (or null at EOF)
+    const curStart = prev ? cur[prev.ci!].end : 0;
+    const curEnd = after ? cur[after.ci!].start : currentText.length;
+    const newStart = prev ? next[prev.ni!].end : 0;
+    const newEnd = after ? next[after.ni!].start : rewrittenText.length;
+    const hunk: EditHunk = { start: curStart, end: curEnd, replacement: rewrittenText.slice(newStart, newEnd) };
+    hunks.push(hunk.start === hunk.end ? anchorInsertion(hunk, currentText) : hunk);
+    i = j;
+  }
+  hunks.sort((a, b) => a.start - b.start);
+  return hunks;
+}
+
 const md = new MarkdownIt({ html: true, linkify: false, breaks: false });
 // mermaid fences → <pre class="mermaid">SRC</pre> for client-side rendering; all
 // other fences fall through to markdown-it's default (escaped <pre><code>).
@@ -316,6 +441,14 @@ function wordMergedMarkdown(beforeRaw: string, afterRaw: string): string {
 export interface RenderOptions {
   /** Per-block markdown→HTML renderer (test seam). Defaults to the bundled markdown-it. */
   render?: (src: string) => string;
+  /**
+   * #48: the baseline was just PINNED (`reason === "pinned"`). With zero changes
+   * since that pin, the on-render is fully clean — no authorship coloring — so a
+   * pin reads as "this is my clean starting point". Distinct from a baseline
+   * advanced by a machine-landing (accept), which keeps its authorship coloring
+   * (F10 INV-33). Only consulted by `renderReview`.
+   */
+  pinned?: boolean;
 }
 
 function defaultRender(src: string): string {
@@ -412,13 +545,33 @@ function authorBadge(authors: Set<AuthorKind>): { cls: string; label: string } |
     : { cls: "cw-by-human", label: "You" };
 }
 
+// Markdown emphasis / code delimiters whose RUNS must never be split by an
+// injected sentinel — a sentinel between two run chars (e.g. `*|*`) breaks
+// markdown-it's delimiter pairing (#33 CASE1).
+const isDelimChar = (c: string): boolean => c === "*" || c === "_" || c === "~" || c === "`";
+
+/**
+ * #33 (CASE1): a sentinel must not land STRICTLY INSIDE a delimiter run. If `at`
+ * sits between two identical delimiter chars, snap it to the run's start (a
+ * position outside the run) so the run stays intact. Delimiters are invisible once
+ * rendered, so snapping only shifts the colored boundary across markup, never over
+ * visible text.
+ */
+function clampOffDelimiterRun(raw: string, at: number): number {
+  if (at <= 0 || at >= raw.length) return at;
+  if (!(isDelimChar(raw[at]) && raw[at - 1] === raw[at])) return at;
+  let p = at;
+  while (p > 0 && raw[p - 1] === raw[at]) p--;
+  return p;
+}
+
 /** Inject paired sentinels into a prose block's raw text for the spans clipped to it. */
 function injectSentinels(raw: string, blockStart: number, spans: AuthorSpan[]): string {
   const inserts: { at: number; marker: string }[] = [];
   for (const s of spans) {
-    const lo = Math.max(0, s.start - blockStart);
-    const hi = Math.min(raw.length, s.end - blockStart);
-    if (hi <= lo) continue;
+    const lo = clampOffDelimiterRun(raw, Math.max(0, s.start - blockStart));
+    const hi = clampOffDelimiterRun(raw, Math.min(raw.length, s.end - blockStart));
+    if (hi <= lo) continue; // empty (or clamped to empty) span contributes nothing
     inserts.push({ at: lo, marker: SENT[s.author].open });
     inserts.push({ at: hi, marker: SENT[s.author].close });
   }
@@ -431,13 +584,69 @@ function injectSentinels(raw: string, blockStart: number, spans: AuthorSpan[]):
   return out;
 }
 
-/** Replace the rendered sentinels with author <span> tags. */
+const SENTINEL_OF: Record<string, { author: AuthorKind; open: boolean } | undefined> = {
+  [SENT.claude.open]: { author: "claude", open: true },
+  [SENT.claude.close]: { author: "claude", open: false },
+  [SENT.human.open]: { author: "human", open: true },
+  [SENT.human.close]: { author: "human", open: false },
+};
+const ALL_SENTINELS = new RegExp(
+  `[${SENT.claude.open}${SENT.claude.close}${SENT.human.open}${SENT.human.close}]`,
+  "g",
+);
+
+/**
+ * #33: token-aware replacement of the rendered author sentinels with `cw-by-*`
+ * spans. A naive global string-replace (the old approach) could emit a span that
+ * CROSSES an element boundary — `<span><strong>bo</span>ld</strong>` — when a
+ * boundary fell inside an emphasis run (CASE3). This walks the rendered HTML and
+ * emits the author span only around TEXT runs, CLOSING it before any `<tag>` and
+ * REOPENING it after, so a span is always well-nested within the inline elements
+ * (one `<span>` segment per text run). Tags are copied verbatim (with any stray
+ * sentinel stripped, so no Private-Use-Area char ever leaks). Pure, deterministic.
+ */
 function sentinelsToSpans(html: string): string {
-  return html
-    .split(SENT.claude.open).join('<span class="cw-by-claude">')
-    .split(SENT.claude.close).join("</span>")
-    .split(SENT.human.open).join('<span class="cw-by-human">')
-    .split(SENT.human.close).join("</span>");
+  const out: string[] = [];
+  let current: AuthorKind | null = null; // which author region we're inside
+  let spanOpen = false; // whether a <span> is currently open in `out`
+  const openSpan = () => {
+    if (current && !spanOpen) {
+      out.push(`<span class="cw-by-${current}">`);
+      spanOpen = true;
+    }
+  };
+  const closeSpan = () => {
+    if (spanOpen) {
+      out.push("</span>");
+      spanOpen = false;
+    }
+  };
+  for (let i = 0; i < html.length; i++) {
+    const ch = html[i];
+    const sentinel = SENTINEL_OF[ch];
+    if (sentinel) {
+      if (sentinel.open) current = sentinel.author; // span opens lazily before the next text char
+      else {
+        closeSpan();
+        current = null;
+      }
+      continue;
+    }
+    if (ch === "<") {
+      // An HTML tag: never let an author span straddle it (text `<` is escaped to
+      // &lt;, so a raw `<` is always a real tag). Copy the tag verbatim, sentinel-free.
+      closeSpan();
+      const gt = html.indexOf(">", i);
+      const end = gt === -1 ? html.length - 1 : gt;
+      out.push(html.slice(i, end + 1).replace(ALL_SENTINELS, ""));
+      i = end;
+      continue;
+    }
+    openSpan();
+    out.push(ch);
+  }
+  closeSpan();
+  return out.join("");
 }
 
 /**
@@ -548,6 +757,14 @@ export function renderReview(
   const render = opts.render ?? defaultRender;
   const ranges = splitBlocksWithRanges(currentText);
   const ops = diffBlocks(baselineText, currentText);
+  // #48: right after a PIN (baseline reason "pinned") with no changes since, the
+  // panel is fully clean: no change marks (already absent) AND no authorship
+  // coloring, so the pin reads as "this is my clean starting point". Skip
+  // colorByAuthor for every block in this case; data-src mapping and any pending
+  // proposals (review actions, not annotations) are kept below. A baseline advanced
+  // by a machine-landing (accept) is ALSO zero-diff but is NOT pinned — it keeps
+  // its authorship coloring (F10 INV-33), so this is gated on the pin specifically.
+  const clean = opts.pinned === true && ops.every((o) => o.kind === "unchanged");
 
   // Associate each resolved proposal with the current-side block index whose range
   // it anchors into: the largest block with start <= anchorStart (the containing
@@ -578,7 +795,7 @@ export function renderReview(
     const blockIndex = op.kind === "removed" ? -1 : ci;
     const blk = op.kind === "removed" ? undefined : ranges[ci++];
     const colored = (raw: string): string =>
-      blk ? colorByAuthor(raw, blk.start, authorSpans, render) : render(raw);
+      blk && !clean ? colorByAuthor(raw, blk.start, authorSpans, render) : render(raw);
     bodyParts.push(renderReviewOp(op, render, colored, srcAttr(blk)));
     const here = blockIndex >= 0 ? byBlock.get(blockIndex) : undefined;
     if (here) for (const p of here) bodyParts.push(proposalBlockHtml(p, render));

src/trackChangesPreview.ts

@@ -13,13 +13,18 @@ import * as vscode from "vscode";
 import type { DiffViewController } from "./diffViewController";
 import type { AttributionController } from "./attributionController";
 import type { ProposalController } from "./proposalController";
-import { renderReview, renderPlain, diffBlocks, diffToHunks, type BlockOp } from "./trackChangesModel";
+import { renderReview, renderPlain, diffBlocks, diffToBlockHunks, type BlockOp } from "./trackChangesModel";
 import { buildFingerprint } from "./anchorer";
 import { isAuthorable } from "./workspacePath";
-import type { EditTurnResult } from "./liveTurn";
+import type { EditTurnResult, RunEditTurnOptions } from "./liveTurn";
+import type { LiveProgressUi } from "./liveProgressUi";
 
-/** F11: a host edit turn (selection/document text + instruction → rewrite). Injectable for tests. */
-type EditTurn = (instruction: string, text: string) => Promise<EditTurnResult>;
+/**
+ * F11: a host edit turn (selection/document text + instruction → rewrite).
+ * Injectable for tests. #60: accepts optional turn options (onProgress/signal);
+ * the arg is optional so existing test stubs that ignore it stay valid.
+ */
+type EditTurn = (instruction: string, text: string, opts?: RunEditTurnOptions) => Promise<EditTurnResult>;
 /** F11: what an Ask-Claude gesture edits — a resolved selection range, or the whole document. */
 type EditTarget = { kind: "range"; start: number; end: number } | { kind: "document" };
 
@@ -37,7 +42,8 @@ type ToolbarMsg =
   | { type: "reject"; proposalId: string }
   | { type: "pinBaseline" }
   | { type: "askClaude"; scope: "document" }
-  | { type: "askClaude"; scope: "selection"; start: number; end: number };
+  | { type: "askClaude"; scope: "selection"; start: number; end: number }
+  | { type: "acceptAll" };
 
 export class TrackChangesPreviewController implements vscode.Disposable {
   private readonly disposables: vscode.Disposable[] = [];
@@ -52,9 +58,9 @@ export class TrackChangesPreviewController implements vscode.Disposable {
    * F11: the host edit turn (INV-8 — runs host-side, @cline/sdk loaded lazily and
    * never bundled). Injectable so host E2E can stub it (no LLM in CI).
    */
-  private editTurn: EditTurn = async (instruction, text) => {
+  private editTurn: EditTurn = async (instruction, text, opts) => {
     const { runEditTurn } = await import("./liveTurn");
-    return runEditTurn(instruction, text);
+    return runEditTurn(instruction, text, opts);
   };
   /** Monotonic per-session counter minting a stable turnId for each Ask-Claude gesture. */
   private turnSeq = 0;
@@ -67,6 +73,7 @@ export class TrackChangesPreviewController implements vscode.Disposable {
     private readonly extensionUri: vscode.Uri,
     private readonly attribution: AttributionController,
     private readonly proposals: ProposalController,
+    private readonly liveProgressUi: LiveProgressUi,
   ) {
     this.disposables.push(
       // F11 (SLICE-5): the editor/title gateway passes the tab's resource Uri;
@@ -82,10 +89,17 @@ export class TrackChangesPreviewController implements vscode.Disposable {
         }
         this.show(vscode.window.activeTextEditor?.document);
       }),
-      // F11: document-scoped Ask-Claude (also reused by #42's gateway). Edits the
-      // active markdown doc; the rewrite is diffed into per-hunk F4 proposals.
-      vscode.commands.registerCommand("cowriting.editDocument", () => {
-        const doc = vscode.window.activeTextEditor?.document;
+      // F11: document-scoped Ask-Claude (also reused by #42's reach gateways).
+      // Edits a markdown doc; the rewrite is diffed into F4 proposals.
+      // #42 (INV-38): the editor/title/context (tab) entry passes the clicked
+      // tab's resource Uri — target THAT document, opening it if it isn't already
+      // an open buffer (mirrors showTrackChangesPreview's #41 resolution); the
+      // palette / keybinding / editor/context pass nothing → the active editor.
+      vscode.commands.registerCommand("cowriting.editDocument", async (uri?: vscode.Uri) => {
+        const doc = uri
+          ? vscode.workspace.textDocuments.find((d) => d.uri.toString() === uri.toString()) ??
+            (await vscode.workspace.openTextDocument(uri))
+          : vscode.window.activeTextEditor?.document;
         if (!doc || !this.isMarkdown(doc)) {
           void vscode.window.showWarningMessage("Cowriting: open a Markdown document to ask Claude to edit it.");
           return;
@@ -183,9 +197,29 @@ export class TrackChangesPreviewController implements vscode.Disposable {
       const target: EditTarget =
         m.scope === "selection" ? { kind: "range", start: m.start, end: m.end } : { kind: "document" };
       void this.askClaude(document, target);
+    } else if (m?.type === "acceptAll") {
+      // #46 (INV-42): batch-accept every pending proposal on this doc, then report.
+      void this.acceptAll(document);
     }
   }
 
+  /**
+   * #46 (INV-42): apply every pending proposal on the document through the F4
+   * accept seam (orphan-skip) and report the applied-vs-skipped tally. No
+   * confirmation dialog — VS Code undo restores (parity with single accept).
+   * Public so the `cowriting.acceptAllProposals` command can reach it for the
+   * active doc (not only the webview button).
+   */
+  async acceptAll(document: vscode.TextDocument): Promise<void> {
+    const { applied, skipped } = await this.proposals.acceptAllProposals(document);
+    this.refresh(document);
+    if (applied === 0 && skipped === 0) return;
+    const skipNote = skipped > 0 ? `, ${skipped} skipped (target text changed — undo or reject)` : "";
+    void vscode.window.showInformationMessage(
+      `Cowriting: accepted ${applied} proposal${applied === 1 ? "" : "s"}${skipNote}.`,
+    );
+  }
+
   /**
    * F11 (PUC-3/4): prompt host-side for the instruction (keeps the LLM/secret
    * surface out of the sealed webview, INV-8/35), run the edit turn, and surface
@@ -202,8 +236,24 @@ export class TrackChangesPreviewController implements vscode.Disposable {
     if (!instruction) return;
     try {
       const ids = await vscode.window.withProgress(
-        { location: vscode.ProgressLocation.Notification, title: "Cowriting: asking Claude…" },
-        () => this.runEditAndPropose(document, target, instruction),
+        {
+          location: vscode.ProgressLocation.Notification,
+          title: "Cowriting: asking Claude…",
+          cancellable: true,
+        },
+        async (progress, token) => {
+          const ui = this.liveProgressUi.begin(instruction, progress, token);
+          try {
+            return await this.runEditAndPropose(document, target, instruction, {
+              onProgress: ui.onProgress,
+              signal: ui.signal,
+            });
+          } catch (err) {
+            // #60 (INV-47): a user cancel proposes nothing (the benign empty path).
+            if (token.isCancellationRequested) return [] as string[];
+            throw err;
+          }
+        },
       );
       if (ids.length === 0) {
         void vscode.window.showInformationMessage("Cowriting: Claude proposed no changes.");
@@ -219,16 +269,18 @@ export class TrackChangesPreviewController implements vscode.Disposable {
   }
 
   /**
-   * F11 (INV-35/37): run one host edit turn and record the result as F4
+   * F11/F12 (INV-35/39): run one host edit turn and record the result as F4
    * proposal(s) — a SELECTION yields one single-range proposal over the resolved
-   * block-union; a DOCUMENT rewrite is `diffToHunks`'d into one single-range
-   * proposal per changed hunk (reusing the F4 single-range model N times, no new
-   * model). Never mutates the document (INV-10). Returns the created proposal ids.
+   * block-union; a DOCUMENT rewrite is `diffToBlockHunks`'d into one proposal per
+   * changed BLOCK (#47, INV-39 supersedes INV-37's per-word cut), each tagged
+   * `granularity:"block"` so accept reconciles attribution per word (INV-40).
+   * Never mutates the document (INV-10). Returns the created proposal ids.
    */
   async runEditAndPropose(
     document: vscode.TextDocument,
     target: EditTarget,
     instruction: string,
+    opts?: RunEditTurnOptions,
   ): Promise<string[]> {
     const full = document.getText();
     // One turnId per gesture — the document case's N hunk-proposals all share it,
@@ -238,17 +290,25 @@ export class TrackChangesPreviewController implements vscode.Disposable {
       ({ kind: "agent" as const, id: "claude", agent: { sdk: "@cline/sdk", model: turn.model, sessionId: turn.sessionId } });
     if (target.kind === "range") {
       const selected = full.slice(target.start, target.end);
-      const turn = await this.editTurn(instruction, selected);
+      const turn = await this.editTurn(instruction, selected, opts);
       if (turn.replacement === "" || turn.replacement === selected) return [];
       const fp = buildFingerprint(full, { start: target.start, end: target.end });
       const id = await this.proposals.propose(document, fp, turn.replacement, provenance(turn), { turnId, instruction });
       return id ? [id] : [];
     }
-    const turn = await this.editTurn(instruction, full);
+    const turn = await this.editTurn(instruction, full, opts);
     const ids: string[] = [];
-    for (const h of diffToHunks(full, turn.replacement)) {
+    // #47 (INV-39, supersedes INV-37): a document rewrite is cut at BLOCK
+    // granularity — one proposal per changed block (the unit a human reviews) —
+    // not per word. Each is tagged `granularity:"block"` so accept reconciles
+    // attribution per word inside the block (INV-40).
+    for (const h of diffToBlockHunks(full, turn.replacement)) {
       const fp = buildFingerprint(full, { start: h.start, end: h.end });
-      const id = await this.proposals.propose(document, fp, h.replacement, provenance(turn), { turnId, instruction });
+      const id = await this.proposals.propose(document, fp, h.replacement, provenance(turn), {
+        turnId,
+        instruction,
+        granularity: "block",
+      });
       if (id) ids.push(id);
     }
     return ids;
@@ -300,7 +360,7 @@ export class TrackChangesPreviewController implements vscode.Disposable {
     void panel.webview.postMessage({
       type: "render",
       mode,
-      html: renderReview(baselineText, current, spans, proposals),
+      html: renderReview(baselineText, current, spans, proposals, { pinned: baseline?.reason === "pinned" }),
       epoch: this.epochLabel(baseline),
       summary,
       authorable,
@@ -376,6 +436,7 @@ export class TrackChangesPreviewController implements vscode.Disposable {
     <label id="cw-toggle"><input type="checkbox" id="cw-annotations" checked /> Annotations</label>
     <button id="cw-pin" type="button" title="Pin the review baseline to now (clears the change-marks)">⌖ Pin baseline</button>
     <button id="cw-ask" type="button" title="Ask Claude to edit (the selection if any, else the whole document)">✦ Ask Claude to Edit Document</button>
+    <button id="cw-acceptall" type="button" hidden title="Accept every pending Claude proposal on this document">✓✓ Accept all</button>
     <span id="cw-epoch">Review</span>
     <span id="cw-summary"></span>
     <span id="cw-legend"></span>
@@ -426,6 +487,7 @@ export class TrackChangesPreviewController implements vscode.Disposable {
       current,
       this.attribution.spansFor(doc),
       this.proposals.listProposals(doc),
+      { pinned: baseline?.reason === "pinned" },
     );
   }
   /** F10: current annotations mode for a panel (default on). */

src/turnProgress.ts

@@ -0,0 +1,122 @@
+/**
+ * turnProgress.ts — pure reduction of @cline/sdk Agent runtime events into a
+ * small UI-facing progress snapshot (#60, spec coauthoring-live-progress.md §3.2).
+ *
+ * INV-43: vscode-free. INV-46: a pure function — no vscode, no SDK runtime
+ * dependency (`AgentRuntimeEvent` is imported TYPE-only, so it is erased at
+ * compile and never pulls the ESM SDK into the bundle). All event→state logic
+ * lives here so it is unit-tested in isolation; the UI call sites only format and
+ * relay snapshots.
+ */
+import type { AgentRuntimeEvent } from "@cline/shared";
+
+export type TurnPhase = "thinking" | "writing" | "tool";
+
+export interface TurnProgressSnapshot {
+  phase: TurnPhase;
+  /** present iff phase === "tool" — the running tool's name. */
+  tool?: string;
+  /** accumulated assistant-text length so far. */
+  chars: number;
+  /** running total tokens (input+output); undefined until the first usage event. */
+  tokens?: number;
+  /** the new assistant-text chunk since the last snapshot (for the OutputChannel). */
+  textDelta?: string;
+}
+
+export interface TurnProgressState {
+  phase: TurnPhase;
+  chars: number;
+  tokens?: number;
+  /** stack of tool names currently running (depth-tracked for overlap). */
+  activeTools: string[];
+  /** true once any assistant text has streamed (tool-finish then reverts to writing). */
+  sawText: boolean;
+}
+
+export function createTurnProgressState(): TurnProgressState {
+  return { phase: "thinking", chars: 0, tokens: undefined, activeTools: [], sawText: false };
+}
+
+function restingPhase(state: TurnProgressState): TurnPhase {
+  if (state.activeTools.length) return "tool";
+  return state.sawText ? "writing" : "thinking";
+}
+
+function toSnapshot(state: TurnProgressState, textDelta?: string): TurnProgressSnapshot {
+  return {
+    phase: state.phase,
+    tool: state.phase === "tool" ? state.activeTools[state.activeTools.length - 1] : undefined,
+    chars: state.chars,
+    tokens: state.tokens,
+    textDelta,
+  };
+}
+
+/**
+ * Fold one SDK event into the state, returning the next state and the snapshot to
+ * emit (snapshot undefined for events that don't change the surface).
+ */
+export function reduceTurnProgress(
+  state: TurnProgressState,
+  event: AgentRuntimeEvent,
+): { state: TurnProgressState; snapshot?: TurnProgressSnapshot } {
+  switch (event.type) {
+    case "run-started":
+    case "turn-started": {
+      const next: TurnProgressState = { ...state, phase: restingPhase(state) };
+      return { state: next, snapshot: toSnapshot(next) };
+    }
+    case "assistant-text-delta": {
+      const next: TurnProgressState = {
+        ...state,
+        phase: state.activeTools.length ? "tool" : "writing",
+        chars: event.accumulatedText.length,
+        sawText: true,
+      };
+      return { state: next, snapshot: toSnapshot(next, event.text) };
+    }
+    case "assistant-reasoning-delta": {
+      // Reasoning TEXT is not surfaced (operator fork); collapse to motion only.
+      const next: TurnProgressState = { ...state, phase: state.activeTools.length ? "tool" : "thinking" };
+      return { state: next, snapshot: toSnapshot(next) };
+    }
+    case "tool-started": {
+      const activeTools = [...state.activeTools, event.toolCall.toolName];
+      const next: TurnProgressState = { ...state, phase: "tool", activeTools };
+      return { state: next, snapshot: toSnapshot(next) };
+    }
+    case "tool-updated": {
+      const next: TurnProgressState = { ...state, phase: "tool" };
+      return { state: next, snapshot: toSnapshot(next) };
+    }
+    case "tool-finished": {
+      const name = event.toolCall.toolName;
+      const idx = state.activeTools.lastIndexOf(name);
+      const activeTools = idx >= 0 ? state.activeTools.filter((_, i) => i !== idx) : state.activeTools.slice(0, -1);
+      const next: TurnProgressState = { ...state, activeTools, phase: "thinking" };
+      next.phase = restingPhase(next);
+      return { state: next, snapshot: toSnapshot(next) };
+    }
+    case "usage-updated": {
+      const tokens = event.usage.inputTokens + event.usage.outputTokens || undefined;
+      const next: TurnProgressState = { ...state, tokens };
+      return { state: next, snapshot: toSnapshot(next) };
+    }
+    default:
+      return { state };
+  }
+}
+
+/** Render the notification activity line from a snapshot (pure; spec §2.1). */
+export function formatProgressLine(s: TurnProgressSnapshot): string {
+  let head: string;
+  if (s.phase === "tool") head = `running ${s.tool ?? "tool"}…`;
+  else if (s.phase === "writing") head = `writing… (${s.chars} chars)`;
+  else head = "thinking…";
+  return s.tokens ? `${head} · ${formatTokens(s.tokens)} tokens` : head;
+}
+
+export function formatTokens(n: number): string {
+  return n >= 1000 ? `${(n / 1000).toFixed(1)}k` : String(n);
+}

test/e2e/suite/f11Toolbar.test.ts

@@ -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;

test/e2e/suite/f12Accept.test.ts

@@ -0,0 +1,128 @@
+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<{ 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() };
+}
+
+// #46 SLICE-3 (accept): one "Accept all" gesture applies every pending proposal
+// on the current document through the existing F4 accept seam (INV-42) — batched,
+// re-anchor-safe (descending), orphan-skip + report. Host E2E, no LLM.
+suite("F12 SLICE-3 — accept-all (#46, INV-42)", () => {
+  // PUC-6: N pending → all applied, text replaced, proposals cleared.
+  test("acceptAll applies every pending proposal and reconstructs the document", async () => {
+    const original = "# All\n\nFirst para alpha.\n\nSecond para beta.\n\nThird para gamma.\n";
+    const rewrite = "# All\n\nFirst para ALPHA.\n\nSecond para BETA.\n\nThird para GAMMA.\n";
+    const { doc, key } = await freshDoc("docs/f12-all.md", original);
+    const api = await getApi();
+    const ctl = api.trackChangesPreviewController;
+    await vscode.commands.executeCommand("cowriting.showTrackChangesPreview");
+    await settle();
+
+    ctl.setEditTurnForTest(async () => ({ replacement: rewrite, model: "sonnet", sessionId: "e2e-f12-all" }));
+    const ids = await ctl.runEditAndPropose(doc, { kind: "document" }, "uppercase the nouns");
+    await settle();
+    assert.strictEqual(ids.length, 3, "three changed blocks → three pending proposals");
+
+    // Simulate the toolbar "Accept all" button posting its intent.
+    ctl.receiveMessage(key, { type: "acceptAll" });
+    await settle();
+    await settle();
+
+    assert.strictEqual(doc.getText(), rewrite, "accept-all reconstructs the intended document");
+    assert.strictEqual(api.proposalController.listProposals(doc).length, 0, "all proposals cleared");
+  });
+
+  // PUC-6 / INV-42: an orphaned proposal is skipped (not force-applied) and the
+  // resolvable ones still apply — reported via the {applied, skipped} tally.
+  test("acceptAllProposals skips an orphaned proposal and applies the rest (report)", async () => {
+    const original = "# Mix\n\nKeep alpha here.\n\nKeep gamma here.\n";
+    const rewrite = "# Mix\n\nKeep ALPHA here.\n\nKeep GAMMA here.\n";
+    const { doc } = await freshDoc("docs/f12-orphan.md", original);
+    const api = await getApi();
+    const ctl = api.trackChangesPreviewController;
+    await vscode.commands.executeCommand("cowriting.showTrackChangesPreview");
+    await settle();
+
+    ctl.setEditTurnForTest(async () => ({ replacement: rewrite, model: "sonnet", sessionId: "e2e-f12-orphan" }));
+    const ids = await ctl.runEditAndPropose(doc, { kind: "document" }, "uppercase");
+    await settle();
+    assert.strictEqual(ids.length, 2, "two pending proposals");
+
+    // Orphan the FIRST block's proposal by mangling its target text in the buffer.
+    const para = "Keep alpha here.";
+    const start = doc.getText().indexOf(para);
+    const edit = new vscode.WorkspaceEdit();
+    edit.replace(
+      doc.uri,
+      new vscode.Range(doc.positionAt(start), doc.positionAt(start + para.length)),
+      "Totally different first paragraph now.",
+    );
+    assert.ok(await vscode.workspace.applyEdit(edit), "mangling edit applied");
+    await settle();
+
+    const { applied, skipped } = await api.proposalController.acceptAllProposals(doc);
+    assert.strictEqual(applied, 1, "the still-resolvable proposal applied");
+    assert.strictEqual(skipped, 1, "the orphaned proposal was skipped, not mangled");
+    assert.ok(doc.getText().includes("Keep GAMMA here."), "the resolvable block landed");
+    assert.ok(
+      doc.getText().includes("Totally different first paragraph now."),
+      "the orphaned block kept the operator's text (never force-applied)",
+    );
+    assert.strictEqual(api.proposalController.listProposals(doc).length, 1, "the orphaned proposal remains pending");
+  });
+
+  // A single pending proposal still applies through the batch path (the button is
+  // hidden < 2 pending in the webview, but the command/seam handle any count).
+  test("acceptAllProposals with one pending proposal applies it", async () => {
+    const { doc } = await freshDoc("docs/f12-one.md", "# One\n\nThe only paragraph here.\n");
+    const api = await getApi();
+    const ctl = api.trackChangesPreviewController;
+    await vscode.commands.executeCommand("cowriting.showTrackChangesPreview");
+    await settle();
+    ctl.setEditTurnForTest(async () => ({
+      replacement: "# One\n\nThe ONLY paragraph here.\n",
+      model: "sonnet",
+      sessionId: "e2e-f12-one",
+    }));
+    const ids = await ctl.runEditAndPropose(doc, { kind: "document" }, "uppercase only");
+    await settle();
+    assert.strictEqual(ids.length, 1, "one pending proposal");
+    const { applied, skipped } = await api.proposalController.acceptAllProposals(doc);
+    assert.strictEqual(applied, 1);
+    assert.strictEqual(skipped, 0);
+    assert.strictEqual(doc.getText(), "# One\n\nThe ONLY paragraph here.\n");
+  });
+
+  // The command is registered + palette-guarded on markdown.
+  test("cowriting.acceptAllProposals is registered and palette-guarded on markdown", async () => {
+    const all = await vscode.commands.getCommands(true);
+    assert.ok(all.includes("cowriting.acceptAllProposals"), "command registered");
+    const pkg = JSON.parse(fs.readFileSync(path.join(__dirname, "../../../../package.json"), "utf8"));
+    const entry = (pkg.contributes.menus.commandPalette as Array<{ command: string; when?: string }>).find(
+      (m) => m.command === "cowriting.acceptAllProposals",
+    );
+    assert.ok(entry, "has a commandPalette entry");
+    assert.match(entry!.when ?? "", /editorLangId == markdown/, "guarded on markdown");
+  });
+});

test/e2e/suite/f12Reach.test.ts

@@ -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, "exports preview controller");
+  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);
+  return { doc, key: uri.toString() };
+}
+
+function pkg(): any {
+  return JSON.parse(fs.readFileSync(path.join(__dirname, "../../../../package.json"), "utf8"));
+}
+function menu(id: string): Array<{ command: string; when?: string; group?: string }> {
+  return pkg().contributes.menus[id] ?? [];
+}
+
+// SLICE-1 / #42 (reach): "Ask Claude to Edit" reachable from the editor BODY and
+// the editor TAB, selection-aware (selection → editSelection; no selection →
+// editDocument), both markdown/authorable-gated, both routing through the single
+// runEditAndPropose path (INV-38). The menu `when` clauses are declarative, so we
+// assert them directly; the tab-targeting behavior is exercised through the command.
+suite("F12 SLICE-1 — Ask-Claude reach (#42, INV-38)", () => {
+  // PUC-1/2: editor BODY (editor/context) is selection-aware + markdown-gated.
+  test("editor/context offers editSelection (with selection) and editDocument (without), markdown+authorable", () => {
+    const m = menu("editor/context");
+    const sel = m.find((e) => e.command === "cowriting.editSelection");
+    const doc = m.find((e) => e.command === "cowriting.editDocument");
+    assert.ok(sel, "editSelection is in editor/context");
+    assert.ok(doc, "editDocument is in editor/context");
+
+    assert.match(sel!.when ?? "", /editorHasSelection/, "editSelection shows only with a selection");
+    assert.ok(!/!\s*editorHasSelection/.test(sel!.when ?? ""), "editSelection is not gated on NO selection");
+    assert.match(sel!.when ?? "", /editorLangId == markdown/, "editSelection gated on markdown");
+    assert.match(sel!.when ?? "", /resourceScheme == file|resourceScheme == untitled/, "editSelection gated authorable");
+
+    assert.match(doc!.when ?? "", /!\s*editorHasSelection/, "editDocument shows only without a selection");
+    assert.match(doc!.when ?? "", /editorLangId == markdown/, "editDocument gated on markdown");
+    assert.match(doc!.when ?? "", /resourceScheme == file|resourceScheme == untitled/, "editDocument gated authorable");
+  });
+
+  // PUC-3: editor TAB (editor/title/context) carries the same selection-aware pair.
+  test("editor/title/context offers editSelection (with selection) and editDocument (without), markdown-gated", () => {
+    const m = menu("editor/title/context");
+    const sel = m.find((e) => e.command === "cowriting.editSelection");
+    const doc = m.find((e) => e.command === "cowriting.editDocument");
+    assert.ok(sel, "editSelection is in editor/title/context");
+    assert.ok(doc, "editDocument is in editor/title/context");
+
+    assert.match(sel!.when ?? "", /editorHasSelection/, "tab editSelection shows only with a selection");
+    assert.ok(!/!\s*editorHasSelection/.test(sel!.when ?? ""), "tab editSelection is not gated on NO selection");
+    assert.match(sel!.when ?? "", /resourceLangId == markdown/, "tab editSelection gated on markdown");
+
+    assert.match(doc!.when ?? "", /!\s*editorHasSelection/, "tab editDocument shows only without a selection");
+    assert.match(doc!.when ?? "", /resourceLangId == markdown/, "tab editDocument gated on markdown");
+  });
+
+  // PUC-3 behavior: editDocument invoked with a tab URI targets THAT document,
+  // not whatever editor happens to be active (mirrors #41's clicked-doc resolution).
+  test("editDocument(uri) targets the clicked tab's document, not the active editor", async () => {
+    const api = await getApi();
+    const ctl = api.trackChangesPreviewController;
+
+    // Doc A is the active editor; Doc B is the "clicked tab" we pass by URI.
+    const a = await freshDoc("docs/f12-active.md", "# Active\n\nThe active editor paragraph.\n");
+    const b = await freshDoc("docs/f12-tab.md", "# Tab\n\nThe tab target paragraph to rewrite.\n");
+    await vscode.window.showTextDocument(a.doc);
+    await settle();
+
+    // Stub the instruction prompt (sealed input box can't run in CI) + the LLM turn.
+    const origInput = vscode.window.showInputBox;
+    (vscode.window as any).showInputBox = async () => "rewrite it";
+    ctl.setEditTurnForTest(async () => ({
+      replacement: "# Tab\n\nThe REWRITTEN tab paragraph.\n",
+      model: "sonnet",
+      sessionId: "e2e-f12-tab",
+    }));
+    try {
+      await vscode.commands.executeCommand("cowriting.editDocument", b.doc.uri);
+      await settle();
+    } finally {
+      (vscode.window as any).showInputBox = origInput;
+    }
+
+    // The proposal(s) landed on the TAB doc (B), and the ACTIVE doc (A) has none.
+    assert.ok(api.proposalController.listProposals(b.doc).length >= 1, "tab doc B received the document-edit proposal(s)");
+    assert.strictEqual(
+      api.proposalController.listProposals(a.doc).length,
+      0,
+      "active doc A was NOT edited — editDocument honored the tab URI",
+    );
+    // INV-10: proposing never mutates the document.
+    assert.ok(b.doc.getText().includes("tab target paragraph"), "tab doc unchanged by propose");
+  });
+
+  // No URI arg (palette / keybinding) → fall back to the active editor.
+  test("editDocument() with no arg targets the active editor", async () => {
+    const api = await getApi();
+    const ctl = api.trackChangesPreviewController;
+    const a = await freshDoc("docs/f12-noarg.md", "# No arg\n\nThe active doc paragraph here.\n");
+    await vscode.window.showTextDocument(a.doc);
+    await settle();
+
+    const origInput = vscode.window.showInputBox;
+    (vscode.window as any).showInputBox = async () => "rewrite it";
+    ctl.setEditTurnForTest(async () => ({
+      replacement: "# No arg\n\nThe REWRITTEN active doc paragraph.\n",
+      model: "sonnet",
+      sessionId: "e2e-f12-noarg",
+    }));
+    try {
+      await vscode.commands.executeCommand("cowriting.editDocument");
+      await settle();
+    } finally {
+      (vscode.window as any).showInputBox = origInput;
+    }
+    assert.ok(api.proposalController.listProposals(a.doc).length >= 1, "active doc received the proposal(s) on no-arg");
+  });
+});

test/e2e/suite/f12Review.test.ts

@@ -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");
+  });
+});

test/e2e/suite/liveProgress.test.ts

@@ -0,0 +1,83 @@
+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, "exports preview controller");
+  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;
+}
+
+// #60 host E2E (no LLM): live progress is purely additive observability. The
+// harness can't read notification subtitles, so it asserts the CONTRACT —
+// progress events don't change the proposals (INV-44), and an aborted turn
+// proposes nothing (INV-47). The live notification/OutputChannel UI itself is
+// covered by the turnProgress unit tests + the manual smoke.
+suite("#60 live turn progress (additive + cancel)", () => {
+  test("a stub that emits progress still produces the same proposals (INV-44)", async () => {
+    const doc = await freshDoc("docs/live60-additive.md", "# Title\n\nOld paragraph.\n");
+    const api = await getApi();
+    const ctl = api.trackChangesPreviewController;
+    await vscode.commands.executeCommand("cowriting.showTrackChangesPreview");
+    await settle();
+
+    // The stub honors opts.onProgress (emitting synthetic snapshots) but returns
+    // the same rewrite — proposals must be unaffected by progress events.
+    ctl.setEditTurnForTest(async (_i, _text, opts) => {
+      opts?.onProgress?.({ phase: "writing", chars: 5 });
+      opts?.onProgress?.({ phase: "writing", chars: 13, tokens: 1234, textDelta: "New paragraph." });
+      return { replacement: "# Title\n\nNew paragraph.\n", model: "sonnet", sessionId: "e2e-live60" };
+    });
+
+    const ids = await ctl.runEditAndPropose(doc, { kind: "document" }, "rewrite the paragraph");
+    await settle();
+    assert.strictEqual(ids.length, 1, "one changed block → one proposal, regardless of progress events");
+    const view = api.proposalController.listProposals(doc).find((v) => v.id === ids[0]);
+    assert.ok(view, "the proposal is live");
+    assert.ok(doc.getText().includes("Old paragraph."), "document unchanged by propose (INV-10)");
+  });
+
+  test("an aborted turn proposes nothing (INV-47)", async () => {
+    const doc = await freshDoc("docs/live60-cancel.md", "# Title\n\nOld paragraph.\n");
+    const api = await getApi();
+    const ctl = api.trackChangesPreviewController;
+    await vscode.commands.executeCommand("cowriting.showTrackChangesPreview");
+    await settle();
+
+    // The stub throws ONLY when the aborted signal reached it — so if opts.signal
+    // failed to thread through runEditAndPropose, the stub would instead return a
+    // rewrite and create a proposal, failing this test. That proves propagation.
+    ctl.setEditTurnForTest(async (_i, _text, opts) => {
+      if (opts?.signal?.aborted) throw new Error("claude-code turn aborted");
+      return { replacement: "# Title\n\nSHOULD NOT BE PROPOSED.\n", model: "sonnet", sessionId: "e2e-live60-nope" };
+    });
+
+    const ac = new AbortController();
+    ac.abort();
+    let ids: string[] = [];
+    try {
+      ids = await ctl.runEditAndPropose(doc, { kind: "document" }, "rewrite", { signal: ac.signal });
+    } catch {
+      ids = [];
+    }
+    await settle();
+    assert.strictEqual(ids.length, 0, "aborted turn must create no proposals");
+    assert.strictEqual(api.proposalController.listProposals(doc).length, 0, "no pending proposals after abort");
+  });
+});

test/e2e/suite/s48PinClean.test.ts

@@ -0,0 +1,63 @@
+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, "exports preview controller");
+  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() };
+}
+
+// #48 host E2E (no LLM): pinning the baseline leaves the review panel fully clean
+// — no authorship coloring on unchanged blocks — while re-divergence brings the
+// annotations back. The author colors are read from the on-state renderReview HTML.
+suite("S48 — pin → fully clean review panel (host E2E, no LLM)", () => {
+  test("pin clears authorship coloring; a later edit brings annotations back", async () => {
+    const { doc, key } = await freshDoc("docs/s48pin.md", "# S48\n\nAn original baseline paragraph.\n");
+    const api = await getApi();
+    const ctl = api.trackChangesPreviewController;
+    await vscode.commands.executeCommand("cowriting.showTrackChangesPreview");
+    await settle();
+
+    // Type a paragraph → a human attribution span + author coloring in the on-state.
+    const edit = new vscode.WorkspaceEdit();
+    edit.insert(doc.uri, doc.positionAt(doc.getText().length), "\n\nA freshly typed human paragraph.\n");
+    assert.ok(await vscode.workspace.applyEdit(edit), "operator edit applied");
+    await settle();
+    assert.match(ctl.renderHtmlFor(key), /cw-by-human/, "typed text is author-colored before the pin");
+
+    // Pin the baseline → zero diff → the panel must be fully clean.
+    ctl.receiveMessage(key, { type: "pinBaseline" });
+    await settle();
+    const pinned = ctl.renderHtmlFor(key);
+    assert.ok(!pinned.includes("cw-by-human"), "no human authorship coloring after pin");
+    assert.ok(!pinned.includes("cw-by-claude"), "no Claude authorship coloring after pin");
+    assert.ok(!pinned.includes("cw-add") && !pinned.includes("cw-del"), "no change marks after pin");
+    assert.match(pinned, /data-src-start/, "blocks still carry data-src offsets (INV-36 mapping kept)");
+    assert.ok(pinned.includes("freshly typed human paragraph"), "the body text is still rendered, just plain");
+
+    // Edit again → there are changes since the pinned baseline → annotations return.
+    const edit2 = new vscode.WorkspaceEdit();
+    edit2.insert(doc.uri, doc.positionAt(doc.getText().length), "\n\nA second typed paragraph diverges again.\n");
+    assert.ok(await vscode.workspace.applyEdit(edit2), "second operator edit applied");
+    await settle();
+    assert.match(ctl.renderHtmlFor(key), /cw-by-human/, "authorship coloring returns once the doc diverges from the pin");
+  });
+});

test/e2e/suite/undoCapable.ts

@@ -0,0 +1,41 @@
+import * as fs from "fs";
+import * as path from "path";
+import * as vscode from "vscode";
+
+/**
+ * #54: `vscode.commands.executeCommand("undo")` is non-functional in some headless
+ * `.vscode-test` instances (it does not restore the buffer), which false-fails
+ * every undo-dependent E2E (#38, #40) and makes `main` E2E red there. This is a
+ * RUNTIME probe: it performs a real edit-then-undo on a scratch buffer and reports
+ * whether undo actually restored it. Undo-dependent suites gate on it — running
+ * normally where undo works (real coverage), skipping with a loud warning where it
+ * doesn't (no false red, no silent loss — the skip is logged). Memoized per run.
+ */
+let cached: boolean | undefined;
+
+export async function undoWorks(): Promise<boolean> {
+  if (cached !== undefined) return cached;
+  const abs = path.join(process.env.E2E_WORKSPACE!, "docs/.undo-probe.md");
+  fs.mkdirSync(path.dirname(abs), { recursive: true });
+  fs.writeFileSync(abs, "undo probe baseline\n", "utf8");
+  const doc = await vscode.workspace.openTextDocument(vscode.Uri.file(abs));
+  await vscode.window.showTextDocument(doc);
+  await new Promise((r) => setTimeout(r, 250));
+  const edit = new vscode.WorkspaceEdit();
+  edit.insert(doc.uri, doc.positionAt(doc.getText().length), "PROBE-EDIT-MARKER");
+  await vscode.workspace.applyEdit(edit);
+  await new Promise((r) => setTimeout(r, 250));
+  if (!doc.getText().includes("PROBE-EDIT-MARKER")) {
+    cached = false; // even the edit didn't take — treat as not undo-capable
+    return cached;
+  }
+  await vscode.commands.executeCommand("undo");
+  await new Promise((r) => setTimeout(r, 250));
+  cached = !doc.getText().includes("PROBE-EDIT-MARKER"); // undo removed the marker → undo works
+  return cached;
+}
+
+/** Loud, single-line reason logged when an undo suite skips (no silent loss — #54). */
+export const UNDO_SKIP_REASON =
+  "[E2E] SKIPPING undo-dependent suite — executeCommand('undo') is non-functional in this " +
+  "VS Code test instance (see vscode-cowriting-plugin#54). These tests run where undo works.";

test/e2e/suite/undoMarks.test.ts

@@ -3,6 +3,7 @@ import * as fs from "fs";
 import * as path from "path";
 import * as vscode from "vscode";
 import type { CowritingApi } from "../../../src/extension";
+import { undoWorks, UNDO_SKIP_REASON } from "./undoCapable";
 
 const WS = process.env.E2E_WORKSPACE!;
 const settle = () => new Promise((r) => setTimeout(r, 400));
@@ -34,6 +35,14 @@ suite("F10 #38 — undo does not mis-attribute restored text (host E2E, no LLM)"
   const DOC_REL = "docs/undo38.md";
   const BASE = "Alpha bravo charlie.\n";
 
+  // #54: skip (loudly) where executeCommand("undo") is non-functional; run where it works.
+  suiteSetup(async function () {
+    if (!(await undoWorks())) {
+      console.warn(UNDO_SKIP_REASON);
+      this.skip();
+    }
+  });
+
   test("undo of a deletion of baseline text leaves it unattributed (not human)", async () => {
     const { doc, key } = await freshDoc(DOC_REL, BASE);
     const api = await getApi();

test/liveTurn.test.ts

@@ -1,5 +1,32 @@
-import { describe, it, expect } from "vitest";
-import { extractReplacement } from "../src/liveTurn";
+import { describe, it, expect, vi } from "vitest";
+import { extractReplacement, runEditTurn } from "../src/liveTurn";
+
+// A fake Agent that replays a scripted event list to subscribers, supports abort,
+// and resolves agent.run() with a completed (or aborted) result.
+const runs = { count: 0 };
+function fakeSdk(events: any[]) {
+  return {
+    Agent: class {
+      private listeners: ((e: any) => void)[] = [];
+      constructor(_cfg: unknown) {}
+      subscribe(fn: (e: any) => void) {
+        this.listeners.push(fn);
+        return () => {
+          this.listeners = this.listeners.filter((l) => l !== fn);
+        };
+      }
+      // The real SDK's abort() is a no-op before run() creates its AbortController,
+      // so this fake does NOT cooperate with a pre-abort — proving runEditTurn's own
+      // short-circuit, not the fake's leniency.
+      abort() {}
+      async run(_input: string) {
+        runs.count += 1;
+        for (const e of events) for (const l of this.listeners) l(e);
+        return { status: "completed", outputText: "EDITED", runId: "r1" };
+      }
+    },
+  };
+}
 
 describe("extractReplacement", () => {
   it("returns plain text untouched", () => {
@@ -24,3 +51,33 @@ describe("extractReplacement", () => {
     expect(extractReplacement("```\nplain\n```", "plain old text")).toBe("plain");
   });
 });
+
+describe("runEditTurn progress + cancel", () => {
+  it("emits progress snapshots and returns the replacement unchanged (INV-44)", async () => {
+    vi.resetModules();
+    vi.doMock("@cline/sdk", () =>
+      fakeSdk([
+        { type: "assistant-text-delta", text: "ED", accumulatedText: "ED" },
+        { type: "usage-updated", usage: { inputTokens: 10, outputTokens: 5, cacheReadTokens: 0, cacheWriteTokens: 0 } },
+      ]),
+    );
+    const seen: string[] = [];
+    const turn = await runEditTurn("do it", "old", { onProgress: (s) => seen.push(s.phase) });
+    expect(turn.replacement).toBe("EDITED");
+    expect(seen).toContain("writing");
+    vi.doUnmock("@cline/sdk");
+    vi.resetModules();
+  });
+
+  it("a pre-aborted AbortSignal short-circuits before run() and throws (INV-47)", async () => {
+    vi.resetModules();
+    vi.doMock("@cline/sdk", () => fakeSdk([]));
+    runs.count = 0;
+    const ac = new AbortController();
+    ac.abort();
+    await expect(runEditTurn("do it", "old", { signal: ac.signal })).rejects.toThrow(/aborted/);
+    expect(runs.count).toBe(0); // the turn never ran — no proposal could be produced
+    vi.doUnmock("@cline/sdk");
+    vi.resetModules();
+  });
+});

test/trackChangesModel.test.ts

@@ -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", () => {
@@ -168,6 +168,45 @@ describe("colorByAuthor", () => {
     expect(html).toContain('<span class="cw-by-human">hello</span>');
     expect(html).toContain("world");
   });
+
+  // #33: author-coloring must be sentinel-safe around markdown emphasis. These
+  // exercise the REAL markdown-it renderer (via renderReview on an unchanged doc),
+  // since the failure is in markdown-it's inline parsing / element nesting.
+  // CASE1 — a span boundary strictly inside a delimiter run must not split it.
+  test("#33 CASE1: a span boundary inside ** does not break emphasis parsing", () => {
+    const doc = "a**b**c";
+    const html = renderReview(doc, doc, [{ start: 0, end: 2, author: "human" }], []);
+    expect(html).toContain("<strong>b</strong>"); // emphasis still renders
+    expect(html).not.toContain("**"); // no raw delimiters left
+    expect(html).not.toContain("<em></em>"); // no stray empty emphasis (the parse-break symptom)
+    expect(html).toContain('class="cw-by-human"'); // coloring present
+  });
+  // CASE3 — a span boundary inside an emphasis run must color the text without
+  // misnesting span/element (the span is split at the element boundary).
+  test("#33 CASE3: a span boundary inside **bold** colors the text without misnesting", () => {
+    const doc = "**bold**";
+    const html = renderReview(doc, doc, [{ start: 0, end: 4, author: "human" }], []); // covers "**bo"
+    expect(html).toContain("<strong>");
+    expect(html).toContain('<span class="cw-by-human">bo</span>ld</strong>'); // span INSIDE strong, closed before "ld"
+    expect(html).not.toContain('cw-by-human"><strong>'); // NOT the old misnest (span wrapping the <strong> open)
+  });
+  // CASE2 — a span covering a whole emphasis run stays correct (regression).
+  test("#33 CASE2: a span over the whole **bold** colors it correctly", () => {
+    const doc = "**bold**";
+    const html = renderReview(doc, doc, [{ start: 0, end: 8, author: "human" }], []);
+    expect(html).toContain("<strong>");
+    expect((html.match(/cw-by-human/g) ?? []).length).toBe(1);
+    expect(html).toContain("bold");
+  });
+  test("#33: no Private-Use-Area sentinel chars leak into the rendered output", () => {
+    const doc = "a**b**c and `co de` and _x_";
+    const spans: AuthorSpan[] = [
+      { start: 0, end: 2, author: "human" },
+      { start: 12, end: 16, author: "claude" },
+    ];
+    const html = renderReview(doc, doc, spans, []);
+    expect(html).not.toMatch(/[\uE000-\uF8FF]/); // no leftover BMP Private-Use-Area sentinels
+  });
 });
 
 import { renderPlain } from "../src/trackChangesModel";
@@ -277,6 +316,54 @@ describe("renderReview", () => {
     expect(uIdx).toBeGreaterThan(html.indexOf("Beta there")); // unanchored still trails the body
     expect(html).toContain("cw-proposal-unanchored");
   });
+  // #48: a PINNED baseline with zero changes leaves the panel fully un-annotated —
+  // no authorship coloring on unchanged blocks — while pending proposals still show.
+  test("renderReview: pinned + zero diff with author spans renders NO authorship coloring", () => {
+    const doc = "Human wrote this.\n\nClaude wrote that.";
+    const spans: AuthorSpan[] = [
+      { start: 0, end: 17, author: "human" },
+      { start: 19, end: doc.length, author: "claude" },
+    ];
+    const html = renderReview(doc, doc, spans, [], { pinned: true });
+    expect(html).not.toContain("cw-by-human");
+    expect(html).not.toContain("cw-by-claude");
+    expect(html).not.toContain("cw-add");
+    expect(html).not.toContain("cw-del");
+    // still a selection→source surface (INV-36): blocks carry data-src offsets.
+    expect(html).toContain("data-src-start");
+    // the body text is still there, just plain.
+    expect(html).toContain("Human wrote this.");
+    expect(html).toContain("Claude wrote that.");
+  });
+  test("renderReview: pinned + zero diff still renders a pending proposal block", () => {
+    const doc = "Human wrote this.\n\nClaude wrote that.";
+    const spans: AuthorSpan[] = [{ start: 0, end: 17, author: "human" }];
+    const proposals: ProposalView[] = [
+      { id: "p1", anchorStart: 0, anchorEnd: 5, replaced: "Human", replacement: "Person" },
+    ];
+    const html = renderReview(doc, doc, spans, proposals, { pinned: true });
+    expect(html).not.toContain("cw-by-human"); // body still clean
+    expect(html).toContain('data-proposal-id="p1"'); // proposal still shows (it is an action)
+    expect(html).toContain("Person");
+  });
+  test("renderReview: zero diff WITHOUT a pin (e.g. machine-landing) keeps authorship coloring (INV-33)", () => {
+    // accepting a Claude edit advances the baseline (zero diff) but is NOT a pin —
+    // the landed author coloring must remain.
+    const doc = "Human wrote this.\n\nClaude wrote that.";
+    const spans: AuthorSpan[] = [{ start: 19, end: doc.length, author: "claude" }];
+    const html = renderReview(doc, doc, spans, []); // no pinned flag
+    expect(html).toContain("cw-by-claude");
+  });
+  test("renderReview: with REAL changes since a pin, author coloring returns", () => {
+    // a genuine added block is still author-colored even when pinned (only the
+    // zero-diff-after-pin state is clean).
+    const baseline = "Hello world";
+    const current = "Hello world\n\nHello world";
+    const spans: AuthorSpan[] = [{ start: 19, end: 24, author: "human" }];
+    const html = renderReview(baseline, current, spans, [], { pinned: true });
+    expect((html.match(/cw-by-human/g) ?? []).length).toBe(1);
+  });
+
   test("renderReview is deterministic with mixed anchored/unanchored proposals", () => {
     const doc = "one two three";
     const proposals: ProposalView[] = [
@@ -402,6 +489,90 @@ 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

test/turnProgress.test.ts

@@ -0,0 +1,102 @@
+import { describe, it, expect } from "vitest";
+import {
+  createTurnProgressState,
+  reduceTurnProgress,
+  formatProgressLine,
+  formatTokens,
+  type TurnProgressSnapshot,
+} from "../src/turnProgress";
+
+// Minimal event factories — structurally match the @cline/sdk AgentRuntimeEvent
+// members the reducer reads. `as any` because we only supply the fields used.
+const ev = (e: any) => e as any;
+const textDelta = (text: string, accumulatedText: string) =>
+  ev({ type: "assistant-text-delta", text, accumulatedText });
+const toolStarted = (toolName: string) => ev({ type: "tool-started", toolCall: { toolName } });
+const toolFinished = (toolName: string) => ev({ type: "tool-finished", toolCall: { toolName } });
+const usage = (inputTokens: number, outputTokens: number) =>
+  ev({ type: "usage-updated", usage: { inputTokens, outputTokens, cacheReadTokens: 0, cacheWriteTokens: 0 } });
+
+// Drive a sequence of events, returning every emitted snapshot.
+function run(events: any[]): TurnProgressSnapshot[] {
+  let state = createTurnProgressState();
+  const out: TurnProgressSnapshot[] = [];
+  for (const e of events) {
+    const r = reduceTurnProgress(state, e);
+    state = r.state;
+    if (r.snapshot) out.push(r.snapshot);
+  }
+  return out;
+}
+
+describe("reduceTurnProgress", () => {
+  it("starts in thinking", () => {
+    const s = run([ev({ type: "run-started" })]);
+    expect(s.at(-1)!.phase).toBe("thinking");
+    expect(s.at(-1)!.chars).toBe(0);
+    expect(s.at(-1)!.tokens).toBeUndefined();
+  });
+
+  it("text deltas move to writing and accumulate chars + carry the delta", () => {
+    const s = run([textDelta("Hel", "Hel"), textDelta("lo", "Hello")]);
+    expect(s.map((x) => x.phase)).toEqual(["writing", "writing"]);
+    expect(s.at(-1)!.chars).toBe(5);
+    expect(s.map((x) => x.textDelta)).toEqual(["Hel", "lo"]);
+  });
+
+  it("usage sets a running token total (input+output)", () => {
+    const s = run([textDelta("Hi", "Hi"), usage(1000, 234)]);
+    expect(s.at(-1)!.tokens).toBe(1234);
+  });
+
+  it("tool start shows the tool name; tool finish reverts to writing once text was seen", () => {
+    const s = run([textDelta("x", "x"), toolStarted("read_file"), toolFinished("read_file")]);
+    expect(s[1].phase).toBe("tool");
+    expect(s[1].tool).toBe("read_file");
+    expect(s.at(-1)!.phase).toBe("writing");
+  });
+
+  it("tool finish reverts to thinking when no text was seen", () => {
+    const s = run([toolStarted("grep"), toolFinished("grep")]);
+    expect(s.at(-1)!.phase).toBe("thinking");
+  });
+
+  it("overlapping tools resolve in order", () => {
+    const s = run([toolStarted("a"), toolStarted("b"), toolFinished("b"), toolFinished("a")]);
+    expect(s.map((x) => x.phase)).toEqual(["tool", "tool", "tool", "thinking"]);
+    expect(s[1].tool).toBe("b");
+    expect(s[2].tool).toBe("a");
+  });
+
+  it("reasoning deltas stay thinking and surface no text", () => {
+    const s = run([ev({ type: "assistant-reasoning-delta", text: "secret", accumulatedText: "secret" })]);
+    expect(s.at(-1)!.phase).toBe("thinking");
+    expect(s.at(-1)!.textDelta).toBeUndefined();
+  });
+
+  it("ignores lifecycle/finish events (no snapshot)", () => {
+    const s = run([ev({ type: "turn-finished" }), ev({ type: "run-finished" })]);
+    expect(s).toEqual([]);
+  });
+});
+
+describe("formatProgressLine / formatTokens", () => {
+  it("thinking", () => {
+    expect(formatProgressLine({ phase: "thinking", chars: 0 })).toBe("thinking…");
+  });
+  it("writing with chars", () => {
+    expect(formatProgressLine({ phase: "writing", chars: 412 })).toBe("writing… (412 chars)");
+  });
+  it("writing with chars + tokens", () => {
+    expect(formatProgressLine({ phase: "writing", chars: 412, tokens: 1234 })).toBe(
+      "writing… (412 chars) · 1.2k tokens",
+    );
+  });
+  it("tool with name", () => {
+    expect(formatProgressLine({ phase: "tool", tool: "read_file", chars: 0 })).toBe("running read_file…");
+  });
+  it("formats token magnitudes", () => {
+    expect(formatTokens(950)).toBe("950");
+    expect(formatTokens(1234)).toBe("1.2k");
+  });
+});