feat: write/edit robustness — fuzzy patch applier + worktree checkpoints (v2.7.1)

#3 Fuzzy patch applier: new pure fuzzy-match.ts (locateMatch, exact→trim→ unicode-canon→Levenshtein≥0.66, refuse-on-ambiguous) wired into pending_changes applyOne/rewindOne so local-model whitespace/unicode drift in old_string no longer loses the edit. #4 Worktree checkpoint + conversation-trim: checkpoints table + checkpoints.ts (shadow-commit of tracked+untracked into refs/boocode/checkpoints, hooked into the 3 external-agent dispatcher paths) + POST restore route (reset --hard + clean -fd -> transcript trim -> backend-session reset) + "Restore to here" UI. Built by 3 parallel agents; DB-integration testing caught a created_at self-deletion bug. Coder suite 234 passing; server+coder build + web tsc clean. Builds on v2.7.0-mit. openspec write-edit-robustness. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-01 12:01:57 +00:00
parent 1108d07fb2
commit 59f07e8cb8
15 changed files with 1443 additions and 11 deletions
--- a/apps/coder/src/index.ts
+++ b/apps/coder/src/index.ts
@@ -25,6 +25,7 @@ import { setInferenceContext, clearInferenceContext } from './services/tools/inf
 import { registerMessageRoutes } from './routes/messages.js';
 import { registerSkillRoutes } from './routes/skills.js';
 import { registerPendingRoutes } from './routes/pending.js';
+import { registerCheckpointRoutes } from './routes/checkpoints.js';
 import { registerAgentSessionRoutes } from './routes/agent-sessions.js';
 import { registerTaskRoutes } from './routes/tasks.js';
 import { registerInboxRoutes } from './routes/inbox.js';
@@ -214,6 +215,7 @@ async function main() {
  registerMessageRoutes(app, sql, broker, inferenceApi);
  registerSkillRoutes(app, sql, broker, inferenceApi);
  registerPendingRoutes(app, sql);
+  registerCheckpointRoutes(app, sql);
  registerAgentSessionRoutes(app, sql);
  registerTaskRoutes(app, sql, inferenceApi);
  registerInboxRoutes(app, sql);
--- a/apps/coder/src/routes/checkpoints.ts
+++ b/apps/coder/src/routes/checkpoints.ts
@@ -0,0 +1,67 @@
+/**
+ * write-edit-robustness #4 — checkpoint restore + list routes (coder side).
+ *
+ * Proxied through the apps/server `/api/coder/*` blanket forwarder (no server-side
+ * change needed for new routes). Restore rewinds the session worktree to the
+ * checkpoint's shadow commit, trims the transcript from the anchor message forward,
+ * and resets the agent backend — see services/checkpoints.ts.
+ */
+import type { FastifyInstance } from 'fastify';
+import type { Sql } from '../db.js';
+import { restoreCheckpoint, CheckpointNotFoundError } from '../services/checkpoints.js';
+
+export function registerCheckpointRoutes(app: FastifyInstance, sql: Sql): void {
+  // GET /api/sessions/:sessionId/checkpoints?chat_id= — list a chat's checkpoints
+  // so the frontend can mark which messages have a restore point. When chat_id is
+  // omitted, returns every checkpoint for the session's chats.
+  app.get<{ Params: { sessionId: string }; Querystring: { chat_id?: string } }>(
+    '/api/sessions/:sessionId/checkpoints',
+    async (req, reply) => {
+      const sessionId = req.params.sessionId;
+      const chatId = req.query.chat_id;
+
+      const session = await sql<{ id: string }[]>`SELECT id FROM sessions WHERE id = ${sessionId}`;
+      if (session.length === 0) {
+        reply.code(404);
+        return { error: 'session not found' };
+      }
+
+      const rows = chatId
+        ? await sql<{ id: string; chat_id: string; message_id: string | null; label: string | null; created_at: Date }[]>`
+            SELECT id, chat_id, message_id, label, created_at
+            FROM checkpoints
+            WHERE chat_id = ${chatId}
+            ORDER BY created_at
+          `
+        : await sql<{ id: string; chat_id: string; message_id: string | null; label: string | null; created_at: Date }[]>`
+            SELECT id, chat_id, message_id, label, created_at
+            FROM checkpoints
+            WHERE session_id = ${sessionId}
+            ORDER BY created_at
+          `;
+      return rows;
+    },
+  );
+
+  // POST /api/sessions/:sessionId/checkpoints/:checkpointId/restore — restore.
+  app.post<{ Params: { sessionId: string; checkpointId: string } }>(
+    '/api/sessions/:sessionId/checkpoints/:checkpointId/restore',
+    async (req, reply) => {
+      const { sessionId, checkpointId } = req.params;
+
+      try {
+        const result = await restoreCheckpoint(sql, checkpointId, {
+          sessionId,
+          log: app.log,
+        });
+        return result;
+      } catch (err) {
+        if (err instanceof CheckpointNotFoundError) {
+          reply.code(404);
+          return { error: err.message };
+        }
+        throw err;
+      }
+    },
+  );
+}
--- a/apps/coder/src/schema.sql
+++ b/apps/coder/src/schema.sql
@@ -240,6 +240,27 @@ END $$;
 -- v2.6: attribution for DiffPanel badges (Phase 1 UX reads this).
 ALTER TABLE pending_changes ADD COLUMN IF NOT EXISTS agent TEXT;

+-- write-edit-robustness #4: worktree checkpoints. A pre-turn shadow-commit of the
+-- session worktree (tracked + untracked, captured without disturbing the real
+-- index/working tree) stored in a private GC-safe ref refs/boocode/checkpoints/<id>.
+-- Created best-effort before each external-agent turn (opencode / warm-ACP / one-shot
+-- ACP+PTY); restore resets the worktree to commit_sha, trims the transcript from
+-- message_id forward, and resets the backend session. chat_id CASCADEs from chats
+-- (like agent_sessions); worktree_id SET NULL so a checkpoint outlives a reaped
+-- worktree row. session_id / message_id are informational (no FK — message rows are
+-- trimmed by a checkpoint restore and we must not block that on a dangling ref).
+CREATE TABLE IF NOT EXISTS checkpoints (
+  id          UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+  chat_id     UUID NOT NULL REFERENCES chats(id) ON DELETE CASCADE,
+  session_id  UUID,
+  worktree_id UUID REFERENCES worktrees(id) ON DELETE SET NULL,
+  message_id  UUID,            -- anchor: the assistant turn row this checkpoint precedes
+  commit_sha  TEXT NOT NULL,   -- shadow-commit capturing the pre-turn worktree tree
+  label       TEXT,
+  created_at  TIMESTAMPTZ NOT NULL DEFAULT clock_timestamp()
+);
+CREATE INDEX IF NOT EXISTS checkpoints_chat_created_idx ON checkpoints(chat_id, created_at);
+
 -- LISTEN/NOTIFY fast path: every tasks INSERT (from any call site — routes,
 -- new_task tool, arena, MCP server) fires pg_notify('tasks_new') in the same
 -- transaction, so the dispatcher reacts immediately instead of waiting for the
--- a/apps/coder/src/services/tests/checkpoints.test.ts
+++ b/apps/coder/src/services/tests/checkpoints.test.ts
@@ -0,0 +1,236 @@
+import { describe, it, expect, beforeAll, afterAll } from 'vitest';
+import { readFileSync } from 'node:fs';
+import { rm, mkdir } from 'node:fs/promises';
+import { resolve } from 'node:path';
+import postgres from 'postgres';
+import {
+  buildShadowCommitCommand,
+  createCheckpoint,
+  restoreCheckpoint,
+  CheckpointNotFoundError,
+} from '../checkpoints.js';
+import { ensureSessionWorktree } from '../worktrees.js';
+import { hostExec } from '../host-exec.js';
+
+/**
+ * write-edit-robustness #4 — worktree checkpoint tests.
+ *
+ * Pure-helper coverage (no DB / no host) for the shadow-commit command builder,
+ * plus a DB+git integration block (DB-opt-in via DATABASE_URL, skips cleanly
+ * otherwise; mirrors reconnect_integration.test.ts) that exercises the real
+ * create → restore round trip against a worktree on the host fs.
+ */
+
+describe('buildShadowCommitCommand (pure)', () => {
+  it('parks the commit under refs/boocode/checkpoints/<id> and prints only the SHA', () => {
+    const cmd = buildShadowCommitCommand('/tmp/booworktrees/sess-abc', 'cp-id-123');
+    // Uses a temp index so the real working tree/index is untouched.
+    expect(cmd).toContain('TMP=$(mktemp)');
+    expect(cmd).toContain('GIT_INDEX_FILE="$TMP" git read-tree HEAD');
+    expect(cmd).toContain('GIT_INDEX_FILE="$TMP" git add -A');
+    expect(cmd).toContain('git write-tree');
+    expect(cmd).toContain("git commit-tree \"$TREE\" -p HEAD -m \"boocode checkpoint\"");
+    // Ref name matches the row id, and stdout is ONLY the SHA (printf, no newline).
+    expect(cmd).toContain("update-ref 'refs/boocode/checkpoints/cp-id-123'");
+    expect(cmd).toContain("printf '%s' \"$SHA\"");
+    expect(cmd).not.toContain('echo "$SHA"');
+  });
+
+  it('shell-escapes the worktree path and the id', () => {
+    const cmd = buildShadowCommitCommand("/tmp/it's a path", "id'; rm -rf /");
+    // Single quotes inside the path/id are escaped via the '\'' wrapping idiom — no
+    // bare interpolation that could break out of the quoting.
+    expect(cmd).toContain("cd '/tmp/it'\\''s a path'");
+    expect(cmd).toContain("refs/boocode/checkpoints/id'\\''; rm -rf /");
+  });
+});
+
+describe.runIf(!!process.env.DATABASE_URL)('checkpoint create + restore (DB + git)', () => {
+  let sql: ReturnType<typeof postgres>;
+  const stamp = Date.now();
+  const projectDir = `/tmp/boocode-checkpoint-proj-${stamp}`;
+  let projectId: string;
+  let sessionId: string;
+  let chatId: string;
+  let worktreePath: string;
+
+  beforeAll(async () => {
+    sql = postgres(process.env.DATABASE_URL!, { max: 3 });
+
+    // Server schema first (FK targets), then coder schema (worktrees + checkpoints).
+    const serverSchema = resolve(__dirname, '../../../../server/src/schema.sql');
+    const coderSchema = resolve(__dirname, '../../schema.sql');
+    await sql.unsafe(readFileSync(serverSchema, 'utf8'));
+    await sql.unsafe(readFileSync(coderSchema, 'utf8'));
+
+    await mkdir(projectDir, { recursive: true });
+    await hostExec(
+      `cd ${projectDir} && git init -q && git config user.email t@t && git config user.name t ` +
+        `&& echo hello > README.md && git add -A && git commit -qm init`,
+      { timeoutMs: 20_000 },
+    );
+
+    const [project] = await sql<{ id: string }[]>`
+      INSERT INTO projects (name, path, status) VALUES ('checkpoint-test', ${projectDir}, 'open') RETURNING id
+    `;
+    projectId = project!.id;
+    const [session] = await sql<{ id: string }[]>`
+      INSERT INTO sessions (project_id, name, model, status)
+      VALUES (${projectId}, 'cp', 'm', 'open') RETURNING id
+    `;
+    sessionId = session!.id;
+    const [chat] = await sql<{ id: string }[]>`
+      INSERT INTO chats (session_id, name, status) VALUES (${sessionId}, 'tab', 'open') RETURNING id
+    `;
+    chatId = chat!.id;
+
+    const wt = await ensureSessionWorktree(sql, projectDir, sessionId);
+    worktreePath = wt.worktreePath;
+  });
+
+  afterAll(async () => {
+    if (sql) {
+      const rows = await sql<{ path: string }[]>`SELECT path FROM worktrees WHERE session_id = ${sessionId}`.catch(() => []);
+      for (const r of rows) {
+        await hostExec(`git -C ${projectDir} worktree remove ${r.path} --force`, { timeoutMs: 10_000 }).catch(() => {});
+      }
+      await sql`DELETE FROM checkpoints WHERE chat_id = ${chatId}`.catch(() => {});
+      await sql`DELETE FROM agent_sessions WHERE chat_id = ${chatId}`.catch(() => {});
+      await sql`DELETE FROM worktrees WHERE session_id = ${sessionId}`.catch(() => {});
+      await sql`DELETE FROM chats WHERE id = ${chatId}`.catch(() => {});
+      await sql`DELETE FROM sessions WHERE id = ${sessionId}`.catch(() => {});
+      await sql`DELETE FROM projects WHERE id = ${projectId}`.catch(() => {});
+      await sql.end({ timeout: 5 });
+    }
+    await rm(projectDir, { recursive: true, force: true });
+  });
+
+  it('createCheckpoint inserts a row + a private ref capturing tracked + untracked', async () => {
+    const [wt] = await sql<{ id: string }[]>`SELECT id FROM worktrees WHERE session_id = ${sessionId} AND status = 'active'`;
+    const worktreeId = wt!.id;
+
+    // Pre-turn untracked + tracked-edit state the agent will start from.
+    await hostExec(`cd ${worktreePath} && echo edited >> README.md && echo new > extra.txt`, { timeoutMs: 10_000 });
+
+    const [assistantMsg] = await sql<{ id: string }[]>`
+      INSERT INTO messages (session_id, chat_id, role, content, status)
+      VALUES (${sessionId}, ${chatId}, 'assistant', '', 'streaming') RETURNING id
+    `;
+    const messageId = assistantMsg!.id;
+
+    const cp = await createCheckpoint(sql, {
+      chatId,
+      sessionId,
+      worktreeId,
+      worktreePath,
+      messageId,
+    });
+    expect(cp).not.toBeNull();
+    expect(cp!.commit_sha).toMatch(/^[0-9a-f]{40}$/);
+
+    const [row] = await sql<{ commit_sha: string; worktree_id: string; message_id: string }[]>`
+      SELECT commit_sha, worktree_id, message_id FROM checkpoints WHERE id = ${cp!.id}
+    `;
+    expect(row!.commit_sha).toBe(cp!.commit_sha);
+    expect(row!.worktree_id).toBe(worktreeId);
+    expect(row!.message_id).toBe(messageId);
+
+    // The ref exists and the captured tree carries the untracked file (proves the
+    // temp-index `git add -A` snapshotted untracked content).
+    const refLs = await hostExec(
+      `git -C ${worktreePath} ls-tree -r --name-only ${cp!.commit_sha}`,
+      { timeoutMs: 10_000 },
+    );
+    expect(refLs.exitCode).toBe(0);
+    expect(refLs.stdout).toContain('extra.txt');
+
+    // The shadow commit did NOT disturb the real working tree: extra.txt is still
+    // present + still untracked (status shows it).
+    const status = await hostExec(`git -C ${worktreePath} status --porcelain`, { timeoutMs: 10_000 });
+    expect(status.stdout).toContain('extra.txt');
+  });
+
+  it('restoreCheckpoint resets the worktree, trims the transcript, and drops later checkpoints', async () => {
+    // Clean slate for this test: reset the worktree to HEAD, clear prior rows.
+    await hostExec(`git -C ${worktreePath} reset --hard HEAD && git -C ${worktreePath} clean -fd`, { timeoutMs: 10_000 });
+    await sql`DELETE FROM checkpoints WHERE chat_id = ${chatId}`;
+    await sql`DELETE FROM messages WHERE chat_id = ${chatId}`;
+
+    const [wt] = await sql<{ id: string }[]>`SELECT id FROM worktrees WHERE session_id = ${sessionId} AND status = 'active'`;
+    const worktreeId = wt!.id;
+
+    // Turn 1: a user msg, then the assistant turn the checkpoint anchors. The
+    // worktree is pristine (matches HEAD) when this checkpoint is captured.
+    await sql`INSERT INTO messages (session_id, chat_id, role, content, status) VALUES (${sessionId}, ${chatId}, 'user', 'do it', 'complete')`;
+    const [a1] = await sql<{ id: string }[]>`
+      INSERT INTO messages (session_id, chat_id, role, content, status)
+      VALUES (${sessionId}, ${chatId}, 'assistant', 'turn 1', 'complete') RETURNING id
+    `;
+    const cp1 = await createCheckpoint(sql, { chatId, sessionId, worktreeId, worktreePath, messageId: a1!.id });
+    expect(cp1).not.toBeNull();
+
+    // The agent (turn 1) writes a file into the worktree.
+    await hostExec(`cd ${worktreePath} && echo agent-wrote > agent.txt`, { timeoutMs: 10_000 });
+
+    // Turn 2: another user msg + assistant turn, AND a second (later) checkpoint.
+    await sql`INSERT INTO messages (session_id, chat_id, role, content, status) VALUES (${sessionId}, ${chatId}, 'user', 'more', 'complete')`;
+    const [a2] = await sql<{ id: string }[]>`
+      INSERT INTO messages (session_id, chat_id, role, content, status)
+      VALUES (${sessionId}, ${chatId}, 'assistant', 'turn 2', 'complete') RETURNING id
+    `;
+    const cp2 = await createCheckpoint(sql, { chatId, sessionId, worktreeId, worktreePath, messageId: a2!.id });
+    expect(cp2).not.toBeNull();
+
+    // An agent_sessions row that restore should mark 'crashed'.
+    await sql`
+      INSERT INTO agent_sessions (chat_id, session_id, worktree_id, agent, backend, agent_session_id, status, last_active_at)
+      VALUES (${chatId}, ${sessionId}, ${worktreeId}, 'goose', 'acp_warm', 'sess-1', 'active', clock_timestamp())
+      ON CONFLICT (chat_id, agent) DO UPDATE SET status = 'active'
+    `;
+
+    const before = await sql<{ id: string }[]>`SELECT id FROM messages WHERE chat_id = ${chatId} ORDER BY created_at`;
+    expect(before.length).toBe(4); // user, a1, user, a2
+
+    // Restore to cp1 (before turn 1's assistant message).
+    const result = await restoreCheckpoint(sql, cp1!.id, { sessionId });
+    expect(result.checkpoint_id).toBe(cp1!.id);
+    expect(result.worktree_reset).toBe(true);
+    expect(result.backend_reset).toBe(true);
+    // a1, user(turn2), a2 deleted (created_at >= a1) → 3 trimmed.
+    expect(result.messages_deleted).toBe(3);
+
+    // Transcript trimmed to just the first user message.
+    const after = await sql<{ role: string; content: string }[]>`SELECT role, content FROM messages WHERE chat_id = ${chatId} ORDER BY created_at`;
+    expect(after.length).toBe(1);
+    expect(after[0]!.role).toBe('user');
+
+    // Worktree reset: the agent's file is gone (it was written after cp1).
+    const ls = await hostExec(`ls ${worktreePath}/agent.txt`, { timeoutMs: 10_000 });
+    expect(ls.exitCode).not.toBe(0);
+
+    // The agent_sessions row was reset to 'crashed'.
+    const [as] = await sql<{ status: string }[]>`SELECT status FROM agent_sessions WHERE chat_id = ${chatId} AND agent = 'goose'`;
+    expect(as!.status).toBe('crashed');
+
+    // cp1 survives (re-restorable); cp2 (later) was dropped.
+    const cps = await sql<{ id: string }[]>`SELECT id FROM checkpoints WHERE chat_id = ${chatId}`;
+    expect(cps.map((c) => c.id)).toEqual([cp1!.id]);
+  });
+
+  it('restoreCheckpoint throws CheckpointNotFoundError for an unknown id', async () => {
+    await expect(
+      restoreCheckpoint(sql, '00000000-0000-0000-0000-000000000000', { sessionId }),
+    ).rejects.toBeInstanceOf(CheckpointNotFoundError);
+  });
+
+  it('restoreCheckpoint throws when the checkpoint is not in the requested session', async () => {
+    // A checkpoint whose session_id differs from the route's sessionId.
+    const [wt] = await sql<{ id: string }[]>`SELECT id FROM worktrees WHERE session_id = ${sessionId} AND status = 'active'`;
+    const cp = await createCheckpoint(sql, { chatId, sessionId, worktreeId: wt!.id, worktreePath, messageId: null });
+    expect(cp).not.toBeNull();
+    await expect(
+      restoreCheckpoint(sql, cp!.id, { sessionId: '11111111-1111-1111-1111-111111111111' }),
+    ).rejects.toBeInstanceOf(CheckpointNotFoundError);
+    await sql`DELETE FROM checkpoints WHERE id = ${cp!.id}`;
+  });
+});
--- a/apps/coder/src/services/tests/fuzzy-match.test.ts
+++ b/apps/coder/src/services/tests/fuzzy-match.test.ts
@@ -0,0 +1,173 @@
+import { describe, it, expect } from 'vitest';
+import { locateMatch, SIMILARITY_THRESHOLD } from '../fuzzy-match.js';
+
+// Helper: assert a resolved span and slice it back out of the content so the
+// test pins the EXACT file text the caller would replace.
+function span(result: ReturnType<typeof locateMatch>): { start: number; end: number } {
+  if (result.kind !== 'exact' && result.kind !== 'fuzzy') {
+    throw new Error(`expected a located span, got ${result.kind}`);
+  }
+  return { start: result.start, end: result.end };
+}
+
+describe('locateMatch — strategy 1: exact', () => {
+  it('returns an exact unique span', () => {
+    const content = 'alpha\nbeta\ngamma\n';
+    const result = locateMatch(content, 'beta');
+    expect(result.kind).toBe('exact');
+    const { start, end } = span(result);
+    expect(content.slice(start, end)).toBe('beta');
+  });
+
+  it('returns the right offsets for a multi-line exact needle', () => {
+    const content = 'one\ntwo\nthree\nfour\n';
+    const needle = 'two\nthree';
+    const result = locateMatch(content, needle);
+    expect(result.kind).toBe('exact');
+    const { start, end } = span(result);
+    expect(content.slice(start, end)).toBe(needle);
+  });
+
+  it('refuses when the exact needle occurs more than once', () => {
+    const content = 'foo\nbar\nfoo\nbar\nfoo\n';
+    const result = locateMatch(content, 'foo');
+    expect(result).toEqual({ kind: 'ambiguous', count: 3 });
+  });
+});
+
+describe('locateMatch — strategy 2: per-line whitespace', () => {
+  it('matches across trailing-whitespace drift at the real span', () => {
+    // File has trailing spaces the model dropped from a TWO-line copy. A
+    // single-line needle would be located by exact indexOf (it's a substring),
+    // so use two lines where line 1's trailing ws breaks an exact substring run.
+    const content = 'function f() {\n  setup();   \n  return 1;\n}\n';
+    const needle = '  setup();\n  return 1;'; // line 1 missing trailing spaces
+    const result = locateMatch(content, needle);
+    expect(result.kind).toBe('fuzzy');
+    const { start, end } = span(result);
+    // The returned span covers the ORIGINAL lines including the trailing spaces.
+    expect(content.slice(start, end)).toBe('  setup();   \n  return 1;');
+  });
+
+  it('matches across indentation drift (multi-line block)', () => {
+    // File indents with 4 spaces; model emitted 2-space indentation. trimEnd
+    // alone does not normalize LEADING whitespace, so this exercises... actually
+    // leading-indent drift is a Levenshtein-tier fallback. Here we keep the
+    // leading indent identical and drift only trailing whitespace per line.
+    const content = ['if (x) {', '    doThing();    ', '    doOther();', '}'].join('\n');
+    const needle = ['    doThing();', '    doOther();'].join('\n');
+    const result = locateMatch(content, needle);
+    expect(result.kind).toBe('fuzzy');
+    const { start, end } = span(result);
+    expect(content.slice(start, end)).toBe('    doThing();    \n    doOther();');
+  });
+
+  it('ignores leading/trailing blank needle lines', () => {
+    const content = 'header\nbody line\nfooter\n';
+    const needle = '\n\nbody line\n\n';
+    const result = locateMatch(content, needle);
+    expect(result.kind).toBe('fuzzy');
+    const { start, end } = span(result);
+    expect(content.slice(start, end)).toBe('body line');
+  });
+
+  it('reports ambiguous when a whitespace-window matches twice', () => {
+    // Both line 1 and line 4 differ from the needle only by trailing whitespace,
+    // so exact indexOf fails (no exact substring) and the whitespace tier finds
+    // two equivalent windows → ambiguous.
+    const content = 'x = 1;  \ny = 2;\nz = 3;\nx = 1;\t\n';
+    const needle = 'x = 1;'; // no trailing ws → not an exact substring of either line
+    const result = locateMatch(content, needle);
+    expect(result).toEqual({ kind: 'ambiguous', count: 2 });
+  });
+});
+
+describe('locateMatch — strategy 3: unicode canonicalization', () => {
+  it('matches across curly quotes', () => {
+    const content = "const s = 'hello';\n";
+    const needle = 'const s = ‘hello’;'; // ‘hello’
+    const result = locateMatch(content, needle);
+    expect(result.kind).toBe('fuzzy');
+    const { start, end } = span(result);
+    // Span maps back to ORIGINAL (straight-quote) text.
+    expect(content.slice(start, end)).toBe("const s = 'hello';");
+  });
+
+  it('matches across curly double-quotes', () => {
+    const content = 'log("done");\n';
+    const needle = 'log(“done”);'; // “done”
+    const result = locateMatch(content, needle);
+    expect(result.kind).toBe('fuzzy');
+    const { start, end } = span(result);
+    expect(content.slice(start, end)).toBe('log("done");');
+  });
+
+  it('matches across an em-dash drift', () => {
+    const content = 'range 1-10 inclusive\n';
+    const needle = 'range 1—10 inclusive'; // em-dash
+    const result = locateMatch(content, needle);
+    expect(result.kind).toBe('fuzzy');
+    const { start, end } = span(result);
+    expect(content.slice(start, end)).toBe('range 1-10 inclusive');
+  });
+
+  it('matches across a non-breaking space drift', () => {
+    const content = 'a b c\n'; // plain spaces
+    const needle = 'a b c'; // nbsp between words
+    const result = locateMatch(content, needle);
+    expect(result.kind).toBe('fuzzy');
+    const { start, end } = span(result);
+    expect(content.slice(start, end)).toBe('a b c');
+  });
+});
+
+describe('locateMatch — strategy 4: Levenshtein', () => {
+  it('matches a >= threshold near-miss (small typo drift)', () => {
+    // Needle has a one-char typo ('totals' vs 'total') so it is NOT an exact
+    // substring and the whitespace/canonical tiers (which require equality) both
+    // miss; Levenshtein similarity stays well above the 0.66 floor.
+    const content = 'const total = sum + tax;\n';
+    const needle = 'const totals = sum + tax;';
+    const result = locateMatch(content, needle);
+    expect(result.kind).toBe('fuzzy');
+    const { start, end } = span(result);
+    // Span maps to the real (correctly-spelled) file line.
+    expect(content.slice(start, end)).toBe('const total = sum + tax;');
+  });
+
+  it('matches a multi-line block with indentation drift via Levenshtein', () => {
+    const content = ['function g() {', '  return compute(a, b);', '}'].join('\n');
+    // 6-space indent vs file's 2-space; trimEnd does not fix leading indent, so
+    // this lands on the Levenshtein tier (joined-trim makes it identical → ~1.0).
+    const needle = ['      return compute(a, b);'].join('\n');
+    const result = locateMatch(content, needle);
+    expect(result.kind).toBe('fuzzy');
+    const { start, end } = span(result);
+    expect(content.slice(start, end)).toBe('  return compute(a, b);');
+  });
+
+  it('returns not_found for a below-threshold miss', () => {
+    const content = 'the quick brown fox jumps over the lazy dog\n';
+    const needle = 'completely unrelated string of text here xyz';
+    const result = locateMatch(content, needle);
+    expect(result).toEqual({ kind: 'not_found' });
+  });
+
+  it('returns not_found for a genuinely-absent needle', () => {
+    const content = 'alpha\nbeta\ngamma\n';
+    const needle = 'this content does not exist anywhere at all';
+    const result = locateMatch(content, needle);
+    expect(result).toEqual({ kind: 'not_found' });
+  });
+});
+
+describe('locateMatch — edge cases', () => {
+  it('returns not_found for an empty needle', () => {
+    expect(locateMatch('anything', '')).toEqual({ kind: 'not_found' });
+  });
+
+  it('exposes a sane similarity threshold', () => {
+    expect(SIMILARITY_THRESHOLD).toBeGreaterThan(0);
+    expect(SIMILARITY_THRESHOLD).toBeLessThanOrEqual(1);
+  });
+});
--- a/apps/coder/src/services/checkpoints.ts
+++ b/apps/coder/src/services/checkpoints.ts
@@ -0,0 +1,297 @@
+/**
+ * write-edit-robustness #4 — worktree checkpoints.
+ *
+ * External agents (opencode / goose / qwen / claude) write DIRECTLY into the
+ * shared session worktree (`/tmp/booworktrees/sess-<id>`); BooCode's own `rewind`
+ * only reverses `pending_changes` against the project root, so it has zero coverage
+ * there. A checkpoint is a pre-turn shadow-commit of the worktree tree (tracked +
+ * untracked) captured WITHOUT touching the real index/working tree, stored in a
+ * private GC-safe ref. `restoreCheckpoint` rewinds the worktree to that commit,
+ * trims the transcript from the anchor message forward, and resets the agent
+ * backend so the next turn re-establishes a fresh context consistent with the
+ * restored files.
+ *
+ * All git goes through hostExec + shellEscape (BooCoder runs on the host; the
+ * worktrees live on the host fs). Checkpoint CREATION is best-effort: a failure
+ * logs and returns null — it must NEVER throw into the dispatch turn.
+ */
+import { randomUUID } from 'node:crypto';
+import type { FastifyBaseLogger } from 'fastify';
+import type { Sql } from '../db.js';
+import { hostExec } from './host-exec.js';
+import { agentPool, OPENCODE_POOL_KEY } from './agent-pool.js';
+import type { AgentSessionHandle } from './agent-backend.js';
+
+/** Minimal shell escape for paths/refs (single-quote wrapping). Mirrors worktrees.ts. */
+function shellEscape(s: string): string {
+  return "'" + s.replace(/'/g, "'\\''") + "'";
+}
+
+/**
+ * Pure builder for the shadow-commit command. Captures tracked + untracked files
+ * in the worktree into a temp index (so the real index/working tree is untouched),
+ * writes a tree, commits it parented on HEAD, and parks the commit under a private
+ * ref `refs/boocode/checkpoints/<id>` so git's GC never reclaims it. Prints ONLY
+ * the resulting SHA on stdout (the trailing `printf '%s'`), so the caller parses
+ * stdout.trim() directly.
+ *
+ * `id` is the row UUID (minted before the ref so the ref name matches the row).
+ * Both the worktree path and the id are shell-escaped.
+ */
+export function buildShadowCommitCommand(worktreePath: string, id: string): string {
+  const wt = shellEscape(worktreePath);
+  const ref = shellEscape(`refs/boocode/checkpoints/${id}`);
+  return (
+    `cd ${wt} && TMP=$(mktemp) && GIT_INDEX_FILE="$TMP" git read-tree HEAD ` +
+    `&& GIT_INDEX_FILE="$TMP" git add -A ` +
+    `&& TREE=$(GIT_INDEX_FILE="$TMP" git write-tree) ` +
+    `&& SHA=$(git commit-tree "$TREE" -p HEAD -m "boocode checkpoint") ` +
+    `&& git update-ref ${ref} "$SHA" && rm -f "$TMP" && printf '%s' "$SHA"`
+  );
+}
+
+export interface CreateCheckpointArgs {
+  chatId: string;
+  sessionId: string | null;
+  worktreeId: string | null;
+  worktreePath: string;
+  messageId: string | null;
+  label?: string | null;
+}
+
+/**
+ * Capture a pre-turn checkpoint of the session worktree. Best-effort: returns the
+ * inserted row's { id, commit_sha } on success, or null on any failure (the turn
+ * proceeds either way — a missing checkpoint just means no restore point for that
+ * turn). NEVER throws.
+ *
+ * The id is minted up front so the git ref name (`refs/boocode/checkpoints/<id>`)
+ * matches the DB row id, keeping ref and row in lockstep.
+ */
+export async function createCheckpoint(
+  sql: Sql,
+  args: CreateCheckpointArgs,
+  opts?: { signal?: AbortSignal; log?: FastifyBaseLogger },
+): Promise<{ id: string; commit_sha: string } | null> {
+  const id = randomUUID();
+  try {
+    const cmd = buildShadowCommitCommand(args.worktreePath, id);
+    const res = await hostExec(cmd, { signal: opts?.signal, timeoutMs: 30_000 });
+    if (res.exitCode !== 0) {
+      opts?.log?.warn(
+        { chatId: args.chatId, worktreePath: args.worktreePath, stderr: res.stderr.trim().slice(0, 500) },
+        'checkpoint: shadow-commit failed (turn proceeds without a checkpoint)',
+      );
+      return null;
+    }
+    const commitSha = res.stdout.trim();
+    if (!commitSha) {
+      opts?.log?.warn(
+        { chatId: args.chatId, worktreePath: args.worktreePath },
+        'checkpoint: shadow-commit produced no SHA (turn proceeds)',
+      );
+      return null;
+    }
+
+    await sql`
+      INSERT INTO checkpoints (id, chat_id, session_id, worktree_id, message_id, commit_sha, label)
+      VALUES (${id}, ${args.chatId}, ${args.sessionId}, ${args.worktreeId}, ${args.messageId}, ${commitSha}, ${args.label ?? null})
+    `;
+    opts?.log?.info({ checkpointId: id, chatId: args.chatId, commitSha }, 'checkpoint: created');
+    return { id, commit_sha: commitSha };
+  } catch (err) {
+    opts?.log?.warn(
+      { chatId: args.chatId, err: err instanceof Error ? err.message : String(err) },
+      'checkpoint: create threw (turn proceeds without a checkpoint)',
+    );
+    return null;
+  }
+}
+
+/** Error the route maps to a 404 when the checkpoint can't be resolved / scoped. */
+export class CheckpointNotFoundError extends Error {
+  constructor(message: string) {
+    super(message);
+    this.name = 'CheckpointNotFoundError';
+  }
+}
+
+export interface RestoreCheckpointResult {
+  checkpoint_id: string;
+  messages_deleted: number;
+  worktree_reset: boolean;
+  backend_reset: boolean;
+}
+
+export interface RestoreCheckpointOpts {
+  signal?: AbortSignal;
+  log?: FastifyBaseLogger;
+  /** If set, the checkpoint MUST belong to this session (route scope guard). */
+  sessionId?: string;
+}
+
+interface CheckpointRow {
+  id: string;
+  chat_id: string;
+  session_id: string | null;
+  worktree_id: string | null;
+  message_id: string | null;
+  commit_sha: string;
+  created_at: Date;
+}
+
+/**
+ * Restore a checkpoint: rewind its worktree to the shadow commit, trim the
+ * transcript from the anchor message forward, reset the backend session, and drop
+ * now-orphaned later checkpoints. Throws CheckpointNotFoundError when the
+ * checkpoint is missing or not in the requested session (route → 404).
+ */
+export async function restoreCheckpoint(
+  sql: Sql,
+  checkpointId: string,
+  opts?: RestoreCheckpointOpts,
+): Promise<RestoreCheckpointResult> {
+  // 1. Resolve the checkpoint.
+  const [cp] = await sql<CheckpointRow[]>`
+    SELECT id, chat_id, session_id, worktree_id, message_id, commit_sha, created_at
+    FROM checkpoints WHERE id = ${checkpointId}
+  `;
+  if (!cp) {
+    throw new CheckpointNotFoundError('checkpoint not found');
+  }
+  if (opts?.sessionId && cp.session_id && cp.session_id !== opts.sessionId) {
+    throw new CheckpointNotFoundError('checkpoint not in session');
+  }
+
+  // 2. Resolve the worktree path (by worktree_id, else the session's active one).
+  let worktreePath: string | null = null;
+  if (cp.worktree_id) {
+    const [wt] = await sql<{ path: string }[]>`
+      SELECT path FROM worktrees WHERE id = ${cp.worktree_id}
+    `;
+    worktreePath = wt?.path ?? null;
+  }
+  if (!worktreePath) {
+    const sid = cp.session_id ?? opts?.sessionId ?? null;
+    if (sid) {
+      const [wt] = await sql<{ path: string }[]>`
+        SELECT path FROM worktrees WHERE session_id = ${sid} AND status = 'active' LIMIT 1
+      `;
+      worktreePath = wt?.path ?? null;
+    }
+  }
+
+  // 3. Worktree reset — hard-reset to the shadow commit, then clean untracked.
+  let worktreeReset = false;
+  if (worktreePath) {
+    const resetRes = await hostExec(
+      `git -C ${shellEscape(worktreePath)} reset --hard ${shellEscape(cp.commit_sha)}`,
+      { signal: opts?.signal, timeoutMs: 30_000 },
+    ).catch((err) => {
+      opts?.log?.warn(
+        { checkpointId, err: err instanceof Error ? err.message : String(err) },
+        'checkpoint restore: reset --hard threw',
+      );
+      return null;
+    });
+    if (resetRes && resetRes.exitCode === 0) {
+      const cleanRes = await hostExec(
+        `git -C ${shellEscape(worktreePath)} clean -fd`,
+        { signal: opts?.signal, timeoutMs: 30_000 },
+      ).catch(() => null);
+      worktreeReset = cleanRes != null && cleanRes.exitCode === 0;
+      if (!worktreeReset) {
+        opts?.log?.warn({ checkpointId, worktreePath }, 'checkpoint restore: clean -fd did not succeed');
+      }
+    } else {
+      opts?.log?.warn(
+        { checkpointId, worktreePath, stderr: resetRes?.stderr?.trim()?.slice(0, 500) },
+        'checkpoint restore: reset --hard did not succeed',
+      );
+    }
+  } else {
+    opts?.log?.warn({ checkpointId }, 'checkpoint restore: no worktree path resolved (files not reset)');
+  }
+
+  // 4. Trim the transcript from the anchor message forward. message_parts FK to
+  //    messages is ON DELETE CASCADE (apps/server schema.sql:49), so parts are
+  //    removed with their messages — no explicit parts delete needed.
+  let messagesDeleted = 0;
+  if (cp.message_id) {
+    const deleted = await sql<{ id: string }[]>`
+      DELETE FROM messages
+      WHERE chat_id = ${cp.chat_id}
+        AND created_at >= (SELECT created_at FROM messages WHERE id = ${cp.message_id})
+      RETURNING id
+    `;
+    messagesDeleted = deleted.length;
+  }
+
+  // 5. Backend reset — mark the chat's agent sessions crashed so the next turn
+  //    re-establishes a fresh backend, and evict the live pool session(s) for this
+  //    (chat, agent). Warm backends hold context server-side with no partial
+  //    rewind, so a full reset is the only consistent option (proposal §4).
+  const agentRows = await sql<{ agent: string; backend: string; agent_session_id: string | null; session_id: string | null; worktree_id: string | null }[]>`
+    SELECT agent, backend, agent_session_id, session_id, worktree_id
+    FROM agent_sessions WHERE chat_id = ${cp.chat_id}
+  `;
+  await sql`
+    UPDATE agent_sessions SET status = 'crashed' WHERE chat_id = ${cp.chat_id}
+  `.catch(() => {});
+
+  let backendReset = false;
+  try {
+    // opencode runs on the SHARED server (keyed on a sentinel, not the chat) — close
+    // just this chat's session(s) on it, mirroring the lifecycle close-hook.
+    const ocBackend = agentPool.peek(OPENCODE_POOL_KEY, 'opencode');
+    if (ocBackend) {
+      for (const row of agentRows) {
+        if (row.backend !== 'opencode_server' || !row.agent_session_id) continue;
+        const handle: AgentSessionHandle = {
+          sessionId: row.session_id ?? '',
+          agent: row.agent,
+          backend: 'opencode_server',
+          chatId: cp.chat_id,
+          worktreeId: row.worktree_id ?? '',
+          agentSessionId: row.agent_session_id,
+          serverPort: null,
+        };
+        await ocBackend.closeSession(handle).catch((err) => {
+          opts?.log?.warn(
+            { checkpointId, err: err instanceof Error ? err.message : String(err) },
+            'checkpoint restore: opencode closeSession threw',
+          );
+        });
+      }
+    }
+    // Warm-ACP backends are pooled under the chat id — dispose them (kills the
+    // goose/qwen child). closeChat skips busy backends (a live turn isn't torn down).
+    const disposed = await agentPool.closeChat(cp.chat_id);
+    backendReset = true;
+    opts?.log?.info({ checkpointId, chatId: cp.chat_id, disposed }, 'checkpoint restore: backend reset');
+  } catch (err) {
+    opts?.log?.warn(
+      { checkpointId, err: err instanceof Error ? err.message : String(err) },
+      'checkpoint restore: backend reset threw',
+    );
+  }
+
+  // 6. Drop now-orphaned later checkpoints for this chat (their anchor messages were
+  //    just trimmed). Compare `created_at` SERVER-SIDE via a subquery (NOT the JS
+  //    Date round-trip, which truncates the stored microsecond precision to ms and
+  //    would make this checkpoint delete ITSELF), and exclude this checkpoint's own
+  //    id so it always survives — letting the user re-restore to it.
+  await sql`
+    DELETE FROM checkpoints
+    WHERE chat_id = ${cp.chat_id}
+      AND id <> ${cp.id}
+      AND created_at > (SELECT created_at FROM checkpoints WHERE id = ${cp.id})
+  `.catch(() => {});
+
+  return {
+    checkpoint_id: checkpointId,
+    messages_deleted: messagesDeleted,
+    worktree_reset: worktreeReset,
+    backend_reset: backendReset,
+  };
+}
--- a/apps/coder/src/services/dispatcher.ts
+++ b/apps/coder/src/services/dispatcher.ts
@@ -4,6 +4,7 @@ import type { Broker } from '@boocode/server/broker';
 import type { WsFrame } from '@boocode/server/ws-frames';
 import type { Config } from '../config.js';
 import { createWorktree, diffWorktree, cleanupWorktree, ensureSessionWorktree } from './worktrees.js';
+import { createCheckpoint } from './checkpoints.js';
 import { makeDcpStreamStripper } from './dcp-strip.js';
 import { dispatchViaAcp } from './acp-dispatch.js';
 import { getResolvedRegistry } from './provider-config-registry.js';
@@ -358,6 +359,16 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
      `;
      const assistantId = assistantMsg!.id;

+      // write-edit-robustness #4: pre-turn worktree checkpoint (best-effort; a
+      // failure logs and never breaks dispatch). This path uses a per-task worktree
+      // (createWorktree, not the session worktree), so there's no worktrees-table id
+      // — pass null for worktreeId, the path is enough for restore's reset.
+      await createCheckpoint(
+        sql,
+        { chatId, sessionId, worktreeId: null, worktreePath, messageId: assistantId },
+        { signal: ac.signal, log },
+      ).catch(() => null);
+
      broker.publishFrame(sessionId, {
        type: 'message_started',
        message_id: assistantId,
@@ -617,6 +628,15 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
      `;
      const assistantId = assistantMsg!.id;

+      // write-edit-robustness #4: pre-turn checkpoint of the persistent session
+      // worktree (best-effort; never breaks dispatch). worktreeId comes from the
+      // worktrees table (ensureSessionWorktree above).
+      await createCheckpoint(
+        sql,
+        { chatId, sessionId, worktreeId, worktreePath, messageId: assistantId },
+        { signal: ac.signal, log },
+      ).catch(() => null);
+
      broker.publishFrame(sessionId, {
        type: 'message_started',
        message_id: assistantId,
@@ -876,6 +896,15 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
      `;
      const assistantId = assistantMsg!.id;

+      // write-edit-robustness #4: pre-turn checkpoint of the persistent session
+      // worktree (best-effort; never breaks dispatch). Same worktree the opencode
+      // path uses — a chat that switches opencode↔goose↔qwen shares one worktree.
+      await createCheckpoint(
+        sql,
+        { chatId, sessionId, worktreeId, worktreePath, messageId: assistantId },
+        { signal: ac.signal, log },
+      ).catch(() => null);
+
      broker.publishFrame(sessionId, {
        type: 'message_started',
        message_id: assistantId,
--- a/apps/coder/src/services/fuzzy-match.ts
+++ b/apps/coder/src/services/fuzzy-match.ts
@@ -0,0 +1,271 @@
+// Fuzzy patch locator for staged edits.
+//
+// Local quantized models (qwen3.6 and friends) frequently reproduce an
+// `old_string` with small, semantically-irrelevant drift: trailing whitespace,
+// a different indent width, or "smart" unicode punctuation (curly quotes, an
+// en/em-dash, a non-breaking space) where the source has the plain ASCII form.
+// An exact `String.includes` then fails and the queued edit is lost even though
+// a human would say it obviously matches.
+//
+// `locateMatch` walks a ladder of progressively looser strategies and returns
+// the real `[start, end)` byte-offset span in the ORIGINAL content so the caller
+// can splice in `new_string` over the true file text (preserving the file's own
+// whitespace/unicode, not the model's drifted copy). The ladder stops at the
+// first strategy that resolves to a single span:
+//
+//   1. exact            — indexOf; >1 hit is reported `ambiguous` (we refuse to
+//                         guess which occurrence the model meant).
+//   2. per-line ws      — line-window compare ignoring per-line trailing
+//                         whitespace and leading/trailing blank needle lines.
+//   3. unicode canon    — same line-window compare after folding smart
+//                         punctuation to ASCII on both sides; the match is
+//                         mapped back to original offsets.
+//   4. levenshtein      — best line-window by normalized edit-distance
+//                         similarity; accepted only at >= SIMILARITY_THRESHOLD.
+//
+// Pure and dependency-free (Levenshtein is the standard iterative two-row DP),
+// reimplemented from the general technique — no vendored source.
+
+export type MatchResult =
+  | { kind: 'exact' | 'fuzzy'; start: number; end: number } // [start,end) offsets into content
+  | { kind: 'ambiguous'; count: number }
+  | { kind: 'not_found' };
+
+/** Levenshtein similarity floor for the final fuzzy fallback (strategy 4). */
+export const SIMILARITY_THRESHOLD = 0.66;
+
+export function locateMatch(content: string, needle: string): MatchResult {
+  // Empty needle has no meaningful match.
+  if (needle.length === 0) return { kind: 'not_found' };
+
+  // --- 1. Exact ----------------------------------------------------------------
+  const exact = locateExact(content, needle);
+  if (exact) return exact;
+
+  // --- 2. Per-line whitespace-insensitive -------------------------------------
+  const ws = locateByLineWindow(content, needle);
+  if (ws) return ws;
+
+  // --- 3. Unicode-canonicalized whitespace pass -------------------------------
+  const canon = locateCanonical(content, needle);
+  if (canon) return canon;
+
+  // --- 4. Levenshtein similarity ----------------------------------------------
+  const lev = locateByLevenshtein(content, needle);
+  if (lev) return lev;
+
+  return { kind: 'not_found' };
+}
+
+// --- Strategy 1: exact -------------------------------------------------------
+
+function locateExact(content: string, needle: string): MatchResult | null {
+  const first = content.indexOf(needle);
+  if (first === -1) return null;
+  const second = content.indexOf(needle, first + 1);
+  if (second === -1) {
+    return { kind: 'exact', start: first, end: first + needle.length };
+  }
+  // Count all occurrences so the caller can report a useful number.
+  let count = 2;
+  let idx = content.indexOf(needle, second + 1);
+  while (idx !== -1) {
+    count++;
+    idx = content.indexOf(needle, idx + 1);
+  }
+  return { kind: 'ambiguous', count };
+}
+
+// --- Line-window machinery ---------------------------------------------------
+
+interface Line {
+  /** Raw line text (no trailing newline). */
+  text: string;
+  /** Offset of the first char of this line in the original content. */
+  start: number;
+  /** Offset one past the last char of this line (before its newline, if any). */
+  end: number;
+}
+
+/**
+ * Split content into lines, tracking each line's real offset span. The span
+ * EXCLUDES the trailing newline so consecutive line spans plus their newlines
+ * exactly reconstruct the content; the match span we hand back covers from the
+ * first matched line's start through the last matched line's end (i.e. without a
+ * trailing newline), which is what an in-place splice wants.
+ */
+function splitLines(content: string): Line[] {
+  const lines: Line[] = [];
+  let start = 0;
+  for (let i = 0; i <= content.length; i++) {
+    if (i === content.length || content[i] === '\n') {
+      lines.push({ text: content.slice(start, i), start, end: i });
+      start = i + 1;
+    }
+  }
+  return lines;
+}
+
+/** Strip leading/trailing all-blank lines; returns the trimmed slice. */
+function trimBlankLines(lines: string[]): string[] {
+  let lo = 0;
+  let hi = lines.length;
+  while (lo < hi && lines[lo]!.trim() === '') lo++;
+  while (hi > lo && lines[hi - 1]!.trim() === '') hi--;
+  return lines.slice(lo, hi);
+}
+
+/**
+ * Find a contiguous window of content lines whose trailing-whitespace-trimmed
+ * text equals the needle's (blank-trimmed) lines. Returns the real offset span
+ * over the matched content lines, or null if zero match. Multiple matches →
+ * ambiguous. `normalize` lets the caller fold unicode before comparing.
+ */
+function locateByLineWindow(
+  content: string,
+  needle: string,
+  normalize: (s: string) => string = (s) => s,
+): MatchResult | null {
+  const contentLines = splitLines(content);
+  const needleLines = trimBlankLines(needle.split('\n'));
+  const n = needleLines.length;
+  if (n === 0) return null;
+  // A single needle line that is itself blank can't be located meaningfully.
+  if (n === 1 && needleLines[0]!.trim() === '') return null;
+
+  const needleKey = needleLines.map((l) => normalize(l.trimEnd())).join('\n');
+
+  const hits: Array<{ start: number; end: number }> = [];
+  for (let i = 0; i + n <= contentLines.length; i++) {
+    const windowKey = contentLines
+      .slice(i, i + n)
+      .map((l) => normalize(l.text.trimEnd()))
+      .join('\n');
+    if (windowKey === needleKey) {
+      hits.push({ start: contentLines[i]!.start, end: contentLines[i + n - 1]!.end });
+    }
+  }
+
+  if (hits.length === 0) return null;
+  if (hits.length > 1) return { kind: 'ambiguous', count: hits.length };
+  return { kind: 'fuzzy', start: hits[0]!.start, end: hits[0]!.end };
+}
+
+// --- Strategy 3: unicode canonicalization ------------------------------------
+
+/**
+ * Fold smart punctuation to its ASCII equivalent. Crucially this is a
+ * length-PRESERVING, per-character map (every replacement is one char → one
+ * char), so an offset into the canonical string is also a valid offset into the
+ * original — letting strategy 3 reuse the line-window matcher and still hand
+ * back true original-content offsets.
+ */
+function canonicalizeChar(ch: string): string {
+  switch (ch) {
+    // single quotes / apostrophes
+    case '‘': // '
+    case '’': // '
+    case '‚': // ‚
+    case '‛': // ‛
+      return "'";
+    // double quotes
+    case '“': // "
+    case '”': // "
+    case '„': // „
+    case '‟': // ‟
+      return '"';
+    // dashes
+    case '–': // – en dash
+    case '—': // — em dash
+    case '‒': // ‒ figure dash
+    case '―': // ― horizontal bar
+    case '−': // − minus sign
+      return '-';
+    // spaces
+    case ' ': // nbsp
+    case ' ': // figure space
+    case ' ': // narrow nbsp
+      return ' ';
+    default:
+      return ch;
+  }
+}
+
+function canonicalize(s: string): string {
+  let out = '';
+  for (const ch of s) out += canonicalizeChar(ch);
+  return out;
+}
+
+function locateCanonical(content: string, needle: string): MatchResult | null {
+  // Only worth running if canonicalization actually changes something on either
+  // side — otherwise it's identical to strategy 2 which already failed.
+  const canonContent = canonicalize(content);
+  const canonNeedle = canonicalize(needle);
+  if (canonContent === content && canonNeedle === needle) return null;
+  // Offsets are preserved (length-preserving fold), so a match on the canonical
+  // content maps directly back to the original.
+  return locateByLineWindow(canonContent, canonNeedle);
+}
+
+// --- Strategy 4: Levenshtein similarity --------------------------------------
+
+/** Standard iterative two-row Levenshtein edit distance. */
+function levenshtein(a: string, b: string): number {
+  if (a === b) return 0;
+  if (a.length === 0) return b.length;
+  if (b.length === 0) return a.length;
+
+  let prev = new Array<number>(b.length + 1);
+  let curr = new Array<number>(b.length + 1);
+  for (let j = 0; j <= b.length; j++) prev[j] = j;
+
+  for (let i = 1; i <= a.length; i++) {
+    curr[0] = i;
+    const ac = a.charCodeAt(i - 1);
+    for (let j = 1; j <= b.length; j++) {
+      const cost = ac === b.charCodeAt(j - 1) ? 0 : 1;
+      curr[j] = Math.min(
+        prev[j]! + 1, // deletion
+        curr[j - 1]! + 1, // insertion
+        prev[j - 1]! + cost, // substitution
+      );
+    }
+    [prev, curr] = [curr, prev];
+  }
+  return prev[b.length]!;
+}
+
+/** Normalized similarity in [0,1]: 1 - dist / max(len). */
+function similarity(a: string, b: string): number {
+  const maxLen = Math.max(a.length, b.length);
+  if (maxLen === 0) return 1;
+  return 1 - levenshtein(a, b) / maxLen;
+}
+
+function locateByLevenshtein(content: string, needle: string): MatchResult | null {
+  const contentLines = splitLines(content);
+  const needleLines = trimBlankLines(needle.split('\n'));
+  const n = needleLines.length;
+  if (n === 0) return null;
+  if (contentLines.length < n) return null;
+
+  const needleJoined = needleLines.map((l) => l.trim()).join('\n');
+
+  let best = -1;
+  let bestSpan: { start: number; end: number } | null = null;
+  for (let i = 0; i + n <= contentLines.length; i++) {
+    const window = contentLines.slice(i, i + n);
+    const windowJoined = window.map((l) => l.text.trim()).join('\n');
+    const score = similarity(windowJoined, needleJoined);
+    if (score > best) {
+      best = score;
+      bestSpan = { start: window[0]!.start, end: window[n - 1]!.end };
+    }
+  }
+
+  if (bestSpan && best >= SIMILARITY_THRESHOLD) {
+    return { kind: 'fuzzy', start: bestSpan.start, end: bestSpan.end };
+  }
+  return null;
+}
--- a/apps/coder/src/services/pending_changes.ts
+++ b/apps/coder/src/services/pending_changes.ts
@@ -2,6 +2,7 @@ import { readFile, writeFile, unlink, mkdir } from 'node:fs/promises';
 import { dirname } from 'node:path';
 import type { Sql } from '../db.js';
 import { resolveWritePath } from './write_guard.js';
+import { locateMatch } from './fuzzy-match.js';

 // --- Types -------------------------------------------------------------------

@@ -121,10 +122,18 @@ export async function applyOne(
      case 'edit': {
        const { old: oldStr, new: newStr } = JSON.parse(change.diff) as { old: string; new: string };
        const content = await readFile(change.file_path, 'utf8');
-        if (!content.includes(oldStr)) {
-          throw new Error('old_string not found in file — file may have changed since the edit was queued');
+        const match = locateMatch(content, oldStr);
+        if (match.kind === 'ambiguous') {
+          throw new Error(
+            `old_string matches ${match.count} locations — add surrounding context to disambiguate`,
+          );
        }
-        const updated = content.replace(oldStr, newStr);
+        if (match.kind === 'not_found') {
+          throw new Error(
+            'old_string not found in file (even fuzzily) — file may have changed since the edit was queued',
+          );
+        }
+        const updated = content.slice(0, match.start) + newStr + content.slice(match.end);
        await writeFile(change.file_path, updated, 'utf8');
        break;
      }
@@ -203,10 +212,18 @@ export async function rewindOne(
        // Reverse an edit: swap old and new
        const { old: oldStr, new: newStr } = JSON.parse(change.diff) as { old: string; new: string };
        const content = await readFile(change.file_path, 'utf8');
-        if (!content.includes(newStr)) {
-          throw new Error('new_string not found in file — cannot rewind; file may have been modified since apply');
+        const match = locateMatch(content, newStr);
+        if (match.kind === 'ambiguous') {
+          throw new Error(
+            `new_string matches ${match.count} locations — cannot rewind; add surrounding context to disambiguate`,
+          );
        }
-        const reverted = content.replace(newStr, oldStr);
+        if (match.kind === 'not_found') {
+          throw new Error(
+            'new_string not found in file (even fuzzily) — cannot rewind; file may have been modified since apply',
+          );
+        }
+        const reverted = content.slice(0, match.start) + oldStr + content.slice(match.end);
        await writeFile(change.file_path, reverted, 'utf8');
        break;
      }