From 057e3a494cb6ee28ef058b6fd8d1122853596d65 Mon Sep 17 00:00:00 2001
From: Volodymyr Kartavyi <vkartaviy@gmail.com>
Date: Wed, 11 Mar 2026 21:59:02 +0100
Subject: [PATCH] fix: ensure embedded PostgreSQL databases use UTF-8 encoding

On macOS, `initdb` defaults to SQL_ASCII encoding because it infers
locale from the system environment. When `ensurePostgresDatabase()`
creates a database without specifying encoding, the new database
inherits SQL_ASCII from the cluster. This causes string functions like
`left()` to operate on bytes instead of characters, producing invalid
UTF-8 when multi-byte characters are truncated.

Two-part fix:
1. Pass `--encoding=UTF8 --locale=C` via `initdbFlags` to all
   EmbeddedPostgres constructors so the cluster defaults to UTF-8.
2. Explicitly set `encoding 'UTF8'` in the CREATE DATABASE statement
   with `template template0` (required because template1 may already
   have a different encoding) and `C` locale for portability.

Existing databases created with SQL_ASCII are NOT automatically fixed;
users must delete their local `data/db` directory and restart to
re-initialize the cluster.

Relates to #636

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---
 cli/src/commands/worktree.ts         | 1 +
 packages/db/src/client.ts            | 2 +-
 packages/db/src/migration-runtime.ts | 1 +
 server/src/index.ts                  | 1 +
 4 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/cli/src/commands/worktree.ts b/cli/src/commands/worktree.ts
index 8781b008..d956f3d3 100644
--- a/cli/src/commands/worktree.ts
+++ b/cli/src/commands/worktree.ts
@@ -505,6 +505,7 @@ async function ensureEmbeddedPostgres(dataDir: string, preferredPort: number): P
     password: "paperclip",
     port,
     persistent: true,
+    initdbFlags: ["--encoding=UTF8", "--locale=C"],
     onLog: () => {},
     onError: () => {},
   });
diff --git a/packages/db/src/client.ts b/packages/db/src/client.ts
index c4275dc4..83b4aa78 100644
--- a/packages/db/src/client.ts
+++ b/packages/db/src/client.ts
@@ -730,7 +730,7 @@ export async function ensurePostgresDatabase(
     `;
     if (existing.length > 0) return "exists";
 
-    await sql.unsafe(`create database "${databaseName}"`);
+    await sql.unsafe(`create database "${databaseName}" encoding 'UTF8' lc_collate 'C' lc_ctype 'C' template template0`);
     return "created";
   } finally {
     await sql.end();
diff --git a/packages/db/src/migration-runtime.ts b/packages/db/src/migration-runtime.ts
index bc90b762..10b7b9b1 100644
--- a/packages/db/src/migration-runtime.ts
+++ b/packages/db/src/migration-runtime.ts
@@ -96,6 +96,7 @@ async function ensureEmbeddedPostgresConnection(
     password: "paperclip",
     port: preferredPort,
     persistent: true,
+    initdbFlags: ["--encoding=UTF8", "--locale=C"],
     onLog: () => {},
     onError: () => {},
   });
diff --git a/server/src/index.ts b/server/src/index.ts
index c220df92..50c6a7b2 100644
--- a/server/src/index.ts
+++ b/server/src/index.ts
@@ -334,6 +334,7 @@ export async function startServer(): Promise<StartedServer> {
         password: "paperclip",
         port,
         persistent: true,
+        initdbFlags: ["--encoding=UTF8", "--locale=C"],
         onLog: appendEmbeddedPostgresLog,
         onError: appendEmbeddedPostgresLog,
       });