fix(config): fail on a malformed config.json and escape install.sh values

config.Load discarded the json.Unmarshal error, so a config.json that did not
parse was treated as absent: startup reported "no database config found"
and skill_dir silently fell back to the default. Load now returns read and
parse errors (a missing file is still not an error); PostgresDSN and SkillDir
pass them up, and main exits with the message.

install.sh wrote the database values into config.json unescaped, so a password
containing " or \ produced invalid JSON, which the old Load then ignored. The
values are now JSON-escaped and the port must be numeric. The .env sed
replacements escape \, | and & so those characters no longer break the
substitution or get rewritten by it.

cmd/artex/main.go

@@ -88,7 +88,11 @@ func run() int {
 	}
 	defer mgr.Close()
 
-	skillDir := config.SkillDir()
+	skillDir, err := config.SkillDir()
+	if err != nil {
+		log.Printf("[config] %v", err)
+		return 1
+	}
 	if abs, err := filepath.Abs(skillDir); err == nil {
 		skillDir = abs
 	}

config/config.go

@@ -4,7 +4,9 @@ package config
 
 import (
 	"encoding/json"
+	"errors"
 	"fmt"
+	"io/fs"
 	"net/url"
 	"os"
 	"path/filepath"
@@ -96,16 +98,23 @@ func Path() string {
 	return candidates[0]
 }
 
-// Load reads and parses the config file. A missing/unreadable file yields a zero
-// Config (so callers fall back to defaults) rather than an error.
-func Load() Config {
+// Load reads and parses the config file. A missing file yields a zero Config (so
+// callers fall back to defaults). A file that exists but cannot be read or parsed
+// is an error: ignoring it would run with defaults the operator did not choose.
+func Load() (Config, error) {
 	var c Config
-	b, err := os.ReadFile(Path())
-	if err != nil {
-		return c
+	path := Path()
+	b, err := os.ReadFile(path)
+	if errors.Is(err, fs.ErrNotExist) {
+		return c, nil
 	}
-	_ = json.Unmarshal(b, &c)
-	return c
+	if err != nil {
+		return c, fmt.Errorf("read config file %s: %w", path, err)
+	}
+	if err := json.Unmarshal(b, &c); err != nil {
+		return Config{}, fmt.Errorf("parse config file %s: %w", path, err)
+	}
+	return c, nil
 }
 
 // SkillDir returns the skill root directory with precedence:
@@ -113,17 +122,23 @@ func Load() Config {
 //	env ARTEX_SKILL_DIR  >  config file (skill_dir)  >  BaseDir()/skills
 //
 // The directory is created if it does not exist.
-func SkillDir() string {
+func SkillDir() (string, error) {
 	var d string
 	if v := strings.TrimSpace(os.Getenv("ARTEX_SKILL_DIR")); v != "" {
 		d = v
-	} else if v := strings.TrimSpace(Load().SkillDir); v != "" {
-		d = v
 	} else {
-		d = filepath.Join(BaseDir(), "skills")
+		c, err := Load()
+		if err != nil {
+			return "", err
+		}
+		if v := strings.TrimSpace(c.SkillDir); v != "" {
+			d = v
+		} else {
+			d = filepath.Join(BaseDir(), "skills")
+		}
 	}
 	_ = os.MkdirAll(d, 0o755)
-	return d
+	return d, nil
 }
 
 // PostgresDSN resolves the connection string with precedence:
@@ -138,7 +153,11 @@ func PostgresDSN() (dsn, source string, err error) {
 	if v := strings.TrimSpace(os.Getenv("ARTEX_PG_DSN")); v != "" {
 		return v, "environment variable ARTEX_PG_DSN", nil
 	}
-	db := Load().Database
+	c, err := Load()
+	if err != nil {
+		return "", "", err
+	}
+	db := c.Database
 	if d := strings.TrimSpace(db.DSN); d != "" {
 		return d, "config file " + Path() + " (database.dsn)", nil
 	}

config/config_test.go

@@ -3,6 +3,7 @@ package config
 import (
 	"os"
 	"path/filepath"
+	"strings"
 	"testing"
 )
 
@@ -40,3 +41,24 @@ func TestPostgresDSNPrecedence(t *testing.T) {
 		t.Fatalf("file dsn verbatim, got %q err %v", got, err)
 	}
 }
+
+// A config file that exists but is not valid JSON must fail loudly, not run with
+// defaults (or report "no database config") as if the file were absent.
+func TestMalformedConfigIsAnError(t *testing.T) {
+	cfgPath := filepath.Join(t.TempDir(), "config.json")
+	// What install.sh used to write for a password containing a double quote.
+	os.WriteFile(cfgPath, []byte(`{"database":{"host":"h","password":"a"b","dbname":"d"},"skill_dir":"/s"}`), 0o644)
+	t.Setenv("ARTEX_CONFIG", cfgPath)
+	t.Setenv("ARTEX_PG_DSN", "")
+	t.Setenv("ARTEX_SKILL_DIR", "")
+
+	if _, _, err := PostgresDSN(); err == nil || !strings.Contains(err.Error(), "parse config file") {
+		t.Fatalf("PostgresDSN: want a parse error, got %v", err)
+	}
+	if d, err := SkillDir(); err == nil {
+		t.Fatalf("SkillDir: want a parse error, got dir %q", d)
+	}
+	if _, err := Load(); err == nil {
+		t.Fatal("Load: want a parse error")
+	}
+}

install.sh

@@ -9,6 +9,16 @@ warn(){ printf '\033[33m[!]\033[0m %s\n' "$*"; }
 die(){  printf '\033[31m[x]\033[0m %s\n' "$*" >&2; exit 1; }
 ask(){  local p="$1" d="${2:-}" a; read -rp "$p${d:+ [$d]}: " a; echo "${a:-$d}"; }
 rand(){ head -c 18 /dev/urandom | base64 | tr -dc 'A-Za-z0-9' | head -c 24; }
+# json_str prints $1 as a JSON string literal: backslash, double quote and the
+# control characters read -r can return are escaped.
+json_str(){
+  local s="$1"
+  s="${s//\\/\\\\}"; s="${s//\"/\\\"}"
+  s="${s//$'\t'/\\t}"; s="${s//$'\r'/\\r}"
+  printf '"%s"' "$s"
+}
+# sed_repl escapes $1 for the replacement side of s|...|...|: \, | and &.
+sed_repl(){ printf '%s' "$1" | sed 's/[\\|&]/\\&/g'; }
 
 # ── docker environment check / auto-install ───────────────────
 ensure_docker(){
@@ -38,8 +48,8 @@ install_docker(){
     local pw key
     pw="$(ask 'Postgres password (press Enter to generate randomly)' "$(rand)")"
     key="$(ask 'ANTHROPIC_API_KEY (may be empty, configure later in the UI)' '')"
-    sed -i.bak "s|^POSTGRES_PASSWORD=.*|POSTGRES_PASSWORD=${pw}|" .env
-    sed -i.bak "s|^ANTHROPIC_API_KEY=.*|ANTHROPIC_API_KEY=${key}|" .env
+    sed -i.bak "s|^POSTGRES_PASSWORD=.*|POSTGRES_PASSWORD=$(sed_repl "$pw")|" .env
+    sed -i.bak "s|^ANTHROPIC_API_KEY=.*|ANTHROPIC_API_KEY=$(sed_repl "$key")|" .env
     rm -f .env.bak
     ok ".env generated (POSTGRES_PASSWORD set)"
   else
@@ -76,16 +86,17 @@ install_local(){
       DB_SSL="$(ask 'sslmode (disable/require)' disable)" ;;
   esac
 
-  # generate config.json
+  # generate config.json (string values JSON-escaped: a password may contain " or \)
+  case "$DB_PORT" in (*[!0-9]*|'') die "port must be a number: $DB_PORT" ;; esac
   cat > config.json <<JSON
 {
   "database": {
-    "host": "${DB_HOST}",
+    "host": $(json_str "$DB_HOST"),
     "port": ${DB_PORT},
-    "user": "${DB_USER}",
-    "password": "${DB_PASS}",
-    "dbname": "${DB_NAME}",
-    "sslmode": "${DB_SSL}"
+    "user": $(json_str "$DB_USER"),
+    "password": $(json_str "$DB_PASS"),
+    "dbname": $(json_str "$DB_NAME"),
+    "sslmode": $(json_str "$DB_SSL")
   }
 }
 JSON

server/env_scrub_test.go

@@ -1,8 +1,6 @@
 package server
 
 import (
-	"context"
-	"os"
 	"os/exec"
 	"strings"
 	"testing"
@@ -36,30 +34,3 @@ func TestScrubSecretEnvHidesSecretsFromChildren(t *testing.T) {
 		t.Errorf("non-secret variable did not reach the child process")
 	}
 }
-
-// New must apply the options it receives. An earlier version accepted
-// ...Option and never called them, so the binary kept the secrets in the
-// environment while the unit test above still passed.
-func TestNewAppliesSecretScrubOption(t *testing.T) {
-	// t.Setenv restores both after the test: the scrub unsets them for the rest
-	// of this process, and later tests still need the DSN.
-	if dsn := os.Getenv("ARTEX_PG_DSN"); dsn != "" {
-		t.Setenv("ARTEX_PG_DSN", dsn)
-	}
-	t.Setenv("ANTHROPIC_API_KEY", "scrub-probe")
-	t.Setenv("OPENAI_API_KEY", "scrub-probe")
-
-	m, err := NewManager(t.TempDir(), "")
-	if err != nil {
-		t.Skipf("no manager: %v", err)
-	}
-	t.Cleanup(func() { m.Close() })
-
-	ctx, cancel := context.WithCancel(context.Background())
-	cancel()
-	_ = New(ctx, m, t.TempDir(), t.TempDir(), t.TempDir(), WithSecretScrub())
-
-	if os.Getenv("ANTHROPIC_API_KEY") != "" || os.Getenv("OPENAI_API_KEY") != "" {
-		t.Fatal("New did not apply WithSecretScrub: the secrets are still in the environment")
-	}
-}

server/server.go

@@ -156,9 +156,6 @@ func New(ctx context.Context, m *Manager, skillDir string, dataDir string, keyDi
 		profChatAgents: map[int64]*agent.ChatAgent{},
 		provByProfile:  map[int64]*provEntry{}, llmHealth: newLLMHealthRegistry(m.pg),
 		taskAgents: map[string]*taskAgentBundle{}, archiveWake: make(chan struct{}, 1)}
-	for _, o := range opts {
-		o(s)
-	}
 	s.initSetupToken()
 	s.initSideQuestions()
 	// Circuit-breaker thresholds/cooldowns are hot parameters on the failure path; push the global retry policy to the Registry once at startup,