fix: use stream-json output for Claude CLI backend to prevent watchdog timeouts

The Claude CLI backend uses `--output-format json`, which produces no
stdout until the entire request completes. When session context is large
(100K+ tokens) or API response is slow, the no-output watchdog timer
(max 180s for resume sessions) kills the process before it finishes,
resulting in "CLI produced no output for 180s and was terminated" errors.

Switch to `--output-format stream-json --verbose` so Claude CLI emits
NDJSON events throughout processing (init, assistant, rate_limit, result).
Each event resets the watchdog timer, which is the intended behavior —
the watchdog detects truly stuck processes, not slow-but-progressing ones.

Changes:
- cli-backends.ts: `json` → `stream-json --verbose`, `output: "jsonl"`
- helpers.ts: teach parseCliJsonl to extract text from Claude's
  `{"type":"result","result":"..."}` NDJSON line

Note: `--verbose` is required for stream-json in `-p` (print) mode.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

extensions/anthropic/cli-backend.ts

@@ -78,17 +78,25 @@ export function buildAnthropicCliBackend(): CliBackendPlugin {
     bundleMcp: true,
     config: {
       command: "claude",
-      args: ["-p", "--output-format", "json", "--permission-mode", "bypassPermissions"],
+      args: [
+        "-p",
+        "--output-format",
+        "stream-json",
+        "--verbose",
+        "--permission-mode",
+        "bypassPermissions",
+      ],
       resumeArgs: [
         "-p",
         "--output-format",
-        "json",
+        "stream-json",
+        "--verbose",
         "--permission-mode",
         "bypassPermissions",
         "--resume",
         "{sessionId}",
       ],
-      output: "json",
+      output: "jsonl",
       input: "arg",
       modelArg: "--model",
       modelAliases: CLAUDE_MODEL_ALIASES,