feat(agent): auto-enable GLM-4.7 thinking mode

Add automatic thinking mode support for Z.AI GLM-4.x models:
- GLM-4.7: Preserved thinking (clear_thinking: false)
- GLM-4.5/4.6: Interleaved thinking (clear_thinking: true)

Uses Z.AI Cloud API format: thinking: { type: "enabled", clear_thinking: boolean }

Includes patches for pi-ai, pi-agent-core, and pi-coding-agent to pass
extraParams through the stream pipeline. User can override via config
or disable via --thinking off.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

package.json

@@ -158,6 +158,8 @@
     },
     "patchedDependencies": {
       "@mariozechner/pi-ai": "patches/@mariozechner__pi-ai.patch",
+      "@mariozechner/pi-agent-core": "patches/@mariozechner__pi-agent-core.patch",
+      "@mariozechner/pi-coding-agent": "patches/@mariozechner__pi-coding-agent.patch",
       "qrcode-terminal": "patches/qrcode-terminal.patch",
       "playwright-core@1.57.0": "patches/playwright-core@1.57.0.patch"
     }
@@ -196,6 +198,8 @@
   },
   "patchedDependencies": {
     "@mariozechner/pi-ai": "patches/@mariozechner__pi-ai.patch",
+    "@mariozechner/pi-agent-core": "patches/@mariozechner__pi-agent-core.patch",
+    "@mariozechner/pi-coding-agent": "patches/@mariozechner__pi-coding-agent.patch",
     "qrcode-terminal": "patches/qrcode-terminal.patch",
     "playwright-core@1.57.0": "patches/playwright-core@1.57.0.patch"
   }