Add SubagentStop hook (#22873)

# What

<img width="1792" height="1024" alt="image"
src="https://github.com/user-attachments/assets/8f81d232-5813-4994-a61d-e42a05a93a3e"
/>

`SubagentStop` runs when a thread-spawned subagent turn is about to
finish. Thread-spawned subagents use `SubagentStop` instead of the
normal root-agent `Stop` hook.

Configured handlers match on `agent_type`. Hook input includes the
normal stop fields plus:

- `agent_id`: the child thread id.
- `agent_type`: the resolved subagent type.
- `agent_transcript_path`: the child subagent transcript path.
- `transcript_path`: the parent thread transcript path.
- `last_assistant_message`: the final assistant message from the child
turn, when available.
- `stop_hook_active`: `true` when the child is already continuing
because an earlier stop-like hook blocked completion.

`SubagentStop` shares the same completion-control semantics as `Stop`,
scoped to the child turn:

- No decision allows the child turn to finish.
- `decision: "block"` with a non-empty `reason` records that reason as
hook feedback and continues the child with that prompt.
- `continue: false` stops the child turn. If `stopReason` is present,
Codex surfaces it as the stop reason.

# Lifecycle Scope

Only thread-spawned subagents run `SubagentStop`.

Internal/system subagents such as Review, Compact, MemoryConsolidation,
and Other do not run normal `Stop` hooks and do not run `SubagentStop`.
This avoids exposing synthetic matcher labels for internal
implementation paths.

# Stack

1. #22782: add `SubagentStart`.
2. This PR: add `SubagentStop`.
3. #22882: add subagent identity to normal hook inputs.

codex-rs/hooks/schema/generated/subagent-stop.command.input.schema.json

@@ -0,0 +1,75 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "definitions": {
+    "NullableString": {
+      "type": [
+        "string",
+        "null"
+      ]
+    }
+  },
+  "properties": {
+    "agent_id": {
+      "type": "string"
+    },
+    "agent_transcript_path": {
+      "$ref": "#/definitions/NullableString"
+    },
+    "agent_type": {
+      "type": "string"
+    },
+    "cwd": {
+      "type": "string"
+    },
+    "hook_event_name": {
+      "const": "SubagentStop",
+      "type": "string"
+    },
+    "last_assistant_message": {
+      "$ref": "#/definitions/NullableString"
+    },
+    "model": {
+      "type": "string"
+    },
+    "permission_mode": {
+      "enum": [
+        "default",
+        "acceptEdits",
+        "plan",
+        "dontAsk",
+        "bypassPermissions"
+      ],
+      "type": "string"
+    },
+    "session_id": {
+      "type": "string"
+    },
+    "stop_hook_active": {
+      "type": "boolean"
+    },
+    "transcript_path": {
+      "$ref": "#/definitions/NullableString"
+    },
+    "turn_id": {
+      "description": "Codex extension: expose the active turn id to internal turn-scoped hooks.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "agent_id",
+    "agent_transcript_path",
+    "agent_type",
+    "cwd",
+    "hook_event_name",
+    "last_assistant_message",
+    "model",
+    "permission_mode",
+    "session_id",
+    "stop_hook_active",
+    "transcript_path",
+    "turn_id"
+  ],
+  "title": "subagent-stop.command.input",
+  "type": "object"
+}