[codex] Add friendly Python SDK sandbox presets (#24772)

## Why

The Python SDK currently exposes sandbox selection differently depending
on where it is used: thread lifecycle methods accept `SandboxMode`,
while turns accept the lower-level `SandboxPolicy` shape. For the common
case of choosing an access level, that leaks app-server wire details
into otherwise straightforward SDK usage.

This makes the common path explicit and discoverable: callers choose a
named sandbox preset once, using the same keyword on threads and turns.
The preset name `workspace_write` also makes the granted capability
clear at the callsite.

## What changed

- Added a root-level `Sandbox` enum with documented presets:
  - `Sandbox.read_only`: read files without allowing writes.
- `Sandbox.workspace_write`: the normal default for projects with a
recorded trust decision; read files and write inside the workspace and
configured writable roots.
  - `Sandbox.full_access`: run without filesystem access restrictions.
- Documented that omitting `sandbox=` delegates to app-server's
configured default, while explicit turn overrides remain sticky for
subsequent turns.
- Updated sync and async thread lifecycle and turn APIs to consistently
accept `sandbox=Sandbox...`, translating to the existing app-server
thread and turn representations internally.
- Updated the public API artifact generator so regenerated SDK wrappers
retain the friendly enum shape.
- Replaced low-level policy construction in Python docs, examples, and
the walkthrough notebook with the preset API.
- Added focused coverage for root exports, method signatures,
preset-to-wire mapping, and rejection of raw string sandbox inputs.

## API impact

High-level turn calls now use `sandbox=` instead of `sandbox_policy=`:

```python
from openai_codex import Codex, Sandbox

with Codex() as codex:
    thread = codex.thread_start(sandbox=Sandbox.workspace_write)
    result = thread.run("Review the diff only.", sandbox=Sandbox.read_only)
```

`thread_start(...)` already defaults to `ApprovalMode.auto_review`, so
normal writable usage is concise:

```python
with Codex() as codex:
    thread = codex.thread_start(sandbox=Sandbox.workspace_write)
    thread.run("Update the files in this workspace.")
```

With that combination, edits inside `cwd` and configured writable roots
run within the workspace-write sandbox. Operations that require
approval, such as edits outside those roots, are routed through auto
review. When `sandbox=` is omitted, app-server resolves its configured
default. A sandbox supplied to `run(...)` or `turn(...)` applies to that
turn and subsequent turns.

## Test coverage

- `sdk/python/tests/test_public_api_signatures.py` covers the public
export and parameter names, including the default approval mode.
- `sdk/python/tests/test_public_api_runtime_behavior.py` covers preset
mappings to the existing wire types and raw string rejection.

sdk/python/notebooks/sdk_walkthrough.ipynb

@@ -220,11 +220,11 @@
    "source": [
     "# Cell 5b: one turn with most optional turn params\n",
     "from pathlib import Path\n",
-    "from openai_codex import (\n",
+    "from openai_codex import Sandbox\n",
+    "from openai_codex.types import (\n",
     "    Personality,\n",
     "    ReasoningEffort,\n",
     "    ReasoningSummary,\n",
-    "    SandboxPolicy,\n",
     ")\n",
     "\n",
     "output_schema = {\n",
@@ -237,7 +237,6 @@
     "    'additionalProperties': False,\n",
     "}\n",
     "\n",
-    "sandbox_policy = SandboxPolicy.model_validate({'type': 'readOnly', 'access': {'type': 'fullAccess'}})\n",
     "summary = ReasoningSummary.model_validate('concise')\n",
     "\n",
     "with Codex() as codex:\n",
@@ -249,7 +248,7 @@
     "        model='gpt-5.4',\n",
     "        output_schema=output_schema,\n",
     "        personality=Personality.pragmatic,\n",
-    "        sandbox_policy=sandbox_policy,\n",
+    "        sandbox=Sandbox.read_only,\n",
     "        summary=summary,\n",
     "    )\n",
     "    result = turn.run()\n",
@@ -266,11 +265,11 @@
    "source": [
     "# Cell 5c: choose highest model + highest supported reasoning, then run turns\n",
     "from pathlib import Path\n",
-    "from openai_codex import (\n",
+    "from openai_codex import Sandbox\n",
+    "from openai_codex.types import (\n",
     "    Personality,\n",
     "    ReasoningEffort,\n",
     "    ReasoningSummary,\n",
-    "    SandboxPolicy,\n",
     ")\n",
     "\n",
     "reasoning_rank = {\n",
@@ -310,7 +309,6 @@
     "    'required': ['summary', 'actions'],\n",
     "    'additionalProperties': False,\n",
     "}\n",
-    "sandbox_policy = SandboxPolicy.model_validate({'type': 'readOnly', 'access': {'type': 'fullAccess'}})\n",
     "\n",
     "with Codex() as codex:\n",
     "    models = codex.models(include_hidden=True)\n",
@@ -337,7 +335,7 @@
     "        model=selected_model.model,\n",
     "        output_schema=output_schema,\n",
     "        personality=Personality.pragmatic,\n",
-    "        sandbox_policy=sandbox_policy,\n",
+    "        sandbox=Sandbox.read_only,\n",
     "        summary=ReasoningSummary.model_validate('concise'),\n",
     "    ).run()\n",
     "    print('agent.message.params:', second.final_response)\n",