feat(agents): support thinkingDefault: "adaptive" for Anthropic models (#31227)

* feat(agents): support `thinkingDefault: "adaptive"` for Anthropic models

Anthropic's Opus 4.6 and Sonnet 4.6 support adaptive thinking where the
model dynamically decides when and how much to think.  This is now
Anthropic's recommended mode and `budget_tokens` is deprecated on these
models.

Add "adaptive" as a valid thinking level:
- Config: `agents.defaults.thinkingDefault: "adaptive"`
- CLI: `/think adaptive` or `/think auto`
- Pi SDK mapping: "adaptive" → "medium" effort at the pi-agent-core
  layer, which the Anthropic provider translates to
  `thinking.type: "adaptive"` with `output_config.effort: "medium"`
- Provider fallbacks: OpenRouter and Google map "adaptive" to their
  respective "medium" equivalents

Closes #30880

Made-with: Cursor

* style(changelog): format changelog with oxfmt

* test(types): fix strict typing in runtime/plugin-context tests

---------

Co-authored-by: Peter Steinberger <steipete@gmail.com>

src/agents/openclaw-tools.plugin-context.test.ts

@@ -1,6 +1,9 @@
 import { describe, expect, it, vi } from "vitest";
 
-const resolvePluginToolsMock = vi.fn(() => []);
+const resolvePluginToolsMock = vi.fn((params?: unknown) => {
+  void params;
+  return [];
+});
 
 vi.mock("../plugins/tools.js", () => ({
   resolvePluginTools: (params: unknown) => resolvePluginToolsMock(params),