fix(agent): downgrade xhigh→max on Anthropic pre-4.7 adaptive models

Regression from #11161 (Claude Opus 4.7 migration, commit 0517ac3e).

The Opus 4.7 migration changed `ADAPTIVE_EFFORT_MAP["xhigh"]` from "max"
(the pre-migration alias) to "xhigh" to preserve the new 4.7 effort level
as distinct from max. This is correct for 4.7, but Opus/Sonnet 4.6 only
expose 4 levels (low/medium/high/max) — sending "xhigh" there now 400s:

    BadRequestError [HTTP 400]: This model does not support effort
    level 'xhigh'. Supported levels: high, low, max, medium.

Users who set reasoning_effort=xhigh as their default (xhigh is the
recommended default for coding/agentic on 4.7 per the Anthropic migration
guide) now 400 every request the moment they switch back to a 4.6 model
via `/model` or config. Verified live against the Anthropic API on
`anthropic==0.94.0`.

Fix: make the mapping model-aware. Add `_supports_xhigh_effort()`
predicate (matches 4-7/4.7 substrings, mirroring the existing
`_supports_adaptive_thinking` / `_forbids_sampling_params` pattern).
On pre-4.7 adaptive models, downgrade xhigh→max (the strongest effort
those models accept, restoring pre-migration behavior). On 4.7+, keep
xhigh as a distinct level.

Per Anthropic's migration guide, xhigh is 4.7-only:
https://platform.claude.com/docs/en/about-claude/models/migration-guide
> Opus 4.7 effort levels: max, xhigh (new), high, medium, low.
> Opus 4.6 effort levels: max, high, medium, low.
SDK typing confirms: `anthropic.types.OutputConfigParam.effort: Literal[
"low", "medium", "high", "max"]` (v0.94.0 not yet updated for xhigh).

## Test plan

Verified live on macOS 15.5 / anthropic==0.94.0:

    claude-opus-4-6 + effort=xhigh → output_config.effort=max  → 200 OK
    claude-opus-4-7 + effort=xhigh → output_config.effort=xhigh → 200 OK
    claude-opus-4-6 + effort=max   → output_config.effort=max  → 200 OK
    claude-opus-4-7 + effort=max   → output_config.effort=max  → 200 OK

`tests/agent/test_anthropic_adapter.py` — 120 pass (replaced 1 bugged
test that asserted the broken behavior, added 1 for 4.7 preservation).

Full adapter suite: 120 passed in 1.05s.
Broader suite (agent + run_agent + cli/gateway reasoning): 2140 passed
(2 pre-existing failures on clean upstream/main, unrelated).

## Platforms

Tested on macOS 15.5. No platform-specific code paths touched.

tests/agent/test_anthropic_adapter.py

@@ -959,11 +959,13 @@ class TestBuildAnthropicKwargs:
         assert "temperature" not in kwargs
         assert kwargs["max_tokens"] == 4096
 
-    def test_reasoning_config_maps_xhigh_to_xhigh_effort_for_4_6_models(self):
-        # Opus 4.7 added "xhigh" as a distinct effort level (the recommended
-        # default for coding/agentic work). Earlier mapping aliased xhigh→max,
-        # which silently over-efforted every request. 2026-04-16 migration
-        # guide: xhigh and max are distinct levels.
+    def test_reasoning_config_downgrades_xhigh_to_max_for_4_6_models(self):
+        # Opus 4.7 added "xhigh" as a distinct effort level (low/medium/high/
+        # xhigh/max). Opus 4.6 only supports low/medium/high/max — sending
+        # "xhigh" there returns an API 400. Preserve the pre-migration
+        # behavior of aliasing xhigh→max on pre-4.7 adaptive models so users
+        # who prefer xhigh as their default don't 400 every request when
+        # switching back to 4.6.
         kwargs = build_anthropic_kwargs(
             model="claude-sonnet-4-6",
             messages=[{"role": "user", "content": "think harder"}],
@@ -972,6 +974,19 @@ class TestBuildAnthropicKwargs:
             reasoning_config={"enabled": True, "effort": "xhigh"},
         )
         assert kwargs["thinking"] == {"type": "adaptive", "display": "summarized"}
+        assert kwargs["output_config"] == {"effort": "max"}
+
+    def test_reasoning_config_preserves_xhigh_for_4_7_models(self):
+        # On 4.7+ xhigh is a real level and the recommended default for
+        # coding/agentic work — keep it distinct from max.
+        kwargs = build_anthropic_kwargs(
+            model="claude-opus-4-7",
+            messages=[{"role": "user", "content": "think harder"}],
+            tools=None,
+            max_tokens=4096,
+            reasoning_config={"enabled": True, "effort": "xhigh"},
+        )
+        assert kwargs["thinking"] == {"type": "adaptive", "display": "summarized"}
         assert kwargs["output_config"] == {"effort": "xhigh"}
 
     def test_reasoning_config_maps_max_effort_for_4_7_models(self):