fix(cli): keep Anthropic exec-only in the interactive TUI

The fleet-foundation provider expansion added Anthropic/Zai/Stepfun/Minimax as
recognized providers (auth parser + PROVIDER_LIST), but also flipped all four to
TUI-supported in provider_is_supported_by_tui — making every ProviderKind
supported, killing the rejection path and breaking three build_tui_command
rejection tests (the flip had no positive test, so it was an unverified side
effect).

Anthropic speaks the native Messages API, not the OpenAI-compatible shape the
interactive loop expects, so it stays exec-only (as it was on origin):
`codewhale --provider anthropic` is rejected with a hint to use
`codewhale exec --provider anthropic`. Zai (GLM/Z.AI — the v0.8.60 headline),
Stepfun, and Minimax are OpenAI-compatible and remain interactively supported.

Restores the rejection guard and the 3 tests (now 95/0 in codewhale-cli).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

crates/cli/src/lib.rs

@@ -845,11 +845,16 @@ fn provider_is_supported_by_tui(provider: ProviderKind) -> bool {
             | ProviderKind::Huggingface
             | ProviderKind::Together
             | ProviderKind::OpenaiCodex
-            | ProviderKind::Anthropic
             | ProviderKind::Zai
             | ProviderKind::Stepfun
             | ProviderKind::Minimax
     )
+    // NOTE: Anthropic is intentionally exec-only in the interactive TUI: it
+    // speaks the native Messages API rather than the OpenAI-compatible shape the
+    // interactive loop expects, so `codewhale --provider anthropic` is rejected
+    // with a hint to use `codewhale exec --provider anthropic`. Zai (GLM/Z.AI),
+    // Stepfun, and Minimax are OpenAI-compatible and supported interactively.
+    // (Re-evaluate if/when the interactive loop gains a native Anthropic client.)
 }
 
 fn supported_tui_providers_csv() -> String {