feat(kimi): declare the 256K context window for Kimi For Coding

Claude Code caps unknown model ids at 200K, so the preset's standalone
CLAUDE_CODE_AUTO_COMPACT_WINDOW=262144 was clamped by min(window, value)
and never took effect. Pair it with CLAUDE_CODE_MAX_CONTEXT_TOKENS and
route the endpoint's kimi-for-coding alias on every tier, since both
context envs are ignored for claude-* prefixed model ids.

Saved providers get the same context defaults injected into effective
live settings at switch time, with a mirror-inverse strip on backfill so
injected values never harden into provider config. Explicit user values
always win over the injected defaults.

src/config/claudeProviderPresets.ts

@@ -486,10 +486,23 @@ export const providerPresets: ProviderPreset[] = [
       env: {
         ANTHROPIC_BASE_URL: "https://api.kimi.com/coding/",
         ANTHROPIC_AUTH_TOKEN: "",
+        // CLAUDE_CODE_MAX_CONTEXT_TOKENS 只对非 claude- 前缀模型 id 生效，
+        // 必须显式路由端点别名 kimi-for-coding（与 codex/hermes/opencode 预设一致）
+        ANTHROPIC_MODEL: "kimi-for-coding",
+        ANTHROPIC_DEFAULT_HAIKU_MODEL: "kimi-for-coding",
+        ANTHROPIC_DEFAULT_SONNET_MODEL: "kimi-for-coding",
+        ANTHROPIC_DEFAULT_OPUS_MODEL: "kimi-for-coding",
+        CLAUDE_CODE_MAX_CONTEXT_TOKENS: "${CLAUDE_CODE_MAX_CONTEXT_TOKENS}",
         CLAUDE_CODE_AUTO_COMPACT_WINDOW: "${CLAUDE_CODE_AUTO_COMPACT_WINDOW}",
       },
     },
     templateValues: {
+      CLAUDE_CODE_MAX_CONTEXT_TOKENS: {
+        label: "Max Context Tokens",
+        placeholder: "262144",
+        defaultValue: "262144",
+        editorValue: "262144",
+      },
       CLAUDE_CODE_AUTO_COMPACT_WINDOW: {
         label: "Auto Compact Window",
         placeholder: "262144",