Merge remote-tracking branch 'origin/master' into gitea/feature/end

Resolved conflicts taking origin/master (v0.5.55) as canonical, with local
features re-applied:
- runtime log level (LOG_LEVEL env + dashboard Settings → Logging, applied
  immediately and persisted across restarts)
- free/noAuth provider enable/disable toggle via providerStrategies.enabled
- parallel model testing (Test All Models / Test Selected Keys)

tests/translator/thinking-unified.test.js

@@ -18,6 +18,12 @@ describe("parseSuffix", () => {
   it("parses level suffix", () => {
     expect(parseSuffix("gpt-5(high)")).toEqual({ cleanModel: "gpt-5", override: { mode: "level", level: "high" } });
   });
+  it("parses ultra suffix", () => {
+    expect(parseSuffix("gpt-5.6-sol(ultra)")).toEqual({
+      cleanModel: "gpt-5.6-sol",
+      override: { mode: "level", level: "ultra" },
+    });
+  });
   it("parses numeric budget suffix", () => {
     expect(parseSuffix("model(8192)")).toEqual({ cleanModel: "model", override: { mode: "budget", budget: 8192 } });
   });
@@ -55,10 +61,14 @@ describe("extractThinking", () => {
 });
 
 describe("applyThinking per provider format", () => {
-  it("claude 4.6+ → adaptive output_config (no budget_tokens)", () => {
+  it("claude 4.6+ → adaptive thinking + output_config (no budget_tokens)", () => {
     const out = apply("claude", "claude-opus-4.7", { reasoning_effort: "high" }, "claude");
     expect(out.output_config).toEqual({ effort: "high" });
-    expect(out.thinking).toBeUndefined();
+    // Anthropic: on Opus 4.6/4.7/4.8 and Sonnet 4.6 thinking stays OFF unless
+    // thinking:{type:"adaptive"} is sent explicitly; output_config alone is not
+    // enough (and Anthropic-compatible shims like Copilot default off even on
+    // Sonnet 5). Both fields together are the documented adaptive shape.
+    expect(out.thinking).toEqual({ type: "adaptive" });
   });
   it("claude haiku → enabled+budget", () => {
     const out = apply("claude", "claude-haiku-4.5", { reasoning_effort: "high" }, "claude");
@@ -78,11 +88,27 @@ describe("applyThinking per provider format", () => {
     const out = apply("gemini", "gemini-3-pro", { reasoning_effort: "auto" }, "gemini");
     expect(out.generationConfig.thinkingConfig.thinkingLevel).toBe("high");
   });
+  it("gemini-3 high thinking raises too-small maxOutputTokens", () => {
+    const out = apply("gemini-cli", "gemini-3.1-pro-preview", {
+      request: { generationConfig: { maxOutputTokens: 128 } },
+      reasoning_effort: "high",
+    }, "gemini-cli");
+    expect(out.request.generationConfig.thinkingConfig).toEqual({ thinkingLevel: "high", includeThoughts: true });
+    expect(out.request.generationConfig.maxOutputTokens).toBe(65535);
+  });
   it("gemini-2.5 → thinkingBudget", () => {
     const out = apply("gemini", "gemini-2.5-flash", { reasoning_effort: "high" }, "gemini");
     expect(out.generationConfig.thinkingConfig.thinkingBudget).toBe(24576);
     expect(out.generationConfig.thinkingConfig.thinkingLevel).toBeUndefined();
   });
+  it("gemini-2.5 budget thinking keeps enough room for answer tokens", () => {
+    const out = apply("gemini-cli", "gemini-2.5-pro", {
+      request: { generationConfig: { maxOutputTokens: 1024 } },
+      reasoning_effort: "high",
+    }, "gemini-cli");
+    expect(out.request.generationConfig.thinkingConfig).toEqual({ thinkingBudget: 24576, includeThoughts: true });
+    expect(out.request.generationConfig.maxOutputTokens).toBe(32768);
+  });
   it("GLM off → enable_thinking:false (not thinking.disabled)", () => {
     const out = apply("openai", "glm-4.6", { reasoning_effort: "none" }, "glm");
     expect(out.enable_thinking).toBe(false);
@@ -106,6 +132,16 @@ describe("applyThinking per provider format", () => {
     const out = apply("openai", "kimi-k2.6", { reasoning_effort: "high" }, "kimi");
     expect(out.reasoning_effort).toBe("high");
   });
+  it("Kimi auto → supported reasoning_effort", () => {
+    const out = apply("openai", "kimi-k2.7", { reasoning_effort: "auto" }, "kimchi");
+    expect(out.reasoning_effort).toBe("high");
+  });
+  it("Kimi unsupported OpenAI levels → supported reasoning_effort", () => {
+    const minimal = apply("openai", "kimi-k2.7", { reasoning_effort: "minimal" }, "kimchi");
+    const xhigh = apply("openai", "kimi-k2.7", { reasoning_effort: "xhigh" }, "kimchi");
+    expect(minimal.reasoning_effort).toBe("low");
+    expect(xhigh.reasoning_effort).toBe("max");
+  });
   it("MiniMax M3 → adaptive", () => {
     const out = apply("claude", "MiniMax-M3", { reasoning_effort: "high" }, "minimax");
     expect(out.thinking).toEqual({ type: "adaptive" });
@@ -127,6 +163,25 @@ describe("applyThinking per provider format", () => {
     const out = apply("openai", "gpt-5.3-codex", { reasoning_effort: "xhigh" }, "codex");
     expect(out.reasoning_effort).toBe("xhigh");
   });
+  it.each([
+    ["gpt-5.6-sol", "max", "max"],
+    ["gpt-5.6-sol", "ultra", "ultra"],
+    ["gpt-5.6-terra", "max", "max"],
+    ["gpt-5.6-terra", "ultra", "ultra"],
+    ["gpt-5.6-luna", "max", "max"],
+    ["gpt-5.6-luna", "ultra", "max"],
+  ])("normalizes Codex %s effort %s to %s", (model, effort, expected) => {
+    const out = apply("openai-responses", model, { reasoning: { effort } }, "codex");
+    expect(out.reasoning_effort).toBe(expected);
+  });
+  it("applies a supported Codex Ultra suffix", () => {
+    const out = apply("openai-responses", "gpt-5.6-sol(ultra)", {}, "codex");
+    expect(out.reasoning_effort).toBe("ultra");
+  });
+  it("keeps Codex-only GPT-5.6 levels out of Kiro translation", () => {
+    const out = apply("openai", "gpt-5.6-sol", { reasoning_effort: "max" }, "kiro");
+    expect(out.reasoning_effort).toBe("xhigh");
+  });
 });
 
 describe("extractReasoningText (response shapes)", () => {