feat(reasoning-effort): persisted per-conversation + per-turn override, threaded to providers

- conversation-store: get/setReasoningEffort (own key space, mirrors cwd)
- session-orchestrator: resolveReasoningEffort (override -> stored -> 'high'),
  StartTurnInput.reasoningEffort, warm() parity (cache-safe)
- transport-http: /chat validation (400 on bad level) + GET/PUT
  /conversations/:id/reasoning-effort
- transport-ws: chat.send threading + validation
- cli: --effort <low|medium|high|xhigh|max>

993 vitest + 189 bun tests green; typecheck + biome clean.

1 files changed, 16 insertions, 0 deletions

diff --git a/packages/cli/src/message.test.ts b/packages/cli/src/message.test.ts
index 8d6d9e1..a3f1e0b 100644
--- a/packages/cli/src/message.test.ts
+++ b/packages/cli/src/message.test.ts
@@ -78,4 +78,20 @@ describe("buildChatRequest", () => {
 		);
 		expect(req.cwd).toBe("/explicit");
 	});
+
+	it("includes reasoningEffort when provided", () => {
+		const req = buildChatRequest(
+			{ modelName: "m", text: "x", reasoningEffort: "xhigh", showReasoning: false },
+			{ cwd: "/work", message: "x" },
+		);
+		expect(req.reasoningEffort).toBe("xhigh");
+	});
+
+	it("omits reasoningEffort when not provided", () => {
+		const req = buildChatRequest(
+			{ modelName: "m", text: "x", showReasoning: false },
+			{ cwd: "/work", message: "x" },
+		);
+		expect(req).not.toHaveProperty("reasoningEffort");
+	});
 });