feat(copilot): strip thinking blocks before forwarding to save premium quota

Copilot routes through OpenAI-compatible endpoints that reject Anthropic's
thinking and redacted_thinking blocks. Previously the request would fail
upstream, burning one premium interaction, and only then trigger
thinking_rectifier to retry. This adds a proactive strip_thinking_blocks
pass in the Copilot optimization pipeline (step 3.5, after tool_result
merging). Signature fields and top-level thinking are left alone — those
are the reactive rectifier's job on the error path.

Also fixes a default-value inconsistency where CopilotOptimizerConfig's
Default impl used "gpt-4o-mini" while the serde default function returned
"gpt-5-mini" (aligned to gpt-5-mini, matching the reference implementation).

Aligned with yuegongzi/copilot-api's /v1/messages handler behavior.

src-tauri/src/proxy/forwarder.rs

@@ -821,6 +821,12 @@ impl RequestForwarder {
                 mapped_body = super::copilot_optimizer::merge_tool_results(mapped_body);
             }
 
+            // 3.5. 主动剥离 thinking block — Copilot 走 OpenAI 兼容端点不识别该块
+            //      避免上游拒绝后由 rectifier 反应式重试（首次请求已消耗 quota）
+            if self.copilot_optimizer_config.strip_thinking {
+                mapped_body = super::copilot_optimizer::strip_thinking_blocks(mapped_body);
+            }
+
             // 4. Warmup 小模型降级
             if self.copilot_optimizer_config.warmup_downgrade && classification.is_warmup {
                 log::info!(