feat: forward generation params via MITM + add usageMetadata to Gemini

- Add GenerationParams struct to MitmStore for temperature, top_p,
  top_k, max_output_tokens, stop_sequences, frequency/presence_penalty
- MITM modify_request injects params into request.generationConfig
- All 3 endpoints (Completions, Responses, Gemini) store client params
- Add usageMetadata to Gemini sync responses (promptTokenCount,
  candidatesTokenCount, totalTokenCount, thoughtsTokenCount)
- Add generation param fields to GeminiRequest (temperature, topP, etc.)
- Completions stream_options.include_usage emits final usage chunk
- Completions reasoning_tokens in completion_tokens_details
- Update endpoint gap analysis doc (all high-priority gaps resolved)

src/mitm/proxy.rs

@@ -561,13 +561,15 @@ async fn handle_http_over_tls(
                     let tool_config = store.get_tool_config().await;
                     let pending_results = store.take_tool_results().await;
                     let last_calls = store.get_last_function_calls().await;
+                    let generation_params = store.get_generation_params().await;
 
-                    let tool_ctx = if tools.is_some() || !pending_results.is_empty() {
+                    let tool_ctx = if tools.is_some() || !pending_results.is_empty() || generation_params.is_some() {
                         Some(super::modify::ToolContext {
                             tools,
                             tool_config,
                             pending_results,
                             last_calls,
+                            generation_params,
                         })
                     } else {
                         None