chore: code cleanup and documentation overhaul

- Remove debug header dump from MITM proxy (was temp debugging code)
- Suppress dead_code warnings for intentional OpenAI compat fields
- Rewrite README with styled mermaid architecture diagrams, full
  feature listing, usage examples, and CLI reference
- Update endpoint-gap-analysis: images implemented, audio only stretch
- Update mitm-interception-status: add request modification and error
  capture components
- Update standalone-ls-todo: add new endpoints to test results
- Zero compiler warnings

src/api/types.rs

@@ -87,8 +87,9 @@ pub(crate) struct CompletionRequest {
     /// Max completion tokens — forwarded to Google as maxOutputTokens via MITM.
     #[serde(default)]
     pub max_completion_tokens: Option<u64>,
-    /// User identifier — accepted, not used.
+    /// User identifier -- accepted, not used.
     #[serde(default)]
+    #[allow(dead_code)]
     pub user: Option<String>,
     /// Frequency penalty — forwarded to Google via MITM.
     #[serde(default)]
@@ -111,8 +112,9 @@ pub(crate) struct CompletionRequest {
     /// Session/conversation ID for multi-turn reuse (custom extension).
     #[serde(default)]
     pub conversation: Option<serde_json::Value>,
-    /// Metadata — accepted and ignored (no upstream equivalent).
+    /// Metadata -- accepted and ignored (no upstream equivalent).
     #[serde(default)]
+    #[allow(dead_code)]
     pub metadata: Option<serde_json::Value>,
     /// Number of completions to generate. Each uses a separate cascade (costs N× quota).
     /// Defaults to 1. Only supported in sync mode; streaming always uses n=1.
@@ -163,12 +165,14 @@ pub(crate) struct ResponseFormat {
 pub(crate) struct JsonSchemaFormat {
     /// Schema name (for client identification).
     #[serde(default)]
+    #[allow(dead_code)]
     pub name: Option<String>,
     /// The actual JSON schema object — forwarded as Gemini's responseSchema.
     #[serde(default)]
     pub schema: Option<serde_json::Value>,
     /// Whether to enable strict schema adherence.
     #[serde(default)]
+    #[allow(dead_code)]
     pub strict: Option<bool>,
 }
 

src/mitm/proxy.rs

@@ -633,16 +633,6 @@ async fn handle_http_over_tls(
         };
 
         // Forward the request — if write fails, reconnect and retry once
-        // DEBUG: dump headers and total size
-        if req_path.contains("streamGenerateContent") {
-            let hdr_end = find_headers_end(&request_buf).unwrap_or(request_buf.len());
-            let hdr_str = String::from_utf8_lossy(&request_buf[..hdr_end.min(request_buf.len())]);
-            info!(
-                total_buf_len = request_buf.len(),
-                body_len = request_buf.len() - hdr_end,
-                "MITM: sending request to upstream\n{hdr_str}"
-            );
-        }
         if let Err(e) = conn.write_all(&request_buf).await {
             debug!(domain, error = %e, "MITM: upstream write failed, reconnecting");
             let c = connect_upstream(domain, &upstream_config).await?;

src/mitm/store.rs

@@ -68,6 +68,7 @@ pub struct UpstreamError {
     /// HTTP status code from Google (e.g. 400, 429, 500).
     pub status: u16,
     /// Raw error body from Google (usually JSON).
+    #[allow(dead_code)]
     pub body: String,
     /// Parsed error message, if available.
     pub message: Option<String>,