Add RAG embedding and AI chat feature

Implement end-to-end RAG pipeline: AST-aware code chunking, LiteLLM
embedding generation, MongoDB vector storage with brute-force cosine
similarity fallback for self-hosted instances, and a chat API with
RAG-augmented responses. Add dedicated /chat/:repo_id dashboard page
with embedding build controls, message history, and source reference
cards.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

compliance-agent/src/config.rs

@@ -24,6 +24,8 @@ pub fn load_config() -> Result<AgentConfig, AgentError> {
             .unwrap_or_else(|| "http://localhost:4000".to_string()),
         litellm_api_key: SecretString::from(env_var_opt("LITELLM_API_KEY").unwrap_or_default()),
         litellm_model: env_var_opt("LITELLM_MODEL").unwrap_or_else(|| "gpt-4o".to_string()),
+        litellm_embed_model: env_var_opt("LITELLM_EMBED_MODEL")
+            .unwrap_or_else(|| "text-embedding-3-small".to_string()),
         github_token: env_secret_opt("GITHUB_TOKEN"),
         github_webhook_secret: env_secret_opt("GITHUB_WEBHOOK_SECRET"),
         gitlab_url: env_var_opt("GITLAB_URL"),