fix(3.6.8): better Ollama error messages, empty-evidence findings go to needs-review, single-model vote warning

- models.rs: detect connection-refused and timeout on local providers
  (ollama/litellm/llamacpp), show actionable error instead of raw reqwest
- pipeline.rs: findings with empty evidence skip adversarial vote (which
  always rejects per 'default to rejected' prompt) and go straight to
  needs-review for human triage
- pipeline.rs: warn when single-model panel + vote_n=1 (same model
  validates its own findings = weaker validation)
- Bump version 3.6.7 → 3.6.8

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_011739wMqPJJPttTLLX6YoQH

neurosploit-rs/app/src/main.rs

@@ -1,4 +1,4 @@
-//! NeuroSploit v3.6.7 — interactive harness + CLI (`run` / `whitebox` / `agents` / `models`).
+//! NeuroSploit v3.6.8 — interactive harness + CLI (`run` / `whitebox` / `agents` / `models`).
 
 mod repl;
 mod tui;
@@ -11,8 +11,8 @@ use std::path::{Path, PathBuf};
 #[command(
     name = "neurosploit",
     version,
-    about = "NeuroSploit v3.6.7 — multi-model autonomous pentest harness",
-    long_about = "NeuroSploit v3.6.7 — a Rust multi-model harness that drives a pool of LLMs \
+    about = "NeuroSploit v3.6.8 — multi-model autonomous pentest harness",
+    long_about = "NeuroSploit v3.6.8 — a Rust multi-model harness that drives a pool of LLMs \
 (API key or local subscription: Claude/Codex/Gemini/Grok) to autonomously test a target. \
 After recon it INTELLIGENTLY selects only the agents matching the discovered surface, runs \
 them in parallel, then validates every finding by cross-model voting before reporting.\n\n\
@@ -765,7 +765,7 @@ pub(crate) fn spawn_engagement(base: &Path, mut cfg: RunConfig, mcp: bool, mode:
     println!("  │  ua     : {ua}");
     write_status(&workdir, "running", &format!("\"target\":{:?}", cfg.target));
 
-    println!("  ┌─ NeuroSploit v3.6.7  ·  by Joas A Santos & Red Team Leaders");
+    println!("  ┌─ NeuroSploit v3.6.8  ·  by Joas A Santos & Red Team Leaders");
     println!("  │  run id : {run_id}");
     println!("  │  target : {}", cfg.target);
     println!("  │  models : {}", cfg.models.join(", "));

neurosploit-rs/app/src/repl.rs

@@ -1,4 +1,4 @@
-//! NeuroSploit v3.6.7 — interactive session (Claude-Code / Codex / Cursor-CLI style).
+//! NeuroSploit v3.6.8 — interactive session (Claude-Code / Codex / Cursor-CLI style).
 //!
 //! Launched when `neurosploit` runs with no subcommand. A persistent REPL with
 //! real line editing (arrow-key history recall, Ctrl-A/E/K, paste), model
@@ -370,7 +370,7 @@ pub async fn repl(base: &Path) -> anyhow::Result<()> {
     let backends = harness::installed_cli_backends();
     println!("\x1b[1m");
     println!("  ███╗   ██╗███████╗██╗   ██╗██████╗  ██████╗");
-    println!("  ████╗  ██║██╔════╝██║   ██║██╔══██╗██╔═══██╗   NeuroSploit v3.6.7");
+    println!("  ████╗  ██║██╔════╝██║   ██║██╔══██╗██╔═══██╗   NeuroSploit v3.6.8");
     println!("  ██╔██╗ ██║█████╗  ██║   ██║██████╔╝██║   ██║   interactive harness");
     println!("  ██║╚██╗██║██╔══╝  ██║   ██║██╔══██╗██║   ██║   by Joas A Santos");
     println!("  ██║ ╚████║███████╗╚██████╔╝██║  ██║╚██████╔╝   & Red Team Leaders");

neurosploit-rs/app/src/tui.rs

@@ -1,4 +1,4 @@
-//! NeuroSploit v3.6.7 — TUI "Mission Control" mode.
+//! NeuroSploit v3.6.8 — TUI "Mission Control" mode.
 //!
 //! Concurrent panels that update live while the engagement runs in the
 //! background, with a composer input that stays active during execution: