NeuroSploit v3.4.0 — Rust multi-model harness + Axum dashboard

New cargo workspace `neurosploit-rs/` (single `neurosploit` binary):

harness crate:
- models.rs: 11 OpenAI-compatible providers / 31 models (Claude, GPT, Grok,
  NVIDIA NIM, DeepSeek, Mistral, Qwen, Groq, Together, OpenRouter, Ollama)
- pool.rs: ModelPool with bounded concurrency, provider failover, and N-model
  validator voting (the panel doubles as the jury)
- agents.rs: loads the existing agents_md/ library (213 agents)
- pipeline.rs: recon → parallel exploit (semaphore-bounded) → N-model
  adversarial vote → score; streams live progress over a channel
- report.rs: HTML report
- tokio + reqwest(rustls); offline mode runs the pipeline without API keys

app binary:
- clap CLI: serve | run | agents | models  (run supports --model x N, --vote-n,
  --max-agents, --offline)
- axum web dashboard with multi-model panel, live console, findings, agent
  browser, embedded report; single binary serves the SPA (no npm/build)

Verified: cargo build clean; agents/models/offline-run CLI; server endpoints
(/api/info, /api/run lifecycle, /report); dashboard + live run in Playwright.

Docs: README v3.4.0 callout + RELEASE.md notes. target/ gitignored.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

README.md

@@ -19,6 +19,21 @@ and a **reinforcement-learning** loop that gets smarter every run.
 
 > The previous Python orchestration now lives in [`legacy/`](legacy/README.md).
 
+> **🦀 v3.4.0 — Rust multi-model harness.** A new high-performance harness lives
+> in [`neurosploit-rs/`](neurosploit-rs/): a single Rust binary (`tokio` + `axum`)
+> that drives a **pool of LLM models** with concurrency, **provider failover**,
+> and **N-model validator voting** (N models must agree a finding is real before
+> it counts). It serves its own solid web dashboard. Build & run:
+> ```bash
+> cd neurosploit-rs && cargo build --release
+> ./target/release/neurosploit serve            # web dashboard → :8788
+> ./target/release/neurosploit run https://target.example --model anthropic:claude-opus-4-8 --model openai:gpt-5.1
+> ./target/release/neurosploit run https://t.example --offline   # pipeline self-test, no API keys
+> ```
+> 11 OpenAI-compatible providers / 31 models (Claude, GPT, Grok, NVIDIA NIM,
+> DeepSeek, Mistral, Qwen, Groq, Together, OpenRouter, Ollama). Reads the same
+> `agents_md/` library (213 agents).
+
 ---
 
 ## Why this architecture