v3.6.2: stream Codex tool-by-tool + capture agent commands in /logs & /status

- Drive `codex exec --json` and parse its JSONL event stream into the same
  categorized live feed as Claude Code (exec/edit/tool/net/tokens), so recon and
  exploitation are visible as each command runs instead of a silent black box.
- Fix the activity feed to keep per-agent tool events (commands, network, files,
  findings) and only filter model reasoning + token telemetry, so /logs shows the
  real command trail and /status 'last:' is a true sign-of-life.
- Surface failed internal commands as 'exec: (exit N)'; keep Codex auth/rate
  detection from stderr.

neurosploit-rs/Cargo.lock

@@ -871,7 +871,7 @@ dependencies = [
 
 [[package]]
 name = "neurosploit"
-version = "3.6.1"
+version = "3.6.2"
 dependencies = [
  "anyhow",
  "clap",
@@ -888,7 +888,7 @@ dependencies = [
 
 [[package]]
 name = "neurosploit-harness"
-version = "3.6.1"
+version = "3.6.2"
 dependencies = [
  "anyhow",
  "futures",

neurosploit-rs/Cargo.toml

@@ -3,7 +3,7 @@ members = ["crates/harness", "app"]
 resolver = "2"
 
 [workspace.package]
-version = "3.6.1"
+version = "3.6.2"
 edition = "2021"
 license = "MIT"
 repository = "https://github.com/JoasASantos/NeuroSploit"

neurosploit-rs/app/src/main.rs

@@ -1,4 +1,4 @@
-//! NeuroSploit v3.6.1 — interactive harness + CLI (`run` / `whitebox` / `agents` / `models`).
+//! NeuroSploit v3.6.2 — 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 v3.6.1 — multi-model autonomous pentest harness",
-    long_about = "NeuroSploit v3.6.1 — a Rust multi-model harness that drives a pool of LLMs \
+    about = "NeuroSploit v3.6.2 — multi-model autonomous pentest harness",
+    long_about = "NeuroSploit v3.6.2 — 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\
@@ -721,7 +721,7 @@ 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 v3.6.1  ·  by Joas A Santos & Red Team Leaders");
+    println!("  ┌─ NeuroSploit v3.6.2  ·  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 v3.6.1 — interactive session (Claude-Code / Codex / Cursor-CLI style).
+//! NeuroSploit v3.6.2 — 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
@@ -52,9 +52,16 @@ impl RunLive {
     fn ingest(&mut self, line: &str) {
         let low = line.to_lowercase();
         self.lines += 1;
-        // Keep a compact activity trail for /logs and the /status sign-of-life
-        // (skip the machine-only finding_json/ai/tokens noise).
-        if !low.starts_with("finding_json:") && !low.starts_with("@") && !low.contains("ai:") && !low.starts_with("tokens:") {
+        // Keep a compact activity trail for /logs and the /status sign-of-life.
+        // Streamed agent events are tagged "@label <event>": keep the actionable
+        // ones (commands, net, tools, file edits, phases) so the operator sees
+        // exactly what each agent is running — drop only long model reasoning
+        // (ai:), token telemetry (tokens:), and machine JSON (finding_json:).
+        let payload = line.strip_prefix('@')
+            .and_then(|r| r.split_once(' ').map(|(_, rest)| rest))
+            .unwrap_or(line);
+        let plow = payload.to_lowercase();
+        if !low.starts_with("finding_json:") && !plow.starts_with("ai:") && !plow.starts_with("tokens:") {
             let clean: String = line.chars().take(160).collect();
             self.last = clean.clone();
             self.feed.push(clean);
@@ -346,7 +353,7 @@ pub async fn repl(base: &Path) -> anyhow::Result<()> {
     let backends = harness::installed_cli_backends();
     println!("\x1b[1m");
     println!("  ███╗   ██╗███████╗██╗   ██╗██████╗  ██████╗");
-    println!("  ████╗  ██║██╔════╝██║   ██║██╔══██╗██╔═══██╗   NeuroSploit v3.6.1");
+    println!("  ████╗  ██║██╔════╝██║   ██║██╔══██╗██╔═══██╗   NeuroSploit v3.6.2");
     println!("  ██╔██╗ ██║█████╗  ██║   ██║██████╔╝██║   ██║   interactive harness");
     println!("  ██║╚██╗██║██╔══╝  ██║   ██║██╔══██╗██║   ██║   by Joas A Santos");
     println!("  ██║ ╚████║███████╗╚██████╔╝██║  ██║╚██████╔╝   & Red Team Leaders");

neurosploit-rs/app/src/tui.rs

@@ -1,4 +1,4 @@
-//! NeuroSploit v3.6.1 — TUI "Mission Control" mode.
+//! NeuroSploit v3.6.2 — 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:

neurosploit-rs/crates/harness/src/belief.rs

@@ -1,4 +1,4 @@
-//! POMDP belief-state world model (v3.6.1).
+//! POMDP belief-state world model (v3.6.2).
 //!
 //! The target is only partially observable, so we don't track booleans — we
 //! track a **belief**: a property graph whose nodes (host / service / vuln /

neurosploit-rs/crates/harness/src/grounding.rs

@@ -1,4 +1,4 @@
-//! Verification / grounding engine (v3.6.1).
+//! Verification / grounding engine (v3.6.2).
 //!
 //! Hard rule: **no claim enters the world model without a tool receipt** — raw
 //! tool output, not the LLM's paraphrase. This is the empirical anti-hallucination

neurosploit-rs/crates/harness/src/lib.rs

@@ -1,4 +1,4 @@
-//! NeuroSploit v3.6.1 harness — a robust multi-model runtime for the
+//! NeuroSploit v3.6.2 harness — a robust multi-model runtime for the
 //! markdown-driven autonomous pentest engine.
 //!
 //! The harness loads the `agents_md/` library, drives a *pool* of LLM models

neurosploit-rs/crates/harness/src/models.rs

@@ -194,6 +194,12 @@ impl ChatClient {
         if bin == "claude" {
             return self.chat_claude_stream(label, model, &prompt, mcp_config, progress).await;
         }
+        // Codex exec streams JSONL events (`--json`): commands it runs, agent
+        // messages, file changes, token usage. Surface them live so recon and
+        // exploitation are visible tool-by-tool instead of a silent black box.
+        if bin == "codex" {
+            return self.chat_codex_stream(label, model, &prompt, mcp_config, progress).await;
+        }
 
         let mut cmd = Command::new(bin);
         match bin {
@@ -366,6 +372,136 @@ impl ChatClient {
         }
         Ok(result)
     }
+
+    /// Drive `codex exec --json` and surface its JSONL event stream as a live,
+    /// categorized activity feed (commands, agent messages, file changes, MCP
+    /// tool calls, token usage). The final agent message is returned as the
+    /// result. Mirrors `chat_claude_stream` so Codex runs are just as visible.
+    async fn chat_codex_stream(
+        &self,
+        label: &str,
+        model: &str,
+        prompt: &str,
+        mcp_config: Option<&str>,
+        progress: Option<tokio::sync::mpsc::Sender<String>>,
+    ) -> Result<String> {
+        let mut cmd = Command::new("codex");
+        cmd.arg("exec").arg("--json").arg("--model").arg(model)
+            .arg("--dangerously-bypass-approvals-and-sandbox");
+        if let Some(mcp) = mcp_config {
+            for (name, cmdline, args) in mcp_servers_from(mcp) {
+                cmd.arg("-c").arg(format!("mcp_servers.{name}.command={cmdline}"));
+                cmd.arg("-c").arg(format!("mcp_servers.{name}.args={args}"));
+            }
+        }
+        cmd.arg("-");
+        cmd.stdin(Stdio::piped()).stdout(Stdio::piped()).stderr(Stdio::piped()).kill_on_drop(true);
+        let mut child = cmd.spawn().map_err(|e| anyhow!("spawn codex failed: {e}"))?;
+        if let Some(mut stdin) = child.stdin.take() {
+            stdin.write_all(prompt.as_bytes()).await?;
+            // Drop closes stdin so Codex processes the prompt and exits.
+        }
+        let stdout = child.stdout.take().ok_or_else(|| anyhow!("no stdout"))?;
+        let stderr = child.stderr.take().ok_or_else(|| anyhow!("no stderr"))?;
+        let mut lines = BufReader::new(stdout).lines();
+        let lbl = if label.is_empty() { String::new() } else { format!("@{label} ") };
+        let emit = |s: String| {
+            if let Some(tx) = &progress {
+                let _ = tx.try_send(format!("{lbl}{s}"));
+            }
+        };
+
+        // Last agent_message is the model's final answer; keep every one so a
+        // run that ends on a tool call still returns the most recent reasoning.
+        let mut result = String::new();
+        let read = async {
+            while let Ok(Some(line)) = lines.next_line().await {
+                let Ok(v) = serde_json::from_str::<serde_json::Value>(&line) else { continue };
+                let ty = v.get("type").and_then(|t| t.as_str()).unwrap_or("");
+                match ty {
+                    "item.started" | "item.completed" => {
+                        let Some(item) = v.get("item") else { continue };
+                        let itype = item.get("type").and_then(|t| t.as_str()).unwrap_or("");
+                        match itype {
+                            "command_execution" => {
+                                // Only announce on start (avoid double lines); note failures on completion.
+                                let c = item.get("command").and_then(|x| x.as_str()).unwrap_or("");
+                                // Strip the `/bin/sh -lc '...'` wrapper Codex adds.
+                                let c = c.strip_prefix("/bin/sh -lc ").map(|s| s.trim_matches('\'')).unwrap_or(c);
+                                if ty == "item.started" {
+                                    let danger = c.contains("rm -rf") || c.contains("mkfs")
+                                        || c.contains(":(){") || c.contains("dd if=") || c.contains("> /dev/");
+                                    emit(format!("{}: {}", if danger { "danger" } else { "exec" }, truncate(c, 200)));
+                                } else if let Some(code) = item.get("exit_code").and_then(|x| x.as_i64()) {
+                                    if code != 0 {
+                                        emit(format!("exec: (exit {code}) {}", truncate(c, 120)));
+                                    }
+                                }
+                            }
+                            "agent_message" => {
+                                if let Some(t) = item.get("text").and_then(|x| x.as_str()) {
+                                    let t = t.trim();
+                                    if !t.is_empty() {
+                                        if ty == "item.completed" { result = t.to_string(); }
+                                        emit(format!("ai: {}", truncate(t, 240)));
+                                    }
+                                }
+                            }
+                            "file_change" | "patch" => {
+                                let p = item.get("path").and_then(|x| x.as_str())
+                                    .or_else(|| item.get("file").and_then(|x| x.as_str())).unwrap_or("file");
+                                emit(format!("edit: {p}"));
+                            }
+                            "mcp_tool_call" => {
+                                let name = item.get("tool").and_then(|x| x.as_str())
+                                    .or_else(|| item.get("name").and_then(|x| x.as_str())).unwrap_or("mcp");
+                                emit(format!("tool: {name}"));
+                            }
+                            "web_search" => {
+                                let q = item.get("query").and_then(|x| x.as_str()).unwrap_or("");
+                                emit(format!("net: search {}", truncate(q, 100)));
+                            }
+                            _ => {}
+                        }
+                    }
+                    "turn.completed" => {
+                        let ti = v.pointer("/usage/input_tokens").and_then(|x| x.as_u64());
+                        let to = v.pointer("/usage/output_tokens").and_then(|x| x.as_u64());
+                        if ti.is_some() || to.is_some() {
+                            emit(format!("tokens: in={} out={}", ti.unwrap_or(0), to.unwrap_or(0)));
+                        }
+                    }
+                    _ => {}
+                }
+            }
+        };
+        // Bound the whole streamed turn (matches the buffered path's cap).
+        if tokio::time::timeout(Duration::from_secs(900), read).await.is_err() {
+            return Err(anyhow!("codex stream timed out after 900s"));
+        }
+        let status = child.wait().await.ok();
+        // Drain stderr for auth/rate diagnostics if we got nothing usable.
+        if result.is_empty() {
+            let mut errbuf = String::new();
+            let mut el = BufReader::new(stderr).lines();
+            while let Ok(Some(l)) = el.next_line().await {
+                if !errbuf.is_empty() { errbuf.push('\n'); }
+                errbuf.push_str(&l);
+                if errbuf.len() > 2000 { break; }
+            }
+            let low = errbuf.to_lowercase();
+            let hard = ["not logged in", "please log in", "please login", "run /login",
+                "unauthorized", "not authenticated", "invalid api key", "no api key",
+                "rate limit", "429", "quota", "credit balance", "usage limit"]
+                .iter().any(|k| low.contains(k));
+            let code = status.and_then(|s| s.code()).map(|c| c.to_string()).unwrap_or_else(|| "signal".into());
+            if hard || !errbuf.trim().is_empty() {
+                return Err(anyhow!("codex subscription CLI exit {}: {}", code, truncate(errbuf.trim(), 240)));
+            }
+            return Err(anyhow!("codex stream produced no result"));
+        }
+        Ok(result)
+    }
 }
 
 /// Categorise a Claude tool_use block into a tagged activity-feed event.

neurosploit-rs/crates/harness/src/pomdp.rs

@@ -1,4 +1,4 @@
-//! POMDP decision layer (v3.6.1): value-of-information planning + the
+//! POMDP decision layer (v3.6.2): value-of-information planning + the
 //! anti-hallucination gate.
 //!
 //! The choice "scan more vs exploit now" is **not** a heuristic here — it falls

neurosploit-rs/crates/harness/src/probe.rs

@@ -1,4 +1,4 @@
-//! Deterministic HTTP request/response analysis (v3.6.1).
+//! Deterministic HTTP request/response analysis (v3.6.2).
 //!
 //! Before the LLM recon runs, the harness performs a **real** probe of the
 //! target and captures observed facts — status, headers, security headers,

neurosploit-rs/crates/harness/src/report.rs

@@ -97,9 +97,9 @@ pub fn html(target: &str, findings: &[Finding]) -> String {
          h4{{margin:12px 0 3px;font-size:12px;text-transform:uppercase;letter-spacing:.5px;color:#8b5cf6}}\
          .b{{color:#8b5cf6;font-weight:800}}</style></head><body>\
          <h1><span class=b>NeuroSploit</span> Penetration Test Report</h1>\
-         <div class=meta>Target: <b>{t}</b> · v3.6.1 Rust harness · multi-model validated</div>\
+         <div class=meta>Target: <b>{t}</b> · v3.6.2 Rust harness · multi-model validated</div>\
          <div>{chips}</div>{graph_block}<h2>Findings ({n})</h2>{body}\
-         <p class=meta>Authorized testing only. Findings confirmed by multi-model adversarial voting.<br>NeuroSploit v3.6.1 · by <b>Joas A Santos</b> &amp; <b>Red Team Leaders</b></p></body></html>",
+         <p class=meta>Authorized testing only. Findings confirmed by multi-model adversarial voting.<br>NeuroSploit v3.6.2 · by <b>Joas A Santos</b> &amp; <b>Red Team Leaders</b></p></body></html>",
         t = esc(target), chips = chips, n = sorted.len(), body = body, graph_block = graph_block,
     )
 }
@@ -135,7 +135,7 @@ pub fn typst_report(target: &str, findings: &[Finding], dir: &Path) -> std::io::
     let mut data = String::new();
     data.push_str(&format!(
         "#let meta = (target: {}, run_id: {}, generated: {}, model: {})\n",
-        tq(target), tq(&run_id), tq("NeuroSploit v3.6.1"), tq("multi-model")
+        tq(target), tq(&run_id), tq("NeuroSploit v3.6.2"), tq("multi-model")
     ));
     data.push_str("#let findings = (\n");
     for f in sorted_findings(findings) {