feat(security): Add Phase 1 security features

* test: add comprehensive recovery tests for agent loop

Add recovery test coverage for all edge cases and failure scenarios
in the agentic loop, addressing the missing test coverage for
recovery use cases.

Tool Call Parsing Edge Cases:
- Empty tool_result tags
- Empty tool_calls arrays
- Whitespace-only tool names
- Empty string arguments

History Management:
- Trimming without system prompt
- Role ordering consistency after trim
- Only system prompt edge case

Arguments Parsing:
- Invalid JSON string fallback
- None arguments handling
- Null value handling

JSON Extraction:
- Empty input handling
- Whitespace only input
- Multiple JSON objects
- JSON arrays

Tool Call Value Parsing:
- Missing name field
- Non-OpenAI format
- Empty tool_calls array
- Missing tool_calls field fallback
- Top-level array format

Constants Validation:
- MAX_TOOL_ITERATIONS bounds (prevent runaway loops)
- MAX_HISTORY_MESSAGES bounds (prevent memory bloat)

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

* feat(security): Add Phase 1 security features - sandboxing, resource limits, audit logging

Phase 1 security enhancements with zero impact on the quick setup wizard:
- ✅ Pluggable sandbox trait system (traits.rs)
- ✅ Landlock sandbox support (Linux kernel 5.13+)
- ✅ Firejail sandbox support (Linux user-space)
- ✅ Bubblewrap sandbox support (Linux/macOS user namespaces)
- ✅ Docker sandbox support (container isolation)
- ✅ No-op fallback (application-layer security only)
- ✅ Auto-detection logic (detect.rs)
- ✅ Audit logging with HMAC signing support (audit.rs)
- ✅ SecurityConfig schema (SandboxConfig, ResourceLimitsConfig, AuditConfig)
- ✅ Feature-gated implementation (sandbox-landlock, sandbox-bubblewrap)
- ✅ 1,265 tests passing

Key design principles:
- Silent auto-detection: no new prompts in wizard
- Graceful degradation: works on all platforms
- Feature flags: zero overhead when disabled
- Pluggable architecture: swap sandbox backends via config
- Backward compatible: existing configs work unchanged

Config usage:
```toml
[security.sandbox]
enabled = false  # Explicitly disable
backend = "auto"  # auto, landlock, firejail, bubblewrap, docker, none

[security.resources]
max_memory_mb = 512
max_cpu_time_seconds = 60

[security.audit]
enabled = true
log_path = "audit.log"
sign_events = false
```

Security documentation:
- docs/sandboxing.md: Sandbox implementation strategies
- docs/resource-limits.md: Resource limit approaches
- docs/audit-logging.md: Audit logging specification
- docs/security-roadmap.md: 3-phase implementation plan
- docs/frictionless-security.md: Zero-impact wizard design
- docs/agnostic-security.md: Platform/hardware agnostic approach

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

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

src/security/traits.rs

@@ -0,0 +1,76 @@
+//! Sandbox trait for pluggable OS-level isolation
+
+use async_trait::async_trait;
+use std::process::Command;
+
+/// Sandbox backend for OS-level isolation
+#[async_trait]
+pub trait Sandbox: Send + Sync {
+    /// Wrap a command with sandbox protection
+    fn wrap_command(&self, cmd: &mut Command) -> std::io::Result<()>;
+
+    /// Check if this sandbox backend is available on the current platform
+    fn is_available(&self) -> bool;
+
+    /// Human-readable name of this sandbox backend
+    fn name(&self) -> &str;
+
+    /// Description of what this sandbox provides
+    fn description(&self) -> &str;
+}
+
+/// No-op sandbox (always available, provides no additional isolation)
+#[derive(Debug, Clone, Default)]
+pub struct NoopSandbox;
+
+impl Sandbox for NoopSandbox {
+    fn wrap_command(&self, _cmd: &mut Command) -> std::io::Result<()> {
+        // Pass through unchanged
+        Ok(())
+    }
+
+    fn is_available(&self) -> bool {
+        true
+    }
+
+    fn name(&self) -> &str {
+        "none"
+    }
+
+    fn description(&self) -> &str {
+        "No sandboxing (application-layer security only)"
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn noop_sandbox_name() {
+        assert_eq!(NoopSandbox.name(), "none");
+    }
+
+    #[test]
+    fn noop_sandbox_is_always_available() {
+        assert!(NoopSandbox.is_available());
+    }
+
+    #[test]
+    fn noop_sandbox_wrap_command_is_noop() {
+        let mut cmd = Command::new("echo");
+        cmd.arg("test");
+        let original_program = cmd.get_program().to_string_lossy().to_string();
+        let original_args: Vec<String> = cmd.get_args().map(|s| s.to_string_lossy().to_string()).collect();
+
+        let sandbox = NoopSandbox;
+        assert!(sandbox.wrap_command(&mut cmd).is_ok());
+
+        // Command should be unchanged
+        assert_eq!(cmd.get_program().to_string_lossy(), original_program);
+        assert_eq!(
+            cmd.get_args().map(|s| s.to_string_lossy().to_string()).collect::<Vec<_>>(),
+            original_args
+        );
+    }
+}