feat(P05): flesh 4 agents with intrinsic mechanical logic

---ci---
project: ci
phase: 5
milestone: v0.8
status: complete
decisions:
  - id: D-033
    decision: Flesh SecurityAuditorAgent with STRIDE-aware mechanical scanning
    rationale: Runs L3 security patterns intrinsically; no backend required
    confidence: 0.90
  - id: D-034
    decision: Flesh DocWriterAgent with template-based doc update
    rationale: Updates ROADMAP.md phase status, REQUIREMENTS.md req status, reads git log for new decisions
    confidence: 0.85
  - id: D-035
    decision: Flesh DebuggerAgent with stack trace parsing + git bisect
    rationale: Parses stack traces to find file:line, bisects to find introducing commit
    confidence: 0.80
  - id: D-036
    decision: Flesh ChallengerAgent with plan DAG/wave/must-have/REQ validation
    rationale: Validates plan structure mechanically; catches circular deps and gaps
    confidence: 0.82
requirements:
  covered: [AGENT-01, AGENT-02, AGENT-03, AGENT-04]
---/ci---

AGENT-01: SecurityAuditorAgent.mechanicalAudit() runs STRIDE+ CWE pattern
scan intrinsically. Each finding has stride_category, cwe, severity, and
disposition (accept/mitigate/flag based on confidence threshold).

AGENT-02: DocWriterAgent.mechanicalDocUpdate() reads plan data, updates
.ciagent/ROADMAP.md phase status to complete, .ciagent/REQUIREMENTS.md
pending→covered, and reads git log for new decision entries.

AGENT-03: DebuggerAgent.mechanicalDebug() parses stack traces (4 regex
patterns for different formats), identifies root file:line, runs
git bisect to find introducing commit, suggests git revert.

AGENT-04: ChallengerAgent.mechanicalChallenge() validates plan structure:
circular dependency detection via DFS, wave ordering validation,
must-haves presence check, and requirement coverage check.
This commit is contained in:
Jon Chery
2026-05-29 20:30:45 +00:00
parent 07e5e70c9b
commit 93967feb68
4 changed files with 550 additions and 16 deletions
+103 -4
View File
@@ -1,13 +1,52 @@
import * as fs from "node:fs";
import * as path from "node:path";
import { BaseAgent, AgentContext, AgentResult } from "./base.js";
interface SecurityFinding {
stride_category: string;
cwe: string;
severity: "low" | "medium" | "high";
disposition: "accept" | "mitigate" | "flag";
file: string;
description: string;
}
const SECURITY_PATTERNS: Array<{
pattern: RegExp;
category: string;
cwe: string;
description: string;
severity: "low" | "medium" | "high";
confidence: number;
}> = [
{ pattern: /password\s*=\s*['"][^'"]+['"]/gi, category: "information_disclosure", cwe: "CWE-259", description: "Hardcoded password", severity: "high", confidence: 0.95 },
{ pattern: /api[_-]?key\s*=\s*['"][^'"]+['"]/gi, category: "information_disclosure", cwe: "CWE-312", description: "Hardcoded API key", severity: "high", confidence: 0.95 },
{ pattern: /secret\s*=\s*['"][^'"]+['"]/gi, category: "information_disclosure", cwe: "CWE-312", description: "Hardcoded secret", severity: "high", confidence: 0.95 },
{ pattern: /token\s*=\s*['"][^'"]+['"]/gi, category: "information_disclosure", cwe: "CWE-312", description: "Hardcoded token", severity: "medium", confidence: 0.80 },
{ pattern: /eval\s*\(\s*[^'"]*\$\{/g, category: "tampering", cwe: "CWE-94", description: "eval() with dynamic content", severity: "high", confidence: 0.90 },
{ pattern: /(?:exec|execSync|spawn|spawnSync)\s*\(\s*[^'"]*[\$`]/g, category: "elevation_of_privilege", cwe: "CWE-78", description: "Command execution with interpolation", severity: "high", confidence: 0.85 },
{ pattern: /catch\s*\(\w*\)\s*\{\s*\}/g, category: "repudiation", cwe: "CWE-778", description: "Empty catch block", severity: "medium", confidence: 0.85 },
{ pattern: /jwt\.decode\s*\(/g, category: "spoofing", cwe: "CWE-287", description: "JWT decode without verify", severity: "high", confidence: 0.85 },
{ pattern: /(?:__proto__|constructor\s*\[|prototype\s*\[)/g, category: "elevation_of_privilege", cwe: "CWE-1321", description: "Prototype pollution", severity: "high", confidence: 0.90 },
{ pattern: /(?:md5|sha1|des|rc4)\s*\(/gi, category: "information_disclosure", cwe: "CWE-328", description: "Weak crypto", severity: "medium", confidence: 0.90 },
{ pattern: /express\.json\s*\(\s*\)/g, category: "denial_of_service", cwe: "CWE-400", description: "JSON parser without size limit", severity: "medium", confidence: 0.80 },
];
export class SecurityAuditorAgent extends BaseAgent {
readonly name = "security-auditor";
readonly description = "Auto-dispositions threats: low=accept, medium=mitigate, high=escalate.";
readonly workflow = "verify";
private confidenceThreshold: number;
constructor(confidenceThreshold: number = 0.6) {
super();
this.confidenceThreshold = confidenceThreshold;
}
async execute(context: AgentContext): Promise<AgentResult> {
const start = Date.now();
this.log("Running security audit...");
if (context.backend) {
const result = await this.executeViaBackend(
context,
@@ -15,14 +54,74 @@ export class SecurityAuditorAgent extends BaseAgent {
);
return { ...result, duration_ms: Date.now() - start };
}
const findings = this.mechanicalAudit(context.project_path);
const highCount = findings.filter((f) => f.severity === "high").length;
const output = this.formatFindings(findings);
return {
success: false,
output: "Security auditing requires an intelligence backend. Configure one with: ci init --backend",
success: highCount === 0,
output,
artifacts_created: [],
decisions: 0,
escalations: 0,
escalations: highCount,
duration_ms: Date.now() - start,
error: "No intelligence backend available",
error: highCount > 0 ? `${highCount} high-severity finding(s) require escalation` : undefined,
};
}
mechanicalAudit(projectPath: string): SecurityFinding[] {
const findings: SecurityFinding[] = [];
const srcDir = path.join(projectPath, "src");
if (!fs.existsSync(srcDir)) return findings;
this.scanDirectory(srcDir, projectPath, findings);
return findings;
}
private getDisposition(severity: SecurityFinding["severity"], confidence: number): SecurityFinding["disposition"] {
if (severity === "low") return "accept";
if (confidence >= this.confidenceThreshold) return "flag";
return "mitigate";
}
private scanDirectory(dir: string, projectPath: string, findings: SecurityFinding[]): void {
const entries = fs.readdirSync(dir, { withFileTypes: true });
for (const entry of entries) {
const fullPath = path.join(dir, entry.name);
if (entry.isDirectory() && entry.name !== "node_modules" && entry.name !== ".git") {
this.scanDirectory(fullPath, projectPath, findings);
} else if (
entry.isFile() &&
(entry.name.endsWith(".ts") || entry.name.endsWith(".js")) &&
!entry.name.endsWith(".test.ts") &&
!entry.name.endsWith(".d.ts")
) {
const content = fs.readFileSync(fullPath, "utf-8");
for (const { pattern, category, cwe, description, severity, confidence } of SECURITY_PATTERNS) {
pattern.lastIndex = 0;
if (pattern.test(content)) {
findings.push({
stride_category: category,
cwe,
severity,
disposition: this.getDisposition(severity, confidence),
file: path.relative(projectPath, fullPath),
description,
});
}
}
}
}
}
private formatFindings(findings: SecurityFinding[]): string {
if (findings.length === 0) return "No security findings — audit passed.";
const lines: string[] = ["Security Audit Findings:", ""];
for (const f of findings) {
lines.push(`[${f.stride_category}|${f.cwe}|${f.disposition}] ${f.severity.toUpperCase()}: ${f.description} (${f.file})`);
}
return lines.join("\n");
}
}