Refactor audit report largefunc slice in pkg/cli

[Copilot]

This PR addresses the lint-monster function-length slice in pkg/cli by breaking up the highest-impact audit-report functions without changing their external behavior. The refactor targets the audit reporting path specifically and reduces the assigned largefunc findings by turning long mixed-responsibility functions into small coordinators over focused helpers.

• Audit report assembly

  • Split buildAuditData into narrow helpers for:
    • overview construction
    • metric fallback resolution
    • job/error extraction
    • narrative assembly
    • final AuditData composition
  • Kept the existing data flow intact while making fallback and enrichment steps independently readable.

• Findings and recommendations

  • Refactored generateFindings into focused helpers for:
    • failure description selection
    • performance findings
    • tooling findings
    • firewall findings
    • success findings
  • Refactored generateRecommendations into helper-driven branches for:
    • failure follow-up
    • cost/iteration guidance
    • tooling and firewall configuration guidance
    • success-only defaults

• Console rendering

  • Reworked renderConsole into a thin top-level renderer that delegates to section-specific helpers:
    • overview/context
    • comparison/fingerprint
    • metrics/session/resource usage
    • jobs/prompt
    • actionable sections
    • operational sections
    • policy/experiments/log path
  • Preserved output shape while making each render block isolated and easier to evolve.

• Focused regression coverage

  • Added targeted tests around extracted formatting logic, including blocked-network descriptions and deterministic experiment ordering in console output.

Example of the new structure:

func renderConsole(data AuditData, logsPath string) {
	auditReportLog.Print("Rendering compact audit report to console")

	renderConsoleOverview(data)
	renderConsoleComparison(data.Comparison)
	renderConsoleFingerprint(data.BehaviorFingerprint)
	renderConsoleMetrics(data.Metrics)
	renderConsoleSession(data.SessionAnalysis)
	renderConsoleTokenUsage(data.FirewallTokenUsage)
	renderConsoleGitHubAPIUsage(data.GitHubRateLimitUsage)
	renderConsoleJobs(data.Jobs)
	renderConsolePrompt(data.PromptAnalysis)
	renderConsoleActionableSections(data)
	renderConsoleOperationalSections(data)
	renderConsolePolicyAndExperiments(data)
	renderConsoleLogsPath(logsPath)
}

• Fixes [lint-monster] lint-monster: function-length refactoring — pkg/cli slice B #47180

[Copilot]

Pull request overview

Refactors audit reporting into focused helpers while preserving report assembly, findings, recommendations, and console output behavior.

Changes:

• Split audit data assembly and metric fallback logic.
• Decomposed findings, recommendations, and console rendering.
• Added focused formatting and ordering tests.

Show a summary per file

File	Description
pkg/cli/audit_report.go	Extracts audit assembly helpers.
pkg/cli/audit_report_analysis.go	Decomposes findings and recommendations.
pkg/cli/audit_report_render.go	Splits console rendering by section.
pkg/cli/audit_report_test.go	Adds formatting regression tests.

Review details

Tip

Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

• Files reviewed: 4/4 changed files
• Comments generated: 0
• Review effort level: Medium

[pelikhan]

/matt

[github-actions]

🧠 Matt Pocock Skills Reviewer has completed the skills-based review. ✅

[gh-aw-bot]

@copilot please run the pr-finisher skill, inspect the latest PR state, fix the failing check below if needed, and rerun checks once the branch is up to date.

Failed checks:

• Alpine Container Test

Generated by 👨‍🍳 PR Sous Chef · gpt54 27.4 AIC · ⌖ 8.1 AIC · ⊞ 5.5K · ◷
_{Comment /souschef to run again}

[github-actions]

Skills-Based Review 🧠

Applied /codebase-design and /tdd — commenting with improvement suggestions; no blocking correctness issues.

📋 Key Themes & Highlights

Key Themes

• Thin pass-through wrappers: buildAuditAssessments and appendToolingRecommendations group calls without adding depth — opportunities to either inline or deepen remain.
• auditDataInputs carries forwarding fields: metrics and mcpToolUsage are in the struct only to thread them into buildSessionAnalysis/buildMCPServerHealth; pre-computing those outside assembleAuditData would let the struct hold only results.
• Test scope: the new TestRenderConsoleExperimentsSorted goes through the full renderConsole path and swaps os.Stderr globally — testing the extracted renderConsoleExperiments helper directly would be tighter and parallel-safe.
• appendToolingRecommendations naming mismatch: it handles missing tools, MCP failures and firewall blocks — inconsistent with the single-concern pattern of the rest of the family.

Positive Highlights

• ✅ The renderConsole decomposition is clean and the naming is consistent — each helper does exactly what its name says.
• ✅ buildFailureFindingDescription is a genuine improvement: early-return structure and named constants make the branching readable.
• ✅ generateErrorVolumeFindings and generateFirewallFindings converting to direct []Finding{{...}} returns is idiomatic Go.
• ✅ TestBuildBlockedNetworkFindingDescription covers all four switch branches — solid table-driven coverage.
• ✅ lookupFallbackMetrics correctly moves the logsPath == "" guard to the top, eliminating a repeated condition.

🧠 Reviewed using Matt Pocock's skills by Matt Pocock Skills Reviewer · sonnet46 78.5 AIC · ⌖ 8.1 AIC · ⊞ 6.7K
_{Comment /matt to run again}

[Copilot]

@copilot please run the pr-finisher skill, inspect the latest PR state, fix the failing check below if needed, and rerun checks once the branch is up to date.

Failed checks:...

Investigated the failure: run 29911655000 / job 88897507342 was on older SHA 4c22df7 and failed on a network timeout while resolving docker.io/library/alpine:3.21, not on the audit-report refactor itself. Current HEAD 16581fe already has Alpine Container Test passing on run 29913946230 / job 88903243960, and local go test ./pkg/cli/..., make fmt, make lint, make test-unit, and make test all passed. No code change or new commit was needed here; if you want a fresh CI signal, a maintainer will need to re-trigger workflows manually.

[github-actions]

🎉 This pull request is included in a new release.

Release: v0.83.0