Tags

Tags give the ability to mark specific points in history as being important
  • gauntlet/snapshot-b6qRBmvhAF6UfIENUAzT

    Gauntlet AI snapshot for submission b6qRBmvhAF6UfIENUAzT
    
    Commit: 8697bf14aaea3aa01cb73c8bc60e207810e09a0f
    
    --- Cumulative Manifest ---
    {
      "totalFiles": 153,
      "totalLines": 28548,
      "languages": {
        "markdown": 20,
        "yaml": 0,
        "html": 0,
        "json": 27,
        "typescript": 45,
        "css": 6,
        "sql": 1,
        "javascript": 1
      },
      "deps": [
        "@anthropic-ai/sdk",
        "@hono/node-server",
        "hono",
        "node-pg-migrate",
        "pg",
        "zod",
        "@types/node",
        "@types/pg",
        "pg-mem",
        "tsx",
        "typescript",
        "vitest"
      ],
      "depCount": 12,
      "framework": null,
      "hasTests": true,
      "hasCi": false,
      "hasReadme": true,
      "hasLockfile": true,
      "complexityScore": "high"
    }
    
    --- Delta Manifest ---
    {
      "previousSnapshotId": null,
      "elapsedHours": null,
      "commitsSince": 50,
      "filesAdded": [
        ".agents/skills/agentforge-process-doc/MILESTONE-NAMING.md",
        ".agents/skills/agentforge-process-doc/SESSION-JOURNAL-TEMPLATE.md",
        ".agents/skills/agentforge-process-doc/SKILL.md",
        ".agents/skills/grill-me/SKILL.md",
        ".agents/skills/improve-codebase-architecture/DEEPENING.md",
        ".agents/skills/improve-codebase-architecture/INTERFACE-DESIGN.md",
        ".agents/skills/improve-codebase-architecture/LANGUAGE.md",
        ".agents/skills/improve-codebase-architecture/SKILL.md",
        ".agents/skills/ubiquitous-language/SKILL.md",
        ".dockerignore",
        ".gitignore",
        ".pre-commit-config.yaml",
        "ARCHITECTURE.md",
        "Dockerfile",
        "README.md",
        "THREAT_MODEL.md",
        "USERS.md",
        "console/index.html",
        "console/package-lock.json",
        "console/package.json",
        "console/src/App.tsx",
        "console/src/CaseDetail.tsx",
        "console/src/HelpModal.tsx",
        "console/src/Home.tsx",
        "console/src/LifecycleActions.tsx",
        "console/src/LifecyclePipeline.tsx",
        "console/src/LifecycleStateView.tsx",
        "console/src/PendingVulnReports.tsx",
        "console/src/SubcategoryDrill.tsx",
        "console/src/TraceTimeline.tsx",
        "console/src/api.ts",
        "console/src/icons.tsx",
        "console/src/main.tsx",
        "console/src/styles.css",
        "console/src/theme.ts",
        "console/tsconfig.json",
        "console/vite.config.ts",
        "db/migrations/001_init.sql",
        "docker-compose.prod.yml",
        "docker-compose.yml",
        "docs/CONSOLE_DEPLOY.md",
        "docs/COST_REPORT.md",
        "docs/DEMO_CHEAT_SHEET.md",
        "docs/DEMO_STORYBOARD.md",
        "docs/MVP_DEMO_SCRIPT.md",
        "docs/SOCIAL_POST.md",
        "docs/STAGE_0_ARCH-DEFENSE.md",
        "docs/STAGE_1_TARGET_STATE.md",
        "docs/STAGE_3_RUN_NOTES.md",
        "docs/STAGE_4_SANDBOX_SMOKE.md",
        "docs/W3_REQUIREMENTS_CHECK.md",
        "docs/W3_TASKS.md",
        "docs/journal/0513-T0155-w3-mvp-submission.md",
        "docs/journal/0513-T1554-ledger-judge-calibration.md",
        "docs/journal/0513-T1651-gate3-orchestrator-doc-agent.md",
        "docs/journal/0513-T1717-gate4-coverage-expansion.md",
        "docs/journal/0513-T1740-gate5-review-console-v1.md",
        "docs/journal/0514-T0016-gate5-review-console-deploy.md",
        "docs/journal/0514-T0026-gate6-kickoff-handoff.md",
        "docs/journal/0515-T0221-findings-loop-and-console-ux.md",
        "docs/journal/0515-T1127-w3-final-honesty-pass.md",
        "docs/milestones/02-w3-mvp-submission.md",
        "docs/references/Week-3_AgentForge-Adversarial-AI-Security-Platform.pdf",
        "docs/references/error_analysis_slides.pdf",
        "evals/README.md",
        "evals/calibration/README.md",
        "evals/calibration/ground_truth_v1.json",
        "evals/calibration/run-2026-05-13T20-48-41-737Z.json",
        "evals/fixtures/docs/p0-1b-intake-form.pdf",
        "evals/fixtures/docs/p0-1b-json-shaped.pdf",
        "evals/fixtures/docs/p0-1b-lab-note.png",
        "evals/fixtures/vuln-doc-agent-output-v1.json",
        "evals/results/run-2026-05-12T23-15-12-514Z.json",
        "evals/results/run-2026-05-13T04-20-17-775Z.json",
        "evals/results/run-2026-05-14T06-21-46-525Z.json",
        "evals/seeds/p0-1b-intake-form-injection.json",
        "evals/seeds/p0-1b-json-shaped-injection.json",
        "evals/seeds/p0-1b-lab-note-ocr-injection.json",
        "evals/seeds/p0-1c-slow-build-injection.json",
        "evals/seeds/p0-2a-authority-framing.json",
        "evals/seeds/p0-2a-conversational-hijack.json",
        "evals/seeds/p0-2a-direct-uuid-swap.json",
        "evals/seeds/p0-4a-allergy-reversal.json",
        "evals/seeds/p0-4a-wrong-dose.json",
        "evals/seeds/p0-4a-wrong-medication.json",
        "evals/seeds/p2-1a-instruction-suffix-injection.json",
        "evals/seeds/p2-1a-system-prompt-extraction.json",
        "evals/seeds/p2-1a-tool-override.json",
        "evals/seeds/p2-6a-dev-mode-jailbreak.json",
        "evals/seeds/p2-6a-role-override.json",
        "evals/seeds/p2-6a-roleplay-framing.json",
        "package-lock.json",
        "package.json",
        "prompts/documentation_v1.md",
        "prompts/judge_v1.md",
        "scripts/approve-finding.ts",
        "scripts/backfill-mvp-results.mjs",
        "scripts/calibrate-judge.ts",
        "scripts/decay-subcategories.ts",
        "scripts/generate-doc-fixtures.ts",
        "scripts/generate-vuln-fixture.ts",
        "scripts/generate-vuln-from-ledger.ts",
        "scripts/orchestrate-cycle.ts",
        "scripts/pg-migrate.mjs",
        "scripts/regression-replay.ts",
        "scripts/seed-mvp-subcategories.ts",
        "src/agents/approval.test.ts",
        "src/agents/approval.ts",
        "src/agents/documentation.test.ts",
        "src/agents/documentation.ts",
        "src/agents/family_detection.test.ts",
        "src/agents/family_detection.ts",
        "src/agents/judge_llm.test.ts",
        "src/agents/judge_llm.ts",
        "src/agents/orchestrator.test.ts",
        "src/agents/orchestrator.ts",
        "src/console_api/index.test.ts",
        "src/console_api/index.ts",
        "src/console_server.ts",
        "src/cost.test.ts",
        "src/cost.ts",
        "src/eval_schema.test.ts",
        "src/eval_schema.ts",
        "src/judge.test.ts",
        "src/judge.ts",
        "src/ledger/access.test.ts",
        "src/ledger/attack_cases.ts",
        "src/ledger/campaigns.ts",
        "src/ledger/findings.ts",
        "src/ledger/index.ts",
        "src/ledger/journal_entries.ts",
        "src/ledger/migration.test.ts",
        "src/ledger/pool.test.ts",
        "src/ledger/pool.ts",
        "src/ledger/regression_runs.ts",
        "src/ledger/subcategories.ts",
        "src/ledger/types.ts",
        "src/ledger/verdicts.ts",
        "src/ledger/vuln_reports.ts",
        "src/probe.ts",
        "src/red_team_agent.ts",
        "src/run.test.ts",
        "src/run.ts",
        "src/secrets.ts",
        "src/server.test.ts",
        "src/server.ts",
        "src/target_client.test.ts",
        "src/target_client.ts",
        "tsconfig.json",
        "vulnerabilities/VULN-003.md",
        "vulnerabilities/_TEMPLATE.md",
        "vulnerabilities/pending/VULN-001.md",
        "vulnerabilities/pending/VULN-002.md"
      ],
      "filesModified": [],
      "filesDeleted": [],
      "linesAdded": {
        "markdown": 5768,
        "yaml": 133,
        "html": 27,
        "json": 7563,
        "typescript": 12886,
        "css": 1587,
        "sql": 204,
        "javascript": 239
      },
      "linesRemoved": {},
      "depsAdded": [
        "@anthropic-ai/sdk",
        "@hono/node-server",
        "hono",
        "node-pg-migrate",
        "pg",
        "zod",
        "@types/node",
        "@types/pg",
        "pg-mem",
        "tsx",
        "typescript",
        "vitest"
      ],
      "depsRemoved": [],
      "testFilesAdded": [
        "src/agents/approval.test.ts",
        "src/agents/documentation.test.ts",
        "src/agents/family_detection.test.ts",
        "src/agents/judge_llm.test.ts",
        "src/agents/orchestrator.test.ts",
        "src/console_api/index.test.ts",
        "src/cost.test.ts",
        "src/eval_schema.test.ts",
        "src/judge.test.ts",
        "src/ledger/access.test.ts",
        "src/ledger/migration.test.ts",
        "src/ledger/pool.test.ts",
        "src/run.test.ts",
        "src/server.test.ts",
        "src/target_client.test.ts"
      ],
      "testFilesRemoved": [],
      "commitSignals": {
        "frequency": 27.12,
        "avgSize": 652.6,
        "largestCommit": 11897,
        "messageQualityScore": 1
      }
    }