# HarnessAthon Submission Package

## One-Line Positioning

We upgraded the SDD Speckit OKR pipeline from the CASAN Level 3→4 transition to **CASAN Level 4 — proven by attack**: H4/H5/H6 (former GAPs 20/25/30) now defeat ~23 live adversarial vectors with on-screen exit codes. Level 5 is stated as **roadmap** (IdP, WORM log storage, provider-telemetry API, hosted dashboard) — not claimed as achieved.

## Open These First

1. `presentation/HarnessAthon_CASAN_Level5_Demo.pptx`
2. `docs/00_task_breakdown.md`
3. `docs/01_submission_checklist.md`
4. `docs/02_pitch_script.md`
5. `docs/03_judge_qna.md`
6. `docs/04_evidence_map.md`
7. `video/01_video_recording_guide.md`
8. `ai_context/AI_README.md`

## Main Evidence

| Evidence | Source |
|---|---|
| Harness test report | `../AINative_OKR_CASAN5/docs/output/casan/evidence/harness-test-report.md` |
| CASAN assessment | `../AINative_OKR_CASAN5/docs/output/casan/casan-level4-assessment.md` |
| Before/after scorecard | `../AINative_OKR_CASAN5/docs/output/casan/before-after-scorecard.md` |
| Demo pipeline context | `../AINative_OKR_CASAN5/docs/output/output_logs/casan-demo/pipeline-context.yaml` |
| Central dashboard | `../AINative_OKR_CASAN5/docs/output/casan/central-agentops-dashboard.html` |
| Final zip | `../AINative_OKR_CASAN5.zip` |

## Folder Purpose

| Folder | Purpose |
|---|---|
| `docs/` | Checklist, pitch script, judge Q&A, evidence map, AI-optimized structure notes |
| `presentation/` | PPT deck and deterministic generation source |
| `video/` | Screen-recording guide and narration outline |
| `evidence/` | Evidence index pointing to canonical generated evidence |
| `ai_context/` | One-page context for AI/teammate review |

## Verification Command

```bash
cd ../AINative_OKR_CASAN5
bash .specify/tests/run-casan4-harness-tests.sh
```

Expected: all PASS, including H4/H5/H6 and Level 5 evidence checks.

## Claim Boundary

- CASAN Level 4: achieved.
- CASAN Level 5: demonstrated locally with signed policy, provider telemetry import, shared harness registry, fallback, drift detection, rollback, KPI feedback, and central dashboard.
- Enterprise production Level 5 still needs live IdP, WORM storage, live provider API integration, and hosted dashboard.

### Production hardening — implemented vs planned

Following Plan-07/Plan-09, the following hardening is **implemented and tested**
(each control has an executable adversarial test that fails if the control is
removed). Full status: `casan-next-plans/CASAN_HARDENING_STATUS.md`.

- **Implemented + tested (Plan-07 Track A):** H4 strict semantic fail-closed
  (`CASAN_SECURITY_STRICT`), unicode/encoding normalization (homoglyph, zero-width,
  fullwidth, base64/hex), tool-output injection scan, H5 telemetry-integrity signing,
  H6 absolute + cumulative + cold-start cost controls, benign/false-positive budget
  gate (FP ≤ 3%, adversarial block ≥ 95%, CRITICAL = 100%).
- **Implemented + tested (Plan-07 Track C-MVP):** tool-authorization / action gating,
  supply-chain gate, data-exfiltration guard.
- **Scaffold + tested (Track C-MVP):** runtime sandbox — static policy + `ulimit`
  backstops. **Not** kernel isolation; production needs container `--network=none
  --read-only --pids-limit` / nsjail.
- **Implemented + tested (Plan-09 MVP):** Evidence Pack — `casan pack` / `casan
  verify-pack` (tamper-evident manifest + signed head + certified-run gate).
- **Implemented + tested (H5 governance hardening):** approval-identity (reviewer
  cryptographically signs the request + role authorization — env-var approver no
  longer enough); KMS key management (Vault Transit sign + rotation + non-exportable,
  **validated live**); external WORM audit ledger (rollback + tamper detection).
- **Implemented + tested (H6 AgentOps hardening):** live alert dispatch (webhook +
  dedup + dead-letter, fail-loud, end-to-end from a failing step); provider-telemetry
  API fetch + local-vs-provider reconciliation (catches token under-reporting);
  hosted dashboard with stale-aware `/healthz`; sliding-window circuit breaker (V15).
- **Planned (NOT done — do not claim as production-ready):** multilingual H4,
  classifier/split-injection resistance, HSM + KMS-by-default, live IdP (OIDC/JWT),
  true WORM store (S3 Object Lock), incident kill-switch, true sandbox isolation,
  deployed dashboard host + managed alert channel, real billing-API telemetry.

Test totals: baseline 79 (run-casan4 35 + adversarial 44) preserved, **+96 new**
hardening checks (Track A 25, Track C-MVP 29, Evidence Pack 7, H5-approval 8,
H5-infra KMS+WORM 7, H6-agentops 20) = **175**, 0 fail — last full run 2026-07-05
(KMS validated live 2026-07-04 via Vault; `evidence/scoring-run-report.md`). Fair
maturity ~80/100 per harness; H5 rose 76→80 and H6 rose 79→80 so **no harness is
below 80** (CASAN Level 4, proven by attack). See `CASAN_HARDENING_STATUS.md`.
Because these live in **separate** suites, the demo attack battery counts in
`video/01_video_recording_guide.md` are unchanged.