thanhnvandClaude Fable 5
da66a36f97
Close the three gaps the scoring report itself flagged for H6 plus V15, each as a real MVP + fail-able adversarial test (same pattern that lifted H5): - D1 alert-dispatch.sh: alerts POST to a real HTTP webhook (severity routing, dedup window, retry) + dead-letter queue with redelivery; fail-loud in strict. Wired into agent-metrics.sh so a failing step pages live end-to-end. - D2 provider-usage-fetch.sh + telemetry-reconcile.sh: pull usage from a provider usage HTTP API (all-or-nothing schema gate, fail-loud) + reconcile local vs provider ground truth — token under-reporting/hidden runs => TELEMETRY_DISCREPANCY. - D3 dashboard-serve.sh + dashboard-server.py: serve the dashboard over HTTP with a stale-aware /healthz probe (fresh=200 ok, telemetry silent-death=503 stale). - D4 circuit-breaker-check.sh: sliding-window failure-rate breaker (V15) — interleaved successes no longer evade the consecutive-failure breaker (CIRCUIT_OPEN_WINDOW). New suite phase-h6-agentops-tests.sh: 20/20, all live against local HTTP endpoints (webhook sink, mock provider API, dashboard server) — deterministic, no model needed. Also fix sign-policy-bundle.sh key-sync invariant: the local-fallback branch only exported policy-public.pem when generating a NEW key, so a Vault-DOWN run after a Vault-signed run verified a local-key signature against the Vault pubkey (RSA padding error, run-casan4 died mid-suite). Now always re-exports the pubkey before signing — same fix class as tool-audit-lib.sh / governance-check.sh. Full battery re-run sequentially: 175/175 PASS, 0 FAIL across 8 suites (KMS SKIP this run — Vault down; validated live 2026-07-04). Docs synced: scoring-run-report (H6 79→80, no harness below 80, 155→175), CASAN_HARDENING_STATUS (Phase 5 D1–D4), Plan-07, submission README, and run-hardening.sh (H6+ scenes HO1–HO4). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
93 lines
4.9 KiB
Markdown
93 lines
4.9 KiB
Markdown
# 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.
|