# V1 Autonomous Content Agents — Verification Audit — 2026-07-13

**Question audited:** are all the agents that autonomously create content for
`V1/` SOTA and production-ready?

**Method:** main-loop verification (no agent fan-out, per session limits)
against the prior ledgers — `V1_AUTONOMOUS_CONTENT_SOTA_AUDIT_2026-07-02.md`
(defect ledger H1–H5, M1–M23, L1–L10, SOTA items R1–R42),
`V1_SOTA_AUDIT_REMEDIATION_TODOS_2026-07-02.md` (42/42 marked done), and
`V1_AUTONOMOUS_CONTENT_LEDGER_APPLICATION_2026-07-04.md` (P0–P2 bindings). This
pass does not take the ledgers on faith: every HIGH fix was re-read in current
source, the adversarial stub battery was re-run over every audited unit, and
every core suite was re-executed on this box today.

## Verdict

**Yes at the code level, with an honest, explicitly-drawn deploy boundary.** The
autonomous content stack for V1 is real, SOTA-grade, adversarially clean, and
fully green in tests and typecheck. What remains open is exactly what the repo's
own ledgers say remains open: live-provider credentials and a handful of
deploy-/policy-bound seams that fail loud rather than fake success. Nothing
found in this pass contradicts a single `[x]` in the remediation ledger.

## 1. The agent inventory (what "the agents" are)

| Layer                  | System                                                                                                             | Role                                                                                                                                        |
| ---------------------- | ------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------- |
| Director plane         | `@oshun/creative-autonomy`                                                                                         | signals → bandit ideation → K variants → ε-BT tournament → calibrated 7-dim gate → review queue → publisher → preference learner            |
| Production search      | `@oshun/creative-orchestrator` (+ `@oshun/ai`)                                                                     | plan-DAG decomposition, plan judging, node best-of-N, critique-revise with argmax draft, replanning, per-node model routing                 |
| Judge plane            | `@shared/content-quality-judge` + `apps/oshun/content-service`                                                     | heterogeneous 3-model panels, injection-fenced prompts, cascaded/reconciliation judging, slop/reward-hack detectors, gold-set κ calibration |
| Execution & governance | `apps/oshun/bff/src/generation` + `src/agentic`, `@oshun/generation-control-isis`, `@shared/content-release-gates` | 7 media executors behind the single fail-closed Isis dispatch seam; watermark + C2PA + safety + quality probes; quotas, budgets, drain loop |
| Composed-work ledgers  | `@isis/workflows` ledger planes (07-04 wave)                                                                       | session/briefing producers, score⇄ledger adapter, lesson spine, claim retakes, persona→bank binding, node-addressed retakes                 |
| Editorial plane        | `@oshun/studio-authoring` + autonomy bindings                                                                      | publish-readiness gates, editorial calendar, checklists, McNemar champion-challenger, staleness sweeps                                      |

## 2. Re-verified in current source (this session)

**All five HIGH defects from 07-02 are fixed in HEAD:**

- H1 — `director.ts:325-331` `snapshotLearnedItemIds`/`restoreLearnedItemIds`,
  wired through `plane-persistence.ts:55,80-83` with a pre-migration fallback.
  No restart double-learning.
- H2 — `apps/oshun/content-service/src/main.ts:47` builds the panel through
  `resolveJudgePanelModels(3, isAvailable)`: distinct models per member with
  degraded-diversity auditing.
- H3 — `judge-engine.ts:32-53`: `UNTRUSTED_BEGIN/END` fencing,
  delimiter-breakout sanitization, immunity clause; red-team regression suite in
  the lib.
- H4 — `jobs-route.ts:182-183` re-checks `status === 'queued'` per job before
  claiming (drain race closed).
- H5 — `editorial-publisher.ts:24,90`: default gate set is the per-content-type
  publish-readiness pipeline (`createPublishReadinessGates`), not a lone tone
  gate.

**The 07-02 audit's biggest structural gap — "the quality engine is text-only,
media is deterministically dead" — is closed** by the post-audit isis wave
(commits `812ad33e…` → `a038318c…`): real image watermarking + C2PA signing +
safety scan + ffmpeg quality prober (image now auto-releases through full
governance), real narration/video/music governance (the last media kinds clear
the release gate), signed C2PA manifests across image/video/narration/music,
audio/video watermark modules, per-user daily quota gate, durable generation
budget gate, real spend capture, media best-of-N with seed control, provider
quality routing, dub-faithfulness scoring. The two remaining
`qualityAggregate: null` sites were read in context: both are honest fail-closed
defaults (pre-governance initial signals in `image-provider-env.ts:124`;
deploy-bound dub watermarker/signer in `caption-dub-provider-env.ts:343` with
blocking behavior documented inline).

**SOTA technique layer spot-checked present and tested:** `cascade.ts`
(cost-aware cascaded judging), reconciliation/debate round in
`judge-panel.ts`/`judge-engine.ts`, `plan-judge.ts` (plan-quality gate before
spend), `preference-log.ts` (DPO/RM-ready preference-pair persistence),
persona-simulation judges, Platt/isotonic calibration, exploration floors +
LinTS contextual bandit, McNemar paired champion-challenger, rubric-version
regression gating.

## 3. Adversarial stub scan — zero actionable hits

The mandatory grep battery plus the silent-stub scan (Math.random in
deterministic paths, fabricated-success catch blocks, excuse comments) was
re-run across all audited units (`creative-autonomy`, `creative-orchestrator`,
`content-quality-judge`, `content-release-gates`, `content-service` lib+app,
`bff/generation`, `bff/agentic`, `studio-authoring`, `generation-control-isis`,
`agentic-studio`, `agent-pipelines`, `shared/ai`). Every hit was read in
context; all are false positives (reward-_hacking_ detector vocabulary,
persona-_simulation_ judges, annotated non-secret id suffixes, Fisher–Yates/A-B
stochastic gating). The M14 fabrication stubs (`prompts/testing.ts` fake
p-values, `advanced/index.ts` embeddings excuse) are confirmed gutted —
`testing.ts` now computes a real Welch t-test with Student-t two-tailed p-values
and fails honest on n<2.

## 4. Test + typecheck evidence (executed on this box, 2026-07-13)

| Suite                                       | Result                                                      |
| ------------------------------------------- | ----------------------------------------------------------- |
| `@oshun/creative-autonomy`                  | 248/248 (16 files)                                          |
| `@shared/content-quality-judge`             | 280/280 (34 files)                                          |
| `@shared/content-release-gates`             | 19/19                                                       |
| `@oshun/generation-control-isis`            | 410/410 (20 files)                                          |
| BFF `src/generation` + `src/agentic`        | 587 passed, 1 creds-gated `skipIf(!ENGINE)` skip (66 files) |
| `@oshun/creative-orchestrator`              | 98/98                                                       |
| `@oshun/studio-authoring`                   | 138/138                                                     |
| `@oshun/content-service` (lib)              | 26/26                                                       |
| `@isis/workflows` (ledger planes/producers) | 376 passed, 1 gated skip (34 files)                         |
| `apps/oshun/bff` `tsc --noEmit`             | exit 0                                                      |

## 5. The honest boundary (what "prod ready" does NOT include)

These are not defects; they are the deliberately drawn seams, all fail-loud:

1. **Live provider credentials are deploy-bound** (`V1/TODOS.md:2942`) — the
   plane only advertises domains whose outputs can actually release (M15 fix);
   with no creds it refuses rather than fabricates.
2. **Deploy-bound media steps** — caption-dub watermark/C2PA signer (blocks on
   the floors until it lands), ASR/WER transcriber seam, FVD evaluator seam for
   Living-Scene continuity (explicit `{absent, policyValue}` sentinel that
   blocks any finite threshold).
3. **Data-gated learning** — engagement-outcome attribution poller, per-member κ
   panel weights, inter-rater dual-review κ, A/B live traffic: real machinery,
   accrues at deploy.
4. **Publish autonomy is per-surface POLICY, kept on purpose** — Veritas named
   attestation, Nisaba scholarly authority, persona consent, crisis screens
   (pass rate pinned 1.0), minor/likeness/cloned-voice human triggers. Autonomy
   raises draft throughput, not publication authority.
5. **BFF ledger stores are BFF-lifetime in-memory** per the house store pattern
   (durable snapshots exist for jobs/catalog/plane).
6. Residual V1 open items are deploy/ops (creds, Stripe live mode), other-studio
   verification sweeps (Bellona/Hathor), a human lineage-sensitivity review, and
   two mobile mentor-presence delivery refinements — none are content-agent code
   gaps.

## 6. Bottom line

- **SOTA:** yes — the stack implements the 07-02 audit's full R1–R42 catalog
  (media VLM judging, cross-modal consistency, ffmpeg probes, preference-pair
  logging, gold-set→κ calibration, cascaded + reconciliation judging, plan
  judging + multi-plan sampling, retrieval-grounded writers, OPRO-style steering
  mining, style memos, contextual bandits with exploration floors,
  publish-readiness binding, staleness sweeps), several of which remain ahead of
  common 2026 practice (discounted Thompson sampling with exact Beta-preserving
  decay, both-orderings BT tournaments, pessimistic-LCB best-of-N with
  excess-correlation hack detection, coverage-discounted partial panels,
  content-hash-bound fail-closed governance).
- **Prod-ready:** yes at the library + wiring level — everything compiles,
  typechecks, and passes its suites today; zero result-faking stubs; every
  absent capability is an explicit fail-loud seam owned by a named deploy step.
  Flipping it live is a credentials-and-ops exercise, not a code exercise.