# V3 Autonomous Content Agents Audit — 2026-07-14 Scope: every agent/pipeline that autonomously creates content for V3 (Lilith Metaverse / Tara Studio / Saraswati Stage). Method: per-library source read, adversarial stub scan (mandatory grep + silent-stub pattern scan), test-suite runs, verifier-script runs — main-loop only, no agent fan-out. Companion audits: `V1_AUTONOMOUS_CONTENT_AGENTS_AUDIT_2026-07-13.md`, `V2_AUTONOMOUS_CONTENT_AGENTS_AUDIT_2026-07-13.md`. Prior V3 adjudications this audit builds on: `V3/VERIFICATION_AUDIT_2026-05-31.md` and `V3/REMEDIATION_2026-06-12.md` (standard: _structural gates are not operational proof; hand-authored "observed" tables must not masquerade as measurements_). ## Verdict **The governance/policy cores are real and strong — several genuinely SOTA-shaped (concert scene quality gating, C2PA signing, pose runtime, scripted-persona containment). The stack is NOT production-ready as an end-to-end autonomous content system**, and — to its credit — it says so itself: `V3/launch/launch-readiness-release-gate.json` is red at 30/41 required commands and 24/39 named gates, with `gaReady: false`, after the 2026-06-12 de-circularization. Two axes to the verdict: 1. **Code quality of what exists**: high. Fail-loud validation everywhere, domain-specific algorithms, real third-party integrations where they matter (MediaPipe/MoveNet, c2pa-rs), 190+ tests green across the audited surface (149 TS across 6 libs + 38 Rust + 3 re-run verifiers). 2. **Distance to "autonomously creates top-notch content"**: material. The _generation_ moments themselves (music synthesis, lyric LLM calls, TTS, motion capture/AI-assist, world assets) are all provider seams or UE-side work that is not in this repo. What IS in repo is the governance shell around those moments. Several of those seams were fail-silent (fabricating results) until this audit — **all locally-actionable fabrication paths are now closed** (fixes 1–8 below): every generation-governance library either evaluates real supplied inputs or fails loud / labels itself a drill. What remains between here and prod-ready is exclusively external: provider credentials, real V1 Isis registration, real pose-capture training data, UE-side execution, and the operational windows the honest-red launch gates are waiting on. None of those can be truthfully closed from this machine. ## Inventory — the autonomous content stack | Layer | Package | What it does | Assessment | | ------------------------------- | ------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------- | | Music generation governance | `@oshun/isis-music` (9 files, ~3.8k LOC) | Provider routing (Suno/Udio/Stable Audio/MusicGen/AudioCraft/Mubert), Sophia-grounded lyric factuality, Lilith tone policy, auto-mix/master review gate, provenance bundles, fingerprint pre-release check, V1 Isis workflow registration | Real policy cores; 3 fabrication seams FIXED this audit | | Virtual-artist tenant | `@oshun/saraswati-stage` (36 files, ~21k LOC) | Persona dossiers, voice-signature consent builds, discography release flow, genre cells, remix rights, Themis adjudication, C2PA manifests, concert authoring pipeline | Real except the concert-authoring evidence generator (structural-only; see findings) | | Live performance engine | `apps/v3/saraswati-service` (Rust, ~5.3k LOC, 38 tests) | Performance-plan → Sequencer compile, per-song execution, between-song speech gates, audience interaction, recording pipeline, royalty settlement, **real C2PA signing (c2pa-rs, PEM signer, Reader-verified)** | C2PA path production-grade; module evaluators are structural gates, honest fail-loud validation | | Backstory grounding | `@oshun/sophia-saraswati-grounding` (~1.3k LOC) | Citation-trail validation for persona backstory; real-culture claims require supporting Sophia sources; fail-closed | Real | | Instructor-persona content | `@oshun/tara-studio` (51 files, ~21k LOC, 69 tests) | **Scripted-only AI personas** (out-of-script asana → sponsor handoff or graceful no-op), invitational-language linter, lineage grounding, TTS voice consent/recording/scope-lock/royalty, practice plans | Real; the containment model (persona can only speak sponsor-approved lines) is the right design | | Pose coaching | `@oshun/aja-pose` (~3.7k LOC) | MediaPipe tasks-vision runtime + MoveNet fallback pipeline, geometric feature extraction, nearest-centroid classifier + confusion-matrix gate, rule-based alignment cues, risk-modification ladder, on-device privacy egress guard | Runtime/features/rules real; synthetic corpus mislabeled as in-house/licensed — FIXED | | Concert quality gates | `@oshun/v3-concert-quality` (~1k LOC) | Judge-panel scene quality scoring, corpus diversity (cluster coverage + pairwise distance), slop-density caps, composed with C2PA/consent gates into one fail-closed export suite | Real; genuinely SOTA-shaped content-quality gating | | Avatar pipeline | `@oshun/avatar-pipeline` (~5.2k LOC) | VRM→Oshun retarget, GA personas, likeness-drift metric (normalized landmark distance per canonical angle, fail-closed on missing views), dual authoring, instructor opt-in | Real metric over synthetic gallery fixtures | | Motion / world-asset generation | `@oshun/isis-motion`, `@oshun/isis-world-asset` | Motion briefs / retarget-pass QA / Sequencer cue export; LOD budgets / cook compliance / asset briefs / provenance | Were descriptor-only shells at audit start; REAL implementations added in the second pass (see fixes 6–7) | ## Fixed during this audit All three mirror the V2 precedent (`fix(shared): fail-loud v2 translation provider seam`): a governance library must never return a result it did not receive from a real upstream call. 1. **HIGH — fabricated lyric generation** (`libs/v3/isis-music/src/grounded-lyric-generation.ts`). `buildSaraswatiGroundedLyricDraft` returned four hardcoded Anaya Veil template lines for ANY persona/theme while stamping `modelFamily: 'claude-opus' | 'claude-sonnet'` as though a model had generated them; the spec pinned the fabrication ("generates … with Claude Sonnet"). Fix: `lines` is now a REQUIRED input (the caller passes real model output); empty/missing lines throw `SaraswatiGroundedLyricProviderError`. The former template is exported as `SARASWATI_ANAYA_VEIL_GROUNDED_LYRIC_FIXTURE_LINES`, explicitly labeled a validation fixture. Tests now assert the fail-loud path. 2. **HIGH — mastering quality gate that could never fail** (`libs/v3/isis-music/src/mix-master-review-gate.ts`). `createSaraswatiAutoMixMasterPass` "checked" loudness/true-peak by comparing release-target CONSTANTS to themselves and hardcoded `reviewPreviewRendered: true`, minting artifact ids for artifacts never produced. Fix: new required `SaraswatiMasteredTrackMeasurements` (master + preview artifact ids, measured integrated LUFS, measured dBTP, preview rendered) — missing/invalid measurements throw `SaraswatiAutoMixMasterMeasurementError`; checks now evaluate measurements against −14 LUFS ±1 LU and ≤ −1 dBTP. Review queue takes `{ track, measurements }` submissions. Tests prove the gate fails on out-of-tolerance measurements. 3. **MEDIUM — implicit synthetic rights catalog** (`libs/v3/isis-music/src/fingerprint-pre-release-check.ts`). `checkSaraswatiPreReleaseFingerprints` defaulted to the 50-track SYNTHETIC reference catalog, so a caller omitting `referenceCatalog` got a guaranteed-'clear' rights verdict against fake references. Fix: the catalog is now a required option (throws otherwise); the synthetic constant is documented as validation-only. 4. **MEDIUM — synthetic pose corpus masquerading as real datasets** (`libs/v3/aja-pose/src/classifier.ts`). The index-harmonic fixture corpus carried manifests claiming `sourceKind: 'in-house'` / `'licensed'` with invented license refs (`licensed-yoga-pose-validation-v3`), making the self-fulfilling ≥ 0.92 accuracy gate look like a measured result. Fix: new `'synthetic-fixture'` source kind used by the default corpus, honest dataset ids/license ref, and a doc contract that production centroids must be trained on real labeled captures. Verifier needles updated to match (`verify-saraswati-grounded-lyric-generation.mjs`, `verify-aja-asana-classifier.mjs`); all three touched verifiers re-run green. Post-fix: isis-music 23/23, aja-pose 21/21, tsc clean on both. ## Fixed in the second pass (same day) After the initial report, the remaining locally-actionable gaps were closed: 5. **Concert authoring pipeline evidence seam** (`libs/v3/saraswati-stage/src/concert-authoring-pipeline.ts`). The pipeline previously self-certified: speech slots built with `editorialReviewState: 'approved'`, dress rehearsals with `signedOff: true` and 5 phantom operators, choreography `true` literals, GA cadence defaulting `?? true` — all 10 gates passed by construction. Now every report carries `evidenceMode: 'declared-drill' | 'recorded'`: with no `recordedEvidence` input the run is a labeled drill; with records supplied (reviewer ids + timestamps, named rehearsal participants, bound-interaction lists, observed cadence counts) the artifacts are built FROM the records and honest-zero cadence records fail the gate. `publishSaraswatiConcertSequencer` now THROWS on drill evidence unless `allowDrillPublish` is explicit, and drill receipts are labeled `evidenceMode: 'declared-drill'`. The Web Studio cockpit passes the explicit drill flag and exposes `data-evidence-mode`. Verifier failure set confirmed byte-identical before/after (the 4 remaining failures are the intentional honest-red GA-window signals from the 2026-06-12 remediation). 6. **`@oshun/isis-motion` implemented** (was an ~85-LOC descriptor shell). Real domain logic behind all three declared capabilities: motion briefs (metronome tempo classes, energy→intensity ladder, contiguous-section and beat-count validation), retarget-pass QA (17-bone canonical coverage, goniometric joint limits — knee/elbow 0–150°, neck ±70° —, contact-frame foot-slip metric at 2 cm tolerance), and cue export (beat→frame quantization at the 30 fps Sequencer rate with gap-free full-coverage validation). 10 tests assert exact computed values (e.g. 16 beats @120 BPM = 240 frames; 6 cm slip fails). 7. **`@oshun/isis-world-asset` implemented** (was an ~86-LOC descriptor shell). Tier-scaled LOD budgets (desktop envelopes per asset class; VR ×0.5, mobile ×0.25, Tier-2 web ×0.1 triangle scales; per-tier texture ceilings; 40%/15% LOD-chain ratios), measured-cook compliance evaluation (fail-loud on over-budget triangles/textures, missing LOD levels, material-slot overruns), tenant-policy asset briefs (per-tenant allowed classes; Tara may not generate architecture), and provenance bundles with a fail-closed inspector that blocks publish on failed cook evidence. 8 tests assert exact budget numbers (hero-prop mobile LOD0 = 37,500 tris). 8. **`v1-isis-registration.ts` publication evidence derived, not asserted.** The five `publicationEvidence` booleans (previously hardcoded `true`) now derive from evidence refs; the in-repo seed points validation/dry-run at the real local artifacts and leaves the three human sign-off refs EMPTY — their booleans are honestly false and `publicationReady: false` until real ack/review/rollback records are supplied. 9. **Registration proven against the real V1 Isis registry** (third pass, same day). New integration spec `apps/isis/workflow-registry/src/routes/saraswati-v3-workflow-registration.spec.ts` registers the Saraswati track-generation workflow through the ACTUAL workflow-registry service — real Hono routes, real zod schema validation (engine `custom`, category `audio-generation` accepted), real service layer + security audit log; only the storage backend is swapped in-memory (the same dependency-boundary double the service's own route specs use). Create → publish → fetch round-trip verified; the payload is derived from the `@oshun/isis-music` catalog entry, so drift between the module and the real registry schema now fails a test. The evidence seed's `validationRunRef` points at this spec. Side fix: the workflow-registry app's vitest OOM'd on 16 GB machines (workspace-wide tsconfig scan) — a minimal-alias `vitest.integration.config.ts` now runs its specs locally (auth spec 11/11, previously OOM). ## Findings noted, not fixed (adjudicated or not locally actionable) - **Production registry deployment.** The registration path is now integration-proven end-to-end against the real service code; executing it against the deployed production registry (real Postgres, real API keys) is a deploy-time step, plus the three human sign-off refs (owner ack, governance review, rollback plan) which stay honestly false until recorded. - **aja-pose "human review" relevance gate** builds its accepted-rule sets procedurally under `reviewerPanel: 'tara-senior-teachers'` — expected-decision fixtures, fine as harness, but `passesHumanReviewGate` should not be quoted as evidence of human approval. - **Rust module evaluators are structural.** e.g. `evaluate_between_song_speech` verifies id shapes/prefixes and emits `triggered: true` receipts for transitions that never ran. Validation is real and fail-loud; the reports are drill artifacts, not showtime telemetry. ## Deploy boundary (what "prod-ready" additionally requires) - Provider credentials + real generation calls behind every seam: music providers (Suno/Udio/…), lyric LLM (via V1 Isis / `@oshun/ai`), TTS (Cartesia/ElevenLabs), fingerprint vendors (Audible Magic/Pex live catalogs). - Real V1 Isis registry registration for `saraswati-stage-track-generation`. - Real pose-capture training data for the aja-pose centroids (the runtime is ready; the shipped default model is fixture-trained). - UE-side execution (Sequencer assets, MetaSounds, motion libraries) — not auditable on this Mac (source-read only; no UE here). - The 11 currently-red launch sub-gates, GA-cadence window actually elapsing, real drills replacing self-attested ones (per `V3/LAUNCH_READINESS.md` and the remediation log). ## Test evidence (all run 2026-07-14 on this machine) | Suite | Result | | ----------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------- | | `libs/v3/isis-music` (post-fix) | 23/23 ✓, tsc clean | | `libs/v3/isis-motion` (post-implementation) | 10/10 ✓, tsc clean | | `libs/v3/isis-world-asset` (post-implementation) | 8/8 ✓, tsc clean | | `libs/v3/aja-pose` (post-fix) | 21/21 ✓, tsc clean | | `libs/v3/saraswati-stage` (post-evidence-seam) | 57/57 ✓, tsc clean | | `libs/v3/sophia-saraswati-grounding` | 8/8 ✓ | | `libs/v3/tara-studio` | 69/69 ✓ | | `libs/v3/avatar-pipeline` | 23/23 ✓ | | `libs/v3/concert-quality` | 14/14 ✓ | | `apps/oshun/web` SaraswatiConcertAuthoringPipeline component | 3/3 ✓ | | `apps/v3/saraswati-service` (cargo) | 38/38 ✓ | | verifiers: grounded-lyric, auto-mix-master, fingerprint, aja-classifier, v1-isis-workflow | all pass post-fix; concert-authoring verifier failure set byte-identical to pre-change (intentional honest-red GA-window signals only) |