# V2 Autonomous Content Agents — Verification Audit — 2026-07-13 **Question audited:** are all the agents that autonomously create content for `V2/` SOTA and production-ready? **Method:** main-loop verification (no agent fan-out, per session limits). Inventory was drawn from `V2/architecture/esports-companion-and-ai-services.md` and `V2/features/community-store-support-and-ai-services.md`, then every unit was read in current source, the mandatory adversarial stub grep battery plus the silent-stub scan was run over all of it, delegation chains were followed into the shared substrates (`@iris/conversation-orchestration`, `@iris/conversation-providers-anthropic`, `@psyche/avatar-lipsync`, `@iris/voice` call-translation, `@hathor/llm-npc`, `@isis/visual-dubbing`), and every suite plus `tsc --noEmit` was executed on this box today. ## Verdict **Yes at the code level, with the same honestly-drawn deploy boundary the architecture docs themselves declare — after this session closed one real fail-silent defect.** The V2 autonomous content plane is real, adversarially clean, rollback-sealed in both TypeScript and C++, and fully green in tests and typecheck. One genuine fabrication path was found and fixed (the realtime translation bridge accepted the `@iris/voice` `local_default` passthrough provider, which invents bracket-tagged pseudo-translations with a fake 0.7 confidence, and reported them as successful deliveries). Everything else absent is a named, fail-loud seam: provider credentials, plan→executor bindings, and the spec-only gRPC tier. ## 1. The agent inventory (what "the agents" are) | Layer | System | Role | | --------------------- | ------------------------------------------------------------------------------------------------------------------------------ | --------------------------------------------------------------------------------------------------------------------------- | | Commentary generation | `@v2/iris-commentary-orchestration` → `@iris/conversation-orchestration` → `@iris/conversation-providers-anthropic` / `-local` | cue plans with 420/240/100/40 ms budget decomposition, rollback-frame rejection, deterministic pre-recorded fallback bank | | Personas & voice | `@v2/calliope-commentator-personas` + `commentator-personas.json` manifest | 4-artist launch roster; voice-clone clearance, consent/likeness license ids, talent signoff, AI disclosure — all cook-gated | | Render bridges | `isis-commentary-lipsync-pipeline`, `psyche-commentary-face-animation`, `euterpe-commentary-ducking` | phoneme→viseme frames with coarticulation (computed in-process), −18 LUFS sidechain ducking math, ≤45 ms drift contract | | Localization & a11y | `iris-realtime-translation`, `iris-accessibility`, `psyche-caption-streaming` | provider-gated chat/commentary translation; caption engine channel plans per surface; cert-gate-blocking a11y bridge | | AI Director | `@v2/psyche-ai-director-hints` + `V2/ue/Plugins/V2AdaptiveAI` | first-order-Markov tendency hints off-rollback only; hashed match-start snapshot vector as the sole rollback-legal input | | In-engine contracts | `V2/ue/Plugins/V2AICommentary` | C++ cue/post-match contracts mirroring the TS budgets, with `IsValidContract` failure reasons and off-rollback flags | | Asset generation | `isis-cosmetic-pipeline`, `isis-venue-capture-pipeline` | model-gen/AI-texturing/rigging/bellona-cook plan contracts; generated-asset payloads demand real URIs + content hashes | | NPC dialogue | `hathor-npc-adapter` → `@hathor/llm-npc` | encounter/dialogue/behavior/bark hooks over a provider chain (circuit breaker, ACE/Inworld/Convai), file dialogue cache | | Post-match & news | `buildV2AIPostMatchExperiencePlan` + `@v2/esports-tools` (`@veritas/fact-checking`) | top-3–5 highlight selection over required moment kinds; claims→evidence→consensus verification that holds publication | | Authored delivery | `patch-notes-service`, `message-of-the-day-service`, `live-event-content-delivery-service` | human-authored content with real targeting/normalization/etag logic — delivery services by design, not generators | ## 2. Verified in current source (this session) - **The rollback envelope is enforced, not described.** TS: `fromRollbackFrame` is rejected by both the V2 cue validator and the Iris stream validator; `assertValidLiveRequest` throws on any live hint under rollback; snapshots serialize a sorted-key JSON vector with a real `sha256` hash. C++: `EvaluateAIDirectorDecision` hard-falls to the static rule-of-the-day for ranked/tournament/multiplayer/opt-out before consulting any profile; `FV2AICommentaryCueContract::IsValidContract` rejects non-Calliope commentators, missing fallback seeds, and non-Iris package bindings. - **Fallback is deterministic, labeled, and never fabricated as success.** The commentary stream returns `source: 'pre-recorded-bank'` plus an explicit `fallbackReason` (`missing-orchestrator` / `latency-budget-exceeded` / `empty-response` / `error`), selected by a stable hash over `(cueKind,ruleset,commentatorId,seed)` under a `Promise.race` latency budget. - **The generation core is a real provider chain.** The orchestrator seam reaches `@iris/conversation-providers-anthropic` (shared LLM service over an OpenRouter-compatible HTTP client with typed errors) with `@iris/conversation-providers-local` as the on-cap route; `@hathor/llm-npc` ships a provider chain with circuit breakers, latency tracking, and fail-loud `not configured` errors for ACE/Inworld/Convai. - **The render math is computed, not asserted.** Face animation invokes `createPhonemeSequence → phonemeSequenceToVisemes → generateLipSyncFrames` (3.6k-line substrate with real coarticulation blending) in-process; ducking computes intensity-based gain with density and loudness compensation — the spec now pins the hand-checked value (climax −10, density −1.5, loudness −3 → **−14.5 dB**, linear 10^(−14.5/20) ≈ 0.18837). - **Persona governance is cook-blocking.** `assertV2CommentatorPersonasReadyForCook` rejects revoked voice clones and missing signoff scopes; the manifest carries consent ids, likeness licenses, similarity thresholds, watermarking and abuse monitoring flags per artist. ## 3. Defects found this session (all fixed in this commit) 1. **HIGH — silent pseudo-translation path** (`iris-realtime-translation.ts`): the bridge's provider argument was optional; omitting it silently engaged the `@iris/voice` `local_default` passthrough, which returns `[lang] text` with a fabricated 0.7 confidence as a _successful_ delivery — invisible to the session's reason codes, and the specs always injected a mock so tests never saw it. **Fix:** provider is now required (`V2IrisRealtimeTranslationError`, code `missing_translation_provider`), and any `local_default` delivery is flagged with an explicit reason code. Two regression tests added. 2. **LOW — cwd-dependent test** (`calliope-commentator-personas`): the spec resolved the repo-root-relative manifest against `process.cwd()`, so the suite failed 0/4 when run from the service directory. Fixed with an `import.meta.url` repo-root anchor. 3. **LOW — un-runnable fact-checking suite** (`V2/tools/esports`): the vitest alias map lacked `@oshun/ai`, whose package entry points at an unbuilt `dist/`, so `veritas-esports-fact-checking.spec.ts` failed at import. Fixed by aliasing `@oshun/ai` to source; 3/3 suites now green. 4. **LOW — under-pinned assertion** (`euterpe-commentary-ducking` spec): gain assertions were range-only (a hardcoded −7 would have passed); now pinned to the known-correct −14.5 dB / linear value. ## 4. Adversarial stub scan — zero actionable hits The mandatory grep battery (excuse comments, placeholder/TODO/dummy/fake vocabulary) returned **zero hits** across all 15 services plus `V2/tools/esports`. The silent-stub scan (Math.random in deterministic paths, fabricated-success catch blocks, ignored `_`-params) surfaced only honest code: typed error rethrows in the NPC bridge, ENOENT→cache-miss in the dialogue cache, URL-validation throws in MOTD, and a hostname fallback in fact-checking. The one genuine fail-silent path found (translation `local_default`) is fixed above. ## 5. Test + typecheck evidence (executed on this box, 2026-07-13) | Suite | Result | | ----------------------------------------------- | ----------------------------------------- | | `@v2/iris-commentary-orchestration` | 9/9 | | `@iris/conversation-orchestration` (substrate) | 114/114 | | `@v2/calliope-commentator-personas` | 4/4 (was 0/4 from service dir) | | `@v2/isis-commentary-lipsync-pipeline` | 3/3 | | `@v2/psyche-commentary-face-animation` | 4/4 | | `@v2/euterpe-commentary-ducking` | 5/5 (exact-value pinned) | | `@v2/iris-realtime-translation` | 5/5 (2 new guards) | | `@v2/iris-accessibility` | 2/2 | | `@v2/psyche-caption-streaming` | 3/3 | | `@v2/psyche-ai-director-hints` | 4/4 | | `@v2/hathor-npc-adapter` | 6/6 | | `@v2/isis-cosmetic-pipeline` | 4/4 | | `@v2/isis-venue-capture-pipeline` | 3/3 | | `@v2/patch-notes-service` | 3/3 | | `@v2/message-of-the-day-service` | 4/4 | | `@v2/live-event-content-delivery-service` | 3/3 | | `@v2/esports-tools` | 7/7 (fact-checking suite was un-runnable) | | `tsc --noEmit`, all 15 services + esports tools | exit 0 everywhere | ## 6. The honest boundary (what "prod ready" does NOT include) These are deliberately drawn seams, all fail-loud, most declared by the architecture docs themselves: 1. **Generation providers are deploy-bound.** Live commentary text, persona TTS, and face rendering come from the provider tier (per `deps§67`: Anthropic Claude for play-by-play, ElevenLabs for TTS, Isis `ai-video` for auto-edit). Absent credentials, the plane degrades to the deterministic fallback bank or silence with explicit `fallbackReason` — never fabricated output. 2. **The gRPC wire tier — CLOSED 2026-07-14.** The three AI-services contracts now ship at `libs/proto/src/oshun/v2/{esports,director,ai_commentary}/` with `@v2/grpc-services` binding them to the real engines (veritas fact-checked Crown Points credit, rollback-rejecting Director, fallback- labeled Commentary streaming); 16 in-process round-trip tests. The other V2 proto packages (online, live, progression, community, racing) remain designed-only. 3. **Isis plan→executor binding is a named seam.** The lipsync, cosmetic, and venue-capture packages are plan contracts: plans never claim rendered output, and rendered/generated payload builders demand a real asset id, URI, and content hash. The dubbing/texturing engines exist as substrates (`@isis/visual-dubbing` et al.); the dispatch wiring is the deploy step. 4. **UE C++ verified by source-read only on this box** (no UE toolchain on this Mac; the compiled UE 5.5 build lives on the Linux sandbox). The TS mirrors of the same contracts are fully test-executed. 5. **Editorial content stays human-authored by policy.** MOTD, patch notes, community spotlights, and procedural fighter dialogue (`seasonScope: 'post-launch-dlc'`, `manualReviewRequired: true`) are delivery-plane, not autonomous generation — matching the EU AI Act disclosure posture (`"AI commentary is machine-generated presentation content."`, cross-ref §80.4). ## 7. Bottom line - **SOTA:** yes — the V2 plane composes the same substrate stack the V1 audit verified as SOTA, and adds the parts that are genuinely hard in a fighting game: a rollback envelope sealed in both languages, a real-time latency budget with a deterministic provider-free fallback bank, cook-blocking voice and likeness governance, and post-match publication held behind claims-vs-replay-hash fact checking. - **Prod-ready:** yes at the library + wiring level — every unit compiles, typechecks, and passes its suites today; zero result-faking stubs remain (the one found was fixed and regression-tested this session); every absent capability is an explicit fail-loud seam owned by a named deploy step.