# Isis — Systems Deep Dive

> The `libs/isis/` area: ~75 Nx libraries that make up **Isis, the generative
> factory** — the AI/LLM provider plane, the ComfyUI/job orchestration plumbing,
> and a deep stack of text-to-3D, mesh, Gaussian-splatting, audio, and video
> generation surfaces that Oshun's creative tooling is built on.

## What this area is

Isis is Oshun's **generative-AI factory**. Where most domains own a single
business surface, `libs/isis/` is a sprawling toolkit: roughly 75 libraries
(`scope:isis` in their `project.json` tags) ranging from a 174k-line unified
provider layer (`@isis/ai-providers`) down to single-file workflow studios
(`@isis/foley-studio`, `@isis/relight-studio`). They divide into a few clear
sub-systems, described below; the catalog further down has one block per node.

The **AI/LLM plane** (`@isis/ai-providers`, `isis-llm-providers`,
`isis-llm-orchestrator`, `isis-batch-llm-processing`, `isis-token-budget`,
`isis-prompt-engineering`, `isis-react-framework`, `isis-agent-consensus`,
`isis-model-fine-tuning`, plus the `§24` governance pair `@isis/managed-models`
and `@isis/entitlements`) is the model-access substrate: typed adapters for
Claude/GPT/Gemini/Grok/Ollama and ElevenLabs, registries, rate-limiting, cost
and budget accounting, prompt templating, ReAct agent loops, multi-agent
consensus, and fine-tuning orchestration.

The **factory plumbing** (`@isis/job-envelope`, `@isis/workflows`,
`@isis/workflow-classes`, the ComfyUI trio `@isis/comfyui-sdk` /
`@isis/comfyui-nodes` / `@isis/comfyui-factory`, `@isis/3d-comfyui-nodes`,
`isis-operation-orchestrator`, `isis-event-publisher`,
`@isis/anomaly-detection`, `@isis/database`, `@isis/client`, `@isis/outputs`,
`@isis/output-gallery`, `@isis/curated-cards`, `@isis/runpod-surface`) is the
canonical job envelope, ComfyUI workflow schema/DSL, queue/retry orchestration,
event bus, Prisma persistence, the client SDK, and the operator/creator surfaces
(`§24`).

The bulk of the area is **3D and media generation**: a text/image-to-3D core
(`@isis/3d-generation`, `@isis/3d-inference-local`, `@isis/three-d-pipelines`,
and a family of typed model-contract libraries — `@isis/fast-generation`,
`@isis/score-distillation`, `@isis/hash-encoding`, `@isis/part-level-3d`,
`@isis/gigascale-3d`, `@isis/3d-control`, `@isis/3d-video-diffusion`,
`@isis/scene-from-image-composer`, `@isis/3d-scene-assembly`); mesh/topology/
rigging/texturing (`@isis/mesh-transformers`, `@isis/quad-mesh-gen`,
`@isis/universal-rigging`, `@isis/ai-texturing`, `@isis/text-mesh-editing`,
`@isis/3d-semantic-editing`, `@isis/video-to-mesh`); a Gaussian-splatting
cluster (`@isis/gaussian-splatting`, `@isis/3dgs-advanced`,
`@isis/3dgs-diffusion-editing`, `@isis/3dgs-relighting-pbr`,
`@isis/3d-browser`); asset-library/marketplace/ governance/quality
(`@isis/3d-asset-library`, `@isis/3d-marketplace-ops`,
`@isis/3d-product-parity`, `@isis/3d-quality-gates`,
`@isis/3d-generation-benchmarks`, `@isis/model-governance-3d`,
`@isis/3d-post-pipeline`); audio (`@isis/audio-generation`,
`@isis/music-generation`, `@isis/foley-studio`, `@isis/voice-cloning`); and a
broad set of video/AV production studios plus face/portrait/dubbing surfaces.

#### A note on the "contracts" libraries

Many of the 3D libraries describe themselves as "contracts." In practice they
are **typed capability-and-planning libraries**: they export workflow constants
(`ISIS_*_WORKFLOW`), `create*Capabilities` descriptors, deterministic
`create*Plan` planners, and a mix of real deterministic compute (e.g.
`computeIsisSdsLoss` in `@isis/score-distillation`, LOD edge-collapse ordering
in `@isis/quad-mesh-gen`, part-quality metrics in `@isis/part-level-3d`). They
describe, validate, and plan model-backed workflows; the heavy GPU/model
inference itself runs in external runtimes (`@isis/3d-inference-local`, ComfyUI,
RunPod). Where a package is thin or still scaffolded, the block below says so.

## How it fits the wider system

These libraries are consumed by Isis's own services and BFF, by the Studio/Admin
front-ends (via `@isis/client` and the `§24` surface/entitlement libraries), and
by sibling creative domains — several video/audio studios are explicitly "for
ISIS and Yemaya," and `@isis/3d-post-pipeline` / `@isis/three-d-pipelines` carry
Mawu-Studio asset-creation contracts. The dependency shape is layered:
`layer:data` (`@isis/database`), `layer:clients` (`@isis/client`), and a large
`layer:domain` core. The AI plane and job/ComfyUI plumbing sit at the bottom;
the 3D/audio/video generation surfaces compose on top of them. Walk the "used
by" edges on any node below to see exactly who depends on it.

## Entity reference

### @isis/ai-providers

The unified AI-provider layer and the area's largest library (~174k LOC). Its
barrel (`libs/isis/ai-providers/src/index.ts`) exports typed adapters and
factories for LLMs (Anthropic Claude, OpenAI GPT, Google Gemini, xAI Grok,
Ollama via `createClaude`/`createGPT`/…), ElevenLabs TTS and Agents Platform 2.0
conversational AI, the Civitai model registry, RunComfy serverless execution, a
usage/cost/budget tracker, and a caching `AIProviderFactory`. The provider spine
the rest of Isis calls models through.

### isis-llm-providers

Provider-registry infrastructure (`libs/isis/llm-providers`): model/provider
registration, rate limiting, token counting, cost calculation, and health/
circuit-breaker tracking (`ProviderRegistryConfig`, `RateLimiterConfig`,
`TokenCounterConfig`, `CostCalculatorConfig`, `CircuitBreakerState`). It governs
_how_ providers are selected and throttled, complementing `@isis/ai-providers`'
concrete adapters.

### isis-llm-orchestrator

Structured-LLM orchestration (`libs/isis/llm-orchestrator`): typed extraction,
schema validation, repair of malformed model output, budget framing, and an
operation queue (`ExtractionResult`, `SchemaValidationConfig`, `RepairConfig`,
`BudgetTrackerConfig`, `OperationEntry`, `QueueStats`). It turns raw model calls
into validated, schema-conformant results.

### isis-batch-llm-processing

Batch LLM pipeline (`libs/isis/batch-llm-processing`): batch request/job
modelling, scheduling within time windows, result correlation, cost reporting,
and throughput snapshots (`BatchRequest`, `ScheduleDecision`, `BatchJobResult`,
`CostReport`, `ThroughputSnapshot`, plus `ToolDefinition`/`ChatMessage`). For
high-volume, cost-aware LLM workloads.

### isis-token-budget

Token-budget engine (`libs/isis/token-budget`): per-tenant budgets with category
allocations, cost prediction from `ModelPricing`, enforcement rules, alerts,
rebalancing/optimization, and provider fallback decisions (`TokenBudget`,
`EnforcementCheckResult`, `CostPrediction`, `FallbackDecision`). The accounting
layer that keeps generation spend bounded.

### isis-prompt-engineering

Prompt toolkit (`libs/isis/prompt-engineering`): versioned prompt templates with
variables/sections, few-shot example selection, chain-of-thought construction
and execution, role definitions, and prompt evaluation/scoring
(`PromptTemplate`, `ChainOfThought`, `FewShotExample`, `PromptEvaluation`,
`PromptVersion`).

### isis-react-framework

A ReAct (reason+act) agent framework (`libs/isis/react-framework`): the
thought→action→observation step loop with execution traces, tool definitions and
results, and trace analysis/metrics (`ReActStep`, `ExecutionTrace`,
`ToolDefinition`, `ThoughtChainAnalysis`, `ActionPatternAnalysis`). The
agent-loop substrate for tool-using LLM agents inside Isis.

### isis-agent-consensus

Multi-agent reasoning and consensus (`libs/isis/agent-consensus`): structured
debate with claims/arguments/evidence, reasoning chains, fallacy detection,
convergence sessions, and compromise proposals (`Debate`, `Argument`,
`DetectedFallacy`, `ConvergenceSession`, `CompromiseProposal`,
`ReasoningQualityMetrics`). Models how several agents argue toward an agreed
answer.

### isis-model-fine-tuning

Fine-tuning orchestration (`libs/isis/model-fine-tuning`): hyperparameter search
trials, dataset curation/deduplication and quality stats, experiment tracking,
model-merge jobs, benchmark runs, and metric snapshots (`HpTrial`,
`CuratedDataset`, `DeduplicationResult`, `MergeJob`, `MetricSnapshot`).

### @isis/managed-models

A thin but real registry-browser surface (`libs/isis/managed-models`, ~74 LOC):
the barrel re-exports `./browser/index`, exposing only **post-intake approved**
models to the creator UI (`§24.2`). Small by design — it is a governed view over
the model registry, not a model store itself.

### @isis/entitlements

The generation-tier resolver and surface allowlist (`§24.1`,
`libs/isis/entitlements`): `generation-tier.ts` deterministically maps an
entitlement bundle to a tier (`operator-admin` / `aaa-creator` /
`curated-creator` / `contemplative`) and a surface allowlist, and
`studio-boundary.ts` enforces the studio edge. The documented single source of
truth BFF/Admin/Studio middleware consult before rendering any generation
surface.

### @isis/job-envelope

The canonical Isis job envelope (`libs/isis/job-envelope`): the versioned queue
schema plus exhaustive generation-type, ControlNet, IP-Adapter, and InstantID
mode manifests with legacy-workflow alias maps (`ISIS_JOB_ENVELOPE_VERSION`,
`ISIS_GENERATION_TYPE_MANIFEST`, `ISIS_CONTROLNET_MAJOR_MODES`, …). Every Isis
generation job is shaped by this contract.

### @isis/workflows

ComfyUI workflow definitions and tooling (`libs/isis/workflows`): the `Workflow`
schema with validation, a versioning/migration pipeline
(`WorkflowSchemaMigration`), a template DSL, and seed management. The typed
representation of the ComfyUI graphs Isis runs.

### @isis/workflow-classes

The Living-Scene workflow-class catalog (`§25.5`, `libs/isis/workflow-classes`):
five domain templates — `tara`, `nyx`, `veritas`, `metis`, `arete` — plus a
`template-catalog`, locale-parity, and fixture eval gates. Curated, gated
workflow blueprints rather than free-form graphs.

### @isis/comfyui-sdk

The "ComfyUI Nodes 2.0" SDK (`libs/isis/comfyui-sdk`): a typed connection system
with branded socket types (`INT`/`FLOAT`/`IMAGE`), node versioning with
migration paths, node discovery/introspection, a validation system, and an
auto-generating testing/benchmark framework (`NodeSpec`, `createNodeValidator`).
For _building_ ComfyUI nodes safely.

### @isis/comfyui-nodes

A **Python** package (`lang:python`,
`libs/isis/comfyui-nodes/src/isis_comfyui_nodes`) of real ComfyUI custom nodes
backing Oshun's spiritual/sacred-art workflows — `consciousness`,
`sacred_geometry`, `lilith` (asset I/O + metadata), `spiritual_styles`, and
`vfx_post` node sets, with pytest suites (`tests/test_vfx_post_nodes.py`,
`tests/test_lilith_nodes.py`) and example workflow JSON. The only Python node
library in the area; it has no TS barrel.

### @isis/comfyui-factory

The ComfyUI workflow factory (`§24.3`, `libs/isis/comfyui-factory`, ~430 LOC):
an approved `workflow-class` catalog with guardrails, `template-diff`,
`portability-check`, and a `rehearsal-harness`. Compact but real — it governs
and diffs the approved class set rather than executing graphs.

### @isis/3d-comfyui-nodes

A typed catalog of ComfyUI **3D** nodes and workflow templates
(`libs/isis/3d-comfyui-nodes`): node-family descriptors, conditioning modes,
canonical workflow stage definitions, and a Hunyuan3D local runtime descriptor
(`ThreeDComfyUiNodeFamilyDescriptor`, `ThreeDComfyUiHunyuanLocalRuntime`). The
3D counterpart to `@isis/workflows`/`@isis/comfyui-sdk`.

### isis-operation-orchestrator

Operation orchestration (`libs/isis/operation-orchestrator`): retry policies
with failure classification, batch composition, dead-letter handling, execution
chains/phases, and pipeline execution with checkpoints (`RetryPolicy`,
`FailureClassification`, `DeadLetterEntry`, `ExecutionChain`,
`PipelineExecution`). The reliability layer for multi-step generation jobs.

### isis-event-publisher

The Isis event publisher (`libs/isis/event-publisher`): `IsisEventPublisher`
plus a typed payload set for the job lifecycle
(queued/started/progress/completed/ failed/cancelled) and asset/workflow/model
events (`IsisJobCompletedPayload`, `IsisAssetGeneratedPayload`,
`IsisWorkflowRegisteredPayload`). How Isis announces work onto the bus.

### @isis/anomaly-detection

Anomaly detection and fraud prevention for the factory
(`libs/isis/anomaly-detection`): an `AnomalyDetectionService` for suspicious
activity, chargeback prediction, and account protection (`RiskLevel`,
`DetectionStatus`, `ActionType`). A compact three-file service over rule/risk
types.

### @isis/database

The Isis persistence layer (`layer:data`, `libs/isis/database`): the Prisma
client wrapper (`createPrismaClient`, `transaction`, `executeRaw`,
`loadGeneratedPrismaClientModule`) plus stable schema-aligned domain types. The
generated client makes this one of the larger libraries by line count.

### @isis/client

The TypeScript client SDK (`layer:clients`, `libs/isis/client`): `IsisClient` /
`createClient` / `createClientFromEnv` with sub-clients such as `generation`
(`textToImage`, `waitForJob`). The typed entry point external callers use to
submit jobs and poll results.

### @isis/outputs

The output manifest and provenance layer (`libs/isis/outputs`): the
`OutputFile`/ manifest schema, provenance records, and lineage-graph utilities
(`ManifestId`, `ProvenanceId`, `LineageNodeId`, `QualityTier`, `FileHash`).
Describes and tracks the artifacts a generation job produces.

### @isis/output-gallery

The unified output gallery surface (`§24.10`, `libs/isis/output-gallery`):
`output-record`, `lineage`, `branch-replay`, `compare-grid`, and `bulk-actions`
modules — filters, lineage, branch/replay, side-by-side compare, and bulk
operations over generated outputs.

### @isis/curated-cards

Curated creator generation cards (`§24.6`, `libs/isis/curated-cards`): card
types, validators, a preflight checker, an entitlement gate, and a catalog
(`card-types`/`card-validators`/`preflight`/`entitlement-gate`/`catalog`). Cards
are bound to approved workflow classes so curated creators get safe, pre-vetted
generation presets.

### @isis/runpod-surface

The RunPod operator surface data model (`§24.4`, `libs/isis/runpod-surface`):
`endpoint-registry`, `cost-quota`, `queue-inspector`, and `secret-rotation`
modules — the typed dashboard model for managing serverless GPU endpoints.

### @isis/3d-generation

The text/image-to-3D generation core (`libs/isis/3d-generation`, ~56k LOC):
request/result types and provider abstractions for text-to-3D and image-to-3D
with post-processing (`TextTo3DRequest`, `ImageTo3DRequest`, `Generated3DModel`,
`QualityPreset`, `Model3DFormat`). One of the substantial implementations, not a
thin contract.

### @isis/3d-inference-local

The self-hosted 3D inference kernel (`libs/isis/3d-inference-local`, ~76k LOC):
config and runtime contracts for serving 3D models on local GPUs — server/device
config, a GPU memory manager with pressure levels and allocation results, queue
policy, model cache policy, and dispatch envelopes
(`createLocal3DGpuMemoryManagerConfig`, `Local3DDispatchEnvelope`). The largest
3D library and the local execution target the contract libraries plan against.

### @isis/three-d-pipelines

The 3D pipeline-class catalog and provider abstraction (`§24.9`,
`libs/isis/three-d-pipelines`): `provider`, `pipeline-class`, `provenance`,
`topology`, a `sky-event-card`, and Mawu-Studio creation modules. The Mawu
product path dispatches `text-to-3d`, `text-to-texture`, `text-to-world`, and
`text-to-npc` requests through separately configured, fail-loud HTTP routes. It
bounds and validates provider responses, recomputes tool-specific usability, and
runs successful output through semantic grounding, attribution, provenance,
content hashing, and prompt-output trust checks. Its local reference backend is
explicitly procedural.

The V7 operational-evidence module inventories all ten headline execution
boundaries: Crucible tabular-Q and match-meta, Loom reference vision and local
terrain ML, the four distinct Mawu product routes, Themis dispatch, and
full-engine parity. A catalog is ready only with exactly one fresh, digest-bound
record per boundary. Each record must match its fixed implementation class and
include exact implementation/model/dataset/output license identity, run/artifact
provenance, sampled USD cost and latency, passing safety scenarios,
threshold-derived quality metrics, and an exercised provider failover,
deterministic retry, or engine restart inside its recovery objective with zero
data loss. Model-free and dataset-free dispositions require an explicit reason;
model-backed routes cannot use them. This is an admission contract, not live
evidence: the V7 operational-evidence task remains open until real retained
records pass it.

The bounded V7 flagship fixture composes all four governed reference artifacts
into `region:mawu-market-quarter:v1`, a 128 m square procedural evidence region.
Its independent evaluator derives completeness from exact terrain coverage,
in-bounds source-linked assets, scheduled NPC roles, zero-sum economy
transactions, an acyclic asset-targeted and reward-bound quest graph, complete
English/Spanish/French message keys, and the V7 accessibility floor. Its
deterministic simulator derives terrain reachability, asset navigation, quest
completion, and ledger integrity from the sealed manifest. The first 32-session
replay exposed one unreachable asset; an exact-replay policy moved it through a
system-authored, full-auto common run and the after replay passed. Both the
simulation and revision records are digest-bound and independently validate
nested common-run and output evidence. This proves a coherent procedural
manifest and governed headless revision, not a UE cook, product-model
generation, player telemetry, playtest, human approval, or canary.

### @isis/fast-generation

Fast-3D contracts for rectified-flow and consistency-model workflows
(`libs/isis/fast-generation`): a consistency-mesh-transformer pipeline with a
real `runIsisConsistencyMeshTransformerPipeline`, latency budgets, and a
generation-speed benchmark with GPU-tier/method profiles. Plans and benchmarks
low-latency 3D generation.

### @isis/score-distillation

Score Distillation Sampling for text-to-3D (`libs/isis/score-distillation`):
genuine deterministic SDS math — `computeIsisSdsLoss`, `addIsisSdsNoise`,
Gaussian-noise and linear noise-schedule builders, parameter-update and
optimization-step helpers (`IsisSdsLossResult`, `IsisSdsNoiseSchedule`). Real
loss utilities, not just descriptors.

### @isis/hash-encoding

Multi-resolution hash-grid encoding for neural fields
(`libs/isis/hash-encoding`): streaming level selection/update plans and an
export path that serializes hash-encoded meshes/textures (e.g.
`serializeIsisHashEncodedMeshToObj`, `exportIsisHashEncodedMesh`). The
Instant-NGP-style encoding contracts plus real OBJ/texture export.

### @isis/part-level-3d

Part-level, PartGen-style compositional 3D generation
(`libs/isis/part-level-3d`): a part-quality metrics computer
(`computeIsisPartGenerationQualityMetrics`) and a text-driven scene-composition
planner (`composeIsisSceneFromText`, `createIsisScenePartGenObjectGenerator`).
Generates and scores compositional multi-part assets.

### @isis/scene-from-image-composer

Scene-from-single-image composition (block B of ISIS_GAPS,
`libs/isis/scene-from-image-composer`, ~9.3k LOC across 66 non-test files). A
substantial, fully-wired pipeline: the barrel exports working
`composeSceneFromImage` / `createSceneFromImagePipeline` entry points plus a
`runPhases` orchestrator over nine ordered phases
(environment/grounding/detection/objects/align/bake/coherence/audio/manifest),
alongside a real `align/` module (`alignMeshToSplatFrame`, anchor resolution
with `UnknownAnchorError`/`UnresolvableAnchorsError`), object cropping,
detection, and a mesh-provider router.

### @isis/3d-scene-assembly

Semantic scene assembly (`libs/isis/3d-scene-assembly`, ~1.9k LOC): a semantic
scene graph with nodes/connectors/constraints, material bindings, and provenance
(`createThreeDSemanticSceneGraph`, `ThreeDSceneConstraintKind`), backing kitbash
assembly and placement validation. Bootstrap-manifest style with a real
scene-graph core.

### @isis/3d-control

3D ControlNet / reference-control contracts (`libs/isis/3d-control`): IP-Adapter
LoRA variant training (dataset manifests, training plans/gates,
`runIsis3dIpAdapterLoraVariantTraining`) and a face-identity-preservation plan
for multi-view generation. Plans conditioned/controlled multi-view 3D.

### @isis/3d-video-diffusion

SV3D-style video-diffusion contracts for image-conditioned multi-view
reconstruction (`libs/isis/3d-video-diffusion`): custom camera-trajectory
construction with emphasis frames/regions, and a video-diffusion ↔
mesh-transformer hybrid generator
(`generateIsisVideoDiffusionMeshTransformerHybrid`).

### @isis/gigascale-3d

Next-generation 3D-model integration contracts (`libs/isis/gigascale-3d`): typed
profiles and readiness evaluation for large external models — a CHORD PBR
pipeline (`createIsisChordPbrGenerationPlan`, `evaluateIsisChordPbrReadiness`)
and Direct3D-S2 (`DIRECT3D_S2_MODEL_ID`), with license-policy and runtime
device/OS modelling. Describes how gigascale models slot into Isis.

### @isis/mesh-transformers

Autoregressive mesh-generation transformer contracts
(`libs/isis/mesh-transformers`): MeshGPT architecture (VQ-VAE tokenizer +
decoder, face-token sequences), vocabulary learning, and the broader
MeshGPT/PolyGen/MeshXL family (`createIsisMeshGptArchitecturePlan`,
`IsisMeshGptVqVaeTokenizerConfig`). Typed model architectures and training
objectives for mesh tokenization.

### @isis/quad-mesh-gen

Quad-dominant mesh generation (`libs/isis/quad-mesh-gen`): a QuadGPT-style
LOD-chain generator with real edge-collapse ordering
(`createIsisQuadMeshEdgeCollapseOrder`, `generateIsisQuadMeshLodChain`) and a
game-ready pipeline with procedural PBR synthesis, boundary-seam prediction, and
engine exporters (`runIsisQuadMeshGameReadyPipeline`).

### @isis/universal-rigging

Topology-agnostic auto-rigging (`libs/isis/universal-rigging`, ~48k LOC and one
of the largest): a broad export surface covering ML skeleton prediction,
automatic skin-weight computation, animation clip core / blending-transition
graphs / export / preview rendering, bone-hierarchy inference, and
species/creature rig templates (bird, fish-marine, facial, eye, clothing,
corrective blend shapes, cross-species retargeting). A substantial rigging
foundation, not a contract stub.

### @isis/ai-texturing

AI-native PBR texturing (`libs/isis/ai-texturing`, ~28k LOC): capability
builders for AI-based texture baking, Hunyuan3D-Paint image-guided PBR, and
PBR-aware super-resolution, denoising, detail synthesis, and compression
(`createLocal3DHunyuan3DPaintImageGuidedPbrCapabilities`, …). Generates and
refines material maps for generated meshes.

### @isis/text-mesh-editing

Text-guided mesh editing (`libs/isis/text-mesh-editing`): multi-view
InstructPix2Pix/SDS edit transfer (`transferIsisTextMeshEditToBatch`) and a
preview/undo workflow with an undo stack (`previewIsisTextMeshEdit`,
`undoIsisTextMeshEdit`, `createIsisTextMeshEditUndoStack`). Plans localized,
instruction-driven mesh edits.

### @isis/3d-semantic-editing

Semantic part decomposition and localized editing
(`libs/isis/3d-semantic-editing`): semantic part nodes/assemblies with masks and
confidence, cross-format part metadata read/write for glTF/USDA/blend payloads
(`readLocal3DSemanticMetadataFromGltfJson`/`…Usda`/`…BlendPayload`), and
assembly validation. Bridges semantic part data across DCC formats.

### @isis/video-to-mesh

Video-first 3D reconstruction (`libs/isis/video-to-mesh`, ~29k LOC): capability
builders for monocular video depth estimation, camera-pose estimation,
multi-frame depth fusion, point-cloud surface reconstruction, texture
projection, and object segmentation (`createLocal3DVideoToMesh*Capabilities`). A
full video→mesh pipeline contract set.

### @isis/gaussian-splatting

The end-to-end 3D Gaussian-Splatting pipeline (`libs/isis/gaussian-splatting`,
~31k LOC): real multi-camera capture (`CaptureManager`,
`FileSystemCameraProvider`, `SharpFrameQualityAnalyzer` using `sharp`),
preprocessing, training, rendering, and optimization. A substantial implemented
pipeline, not just types.

### @isis/3dgs-advanced

Advanced 3DGS production contracts (`libs/isis/3dgs-advanced`): GI-GS global
illumination (G-buffer/decomposition plans), MiLo mesh-in-loop extraction,
reflective-GS integration, SplatPainter interactive editing, and
confidence-based mesh extraction, over a shared `common` module with
scene/camera/light validators. Production-grade splatting techniques as typed
plans.

### @isis/3dgs-diffusion-editing

Diffusion-guided 3DGS editing (`libs/isis/3dgs-diffusion-editing`): a GaussCtrl
model-integration plan with depth conditioning, latent alignment, cross-view
consistency, and propagation graphs
(`createIsis3DGSGaussCtrlModelIntegrationPlan`). Plans diffusion-driven edits
over a splat scene.

### @isis/3dgs-relighting-pbr

Material-decomposed 3DGS relighting (`libs/isis/3dgs-relighting-pbr`): a
LumiGauss model loader with geometry/material/transfer-coefficient buffer
layouts and integrity checks, plus a LumiGauss training pipeline
(`createIsisLumiGaussModelLoaderPlan`,
`createIsisLumiGaussTrainingPipelinePlan`). Decomposes splats into PBR materials
for relighting.

### @isis/3d-browser

Browser-first 3D viewing/splatting/editing/inference contracts
(`libs/isis/3d-browser`, ~27k LOC): a module/blueprint manifest plus a runtime
capability assessor (`assessBrowser3DRuntime`) that reads navigator/WebGPU
adapter support snapshots and picks a runtime class with a fallback backend. The
browser-side delivery surface for 3D.

### @isis/3d-asset-library

The searchable 3D asset marketplace library (`libs/isis/3d-asset-library`, ~27k
LOC): a module-blueprint manifest plus `community`, `core`, `provenance`,
`style`, and `variation` sub-modules for discovery, contracts, and asset
blueprints. The catalog/discovery infrastructure for the 3D marketplace.

### @isis/3d-marketplace-ops

Marketplace trust and IP-governance ops (`libs/isis/3d-marketplace-ops`, ~2.2k
LOC over many small modules): seller/publisher verification workflows
(`planSellerVerificationWorkflow`), license declaration, and listing controls.
Bootstrap-manifest style — the seller-operations side of 3D commerce.

### @isis/3d-product-parity

Prompting and product-parity primitives (`libs/isis/3d-product-parity`, ~2k
LOC): a prompt helper with scored dimensions (`create3DPromptHelper`) and a
structured prompt builder targeting topology/export targets
(`buildStructured3DPrompt`), plus review-flow primitives. Input-quality
assistance for 3D product workflows.

### @isis/3d-quality-gates

Release-gate taxonomy and review governance (`libs/isis/3d-quality-gates`): a
failure-taxonomy with `count3DQualityFailureDefinitions`, a gold-standard
benchmark corpus with coverage summaries and acceptance/approval records, and
corpus/operations/taxonomy blueprints. The quality-gate vocabulary for 3D
output.

### @isis/3d-generation-benchmarks

The 3D-generation benchmarking suite (`libs/isis/3d-generation-benchmarks`):
standardized image and prompt suites with minimum counts and reference-image
profiles, an automated benchmark runner with concurrency limits, and result
storage versioning. Measures pipeline quality against fixed suites.

### @isis/model-governance-3d

License/deployment/compliance governance for 3D models
(`libs/isis/model-governance-3d`): an exception-approval workflow with audit
entries (`create3DModelGovernanceExceptionApproval`,
`evaluate3DModelGovernanceExceptionApproval`) and near-duplicate checking. The
compliance gate before a 3D model is usable.

### @isis/3d-post-pipeline

Unified 3D post-processing orchestration (`libs/isis/3d-post-pipeline`, ~31k
LOC): a module-blueprint manifest plus Mawu-Studio asset import/attribution
contracts (import receipts, mapped materials, pipeline diagnostics, eval
fixtures/reports). Stitches post-processing stages after generation and bridges
to Mawu Studio.

### @isis/audio-generation

AI audio generation (`libs/isis/audio-generation`, ~16k LOC): music synthesis,
voice synthesis, and sound-effects generation with shared audio-format/metadata
types (`MusicGenerationRequest`, `VoiceID`, audio format/sample-rate/bit-depth
types). The general-purpose audio factory surface.

### @isis/music-generation

Music + ambient generation (`§24.8`, `libs/isis/music-generation`, ~540 LOC): a
`provider` abstraction, `guardrails`, `provenance`, and `stems` modules. Compact
— the governed, watermark/provenance-aware music surface layered over a provider
seam.

### @isis/foley-studio

Foley and sound-design orchestration for ISIS and Yemaya
(`libs/isis/foley-studio`, a single ~1.3k-line module): detected foley events
typed by kind/material/intensity, provider options (`foleycrafter`, `av-link`,
`any2audio`), DAW targets, and AAF/OMF/BWF-P export. Production foley as a typed
workflow.

### @isis/voice-cloning

Professional voice cloning and synthesis (`libs/isis/voice-cloning`): a
voice-profile creation planner (dataset prep steps, source types, training
strategies, quality gates) plus a capabilities/workflow manifest
(`VoiceProfileCreationPlanner`, `createVoiceCloningLibraryManifest`). Plans the
clone-and-synthesize pipeline.

### @isis/ai-video

AI video-generation providers and workflows (`libs/isis/ai-video`): typed
clients for Runway Gen-4, OpenAI Sora, Kling, Pika, Luma Ray2, Google Veo, and
self-hosted Stable Video Diffusion (`RunwayClient`, `VideoProviderClient`,
`buildNextGenProviderPayload`, plus Haiper/Higgsfield adapters). The
multi-vendor video-gen entry point.

### @isis/seedance-provider

The Seedance 2.0 provider (`libs/isis/seedance-provider`, ~22k LOC):
multi-backend provider interfaces and exhaustive typed configuration —
resolution/aspect/ duration/motion options, reference-asset conditioning
(image/video), and a capability matrix (`SeedanceCapabilityMatrix`,
`SeedanceReferenceAssetInput`). A deep single-vendor integration surface.

### @isis/video-enhancement

AI video enhancement/restoration (`libs/isis/video-enhancement`, ~19k LOC): a
capabilities manifest plus planners for super-resolution, frame interpolation,
denoising, grain management, and cadence correction/deinterlacing
(`CadenceCorrectionPlanner`, with pull-down patterns and field-dominance modes).

### @isis/video-edit-studio

Production video-editing orchestration for ISIS and Yemaya
(`libs/isis/video-edit-studio`, a single ~970-line module): inpaint/outpaint/
restyle/extend/reference-to-video tasks with masks, reference kinds, aspect
ratios, comparison modes, and versioning (`VideoEditTaskMode`,
`VideoEditVersionStatus`).

### @isis/video-object-removal

Production object-removal orchestration for ISIS and Yemaya
(`libs/isis/video-object-removal`, a single ~3.2k-line module): selection tools
(point/box/lasso/text-prompt), quality tiers, comparison modes, cross-shot
subject tracking, and a set of domain pipelines (product-placement,
safety-wire-rig, anachronism-removal, weather-element, …) with NLE-host targets.

### @isis/motion-camera-control

Interactive motion and camera-control orchestration for ISIS and Yemaya
(`libs/isis/motion-camera-control`, a single ~835-line module):
camera-trajectory presets (orbit/dolly/crane/…), easing curves, and motion
validation that flags teleportation, interpenetration, impossible acceleration,
and gravity violations (`MotionValidationIssueKind`).

### @isis/relight-studio

Generative relighting workflow orchestration for ISIS and Yemaya
(`libs/isis/relight-studio`, a single ~2.4k-line module): light types/falloff,
preview engines (`ic-light`/`genlit`/`lightlab`), lighting presets
(golden-hour/rembrandt/butterfly/…), comparison modes, batch scopes, and
NLE/comp export hosts.

### @isis/av-narrative-studio

Joint audio-video narrative production for ISIS and Yemaya
(`libs/isis/av-narrative-studio`, a single ~2.2k-line module): AV stems
(dialogue/music/effects/ambient) sourced from Seedance joint-AV or editor
generation, narrative shot/transition types, narrative templates, and ProRes/
DNxHR + broadcast-WAV export. Orchestrates synchronized AV storytelling.

### @isis/post-production-ai

Per-production post-production intelligence (`libs/isis/post-production-ai`,
~31k LOC): a library manifest of analysis capabilities, a dailies-ingestion
pipeline with staged timing and a media-probe seam (`DailiesIngestionPipeline`,
`NoopDailiesMediaProbe` as the fail-safe default), and per-production model
training/orchestration for AI-assisted finishing.

### @isis/lora-training-surface

The LoRA training surface (`§24.5`, `libs/isis/lora-training-surface`, ~720
LOC): `training-run`, `model-merging`, `quality-view`, and `lineage-tree`
modules — the training queue, model merging, tuning rehearsal, quality scoring,
and lineage tracking for creator-trained LoRAs.

### @isis/face-synthesis

AI face synthesis, de-aging, and identity-transfer orchestration
(`libs/isis/face-synthesis`): notably an ethical-safeguards planner with consent
records, watermark modes, safeguard alerts/decisions, usage contexts, and audit
event plans (`FaceSynthesisEthicalSafeguardsPlanner`). Consent/safeguard-first
by construction.

### @isis/portrait-studio

Virtual-presenter and performance orchestration for ISIS and Yemaya
(`libs/isis/portrait-studio`, a single ~1.2k-line module): inference providers
(Hallo3/LivePortrait/MuseTalk/RAP), voice providers, presenter emotion/camera
angles, lip-sync quality gates (`syncnet`/`face-embedding`), and multi-language
dubbing types.

### @isis/visual-dubbing

Visual dubbing and dialogue-editing orchestration (`libs/isis/visual-dubbing`,
~7k LOC): a voice-cloning visual-synchronization planner and an
emotional-regrade planner with strategies/review-modes/quality-gates
(`VoiceCloningVisualSynchronizationPlanner`, `EmotionalRegradePlanner`). Aligns
re-voiced dialogue to on-screen performance.

### @isis/training-data

Phase 85–86 flywheel producer for generative media
(`libs/isis/training-data/src`): `IsisTrainingDataPipeline` covers the widest
signal surface of the flywheel — sixteen `IsisTrainingKind`s from
`prompt-quality`, `generation-preference`, and `lora-effectiveness` to
`three-d-quality`, `gaussian-splat-quality`, `vfx-pair`, and
`llm-orchestration`. Every record is gated by an explicit `IsisRightsGrant`
(rights-based rather than plain consent, reflecting creator content) before it
reaches the `IsisTrainingSink`.