DEEPBOM 1.103.0 Usage: deepbom audit [options] deepbom gguf [options] deepbom verify --contract [options] deepbom diff [options] deepbom explore [options] deepbom graph [options] deepbom visualize [options] deepbom accelerator collect nvidia [options] deepbom capabilities [--json|--compact] Supported inputs: Stable or existing: .tflite, .onnx, .gguf, .safetensors, .mlmodel, .pte, .ptd Preview static graph: GraphDef or saved_model.pb Preview safe envelope: .h5, .hdf5, .keras, .pt2, .pt, .pth, .ckpt Packages: .mlpackage directories and sharded SafeTensors repository directories Options: --target TFLite target profile (default: android_mid_a55) --target-profile Bind a strict custom TFLite target profile (mutually exclusive with --target) --contract Production external-interface contract for verify --request Bound redesign request for explore --external-data-dir Resolve ONNX external_data or ExecuTorch PTD sidecars from this directory --context Declared text-token scenario for a statically derived LLM KV contract --images Declared image count; requires --tokens-per-image --tokens-per-image Declared projector output tokens per image; never inferred --batch LLM scenario batch size (default: 1) --state-bits LLM state width: 8, 16, or 32 (default: 16) --memory-mib Compare the conditional lower bound with a declared capacity --tensorrt-profile Bind an ONNX TensorRT native/ORT EP build profile --tensorrt-parser-evidence Import identity-bound TensorRT parser/build evidence --tensorrt-llm-config Assess a TensorRT-LLM engine config with SafeTensors --tensorrt-llm-binding Bind that config to model-source/component digests --llm-memory-profile Evaluate serialized layer/state lower bounds against declared CPU and accelerator pools --output-format summary, json, json-compact, envelope, cyclonedx, or sarif --section Emit selected analysis sections; use --list-sections to discover names --pointer Emit one RFC 6901 JSON Pointer result with artifact identity --list-sections List selectable analysis sections for this artifact --gate defects Exit 2 only when an artifact_defect finding is present --timestamp Fixed generation timestamp; SOURCE_DATE_EPOCH is also honored --fail-on Compatibility severity gate: informational, low, medium, or high --policy-output Write the deterministic finding-gate decision JSON --output, -o Atomically write the complete document; use - for stdout --no-clobber Refuse to replace an existing output or policy file --error-format text or json structured stderr (default: text) --json Compatibility alias for --output-format json --compact Compatibility alias for --output-format json-compact --version Print version --help Show this help Safe-envelope boundary: Keras, HDF5, PT2, and PyTorch checkpoint previews do not construct framework objects or claim an executable graph. Exit codes: 0 pass; 1 invocation/input/analysis/output failure; 2 policy or verification block; 3 incomplete verification binding Additional command: deepbom model-summary [--level auto|operation|block|storage] [--format table|markdown|json|json-compact] SavedModel package preview: TensorFlow SavedModel directories are accepted with bounded member hashing and first-MetaGraph projection. GraphDef, Keras config, and PT2 JSON expose serialized declarative relationships only; HDF5 and PyTorch checkpoints remain safe-envelope-only. GGUF quick inspection: --tensors Emit a concise tensor table; add --json or --compact for deepbom.tensor_table.v1 Format-neutral tensor evidence: --encoding-inventory Emit serialized encoding counts, assignments, and reproducible hashes for GGUF, SafeTensors, ONNX, or TFLite Windows-safe batch audit: deepbom batch --batch-output-dir [--json|--compact] Manifest: deepbom.batch_manifest.v1 with safe relative paths and required SHA-256 identities Built-in gate profiles: --policy engineering Block artifact defects; keep cautions and evidence gaps visible --policy regulatory Block artifact defects and unresolved evidence gaps; this is not a legal-compliance determination Human-readable audit output: --output-format summary Emit the bounded projection derived from deepbom.review_summary.v1 --summary Compatibility alias for --output-format summary Installation and rule checks: deepbom self-test [--json|--compact] deepbom explain-rule [--json|--compact] deepbom explain-rule --list Agent-native local use (no hosted analysis server): deepbom capabilities --format agent-json deepbom integrate codex Preview .agents/skills/deepbom deepbom integrate claude-code Preview .claude/skills/deepbom deepbom integrate generic Preview skills/deepbom deepbom integrate --apply Write only managed Skill files deepbom integrate status [target] Inspect without changing files deepbom integrate remove Preview managed-file removal deepbom integrate remove --apply Remove only unchanged managed files Assistant tool access (Model Context Protocol over stdio, local process only): deepbom mcp Tools: deepbom_capabilities, deepbom_audit, deepbom_diff, deepbom_explain_rule Audit default: bounded human summary; request envelope, section, or pointer for detail Local paths: launch directory, or roots declared by DEEPBOM_MCP_ALLOWED_ROOTS NVIDIA accelerator binding: --accelerator-profile Bind an observed NVIDIA host profile without inferring selected-build or runtime assignment --accelerator-device Select one device when the bound profile contains multiple NVIDIA devices N-way placement comparison: deepbom placement [--profiles ] [--json|--compact] --profiles Compare selected independent profiles (default: all available profiles) Compiled accelerator evidence: --coreml-compute-plan Import an artifact- and compiled-model-bound MLComputePlan estimate; not executed placement --edgetpu-compiler-evidence Import an artifact/compiler/invocation/compiled-artifact-bound Edge TPU operation ledger --litert-qualcomm-evidence Import an artifact/source/compiler/QNN-plan-bound operation ledger Conversion provenance: --conversion-receipt Bind a self-hashed source/converter/environment receipt to the observed output artifact. Source .pt/.pth/.h5 files are identified by digest only and are never deserialized. NVIDIA accelerator observation: deepbom accelerator collect nvidia [--device ] [--json|--compact] --device Collect one NVIDIA device index (default: all devices) --include-device-identifiers Include raw GPU UUID and PCI bus ID; hashes are always emitted Remote immutable artifact input: hf://owner/repo@<40-hex-commit>/path gs://bucket/object#generation= https://host/path#sha256=<64-hex> --expected-sha256 Add an independent content digest requirement --cache-dir Use a content-addressed cache directory --offline Refuse network access and require a verified cache receipt --max-download-gib Bound one remote download (default: 50, maximum: 1024) Bounded scan policy: --scan auto, structure, integrity, or full GGUF/SafeTensors use range reads; auto selects structure above 10 GiB and streamed integrity above 2 GiB. Monolithic TFLite/ONNX/ExecuTorch files above 1 GiB fail before full-file allocation. Repeat-review policy: --review-policy Bind required analysis coverage, finding threshold, and identity-scoped expiring exceptions --policy-output Write the deterministic policy decision JSON --policy, --gate, --review-policy, and --fail-on are mutually exclusive policy sources. Output format selection: --output-format Preferred unambiguous spelling for --format --format Backward-compatible alias; retained for existing automation Deterministic graph export: deepbom graph --view structure --output-format svg -o graph.svg --view structure, placement, quantization, or architecture --output-format svg, png, html, mermaid, dot, or json for graph Regulatory-document model views: deepbom visualize --view all --orientation portrait -o model-views.zip --view all or comma-separated identity-boundary, architecture-overview, block-detail, exhaustive, static-runtime, observed-runtime --orientation portrait or landscape ISO A4 --output-format bundle (SVG, captions, manifest) or json manifest These monochrome, hash-bound engineering views do not assert regulatory approval or standard conformance. Format-neutral Keras-style model summary: deepbom model-summary --level auto --format table --level auto, operation, block, or storage --format table, markdown, json, or json-compact Rows are projections of deepbom.model_ir.v1; storage is not relabeled as trainable parameters and display order is not runtime order. TensorRT optimized-engine option: --tensorrt-engine-inspector Import identity-bound TensorRT optimized-engine inspector evidence ExecuTorch selected-build option: --executorch-build Bind backend/operator inventories and runtime binary digests to a PTE audit Artifact reconciliation and baseline capture: deepbom verify --bom [--component-ref ] deepbom contract capture [-o baseline.interface-contract.json] deepbom diff --tensors --render markdown Render audit, diff, or verify results as Markdown Agent capability summary: deepbom capabilities --format agent-text Additional exit code: 4 independently supplied artifact SHA-256 mismatch