genblaze-cli 0.3.0__tar.gz → 0.3.4__tar.gz

{genblaze_cli-0.3.0 → genblaze_cli-0.3.4}/.gitignore

@@ -54,7 +54,12 @@ ehthumbs.db
 !.env.example
 *.pem
 *.key
-credentials.json
+credentials*
+*.credentials
+*_rsa
+*.p12
+*.pfx
+*.keystore
 
 # Jupyter
 .ipynb_checkpoints/

{genblaze_cli-0.3.0 → genblaze_cli-0.3.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: genblaze-cli
-Version: 0.3.0
+Version: 0.3.4
 Summary: CLI for genblaze manifest operations
 Project-URL: Homepage, https://github.com/backblaze-labs/genblaze
 Project-URL: Documentation, https://github.com/backblaze-labs/genblaze#readme
@@ -20,7 +20,7 @@ Classifier: Topic :: Multimedia
 Classifier: Topic :: Software Development :: Libraries
 Requires-Python: >=3.11
 Requires-Dist: click>=8.0
-Requires-Dist: genblaze-core<0.4,>=0.2.0
+Requires-Dist: genblaze-core<0.4,>=0.3.6
 Provides-Extra: dev
 Requires-Dist: pillow>=10.0; extra == 'dev'
 Requires-Dist: pytest>=7.0; extra == 'dev'
@@ -31,11 +31,11 @@ Description-Content-Type: text/markdown
 
 **Command-line toolkit for inspecting, verifying, and indexing genblaze AI-generated-media provenance manifests.**
 
-`genblaze-cli` is the companion CLI for [genblaze](https://github.com/backblaze-labs/genblaze) — the Python SDK for generative AI pipelines across video, image, and audio. It lets anyone (not just Python developers) audit AI-generated media: extract the embedded provenance manifest from an MP4 / PNG / MP3, verify its SHA-256 hash, replay a run, or index manifests into Parquet for downstream analytics.
+`genblaze-cli` is the companion CLI for [genblaze](https://github.com/backblaze-labs/genblaze) — the Python SDK for generative AI pipelines across video, image, and audio. It lets anyone (not just Python developers) audit AI-generated media: extract the embedded provenance manifest from an MP4 / PNG / MP3, verify its manifest hash and output sha256 coverage, replay a run, or index manifests into Parquet for downstream analytics.
 
 ## Why genblaze-cli
 
-- **Audit AI-generated media in one command** — `genblaze verify video.mp4` confirms a file's manifest hash hasn't been tampered with.
+- **Audit AI-generated media in one command** — `genblaze verify video.mp4` confirms a file's manifest hash hasn't been tampered with and all output assets declare sha256.
 - **Works on any genblaze output** — PNG, JPEG, WebP, MP4, MP3, WAV with embedded manifests.
 - **Analytics-ready** — `genblaze index` emits partitioned Parquet tables (runs, steps, assets) for BI tools and data warehouses.
 - **Zero provider dependencies** — reads manifests; doesn't call any AI API.
@@ -57,7 +57,7 @@ genblaze --help
 genblaze extract video.mp4                # Extract embedded manifest → stdout (JSON)
 genblaze extract video.mp4 -o m.json      # …or to a file
 
-genblaze verify video.mp4                 # Verify the embedded manifest's SHA-256
+genblaze verify video.mp4                 # Verify manifest hash + output sha256 declarations
 genblaze verify manifest.json             # Or verify a standalone manifest file
 
 genblaze replay manifest.json             # Show what a replay would do (dry run)
@@ -65,7 +65,7 @@ genblaze replay manifest.json             # Show what a replay would do (dry run
 genblaze index manifest.json -o data/     # Index into partitioned Parquet tables
 ```
 
-Exit codes are non-zero on verification failure — safe to drop into CI pipelines, release checks, or content-moderation workflows.
+Exit codes are non-zero on verification failure — safe to drop into CI pipelines, release checks, or content-moderation workflows. The command does not fetch remote asset URLs; consumers that dereference `asset.url` must hash those bytes separately and compare them with the manifest's `asset.sha256`.
 
 ## Typical flow
 

{genblaze_cli-0.3.0 → genblaze_cli-0.3.4}/README.md

@@ -3,11 +3,11 @@
 
 **Command-line toolkit for inspecting, verifying, and indexing genblaze AI-generated-media provenance manifests.**
 
-`genblaze-cli` is the companion CLI for [genblaze](https://github.com/backblaze-labs/genblaze) — the Python SDK for generative AI pipelines across video, image, and audio. It lets anyone (not just Python developers) audit AI-generated media: extract the embedded provenance manifest from an MP4 / PNG / MP3, verify its SHA-256 hash, replay a run, or index manifests into Parquet for downstream analytics.
+`genblaze-cli` is the companion CLI for [genblaze](https://github.com/backblaze-labs/genblaze) — the Python SDK for generative AI pipelines across video, image, and audio. It lets anyone (not just Python developers) audit AI-generated media: extract the embedded provenance manifest from an MP4 / PNG / MP3, verify its manifest hash and output sha256 coverage, replay a run, or index manifests into Parquet for downstream analytics.
 
 ## Why genblaze-cli
 
-- **Audit AI-generated media in one command** — `genblaze verify video.mp4` confirms a file's manifest hash hasn't been tampered with.
+- **Audit AI-generated media in one command** — `genblaze verify video.mp4` confirms a file's manifest hash hasn't been tampered with and all output assets declare sha256.
 - **Works on any genblaze output** — PNG, JPEG, WebP, MP4, MP3, WAV with embedded manifests.
 - **Analytics-ready** — `genblaze index` emits partitioned Parquet tables (runs, steps, assets) for BI tools and data warehouses.
 - **Zero provider dependencies** — reads manifests; doesn't call any AI API.
@@ -29,7 +29,7 @@ genblaze --help
 genblaze extract video.mp4                # Extract embedded manifest → stdout (JSON)
 genblaze extract video.mp4 -o m.json      # …or to a file
 
-genblaze verify video.mp4                 # Verify the embedded manifest's SHA-256
+genblaze verify video.mp4                 # Verify manifest hash + output sha256 declarations
 genblaze verify manifest.json             # Or verify a standalone manifest file
 
 genblaze replay manifest.json             # Show what a replay would do (dry run)
@@ -37,7 +37,7 @@ genblaze replay manifest.json             # Show what a replay would do (dry run
 genblaze index manifest.json -o data/     # Index into partitioned Parquet tables
 ```
 
-Exit codes are non-zero on verification failure — safe to drop into CI pipelines, release checks, or content-moderation workflows.
+Exit codes are non-zero on verification failure — safe to drop into CI pipelines, release checks, or content-moderation workflows. The command does not fetch remote asset URLs; consumers that dereference `asset.url` must hash those bytes separately and compare them with the manifest's `asset.sha256`.
 
 ## Typical flow
 

genblaze_cli-0.3.4/genblaze_cli/commands/extract.py

@@ -0,0 +1,54 @@
+"""Extract command — print embedded manifest from a media file."""
+
+from pathlib import Path
+
+import click
+from genblaze_core.canonical.json import canonical_json
+from genblaze_core.exceptions import ManifestError
+from genblaze_core.models.manifest import Manifest
+
+from genblaze_cli.manifest_io import extract_manifest
+
+
+def _manifest_json_for_display(manifest: Manifest) -> str:
+    """Serialize for inspection without bypassing write-schema guards."""
+    try:
+        manifest.assert_writable_schema()
+    except ManifestError:
+        return canonical_json(manifest.model_dump(mode="python"))
+    return manifest.to_canonical_json()
+
+
+@click.command()
+@click.argument("file", type=click.Path(exists=True, dir_okay=False, path_type=Path))
+@click.option("--format", "fmt", type=click.Choice(["json", "summary"]), default="json")
+@click.option(
+    "-o",
+    "--output",
+    type=click.Path(path_type=Path),
+    default=None,
+    help="Write extracted manifest JSON to this file instead of stdout.",
+)
+def extract(file: Path, fmt: str, output: Path | None) -> None:
+    """Extract and display the genblaze manifest from a media file."""
+    try:
+        manifest = extract_manifest(file)
+        if fmt == "json":
+            json_str = _manifest_json_for_display(manifest)
+            if output is not None:
+                output.write_text(json_str, encoding="utf-8")
+            else:
+                click.echo(json_str)
+        else:
+            report = manifest.verification_report()
+            click.echo(f"Run ID:    {manifest.run.run_id}")
+            click.echo(f"Steps:     {len(manifest.run.steps)}")
+            click.echo(f"Hash:      {manifest.canonical_hash}")
+            click.echo(f"Hash OK:   {report.hash_ok}")
+            click.echo(f"Output sha256: {len(report.unverified_sha256_ids)} missing or malformed")
+            # Itemize metadata too, so a False `Verified:` line always has a
+            # visible reason (report.ok folds in invalid_metadata_ids, #149).
+            click.echo(f"Output metadata: {len(report.invalid_metadata_ids)} out of spec")
+            click.echo(f"Verified:  {report.ok} (asset bytes were not fetched or compared)")
+    except Exception as exc:
+        raise click.ClickException(f"{type(exc).__name__}: {exc}") from exc

{genblaze_cli-0.3.0 → genblaze_cli-0.3.4}/genblaze_cli/commands/index.py

@@ -7,7 +7,7 @@ import click
 
 
 @click.command()
-@click.argument("manifest_file", type=click.Path(exists=True, path_type=Path))
+@click.argument("manifest_file", type=click.Path(exists=True, dir_okay=False, path_type=Path))
 @click.option(
     "--output",
     "-o",
@@ -17,12 +17,12 @@ import click
 )
 def index(manifest_file: Path, output: Path) -> None:
     """Write manifest data to a Parquet sink for querying."""
-    from genblaze_core.models.manifest import Manifest
+    from genblaze_core.models.manifest import parse_manifest
     from genblaze_core.sinks.parquet import ParquetSink
 
     try:
         data = json.loads(manifest_file.read_text(encoding="utf-8"))
-        manifest = Manifest.model_validate(data)
+        manifest = parse_manifest(data)
     except Exception as exc:
         raise click.ClickException(f"Failed to load manifest: {exc}") from exc
 

{genblaze_cli-0.3.0 → genblaze_cli-0.3.4}/genblaze_cli/commands/replay.py

@@ -2,12 +2,16 @@
 
 import json
 from pathlib import Path
+from typing import TYPE_CHECKING
 
 import click
-from genblaze_core.models.enums import PromptVisibility
+from genblaze_core.models.enums import PromptVisibility, RunStatus
 
+if TYPE_CHECKING:
+    from genblaze_core.providers.base import BaseProvider
 
-def _load_provider(provider_name: str, allowed: tuple[str, ...] | None):
+
+def _load_provider(provider_name: str, allowed: tuple[str, ...] | None) -> "BaseProvider":
     """Load a provider by name using entry point discovery.
 
     If allowed is set, reject providers not in the allowlist.
@@ -77,7 +81,7 @@ _UNREPLAYABLE_FIELDS = [
 
 
 @click.command()
-@click.argument("manifest_file", type=click.Path(exists=True, path_type=Path))
+@click.argument("manifest_file", type=click.Path(exists=True, dir_okay=False, path_type=Path))
 @click.option("--dry-run/--no-dry-run", default=True, help="Preview without executing.")
 @click.option(
     "--allow-provider",
@@ -99,7 +103,6 @@ def replay(
 ) -> None:
     """Re-execute a pipeline from a manifest JSON file."""
     from genblaze_core.models.manifest import parse_manifest
-    from genblaze_core.pipeline import Pipeline
 
     try:
         data = json.loads(manifest_file.read_text(encoding="utf-8"))
@@ -107,14 +110,25 @@ def replay(
     except Exception as exc:
         raise click.ClickException(f"Failed to load manifest: {exc}") from exc
 
-    # Verify manifest hash integrity
-    if not force and not manifest.verify():
+    # Verify manifest hash integrity before replay. Output sha256 coverage is
+    # reported separately because URL-only outputs can be metadata-valid but
+    # not sha256-covered.
+    report = manifest.verification_report()
+    if not force and not report.hash_ok:
         click.echo(
             "WARNING: Manifest hash does not match content. The file may have been modified.",
             err=True,
         )
         if not click.confirm("Continue anyway?"):
             raise click.Abort()
+    elif not force:
+        if report.unverified_sha256_ids:
+            click.echo(
+                "WARNING: Manifest hash matches, but output asset bytes are not "
+                f"bound for {len(report.unverified_sha256_ids)} asset(s) "
+                "missing or malformed sha256.",
+                err=True,
+            )
 
     run = manifest.run
     _print_summary(run, show_prompts=show_prompts)
@@ -132,9 +146,13 @@ def replay(
 
     # Safety: when no allowlist is provided, confirm each unique provider.
     # A hostile manifest could reference any installed provider and execute
-    # paid API calls on the user's credentials without consent.
+    # paid API calls on the user's credentials without consent. Steps with no
+    # provider (INGEST/IMPORT, see the loop below) don't invoke one, so they're
+    # excluded here rather than flowing `None` into sorted() (issue #43).
     if allowed is None:
-        unique_providers = sorted({step.provider for step in run.steps})
+        unique_providers = sorted(
+            {step.provider for step in run.steps if step.provider is not None}
+        )
         click.echo(
             "No --allow-provider allowlist set. Confirm each provider before execution:",
             err=True,
@@ -153,7 +171,9 @@ def replay(
         click.echo("  Detected chain mode from manifest step inputs.", err=True)
 
     # Cache providers by name to avoid re-instantiating
-    providers: dict[str, object] = {}
+    from genblaze_core.pipeline import Pipeline
+
+    providers: dict[str, BaseProvider] = {}
     pipe = Pipeline(
         run.name,
         tenant_id=run.tenant_id,
@@ -165,6 +185,17 @@ def replay(
     _reserved = {"model", "prompt", "modality", "step_type", "seed", "negative_prompt"}
 
     for step_idx, step in enumerate(run.steps):
+        # A None provider (only valid for INGEST/IMPORT steps, see Step's
+        # own validator) has no upstream service to re-invoke here — replay
+        # only supports Pipeline.step()-shaped generative steps. Without this
+        # guard, None flowed into a dict[str, ...] key and _load_provider's
+        # str parameter, raising a confusing TypeError instead (issue #43).
+        if step.provider is None:
+            raise click.ClickException(
+                f"Step {step_idx + 1} (step_type={step.step_type}) has no provider; "
+                "replay does not support re-executing provider-less steps "
+                "(e.g. INGEST/IMPORT)."
+            )
         if step.provider not in providers:
             providers[step.provider] = _load_provider(step.provider, allowed)
 
@@ -202,10 +233,17 @@ def replay(
         )
 
     try:
-        result = pipe.run()
+        result = pipe.run(raise_on_failure=False)
         click.echo()
+        if result.run.status in {RunStatus.FAILED, RunStatus.CANCELLED}:
+            click.echo(f"Replay failed. New run ID: {result.run.run_id}", err=True)
+            click.echo(f"Hash: {result.manifest.canonical_hash}", err=True)
+            click.echo(f"Status: {result.run.status}", err=True)
+            raise click.exceptions.Exit(1)
         click.echo(f"Replay complete. New run ID: {result.run.run_id}")
         click.echo(f"Hash: {result.manifest.canonical_hash}")
         click.echo(f"Status: {result.run.status}")
+    except click.exceptions.Exit:
+        raise
     except Exception as exc:
         raise click.ClickException(f"Replay failed: {exc}") from exc

genblaze_cli-0.3.4/genblaze_cli/commands/verify.py

@@ -0,0 +1,56 @@
+"""Verify command — check manifest hash and output sha256 coverage."""
+
+from pathlib import Path
+
+import click
+
+from genblaze_cli.manifest_io import extract_manifest
+
+
+@click.command()
+@click.argument("file", type=click.Path(exists=True, dir_okay=False, path_type=Path))
+@click.option(
+    "--hash-only",
+    is_flag=True,
+    help="Only verify canonical_hash; skip output sha256 and asset-metadata checks.",
+)
+def verify(file: Path, hash_only: bool) -> None:
+    """Verify an embedded, sidecar, or standalone genblaze manifest."""
+    try:
+        manifest = extract_manifest(file)
+        report = manifest.verification_report()
+        if not report.hash_ok:
+            click.echo("FAIL: manifest hash mismatch.", err=True)
+            raise click.exceptions.Exit(1)
+        if hash_only:
+            click.echo("OK: manifest hash verified. Asset bytes were not fetched or compared.")
+            return
+        if report.unverified_sha256_ids:
+            click.echo(
+                f"FAIL: {len(report.unverified_sha256_ids)} output asset(s) "
+                "missing or malformed sha256.",
+                err=True,
+            )
+            raise click.exceptions.Exit(1)
+        # Out-of-spec numeric/media_type metadata (e.g. width=0) is tolerated on
+        # load by parse_manifest() but fails verify() (#149); surface it here so
+        # the CLI verdict matches Manifest.verify()/report.ok instead of a stale
+        # "OK" that only checked sha256.
+        if report.invalid_metadata_ids:
+            click.echo(
+                f"FAIL: {len(report.invalid_metadata_ids)} output asset(s) "
+                "carry out-of-spec numeric/media_type metadata "
+                "(e.g. width=0, or a malformed media_type).",
+                err=True,
+            )
+            raise click.exceptions.Exit(1)
+        click.echo(
+            "OK: manifest hash verified; all output assets declare sha256 and "
+            "carry in-spec metadata. Asset bytes were not fetched or compared."
+        )
+    except click.exceptions.Exit:
+        raise
+    except Exception as exc:
+        # Prefix with exception type so "PermissionError: ..." and
+        # "EmbeddingError: ..." are distinguishable at a glance.
+        raise click.ClickException(f"{type(exc).__name__}: {exc}") from exc

{genblaze_cli-0.3.0 → genblaze_cli-0.3.4}/genblaze_cli/main.py

@@ -9,7 +9,7 @@ from genblaze_cli.commands.verify import verify
 
 
 @click.group()
-@click.version_option(package_name="genblaze-cli")
+@click.version_option(package_name="genblaze-cli", prog_name="genblaze-cli")
 def cli() -> None:
     """genblaze — media generation manifest toolkit."""
 

genblaze_cli-0.3.4/genblaze_cli/manifest_io.py

@@ -0,0 +1,42 @@
+"""Shared CLI manifest loading helpers."""
+
+from __future__ import annotations
+
+import json
+from pathlib import Path
+
+from genblaze_core._utils import MAX_MANIFEST_BYTES
+from genblaze_core.exceptions import EmbeddingError
+from genblaze_core.media import get_handler, guess_mime
+from genblaze_core.media.sidecar import PointerSidecarError, SidecarHandler
+from genblaze_core.models.manifest import Manifest, parse_manifest
+
+
+def load_standalone_json_manifest(file: Path) -> Manifest:
+    size = file.stat().st_size
+    if size > MAX_MANIFEST_BYTES:
+        raise EmbeddingError(
+            f"Manifest JSON exceeds size limit: {size} > {MAX_MANIFEST_BYTES} bytes"
+        )
+    data = json.loads(file.read_text(encoding="utf-8"))
+    if "run" not in data and "manifest_uri" in data:
+        raise PointerSidecarError(
+            manifest_uri=data["manifest_uri"],
+            canonical_hash=data.get("canonical_hash", ""),
+        )
+    return parse_manifest(data)
+
+
+def extract_manifest(file: Path) -> Manifest:
+    """Extract a manifest from standalone JSON, media, or sidecar files."""
+    if file.suffix.lower() == ".json":
+        return load_standalone_json_manifest(file)
+
+    mime = guess_mime(file)
+    handler = get_handler(mime)
+    if handler is not None:
+        try:
+            return handler.extract(file)
+        except EmbeddingError:
+            pass
+    return SidecarHandler().extract(file)

{genblaze_cli-0.3.0 → genblaze_cli-0.3.4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "genblaze-cli"
-version = "0.3.0"
+version = "0.3.4"
 description = "CLI for genblaze manifest operations"
 authors = [{name = "Jeronimo De Leon", email = "jdeleon@backblaze.com"}]
 readme = "README.md"
@@ -23,7 +23,7 @@ classifiers = [
 keywords = ["genblaze", "ai", "media", "manifest", "provenance", "c2pa-ready", "genai", "pipeline", "cli", "command-line"]
 
 dependencies = [
-    "genblaze-core>=0.2.0,<0.4",
+    "genblaze-core>=0.3.6,<0.4",
     "click>=8.0",
 ]
 
@@ -48,3 +48,8 @@ packages = ["genblaze_cli"]
 
 [tool.pytest.ini_options]
 testpaths = ["tests"]
+
+[tool.deptry]
+# Treat the `dev` extra as dev-only tooling so deptry does not flag pytest
+# (and other test-only deps) as unused declared deps (DEP002).
+optional_dependencies_dev_groups = ["dev"]