data-annotations 2.2.0__tar.gz → 2.4.0__tar.gz

{data_annotations-2.2.0 → data_annotations-2.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: data-annotations
-Version: 2.2.0
+Version: 2.4.0
 Summary: Annotate generated data artifacts
 Keywords: annotations,data,metadata,provenance,reproducibility
 Author: Rodrigo C.  G.  Pena
@@ -18,6 +18,7 @@ Classifier: Programming Language :: Python :: 3.14
 Classifier: Topic :: Scientific/Engineering
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Requires-Dist: pydantic>=2.13.1
+Requires-Dist: pyyaml>=6.0.2 ; extra == 'cli'
 Requires-Dist: questionary>=2.1.1 ; extra == 'cli'
 Requires-Dist: typer>=0.16.0 ; extra == 'cli'
 Requires-Python: >=3.12
@@ -102,6 +103,9 @@ Every annotation document includes provenance with:
 - Git commit, branch, dirty state, canonical repository remote, exact tags, and
   `git describe` output when available
 - The current `SLURM_JOB_ID` when available
+- Structured snapshots for recorded local inputs, including file checksums,
+  directory content digests, and upstream annotation sidecar references when
+  present
 
 You can also attach your own parameters, input file paths, and function names.
 Local filesystem paths in provenance are stored as absolute paths. URI-style inputs
@@ -380,6 +384,7 @@ File annotations store:
 - `subject.kind`
 - `subject.sha256`
 - `provenance.*`
+- `provenance.input_artifacts[]`
 - `description.title`
 - `description.summary`
 - `description.fields`
@@ -396,6 +401,7 @@ Directory annotations store:
 - `subject.child_bundles[]`
 - `subject.content_digest`
 - `provenance.*`
+- `provenance.input_artifacts[]`
 - `description.title`
 - `description.summary`
 - `description.artifact_groups[]`
@@ -529,13 +535,16 @@ per call.
 ## Recovery Helpers
 
 Use `artifact_matches_manifest(...)` to verify whether a detached artifact still
-matches an annotation document, and `checkout_manifest_source(...)` to recover the
-recorded code state from Git metadata.
+matches an annotation document. Use `analyze_provenance_chain(...)` when you also
+want to verify recorded inputs and recursively follow upstream annotation
+sidecars. Use `checkout_manifest_source(...)` to recover the recorded code state
+from Git metadata.
 
 ```python
 from pathlib import Path
 
 from data_annotations.provenance import (
+    analyze_provenance_chain,
     artifact_matches_manifest,
     checkout_manifest_source,
 )
@@ -544,6 +553,8 @@ annotation_path = Path("outputs/participants.csv.annotation.json")
 artifact_path = Path("downloads/participants.csv")
 
 if artifact_matches_manifest(artifact_path, annotation_path):
+    chain = analyze_provenance_chain(artifact_path)
+    print(chain.status)
     recovered = checkout_manifest_source(annotation_path)
     print(recovered.checkout_path)
     print(recovered.script_path)
@@ -589,6 +600,91 @@ These commands prompt for missing details, write `*.annotation.json` or `data-an
 and optionally derive README sidecars. Post-hoc records are marked with
 `capture_mode="post_hoc"`.
 
+For shell workflows, you can move the prompt answers into a YAML file and run
+the command non-interactively:
+
+```bash
+data-annotations annotate file path/to/participants.csv --answers participants.yaml
+data-annotations annotate directory path/to/run-001 --answers run-001.yaml
+data-annotations annotate answers check participants.yaml
+```
+
+When `--answers` is provided, `--no-interactive` is the default. Use
+`--interactive` if you want the YAML file to provide defaults and still prompt
+for missing required values. If the YAML file includes `target`, the positional
+target may be omitted; when both are provided, they must resolve to the same
+path. Environment variables such as `$DATA_ROOT` and `${DATA_ROOT}` are expanded
+inside string values, and validation fails if a referenced variable is not set.
+The `answers check` helper requires `target` so it can infer whether the answers
+describe a file or a directory.
+
+File answers can use top-level prompt-style keys:
+
+```yaml
+target: path/to/participants.csv
+title: Participant Cohort
+summary: Participant-level cohort assignments.
+kind: dataset
+
+inputs:
+  - ${DATA_ROOT}/raw/participants.csv
+
+params:
+  split: validation
+
+provenance:
+  command: bash scripts/build_participants.sh
+  script: scripts/build_participants.sh
+  git_sha: deadbeef
+
+fields:
+  - name: participant_id
+    summary: Stable participant identifier.
+    data_type: string
+    required: true
+    nullable: false
+
+primary_key:
+  - participant_id
+```
+
+Directory answers use an explicit inventory. Paths in `artifacts`,
+`artifact_groups.paths`, and `child_bundles` are relative to the annotated
+directory unless absolute:
+
+```yaml
+target: path/to/run-001
+title: Processing outputs
+summary: Files produced by the shell processing workflow.
+
+provenance:
+  command: bash process_from_instrument.sh
+  script: process_from_instrument.sh
+
+artifacts:
+  - path: processed.csv
+    kind: dataset
+    title: Processed instrument output
+    summary: Normalized output from the processing script.
+
+artifact_groups:
+  - title: Diagnostic plots
+    kind: plot
+    selector: plots/*.png
+    paths:
+      - plots/qc-1.png
+      - plots/qc-2.png
+
+child_bundles:
+  - path: model
+    annotation_path: model/data-annotations.json
+```
+
+Answers files may also use schema-style aliases such as `subject.path`,
+`subject.kind`, `description.title`, `description.summary`,
+`description.artifacts`, `description.artifact_groups`, `provenance.inputs`,
+and `provenance.params`.
+
 When group selectors are provided, the CLI expands them to concrete member paths
 at annotation time. Grouped files are tracked in `subject.produced_files[]` but
 are skipped by the per-file prompt flow, so you do not have to answer the same
@@ -602,12 +698,49 @@ For provenance inspection and source recovery:
 
 ```bash
 data-annotations provenance match path/to/artifact
+data-annotations provenance chain path/to/artifact
+data-annotations provenance chain path/to/artifact --full-paths
 data-annotations provenance checkout path/to/artifact
 ```
 
+Command `checkout` downloads the recorded Git remote and checks out the recorded
+commit. It prompts before downloading source code and defaults to No; use
+`--force` when running trusted provenance checkout non-interactively.
+
 Command `match` auto-discovers `*.annotation.json` for files and `data-annotations.json` for
 directories, prints a verification summary, and suggests the exact `checkout`
 command to run next when Git recovery metadata is available.
+Command `chain` uses the same sidecar discovery, then verifies the artifact,
+recorded input snapshots, and any upstream annotation sidecars reachable from
+those inputs. Its default output shows a compact relative-path tree and lists
+stale, missing, or unverifiable nodes first; use `--full-paths` when you need
+absolute paths.
+
+For publication workflows, create a sanitized copy of an annotated artifact tree:
+
+```bash
+data-annotations publish path/to/run-001 path/to/publish-bundle
+data-annotations publish path/to/run-001 path/to/publish-bundle \
+  --prefix /private/raw/study-a='$INPUT_ROOT'
+data-annotations publish path/to/run-001 path/to/publish-metadata \
+  --annotations-only
+data-annotations publish path/to/run-001 path/to/publish-bundle --dry-run
+```
+
+Command `publish` recursively discovers file annotations (`*.annotation.json`) and
+directory annotations (`data-annotations.json`), writes a mirrored publish bundle,
+and regenerates README sidecars from sanitized annotation JSON. Paths under the
+source directory are rewritten to `$ARTIFACT_ROOT/...`; additional `--prefix`
+mappings rewrite other private path roots. Hostname, username, and SLURM job ID
+are redacted by default. Git remote URLs are preserved unless
+`--redact-git-remote` is provided. Strict mode is enabled by default and fails if
+any local absolute path remains after sanitization; use `--no-strict` only after
+reviewing `--dry-run` output.
+
+If `data-annotations provenance --help` does not list `chain`, your shell is
+resolving an older installed command. From a source checkout, use
+`uv run data-annotations provenance chain ...`, or reinstall the CLI from the
+updated source before using the bare `data-annotations` command.
 
 ### Run With `uvx`
 
@@ -632,7 +765,9 @@ the project environment. You can then run:
 uv run data-annotations annotate file path/to/participants.csv
 uv run data-annotations annotate directory path/to/run-001
 uv run data-annotations provenance match path/to/participants.csv
+uv run data-annotations provenance chain path/to/participants.csv
 uv run data-annotations provenance checkout path/to/participants.csv
+uv run data-annotations publish path/to/run-001 path/to/publish-bundle
 ```
 
 ## API Overview
@@ -684,9 +819,12 @@ uv run data-annotations provenance checkout path/to/participants.csv
 
 - `ProducedFile`
 - `ChildBundle`
+- `InputArtifact`
 - `BaseProvenance`
 - `FileManifest`
 - `DirectoryManifest`
+- `ProvenanceChainNode`
+- `ProvenanceChainReport`
 - `RecoveredSource`
 
 ### Provenance Functions
@@ -696,9 +834,18 @@ uv run data-annotations provenance checkout path/to/participants.csv
 - `write_file_manifest(...)`
 - `write_directory_manifest(...)`
 - `directory_content_digest(...)`
+- `analyze_provenance_chain(...)`
+- `provenance_chain_is_fresh(...)`
 - `artifact_matches_manifest(...)`
 - `checkout_manifest_source(...)`
 
+### Publish Functions
+
+- `discover_annotation_paths(...)`
+- `sanitize_annotation_document(...)`
+- `sanitize_annotation_path(...)`
+- `publish_directory(...)`
+
 ## Examples
 
 Runnable examples live in `examples/` and mirror the README workflows.
@@ -713,12 +860,16 @@ uv run python examples/record_file_description.py
 uv run python examples/record_directory_description.py
 uv run python examples/annotate_file.py
 uv run python examples/annotate_directory.py
+uv run python examples/annotate_file_answers_cli.py
 uv run python examples/write_file_manifest.py
 uv run python examples/write_directory_manifest.py
 uv run python examples/write_file_description.py
 uv run python examples/write_directory_description.py
+uv run python examples/provenance_chain.py
+uv run python examples/provenance_chain_cli.py
 uv run python examples/recover_provenance.py
 uv run python examples/recover_provenance_cli.py
+uv run python examples/publish_cli.py
 ```
 
 Each example writes its outputs to a fresh temporary directory and prints the

{data_annotations-2.2.0 → data_annotations-2.4.0}/README.md

@@ -73,6 +73,9 @@ Every annotation document includes provenance with:
 - Git commit, branch, dirty state, canonical repository remote, exact tags, and
   `git describe` output when available
 - The current `SLURM_JOB_ID` when available
+- Structured snapshots for recorded local inputs, including file checksums,
+  directory content digests, and upstream annotation sidecar references when
+  present
 
 You can also attach your own parameters, input file paths, and function names.
 Local filesystem paths in provenance are stored as absolute paths. URI-style inputs
@@ -351,6 +354,7 @@ File annotations store:
 - `subject.kind`
 - `subject.sha256`
 - `provenance.*`
+- `provenance.input_artifacts[]`
 - `description.title`
 - `description.summary`
 - `description.fields`
@@ -367,6 +371,7 @@ Directory annotations store:
 - `subject.child_bundles[]`
 - `subject.content_digest`
 - `provenance.*`
+- `provenance.input_artifacts[]`
 - `description.title`
 - `description.summary`
 - `description.artifact_groups[]`
@@ -500,13 +505,16 @@ per call.
 ## Recovery Helpers
 
 Use `artifact_matches_manifest(...)` to verify whether a detached artifact still
-matches an annotation document, and `checkout_manifest_source(...)` to recover the
-recorded code state from Git metadata.
+matches an annotation document. Use `analyze_provenance_chain(...)` when you also
+want to verify recorded inputs and recursively follow upstream annotation
+sidecars. Use `checkout_manifest_source(...)` to recover the recorded code state
+from Git metadata.
 
 ```python
 from pathlib import Path
 
 from data_annotations.provenance import (
+    analyze_provenance_chain,
     artifact_matches_manifest,
     checkout_manifest_source,
 )
@@ -515,6 +523,8 @@ annotation_path = Path("outputs/participants.csv.annotation.json")
 artifact_path = Path("downloads/participants.csv")
 
 if artifact_matches_manifest(artifact_path, annotation_path):
+    chain = analyze_provenance_chain(artifact_path)
+    print(chain.status)
     recovered = checkout_manifest_source(annotation_path)
     print(recovered.checkout_path)
     print(recovered.script_path)
@@ -560,6 +570,91 @@ These commands prompt for missing details, write `*.annotation.json` or `data-an
 and optionally derive README sidecars. Post-hoc records are marked with
 `capture_mode="post_hoc"`.
 
+For shell workflows, you can move the prompt answers into a YAML file and run
+the command non-interactively:
+
+```bash
+data-annotations annotate file path/to/participants.csv --answers participants.yaml
+data-annotations annotate directory path/to/run-001 --answers run-001.yaml
+data-annotations annotate answers check participants.yaml
+```
+
+When `--answers` is provided, `--no-interactive` is the default. Use
+`--interactive` if you want the YAML file to provide defaults and still prompt
+for missing required values. If the YAML file includes `target`, the positional
+target may be omitted; when both are provided, they must resolve to the same
+path. Environment variables such as `$DATA_ROOT` and `${DATA_ROOT}` are expanded
+inside string values, and validation fails if a referenced variable is not set.
+The `answers check` helper requires `target` so it can infer whether the answers
+describe a file or a directory.
+
+File answers can use top-level prompt-style keys:
+
+```yaml
+target: path/to/participants.csv
+title: Participant Cohort
+summary: Participant-level cohort assignments.
+kind: dataset
+
+inputs:
+  - ${DATA_ROOT}/raw/participants.csv
+
+params:
+  split: validation
+
+provenance:
+  command: bash scripts/build_participants.sh
+  script: scripts/build_participants.sh
+  git_sha: deadbeef
+
+fields:
+  - name: participant_id
+    summary: Stable participant identifier.
+    data_type: string
+    required: true
+    nullable: false
+
+primary_key:
+  - participant_id
+```
+
+Directory answers use an explicit inventory. Paths in `artifacts`,
+`artifact_groups.paths`, and `child_bundles` are relative to the annotated
+directory unless absolute:
+
+```yaml
+target: path/to/run-001
+title: Processing outputs
+summary: Files produced by the shell processing workflow.
+
+provenance:
+  command: bash process_from_instrument.sh
+  script: process_from_instrument.sh
+
+artifacts:
+  - path: processed.csv
+    kind: dataset
+    title: Processed instrument output
+    summary: Normalized output from the processing script.
+
+artifact_groups:
+  - title: Diagnostic plots
+    kind: plot
+    selector: plots/*.png
+    paths:
+      - plots/qc-1.png
+      - plots/qc-2.png
+
+child_bundles:
+  - path: model
+    annotation_path: model/data-annotations.json
+```
+
+Answers files may also use schema-style aliases such as `subject.path`,
+`subject.kind`, `description.title`, `description.summary`,
+`description.artifacts`, `description.artifact_groups`, `provenance.inputs`,
+and `provenance.params`.
+
 When group selectors are provided, the CLI expands them to concrete member paths
 at annotation time. Grouped files are tracked in `subject.produced_files[]` but
 are skipped by the per-file prompt flow, so you do not have to answer the same
@@ -573,12 +668,49 @@ For provenance inspection and source recovery:
 
 ```bash
 data-annotations provenance match path/to/artifact
+data-annotations provenance chain path/to/artifact
+data-annotations provenance chain path/to/artifact --full-paths
 data-annotations provenance checkout path/to/artifact
 ```
 
+Command `checkout` downloads the recorded Git remote and checks out the recorded
+commit. It prompts before downloading source code and defaults to No; use
+`--force` when running trusted provenance checkout non-interactively.
+
 Command `match` auto-discovers `*.annotation.json` for files and `data-annotations.json` for
 directories, prints a verification summary, and suggests the exact `checkout`
 command to run next when Git recovery metadata is available.
+Command `chain` uses the same sidecar discovery, then verifies the artifact,
+recorded input snapshots, and any upstream annotation sidecars reachable from
+those inputs. Its default output shows a compact relative-path tree and lists
+stale, missing, or unverifiable nodes first; use `--full-paths` when you need
+absolute paths.
+
+For publication workflows, create a sanitized copy of an annotated artifact tree:
+
+```bash
+data-annotations publish path/to/run-001 path/to/publish-bundle
+data-annotations publish path/to/run-001 path/to/publish-bundle \
+  --prefix /private/raw/study-a='$INPUT_ROOT'
+data-annotations publish path/to/run-001 path/to/publish-metadata \
+  --annotations-only
+data-annotations publish path/to/run-001 path/to/publish-bundle --dry-run
+```
+
+Command `publish` recursively discovers file annotations (`*.annotation.json`) and
+directory annotations (`data-annotations.json`), writes a mirrored publish bundle,
+and regenerates README sidecars from sanitized annotation JSON. Paths under the
+source directory are rewritten to `$ARTIFACT_ROOT/...`; additional `--prefix`
+mappings rewrite other private path roots. Hostname, username, and SLURM job ID
+are redacted by default. Git remote URLs are preserved unless
+`--redact-git-remote` is provided. Strict mode is enabled by default and fails if
+any local absolute path remains after sanitization; use `--no-strict` only after
+reviewing `--dry-run` output.
+
+If `data-annotations provenance --help` does not list `chain`, your shell is
+resolving an older installed command. From a source checkout, use
+`uv run data-annotations provenance chain ...`, or reinstall the CLI from the
+updated source before using the bare `data-annotations` command.
 
 ### Run With `uvx`
 
@@ -603,7 +735,9 @@ the project environment. You can then run:
 uv run data-annotations annotate file path/to/participants.csv
 uv run data-annotations annotate directory path/to/run-001
 uv run data-annotations provenance match path/to/participants.csv
+uv run data-annotations provenance chain path/to/participants.csv
 uv run data-annotations provenance checkout path/to/participants.csv
+uv run data-annotations publish path/to/run-001 path/to/publish-bundle
 ```
 
 ## API Overview
@@ -655,9 +789,12 @@ uv run data-annotations provenance checkout path/to/participants.csv
 
 - `ProducedFile`
 - `ChildBundle`
+- `InputArtifact`
 - `BaseProvenance`
 - `FileManifest`
 - `DirectoryManifest`
+- `ProvenanceChainNode`
+- `ProvenanceChainReport`
 - `RecoveredSource`
 
 ### Provenance Functions
@@ -667,9 +804,18 @@ uv run data-annotations provenance checkout path/to/participants.csv
 - `write_file_manifest(...)`
 - `write_directory_manifest(...)`
 - `directory_content_digest(...)`
+- `analyze_provenance_chain(...)`
+- `provenance_chain_is_fresh(...)`
 - `artifact_matches_manifest(...)`
 - `checkout_manifest_source(...)`
 
+### Publish Functions
+
+- `discover_annotation_paths(...)`
+- `sanitize_annotation_document(...)`
+- `sanitize_annotation_path(...)`
+- `publish_directory(...)`
+
 ## Examples
 
 Runnable examples live in `examples/` and mirror the README workflows.
@@ -684,12 +830,16 @@ uv run python examples/record_file_description.py
 uv run python examples/record_directory_description.py
 uv run python examples/annotate_file.py
 uv run python examples/annotate_directory.py
+uv run python examples/annotate_file_answers_cli.py
 uv run python examples/write_file_manifest.py
 uv run python examples/write_directory_manifest.py
 uv run python examples/write_file_description.py
 uv run python examples/write_directory_description.py
+uv run python examples/provenance_chain.py
+uv run python examples/provenance_chain_cli.py
 uv run python examples/recover_provenance.py
 uv run python examples/recover_provenance_cli.py
+uv run python examples/publish_cli.py
 ```
 
 Each example writes its outputs to a fresh temporary directory and prints the

{data_annotations-2.2.0 → data_annotations-2.4.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "data-annotations"
-version = "2.2.0"
+version = "2.4.0"
 description = "Annotate generated data artifacts"
 readme = "README.md"
 authors = [
@@ -30,7 +30,7 @@ Changelog = "https://gitlab.com/ceda-unibas/tools/data-annotations/-/blob/main/C
 Issues = "https://gitlab.com/ceda-unibas/tools/data-annotations/-/issues"
 
 [project.optional-dependencies]
-cli = ["questionary>=2.1.1", "typer>=0.16.0"]
+cli = ["PyYAML>=6.0.2", "questionary>=2.1.1", "typer>=0.16.0"]
 
 [project.scripts]
 data-annotations = "data_annotations.cli:main"

{data_annotations-2.2.0 → data_annotations-2.4.0}/src/data_annotations/annotations/models.py

@@ -22,14 +22,14 @@ class DirectoryArtifactSubject(BaseModel):
 
 
 class FileAnnotationDocument(BaseModel):
-    annotation_version: Literal["4"] = "4"
+    annotation_version: Literal["5"] = "5"
     subject: FileArtifactSubject
     provenance: BaseProvenance
     description: FileDescription
 
 
 class DirectoryAnnotationDocument(BaseModel):
-    annotation_version: Literal["4"] = "4"
+    annotation_version: Literal["5"] = "5"
     subject: DirectoryArtifactSubject
     provenance: BaseProvenance
     description: DirectoryDescription

{data_annotations-2.2.0 → data_annotations-2.4.0}/src/data_annotations/annotations/writers.py

@@ -1,3 +1,4 @@
+from collections.abc import Sequence
 from pathlib import Path
 from typing import Any, Callable
 
@@ -154,7 +155,7 @@ def _build_file_annotation_document(
     generation_context: dict[str, Any] | None = None,
     artifact_kind: ArtifactKind = "other",
     params: dict[str, Any] | None = None,
-    inputs: list[str] | None = None,
+    inputs: Sequence[str | Path] | None = None,
     function: Callable[..., Any] | None = None,
     capture_mode: str = "runtime",
     provenance_overrides: dict[str, Any] | None = None,
@@ -205,7 +206,7 @@ def _build_directory_annotation_document(
     acquisition_context: dict[str, Any] | None = None,
     generation_context: dict[str, Any] | None = None,
     params: dict[str, Any] | None = None,
-    inputs: list[str] | None = None,
+    inputs: Sequence[str | Path] | None = None,
     function: Callable[..., Any] | None = None,
     capture_mode: str = "runtime",
     provenance_overrides: dict[str, Any] | None = None,
@@ -285,7 +286,7 @@ def write_file_annotation(
     generation_context: dict[str, Any] | None = None,
     artifact_kind: ArtifactKind = "other",
     params: dict[str, Any] | None = None,
-    inputs: list[str] | None = None,
+    inputs: Sequence[str | Path] | None = None,
     function: Callable[..., Any] | None = None,
     capture_mode: str = "runtime",
     provenance_overrides: dict[str, Any] | None = None,
@@ -324,7 +325,7 @@ def write_directory_annotation(
     acquisition_context: dict[str, Any] | None = None,
     generation_context: dict[str, Any] | None = None,
     params: dict[str, Any] | None = None,
-    inputs: list[str] | None = None,
+    inputs: Sequence[str | Path] | None = None,
     function: Callable[..., Any] | None = None,
     capture_mode: str = "runtime",
     provenance_overrides: dict[str, Any] | None = None,
@@ -363,7 +364,7 @@ def annotate_file(
     generation_context: dict[str, Any] | None = None,
     artifact_kind: ArtifactKind = "other",
     params: dict[str, Any] | None = None,
-    inputs: list[str] | None = None,
+    inputs: Sequence[str | Path] | None = None,
     function: Callable[..., Any] | None = None,
     write_readme: bool = True,
     write_schema: bool | None = None,
@@ -418,7 +419,7 @@ def annotate_directory(
     acquisition_context: dict[str, Any] | None = None,
     generation_context: dict[str, Any] | None = None,
     params: dict[str, Any] | None = None,
-    inputs: list[str] | None = None,
+    inputs: Sequence[str | Path] | None = None,
     function: Callable[..., Any] | None = None,
     write_readme: bool = True,
     write_schema: bool | None = None,

{data_annotations-2.2.0 → data_annotations-2.4.0}/src/data_annotations/cli.py

@@ -1,7 +1,7 @@
 from typing import Any
 
 _CLI_IMPORT_ERROR: ModuleNotFoundError | None = None
-_CLI_OPTIONAL_DEPENDENCIES = {"questionary", "typer"}
+_CLI_OPTIONAL_DEPENDENCIES = {"questionary", "typer", "yaml"}
 app: Any = None
 
 try:
@@ -9,6 +9,7 @@ try:
 
     from data_annotations.cli_app.annotate import annotate_app
     from data_annotations.cli_app.provenance_commands import provenance_app
+    from data_annotations.cli_app.publish import publish_command
 except ModuleNotFoundError as exc:
     if exc.name not in _CLI_OPTIONAL_DEPENDENCIES:
         raise
@@ -17,6 +18,7 @@ else:
     app = typer.Typer(no_args_is_help=True)
     app.add_typer(annotate_app, name="annotate")
     app.add_typer(provenance_app, name="provenance")
+    app.command("publish")(publish_command)
 
 
 def main() -> None: