infer-stack 0.6.0__tar.gz → 0.7.0__tar.gz

infer_stack-0.7.0/LICENSE

@@ -0,0 +1,13 @@
+Copyright 2026 Kitware Inc 
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+  http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.

{infer_stack-0.6.0/infer_stack.egg-info → infer_stack-0.7.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: infer-stack
-Version: 0.6.0
+Version: 0.7.0
 Summary: Profile-driven compose and KubeAI deployment compiler for inference stacks
 Author-email: "jon.crall" <jon.crall@kitware.com>
 License-Expression: Apache-2.0
@@ -12,11 +12,14 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
 Classifier: Programming Language :: Python :: 3.14
+Classifier: Programming Language :: Python :: 3.15
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Classifier: Topic :: Utilities
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
+License-File: LICENSE
 Requires-Dist: jinja2>=3.1
+Requires-Dist: loguru>=0.7
 Requires-Dist: pyyaml>=6.0
 Requires-Dist: requests>=2.31
 Requires-Dist: rich>=13.0
@@ -25,9 +28,37 @@ Requires-Dist: ubelt>=1.3
 Provides-Extra: tests
 Requires-Dist: pytest>=7.0; extra == "tests"
 Requires-Dist: pytest-codeblocks>=0.17; extra == "tests"
+Requires-Dist: pytest-cov>=3.0; extra == "tests"
+Requires-Dist: xdoctest>=1.1.5; extra == "tests"
+Provides-Extra: tui
+Requires-Dist: textual>=0.50; extra == "tui"
+Dynamic: license-file
 
 # Infer Stack
 
+[![PyPI version](https://img.shields.io/pypi/v/infer-stack.svg)](https://pypi.org/project/infer-stack/)
+[![Python versions](https://img.shields.io/pypi/pyversions/infer-stack.svg)](https://pypi.org/project/infer-stack/)
+[![License](https://img.shields.io/pypi/l/infer-stack.svg)](https://github.com/AIQ-Kitware/infer_stack/blob/main/LICENSE)
+
+> **Heads up — the leasing model is now the primary workflow.** Declare models
+> in a catalog (`infer-stack catalog …`) and `acquire`/`run` endpoints
+> on demand; see `docs/source/manual/` (the Ollama + Open WebUI tutorial and the
+> leasing demo) and `infer-stack help tree`. The
+> **named stack profiles** documented below (`setup`/`render`/`up`/`switch`/…)
+> are the pre-leasing model and now live under **`infer-stack legacy <command>`**
+> (e.g. `infer-stack legacy render`). This README still describes that legacy
+> flow; a leasing-oriented rewrite is pending.
+
+## Supported platform
+
+`infer-stack` supports **Linux hosts only**. Its process locking, container
+runtime integration, GPU discovery, and deployment workflows are intentionally
+Linux-oriented. Windows is not a supported or tested execution platform.
+
+Operational and security constraints that are accepted during the current
+planning-stage release are tracked in
+[docs/planning/known-limitations.md](docs/planning/known-limitations.md).
+
 `infer_stack` manages **named stack profiles** for local and Kubernetes-backed inference.
 
 A stack profile is a small graph made from:
@@ -58,6 +89,8 @@ infer-stack deploy
 infer-stack switch <profile> --apply  # re-render and converge; no separate up needed
 infer-stack status
 infer-stack smoke-test
+infer-stack version                   # print the installed version
+infer-stack config paths              # show where config / artifacts / caches live
 ```
 
 The CLI is built on [`scriptconfig`](https://gitlab.kitware.com/utils/scriptconfig),
@@ -164,7 +197,13 @@ There are exactly two path roots:
 | **Everything generated** — `generated/` (docker-compose.yml, .env, plan.yaml, kubeai/*) **and** `state/` (hf-cache, postgres volumes, Ollama store, runtime bind mounts) | `~/.local/share/infer_stack/` (resp. `$XDG_DATA_HOME`) | `--data-dir` (or `INFER_STACK_DATA_DIR`) |
 
 `--data-dir` is the single knob for "put everything I generate in one
-directory." Set it once at `setup`; it is baked into the absolute
+directory." It **relocates the one infer-stack installation controlling a
+host/backend; it does not create an isolated second installation**. Do not run
+controllers from multiple config/data roots against the same Docker host or
+Kubernetes namespace. See the
+[single-owner limitation](docs/planning/known-limitations.md#one-control-plane-per-host-or-backend-namespace).
+
+Set it once at `setup`; it is baked into the absolute
 `state.*` and `output.generated_dir` paths written to `config.yaml`, so
 later commands don't need it again:
 

infer_stack-0.6.0/PKG-INFO → infer_stack-0.7.0/README.md

@@ -1,33 +1,28 @@
-Metadata-Version: 2.4
-Name: infer-stack
-Version: 0.6.0
-Summary: Profile-driven compose and KubeAI deployment compiler for inference stacks
-Author-email: "jon.crall" <jon.crall@kitware.com>
-License-Expression: Apache-2.0
-Project-URL: Homepage, https://github.com/AIQ-Kitware/infer_stack
-Classifier: Development Status :: 1 - Planning
-Classifier: Intended Audience :: Developers
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Classifier: Programming Language :: Python :: 3.13
-Classifier: Programming Language :: Python :: 3.14
-Classifier: Topic :: Software Development :: Libraries :: Python Modules
-Classifier: Topic :: Utilities
-Requires-Python: >=3.10
-Description-Content-Type: text/markdown
-Requires-Dist: jinja2>=3.1
-Requires-Dist: pyyaml>=6.0
-Requires-Dist: requests>=2.31
-Requires-Dist: rich>=13.0
-Requires-Dist: scriptconfig>=0.9
-Requires-Dist: ubelt>=1.3
-Provides-Extra: tests
-Requires-Dist: pytest>=7.0; extra == "tests"
-Requires-Dist: pytest-codeblocks>=0.17; extra == "tests"
-
 # Infer Stack
 
+[![PyPI version](https://img.shields.io/pypi/v/infer-stack.svg)](https://pypi.org/project/infer-stack/)
+[![Python versions](https://img.shields.io/pypi/pyversions/infer-stack.svg)](https://pypi.org/project/infer-stack/)
+[![License](https://img.shields.io/pypi/l/infer-stack.svg)](https://github.com/AIQ-Kitware/infer_stack/blob/main/LICENSE)
+
+> **Heads up — the leasing model is now the primary workflow.** Declare models
+> in a catalog (`infer-stack catalog …`) and `acquire`/`run` endpoints
+> on demand; see `docs/source/manual/` (the Ollama + Open WebUI tutorial and the
+> leasing demo) and `infer-stack help tree`. The
+> **named stack profiles** documented below (`setup`/`render`/`up`/`switch`/…)
+> are the pre-leasing model and now live under **`infer-stack legacy <command>`**
+> (e.g. `infer-stack legacy render`). This README still describes that legacy
+> flow; a leasing-oriented rewrite is pending.
+
+## Supported platform
+
+`infer-stack` supports **Linux hosts only**. Its process locking, container
+runtime integration, GPU discovery, and deployment workflows are intentionally
+Linux-oriented. Windows is not a supported or tested execution platform.
+
+Operational and security constraints that are accepted during the current
+planning-stage release are tracked in
+[docs/planning/known-limitations.md](docs/planning/known-limitations.md).
+
 `infer_stack` manages **named stack profiles** for local and Kubernetes-backed inference.
 
 A stack profile is a small graph made from:
@@ -58,6 +53,8 @@ infer-stack deploy
 infer-stack switch <profile> --apply  # re-render and converge; no separate up needed
 infer-stack status
 infer-stack smoke-test
+infer-stack version                   # print the installed version
+infer-stack config paths              # show where config / artifacts / caches live
 ```
 
 The CLI is built on [`scriptconfig`](https://gitlab.kitware.com/utils/scriptconfig),
@@ -164,7 +161,13 @@ There are exactly two path roots:
 | **Everything generated** — `generated/` (docker-compose.yml, .env, plan.yaml, kubeai/*) **and** `state/` (hf-cache, postgres volumes, Ollama store, runtime bind mounts) | `~/.local/share/infer_stack/` (resp. `$XDG_DATA_HOME`) | `--data-dir` (or `INFER_STACK_DATA_DIR`) |
 
 `--data-dir` is the single knob for "put everything I generate in one
-directory." Set it once at `setup`; it is baked into the absolute
+directory." It **relocates the one infer-stack installation controlling a
+host/backend; it does not create an isolated second installation**. Do not run
+controllers from multiple config/data roots against the same Docker host or
+Kubernetes namespace. See the
+[single-owner limitation](docs/planning/known-limitations.md#one-control-plane-per-host-or-backend-namespace).
+
+Set it once at `setup`; it is baked into the absolute
 `state.*` and `output.generated_dir` paths written to `config.yaml`, so
 later commands don't need it again:
 

infer_stack-0.7.0/infer_stack/__init__.py

@@ -0,0 +1,2 @@
+__all__ = []
+__version__ = '0.7.0'

infer_stack-0.7.0/infer_stack/__main__.py

@@ -0,0 +1,6 @@
+"""Enable ``python -m infer_stack`` to run the CLI."""
+
+from .cli import main
+
+if __name__ == '__main__':
+    raise SystemExit(main())

infer_stack-0.7.0/infer_stack/_log.py

@@ -0,0 +1,51 @@
+"""loguru-based "behind the scenes" feedback for the leasing CLI.
+
+This is deliberately kept off the ``--help`` import path (loguru is ~50ms to
+import): nothing at module scope in the CLI imports this. It is pulled in only
+at runtime by the leasing verbs (``configure_logging``) and the converge/
+reconcile code that narrates what it is doing.
+
+The ``infer_stack`` package is ``disable``d here on import, so importing the
+library (or running the test suite, which calls subcommands directly) stays
+silent until the CLI explicitly calls :func:`configure_logging`.
+"""
+
+from __future__ import annotations
+
+import os
+import sys
+
+from loguru import logger
+
+__all__ = ['logger', 'configure_logging']
+
+# Silent by default; the CLI entry points re-enable via configure_logging().
+logger.disable('infer_stack')
+_CONFIGURED = False
+
+
+def configure_logging(level: str | None = None, *, force: bool = False):
+    """Route infer-stack's narration to stderr (idempotent).
+
+    Level resolves to ``level`` arg > ``$INFER_STACK_LOG_LEVEL`` > ``INFO``.
+    Narration goes to stderr so it never pollutes a command's stdout (JSON,
+    ``$(infer-stack env KEY)``, etc.). Colorized only on a real terminal.
+    """
+    global _CONFIGURED
+    logger.enable('infer_stack')
+    if _CONFIGURED and not force:
+        return logger
+    level = (level or os.environ.get('INFER_STACK_LOG_LEVEL') or 'INFO').upper()
+    colorize = sys.stderr.isatty() and os.environ.get('NO_COLOR') is None
+    logger.remove()
+    logger.add(
+        sys.stderr,
+        level=level,
+        colorize=colorize,
+        format=(
+            '<dim>{time:HH:mm:ss}</dim> '
+            '<level>{level: <7}</level> {message}'
+        ),
+    )
+    _CONFIGURED = True
+    return logger

infer_stack-0.7.0/infer_stack/backends/__init__.py

@@ -0,0 +1,4 @@
+from .kubeai import KubeaiBackend
+from .kubeai_renderer import render_kubeai_artifacts  # legacy profile-era path
+
+__all__ = ['KubeaiBackend', 'render_kubeai_artifacts']