nlp2cmd-intent 0.1.1__tar.gz

nlp2cmd_intent-0.1.1/.gitignore

@@ -0,0 +1,248 @@
+tauri-wrapper/.env.example
+backend/.env.example
+nlp-service/.env.example
+tests/.env.example
+worker/.env.example
+__pycache__/
+*.pyc
+.env
+.env.backup
+node_modules
+
+.env.local
+.venv/
+*.egg-info/
+dist/
+build/
+.idea/
+.vscode/
+*.db
+.idea/llx.iml
+my-api/.env.example
+test-api-qwen/.env.example
+.idea
+.pyqual
+.code2llm
+.code2llm_cache
+litellm_config.yaml
+litellm-config.yaml
+.llm
+managed_components
+.gui-agent.pid
+.gui-server.pid
+.gui-server.log
+gui-server/app_old.py
+gui-server/app.py.bak
+gui-server/index_old.html
+gui-server/index.html.bak
+gui-server/logs/
+gui-agent/logs/
+logs/
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer,
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+.aider*

nlp2cmd_intent-0.1.1/PKG-INFO

@@ -0,0 +1,74 @@
+Metadata-Version: 2.4
+Name: nlp2cmd-intent
+Version: 0.1.1
+Summary: NL normalization, intent detection, and entity extraction for nlp2cmd
+License-Expression: Apache-2.0
+Requires-Python: >=3.10
+Requires-Dist: pact-ir>=0.1.0
+Requires-Dist: pydantic>=2.0
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# nlp2cmd-intent
+
+NL → **IntentIR**: normalizacja, detekcja intencji, encje.
+
+Kanoniczna implementacja `KeywordIntentDetector` — nlp2cmd re-eksportuje ją z `nlp2cmd.generation.keywords`.
+
+## Użycie
+
+```python
+from nlp2cmd_intent import IntentPipeline, analyze_query, ensure_intent_clear
+
+intent = IntentPipeline().run("znajdź pliki *.py w src")
+print(intent.intent, intent.target_kind, intent.confidence)
+
+if intent.needs_clarification():
+    # confidence < 0.5 lub niepuste ambiguities
+    ...
+
+ensure_intent_clear(intent, enforced=True)  # raises IntentClarificationRequired
+
+structure = analyze_query("znajdź pliki *.py w src", include_plan=True)
+```
+
+### Egzekwowanie clarification
+
+```mermaid
+flowchart LR
+    IR[IntentIR] --> NC{needs_clarification?}
+    NC -->|plan — zawsze| BLOCK[IntentClarificationRequired]
+    NC -->|show — opcjonalnie| ENV{NLP2CMD_ENFORCE_CLARIFICATION=1}
+    ENV -->|tak| BLOCK
+    ENV -->|nie| OK[kontynuuj]
+```
+
+| Ścieżka | Zachowanie |
+|---------|------------|
+| `nlp2cmd plan` | zawsze blokuje przy niskiej pewności |
+| `nlp2dsl show` | tylko z `NLP2CMD_ENFORCE_CLARIFICATION=1` |
+
+Kontrakty Intract (plan steps) — w **nlp2cmd**, nie w tym pakiecie. Zob. [`docs/intract-integration.md`](../../docs/intract-integration.md).
+
+## CLI (przez nlp2dsl-show)
+
+```bash
+nlp2dsl show "znajdź pliki *.py w src"
+```
+
+## Instalacja
+
+```bash
+pip install -e packages/pact-ir
+pip install -e packages/nlp2cmd-intent
+```
+
+## Pliki danych
+
+Bundlowane w `src/nlp2cmd_intent/data/`:
+
+- `patterns.json`
+- `keyword_intent_detector_config.json`
+
+Override: `NLP2CMD_PATTERNS_FILE`, `NLP2CMD_DETECTOR_CONFIG_FILE`, `NLP2CMD_CONFIG_DIR`.

nlp2cmd_intent-0.1.1/README.md

@@ -0,0 +1,62 @@
+# nlp2cmd-intent
+
+NL → **IntentIR**: normalizacja, detekcja intencji, encje.
+
+Kanoniczna implementacja `KeywordIntentDetector` — nlp2cmd re-eksportuje ją z `nlp2cmd.generation.keywords`.
+
+## Użycie
+
+```python
+from nlp2cmd_intent import IntentPipeline, analyze_query, ensure_intent_clear
+
+intent = IntentPipeline().run("znajdź pliki *.py w src")
+print(intent.intent, intent.target_kind, intent.confidence)
+
+if intent.needs_clarification():
+    # confidence < 0.5 lub niepuste ambiguities
+    ...
+
+ensure_intent_clear(intent, enforced=True)  # raises IntentClarificationRequired
+
+structure = analyze_query("znajdź pliki *.py w src", include_plan=True)
+```
+
+### Egzekwowanie clarification
+
+```mermaid
+flowchart LR
+    IR[IntentIR] --> NC{needs_clarification?}
+    NC -->|plan — zawsze| BLOCK[IntentClarificationRequired]
+    NC -->|show — opcjonalnie| ENV{NLP2CMD_ENFORCE_CLARIFICATION=1}
+    ENV -->|tak| BLOCK
+    ENV -->|nie| OK[kontynuuj]
+```
+
+| Ścieżka | Zachowanie |
+|---------|------------|
+| `nlp2cmd plan` | zawsze blokuje przy niskiej pewności |
+| `nlp2dsl show` | tylko z `NLP2CMD_ENFORCE_CLARIFICATION=1` |
+
+Kontrakty Intract (plan steps) — w **nlp2cmd**, nie w tym pakiecie. Zob. [`docs/intract-integration.md`](../../docs/intract-integration.md).
+
+## CLI (przez nlp2dsl-show)
+
+```bash
+nlp2dsl show "znajdź pliki *.py w src"
+```
+
+## Instalacja
+
+```bash
+pip install -e packages/pact-ir
+pip install -e packages/nlp2cmd-intent
+```
+
+## Pliki danych
+
+Bundlowane w `src/nlp2cmd_intent/data/`:
+
+- `patterns.json`
+- `keyword_intent_detector_config.json`
+
+Override: `NLP2CMD_PATTERNS_FILE`, `NLP2CMD_DETECTOR_CONFIG_FILE`, `NLP2CMD_CONFIG_DIR`.

nlp2cmd_intent-0.1.1/pyproject.toml

@@ -0,0 +1,24 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "nlp2cmd-intent"
+version = "0.1.1"
+description = "NL normalization, intent detection, and entity extraction for nlp2cmd"
+readme = "README.md"
+requires-python = ">=3.10"
+license = "Apache-2.0"
+dependencies = [
+    "pact-ir>=0.1.0",
+    "pydantic>=2.0",
+]
+
+[project.optional-dependencies]
+dev = ["pytest>=8.0"]
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/nlp2cmd_intent"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]

nlp2cmd_intent-0.1.1/src/nlp2cmd_intent/__init__.py

@@ -0,0 +1,31 @@
+"""NL → IntentIR pipeline."""
+
+from nlp2cmd_intent.clarification import (
+    IntentClarificationRequired,
+    clarification_enforced,
+    ensure_intent_clear,
+)
+from nlp2cmd_intent.facade import IntentPipeline, default_intent_detector
+from nlp2cmd_intent.input import analyze_query
+from nlp2cmd_intent.keywords import DetectionResult, KeywordIntentDetector, KeywordPatterns
+from nlp2cmd_intent.normalize import QueryNormalizer
+from nlp2cmd_intent.nlp2cmd_convert import detection_to_intent_ir
+from nlp2cmd_intent.protocols import EntityExtractor, IntentDetector
+
+__all__ = [
+    "DetectionResult",
+    "EntityExtractor",
+    "IntentClarificationRequired",
+    "IntentDetector",
+    "IntentPipeline",
+    "KeywordIntentDetector",
+    "KeywordPatterns",
+    "QueryNormalizer",
+    "analyze_query",
+    "clarification_enforced",
+    "default_intent_detector",
+    "detection_to_intent_ir",
+    "ensure_intent_clear",
+]
+
+__version__ = "0.1.0"

nlp2cmd_intent-0.1.1/src/nlp2cmd_intent/clarification.py

@@ -0,0 +1,37 @@
+"""Intent clarification enforcement for low-confidence queries."""
+
+from __future__ import annotations
+
+import os
+
+from pact_ir import IntentIR
+
+
+class IntentClarificationRequired(Exception):
+    """Raised when IntentIR needs user clarification before planning."""
+
+    def __init__(self, intent: IntentIR) -> None:
+        self.intent = intent
+        messages: list[str] = []
+        for ambiguity in intent.ambiguities:
+            messages.append(ambiguity.message)
+        if intent.confidence < 0.5:
+            messages.append(f"confidence {intent.confidence:.2f} below threshold 0.5")
+        super().__init__("; ".join(messages) or "intent needs clarification")
+
+
+def clarification_enforced() -> bool:
+    return os.getenv("NLP2CMD_ENFORCE_CLARIFICATION", "0").strip().lower() in {
+        "1",
+        "true",
+        "yes",
+        "on",
+    }
+
+
+def ensure_intent_clear(intent: IntentIR, *, enforced: bool | None = None) -> None:
+    """Raise IntentClarificationRequired when clarification is required."""
+    if enforced is None:
+        enforced = clarification_enforced()
+    if enforced and intent.needs_clarification():
+        raise IntentClarificationRequired(intent)

nlp2cmd_intent-0.1.1/src/nlp2cmd_intent/data/keyword_intent_detector_config.json

@@ -0,0 +1,215 @@
+{
+  "$schema": "keyword_intent_detector_config.v1",
+  "domain_boosters": {
+    "sql": [
+      "tabel",
+      "tabela",
+      "table",
+      "kolumna",
+      "column",
+      "baz",
+      "baza",
+      "database",
+      "sql",
+      "where",
+      "join",
+      "tabeli",
+      "z tabeli",
+      "select",
+      "insert",
+      "update",
+      "delete",
+      "SELECT",
+      "INSERT",
+      "UPDATE",
+      "DELETE"
+    ],
+    "shell": [
+      "list_processes",
+      "process",
+      "reboot",
+      "service_start",
+      "service_restart",
+      "service_stop",
+      "service_status",
+      "open_url",
+      "search_web",
+      "file_operation",
+      "find",
+      "archive",
+      "disk",
+      "system_maintenance",
+      "development",
+      "security",
+      "process_management",
+      "find",
+      "list",
+      "znajd\u017a",
+      "plik",
+      "pliki",
+      "u\u017cytkownik",
+      "u\u017cytkownika",
+      "poka\u017c",
+      "pokaz"
+    ],
+    "docker": [
+      "docker",
+      "doker",
+      "dokcer",
+      "kontener",
+      "container",
+      "obraz",
+      "image",
+      "compose",
+      "dockerfile",
+      "ker\u00f3w",
+      "k\u00f3r\u00f3w",
+      "dker\u00f3w",
+      "dkor\u00f3w",
+      "logi",
+      "logs"
+    ],
+    "kubernetes": [
+      "kubernetes",
+      "k8s",
+      "kubectl",
+      "pod",
+      "deployment",
+      "namespace",
+      "helm",
+      "cluster",
+      "node",
+      "service"
+    ],
+    "git": [
+      "git",
+      "repo",
+      "repository",
+      "commit",
+      "branch",
+      "ga\u0142\u0105\u017a",
+      "merge",
+      "push",
+      "pull",
+      "clone"
+    ],
+    "dql": [
+      "entity",
+      "graph",
+      "node",
+      "edge",
+      "relation"
+    ],
+    "browser": [
+      "przegl\u0105dark",
+      "browser",
+      "strona",
+      "website",
+      "kliknij",
+      "click",
+      "formularz",
+      "form",
+      "przycisk",
+      "button",
+      "link",
+      "url",
+      "google",
+      "github",
+      "amazon",
+      "szukaj",
+      "wyszukaj",
+      "wpisz",
+      "type"
+    ]
+  },
+  "priority_intents": {
+    "sql": [
+      "delete",
+      "update",
+      "insert",
+      "show_tables",
+      "aggregate",
+      "select"
+    ],
+    "shell": [
+      "find",
+      "list_processes",
+      "process",
+      "reboot",
+      "service_start",
+      "service_restart",
+      "service_stop",
+      "service_status",
+      "open_url",
+      "search_web",
+      "file_operation",
+      "archive",
+      "disk",
+      "system_maintenance",
+      "development",
+      "security",
+      "process_management",
+      "list_dirs",
+      "find"
+    ],
+    "docker": [
+      "stop",
+      "prune",
+      "build",
+      "run",
+      "list",
+      "logs",
+      "exec",
+      "start",
+      "remove"
+    ],
+    "kubernetes": [
+      "delete",
+      "scale",
+      "describe",
+      "logs"
+    ],
+    "git": [
+      "reset",
+      "revert",
+      "merge",
+      "rebase",
+      "push",
+      "commit",
+      "stash"
+    ],
+    "browser": [
+      "web_action",
+      "navigate",
+      "click",
+      "fill_form"
+    ]
+  },
+  "fast_path": {
+    "browser_keywords": [
+      "przegl\u0105dark",
+      "browser",
+      "otw\u00f3rz stron\u0119",
+      "open url",
+      "open website",
+      "go to",
+      "navigate to"
+    ],
+    "search_keywords": [
+      "szukaj w internecie",
+      "szukaj online",
+      "znajd\u017a w internecie",
+      "look up online"
+    ],
+    "common_images": [
+      "nginx",
+      "redis",
+      "postgres",
+      "postgresql",
+      "mysql",
+      "mongo",
+      "mongodb",
+      "rabbitmq"
+    ]
+  }
+}