Code import - branch release/SIENTIAPDE-1645

2026-06-28 03:02:55 +00:00
commit d607d5fed0
183 changed files with 178293 additions and 0 deletions
--- a/.dockerignore
+++ b/.dockerignore
@@ -0,0 +1,93 @@
+# ============================================================================
+# WHITELIST APPROACH: Block everything by default, then allow only what's needed
+# ============================================================================
+
+# Block everything first
+*
+
+# ============================================================================
+# ALLOW: Application source code (model_manager package)
+# ============================================================================
+
+# Allow the main package directory and all Python files
+!model_manager/
+!model_manager/**/*.py
+!model_manager/**/__init__.py
+
+# Allow subdirectories structure
+!model_manager/activities/
+!model_manager/activities/**
+!model_manager/schedules/
+!model_manager/schedules/**
+!model_manager/sientia/
+!model_manager/sientia/**
+!model_manager/utils/
+!model_manager/utils/**
+!model_manager/utils/models/
+!model_manager/utils/models/**
+!model_manager/utils/repository/
+!model_manager/utils/repository/**
+!model_manager/worker/
+!model_manager/worker/**
+!model_manager/workflows/
+!model_manager/workflows/**
+
+# Allow reports directory with header.html
+!model_manager/reports/
+!model_manager/reports/header.html
+
+# Allow temp directory structure (but not its contents)
+!model_manager/reports/temp/
+
+# ============================================================================
+# ALLOW: Dependencies file (needed for pip install in Dockerfile)
+# ============================================================================
+!requirements.txt
+
+# ============================================================================
+# BLOCK: Explicitly block unwanted files even if they match above patterns
+# ============================================================================
+
+# Python cache and compiled files
+**/__pycache__/
+**/*.pyc
+**/*.pyo
+**/*.pyd
+**/.Python
+**/*.so
+**/*.egg
+**/*.egg-info/
+
+# Tests (not needed in production)
+model_manager/**/test_*.py
+model_manager/**/*_test.py
+
+# IDE and editor files
+**/.vscode/
+**/.idea/
+**/*.swp
+**/*.swo
+**/*~
+
+# OS files
+**/.DS_Store
+**/Thumbs.db
+
+# Logs and temporary files
+**/*.log
+**/*.tmp
+**/*.temp
+
+# Local configuration
+**/.env
+**/.env.local
+**/*.local
+
+# Documentation inside code
+**/*.md
+**/README*
+
+# Backup files
+**/*.bak
+**/*.backup
+**/*.old
--- a/.env
+++ b/.env
@@ -0,0 +1,54 @@
+POSTGRES_HOST=db.sientia.ai
+POSTGRES_PORT=30432
+POSTGRES_USER=postgres
+POSTGRES_PASSWORD=nFqc81y6kwmr2zuAIx43DhiOosFCVPpeEfTtTWZflkNjB2j1KtEeIANkhFR9mAX3
+POSTGRES_DBNAME=sientia-core-mlops-bff
+POSTGRES_MIN_CONNECTIONS=10
+POSTGRES_MAX_CONNECTIONS=30
+
+MLFLOW_URL=https://tracking.sientia.ai
+MLFLOW_USERNAME=aignosi
+MLFLOW_PASSWORD=1L0FP50j3ncp123
+
+LOG_LEVEL=DEBUG
+HTTP_METRICS_PORT=9090
+HTTP_SDK_METRICS_PORT=9091
+PROJECT_NAME=sientia-model-manager
+
+TEMPORAL_HOST=orchestrator.sientia.ai
+TEMPORAL_NAMESPACE=model-manager
+TRAIN_TASK_QUEUE=train_model-local_queue
+CLEANUP_TASK_QUEUE=cleanup-local_queue
+TEMPORAL_USE_TLS=true
+
+MONGODB_USERNAME=root
+MONGODB_PASSWORD=wKZDbMNU1c
+MONGODB_URL=db.sientia.ai:32017
+MONGODB_DATABASE=sientia
+MONGODB_TTL_INDEX_HOURS=1
+
+MINIO_ENDPOINT_URL=https://storage.sientia.ai
+MINIO_ACCESS_KEY=model-training-user
+MINIO_SECRET_KEY=modelTrainingUser123
+MINIO_REGION=us-east-1
+MINIO_USE_SSL=false
+MINIO_MAX_RETRY_ATTEMPTS=3
+MINIO_RETRY_MODE=adaptive
+MINIO_CONNECT_TIMEOUT=10
+MINIO_READ_TIMEOUT=60
+
+TIMEOUT_VALIDATE_PARAMS=30
+TIMEOUT_TRAIN_MODEL=2700
+TIMEOUT_DELETE_FILE=120
+TIMEOUT_UPDATE_DATABASE=30
+
+CLEANUP_RETENTION_HOURS=24
+CLEANUP_DRY_RUN=true
+TIMEOUT_CLEANUP_LOCAL=120
+
+CLEANUP_SCHEDULE_ID=cleanup-files-daily
+CLEANUP_CRON="0 21 * * *"
+CLEANUP_TIMEZONE=UTC
+CLEANUP_EXECUTION_TIMEOUT_HOURS=1
+
+EXTRA_PIP_REQUIREMENTS=git+https://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@github.com/Aignosi/sientia-mlops-library.git
--- a/.env.example
+++ b/.env.example
@@ -0,0 +1,57 @@
+POSTGRES_HOST=localhost
+POSTGRES_PORT=5432
+POSTGRES_USER=postgres
+POSTGRES_PASSWORD=changeme
+POSTGRES_DBNAME=sientia
+POSTGRES_MIN_CONNECTIONS=10
+POSTGRES_MAX_CONNECTIONS=30
+
+MLFLOW_URL=http://localhost:5080
+MLFLOW_USERNAME=aignosi
+MLFLOW_PASSWORD=changeme
+
+LOG_LEVEL=DEBUG
+HTTP_METRICS_PORT=9090
+HTTP_SDK_METRICS_PORT=9091
+PROJECT_NAME=sientia-model-manager
+
+TEMPORAL_HOST=localhost:7233
+TEMPORAL_NAMESPACE=model-manager
+TEMPORAL_USE_TLS=false
+RUNTIME=single
+
+MONGODB_USERNAME=root
+MONGODB_PASSWORD=changeme
+MONGODB_URL=localhost:27017
+MONGODB_DATABASE=sientia
+MONGODB_TTL_INDEX_HOURS=1
+
+MINIO_ENDPOINT_URL=http://localhost:9000
+MINIO_ACCESS_KEY=minioadmin
+MINIO_SECRET_KEY=minioadmin
+MINIO_DEFAULT_BUCKET=model-training
+MINIO_SECURE=false
+
+STORE_BASE_URL=http://localhost:3000
+STORE_OWNER=aignosi
+STORE_REPO=suse-model-store
+STORE_USERNAME=
+STORE_PASSWORD=
+STORE_CACHE_TTL_SECONDS=3600
+PYPI_SERVER=http://localhost:5000
+PYPI_USERNAME=
+PYPI_PASSWORD=
+
+TIMEOUT_VALIDATE_PARAMS=30
+TIMEOUT_TRAIN_MODEL=2700
+TIMEOUT_DELETE_FILE=120
+TIMEOUT_UPDATE_DATABASE=30
+
+CLEANUP_RETENTION_HOURS=24
+CLEANUP_DRY_RUN=false
+TIMEOUT_CLEANUP_LOCAL=120
+
+CLEANUP_SCHEDULE_ID=cleanup-files-daily
+CLEANUP_CRON="0 0 * * *"
+CLEANUP_TIMEZONE=UTC
+CLEANUP_EXECUTION_TIMEOUT_HOURS=1
--- a/.event.json
+++ b/.event.json
@@ -0,0 +1,14 @@
+{
+  "action": "closed",
+  "pull_request": {
+    "merged": true,
+    "head": {
+      "ref": "release/SIENTIAPDE-1252"
+    },
+    "base": {
+      "ref": "main"
+    },
+    "number": 1,
+    "title": "Test PR"
+  }
+}
--- a/.github/workflows/deploy.yml
+++ b/.github/workflows/deploy.yml
@@ -0,0 +1,33 @@
+name: Deploy Python Application
+
+on:
+  pull_request:
+    types:
+      - closed
+    branches:
+      - main
+      - 'release/**'
+      - 'feature/**'
+
+jobs:
+  deploy:
+    name: Deploy
+    if: github.event.pull_request.merged == true
+    permissions: write-all
+    uses: Aignosi/github_workflow_templates/.github/workflows/reusable-deploy.yml@main
+    with:
+      branch_name: ${{ github.event.pull_request.head.ref }}
+      project_type: 'python'
+      image_name: 'sientia-dataops-model-manager'
+      helm_chart_path: 'sientia-module'
+      helm_release_name: 'sientia-dataops-model-manager'
+      helm_namespace: 'sientia'
+      update_version_in: '["pyproject", "values"]'
+      app_owner: 'Aignosi'
+      private_repos: 'sientia-dataops-library'
+      helm_repo_name: 'sientia'
+      helm_repo_url: 'https://raw.githubusercontent.com/Aignosi/sientia-dataops-helm-repo/refs/heads/main/'
+      helm_chart_version: '0.6.0'
+      helm_values_file: './values.yaml'
+      use_vpn: true
+    secrets: inherit
--- a/.github/workflows/quality-gate.yml
+++ b/.github/workflows/quality-gate.yml
@@ -0,0 +1,18 @@
+name: Quality gate
+
+on:
+  pull_request:
+    branches:
+      - main
+      - 'release/**'
+      - 'feature/**'
+    types: [ opened, synchronize, reopened ]
+
+jobs:
+  quality-gate:
+    uses: Aignosi/github_workflow_templates/.github/workflows/python-quality-gate.yml@main
+    permissions: write-all
+    with:
+      project_name: 'model_manager'
+      repositories: 'sientia-dataops-library,sientia-model-library'
+    secrets: inherit
--- a/.gitignore
+++ b/.gitignore
@@ -0,0 +1,250 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$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/
+
+# Code quality tools cache
+.bandit/
+validate.txt
+
+# 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/
+venv_311/
+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__/
+
+# Ignore Docker volumes
+docker-compose.override.yml
+**/db_data/
+**/kafka-volume/
+**/zookeeper-volume/
+**/mage_data/
+**/minio_data/
+**/venv/
+**/certs/*.pem
+**/certs/*.der
+**/certs/*.csr
+**/deploy/*.yaml
+scouter/.file_versions/
+scouter/pipelines/**/triggers.yaml
+**/postgres_data/**
+
+# Ignore Python cache files
+*.pyc
+*.pyo
+*.pyd
+
+# Ignore temporary files
+*.swp
+
+# Ignore test run reports in model_manager/reports/temp (but keep temp folder and .gitkeep)
+model_manager/reports/temp/*
+!model_manager/reports/temp/.gitkeep
+
+# Miscellaneous
+git_key*
+git_log
+tmp/
+sientia-module/
+.secrets
+.event.json
+
+models/
--- a/.idea/.gitignore
+++ b/.idea/.gitignore
@@ -0,0 +1,10 @@
+# Default ignored files
+/shelf/
+/workspace.xml
+# Ignored default folder with query files
+/queries/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml
+# Editor-based HTTP Client requests
+/httpRequests/
--- a/.idea/inspectionProfiles/Project_Default.xml
+++ b/.idea/inspectionProfiles/Project_Default.xml
@@ -0,0 +1,13 @@
+<component name="InspectionProjectProfileManager">
+  <profile version="1.0">
+    <option name="myName" value="Project Default" />
+    <inspection_tool class="GrazieInspection" enabled="false" level="GRAMMAR_ERROR" enabled_by_default="false" />
+    <inspection_tool class="GrazieStyle" enabled="false" level="STYLE_SUGGESTION" enabled_by_default="false" />
+    <inspection_tool class="LanguageDetectionInspection" enabled="false" level="WEAK WARNING" enabled_by_default="false" />
+    <inspection_tool class="SpellCheckingInspection" enabled="false" level="TYPO" enabled_by_default="false">
+      <option name="processCode" value="true" />
+      <option name="processLiterals" value="true" />
+      <option name="processComments" value="true" />
+    </inspection_tool>
+  </profile>
+</component>
--- a/.idea/inspectionProfiles/profiles_settings.xml
+++ b/.idea/inspectionProfiles/profiles_settings.xml
@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>
--- a/.idea/misc.xml
+++ b/.idea/misc.xml
@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="Black">
+    <option name="sdkName" value="$PROJECT_DIR$/venv" />
+  </component>
+  <component name="ProjectRootManager" version="2" project-jdk-name="$PROJECT_DIR$/venv" project-jdk-type="Python SDK" />
+</project>
--- a/.idea/modules.xml
+++ b/.idea/modules.xml
@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/sientia-dataops-model-manager.iml" filepath="$PROJECT_DIR$/.idea/sientia-dataops-model-manager.iml" />
+    </modules>
+  </component>
+</project>
--- a/.idea/sientia-dataops-model-manager.iml
+++ b/.idea/sientia-dataops-model-manager.iml
@@ -0,0 +1,24 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$">
+      <excludeFolder url="file://$MODULE_DIR$/venv" />
+    </content>
+    <orderEntry type="jdk" jdkName="$MODULE_DIR$/venv" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+  <component name="PyDocumentationSettings">
+    <option name="format" value="PLAIN" />
+    <option name="myDocStringFormat" value="Plain" />
+  </component>
+  <component name="TemplatesService">
+    <option name="TEMPLATE_FOLDERS">
+      <list>
+        <option value="$MODULE_DIR$/sientia-module/templates" />
+      </list>
+    </option>
+  </component>
+  <component name="TestRunnerService">
+    <option name="PROJECT_TEST_RUNNER" value="py.test" />
+  </component>
+</module>
--- a/.idea/sonarlint.xml
+++ b/.idea/sonarlint.xml
@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="SonarLintProjectSettings">
+    <option name="bindingEnabled" value="true" />
+    <option name="projectKey" value="Aignosi_sientia-dataops-model-manager_dc6e051c-995a-4b57-9cde-f511018184c7" />
+    <option name="serverId" value="Sonarqube Aignosi" />
+  </component>
+</project>
--- a/.idea/vcs.xml
+++ b/.idea/vcs.xml
@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="" vcs="Git" />
+  </component>
+</project>
--- a/.idea/workspace.xml
+++ b/.idea/workspace.xml
@@ -0,0 +1,71 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ChangeListManager">
+    <list default="true" id="92ccf6be-e6f3-48c1-ab39-aeaebc5aef5b" name="Changes" comment="" />
+    <option name="SHOW_DIALOG" value="false" />
+    <option name="HIGHLIGHT_CONFLICTS" value="true" />
+    <option name="HIGHLIGHT_NON_ACTIVE_CHANGELIST" value="false" />
+    <option name="LAST_RESOLUTION" value="IGNORE" />
+  </component>
+  <component name="FlaskConsoleOptions" custom-start-script="import sys; print('Python %s on %s' % (sys.version, sys.platform)); sys.path.extend([WORKING_DIR_AND_PYTHON_PATHS])&#10;from flask.cli import ScriptInfo, NoAppException&#10;for module in [&quot;main.py&quot;, &quot;wsgi.py&quot;, &quot;app.py&quot;]:&#10;    try: locals().update(ScriptInfo(app_import_path=module, create_app=None).load_app().make_shell_context()); print(&quot;\nFlask App: %s&quot; % app.import_name); break&#10;    except NoAppException: pass">
+    <envs>
+      <env key="FLASK_APP" value="app" />
+    </envs>
+    <option name="myCustomStartScript" value="import sys; print('Python %s on %s' % (sys.version, sys.platform)); sys.path.extend([WORKING_DIR_AND_PYTHON_PATHS])&#10;from flask.cli import ScriptInfo, NoAppException&#10;for module in [&quot;main.py&quot;, &quot;wsgi.py&quot;, &quot;app.py&quot;]:&#10;    try: locals().update(ScriptInfo(app_import_path=module, create_app=None).load_app().make_shell_context()); print(&quot;\nFlask App: %s&quot; % app.import_name); break&#10;    except NoAppException: pass" />
+    <option name="myEnvs">
+      <map>
+        <entry key="FLASK_APP" value="app" />
+      </map>
+    </option>
+  </component>
+  <component name="Git.Settings">
+    <option name="RECENT_GIT_ROOT_PATH" value="$PROJECT_DIR$" />
+  </component>
+  <component name="ProjectColorInfo">{
+  &quot;associatedIndex&quot;: 4,
+  &quot;fromUser&quot;: false
+}</component>
+  <component name="ProjectId" id="3BfRCyO6razhElE9LcPDboXcAv2" />
+  <component name="ProjectViewState">
+    <option name="hideEmptyMiddlePackages" value="true" />
+    <option name="showLibraryContents" value="true" />
+  </component>
+  <component name="PropertiesComponent">{
+  &quot;keyToString&quot;: {
+    &quot;ModuleVcsDetector.initialDetectionPerformed&quot;: &quot;true&quot;,
+    &quot;RunOnceActivity.ShowReadmeOnStart&quot;: &quot;true&quot;,
+    &quot;RunOnceActivity.git.unshallow&quot;: &quot;true&quot;,
+    &quot;RunOnceActivity.typescript.service.memoryLimit.init&quot;: &quot;true&quot;,
+    &quot;ai.playground.ignore.import.keys.banner.in.settings&quot;: &quot;true&quot;,
+    &quot;git-widget-placeholder&quot;: &quot;feature/SIENTIAPDE-1717&quot;,
+    &quot;last_opened_file_path&quot;: &quot;/home/bruno-domingues/repos/sientia-dataops-model-manager&quot;,
+    &quot;nodejs_package_manager_path&quot;: &quot;npm&quot;,
+    &quot;settings.editor.selected.configurable&quot;: &quot;preferences.pluginManager&quot;,
+    &quot;vue.rearranger.settings.migration&quot;: &quot;true&quot;
+  }
+}</component>
+  <component name="SharedIndexes">
+    <attachedChunks>
+      <set>
+        <option value="bundled-js-predefined-d6986cc7102b-9b0f141eb926-JavaScript-PY-253.32098.74" />
+        <option value="bundled-python-sdk-1cd77e80b48f-6d6dccd035ac-com.jetbrains.pycharm.pro.sharedIndexes.bundled-PY-253.32098.74" />
+      </set>
+    </attachedChunks>
+  </component>
+  <component name="TaskManager">
+    <task active="true" id="Default" summary="Default task">
+      <changelist id="92ccf6be-e6f3-48c1-ab39-aeaebc5aef5b" name="Changes" comment="" />
+      <created>1774878015053</created>
+      <option name="number" value="Default" />
+      <option name="presentableId" value="Default" />
+      <updated>1774878015053</updated>
+      <workItem from="1774878016366" duration="289000" />
+      <workItem from="1774878319177" duration="4459000" />
+      <workItem from="1774886754051" duration="6220000" />
+    </task>
+    <servers />
+  </component>
+  <component name="TypeScriptGeneratedFilesManager">
+    <option name="version" value="3" />
+  </component>
+</project>
--- a/.ruff_cache/.gitignore
+++ b/.ruff_cache/.gitignore
@@ -0,0 +1,2 @@
+# Automatically created by ruff.
+*
--- a/.ruff_cache/0.14.0/11421224432631349604
+++ b/.ruff_cache/0.14.0/11421224432631349604
--- a/.ruff_cache/0.14.0/13638193022509832714
+++ b/.ruff_cache/0.14.0/13638193022509832714
--- a/.ruff_cache/0.14.0/14768006296384232627
+++ b/.ruff_cache/0.14.0/14768006296384232627
--- a/.ruff_cache/0.14.0/17253447349985294139
+++ b/.ruff_cache/0.14.0/17253447349985294139
--- a/.ruff_cache/0.14.0/18306982222913251416
+++ b/.ruff_cache/0.14.0/18306982222913251416
--- a/.ruff_cache/0.14.0/1907964205955133157
+++ b/.ruff_cache/0.14.0/1907964205955133157
--- a/.ruff_cache/0.14.0/8583545915449908552
+++ b/.ruff_cache/0.14.0/8583545915449908552
--- a/.ruff_cache/0.14.1/12824041124828081429
+++ b/.ruff_cache/0.14.1/12824041124828081429
--- a/.ruff_cache/0.14.1/1423718500153736471
+++ b/.ruff_cache/0.14.1/1423718500153736471
--- a/.ruff_cache/0.14.1/14699563893607295064
+++ b/.ruff_cache/0.14.1/14699563893607295064
--- a/.ruff_cache/0.14.1/18410434495952575929
+++ b/.ruff_cache/0.14.1/18410434495952575929
--- a/.ruff_cache/0.14.1/3972779882112180275
+++ b/.ruff_cache/0.14.1/3972779882112180275
--- a/.ruff_cache/0.14.1/5295742865236120757
+++ b/.ruff_cache/0.14.1/5295742865236120757
--- a/.ruff_cache/0.15.1/1026417868275141200
+++ b/.ruff_cache/0.15.1/1026417868275141200
--- a/.ruff_cache/0.15.1/12811633795799061953
+++ b/.ruff_cache/0.15.1/12811633795799061953
--- a/.ruff_cache/0.15.1/12843606693581798950
+++ b/.ruff_cache/0.15.1/12843606693581798950
--- a/.ruff_cache/0.15.1/14817865410155751013
+++ b/.ruff_cache/0.15.1/14817865410155751013
--- a/.ruff_cache/0.15.1/15009315736734947678
+++ b/.ruff_cache/0.15.1/15009315736734947678
--- a/.ruff_cache/0.15.1/9978076514612901822
+++ b/.ruff_cache/0.15.1/9978076514612901822
--- a/.ruff_cache/CACHEDIR.TAG
+++ b/.ruff_cache/CACHEDIR.TAG
@@ -0,0 +1 @@
+Signature: 8a477f597d28d172789f06886806bc55
--- a/.secrets
+++ b/.secrets
@@ -0,0 +1,14 @@
+GITHUB_TOKEN=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
+CI_DEPS_APP_ID=1275848
+CI_DEPS_PRIVATE_KEY="-----BEGIN RSA PRIVATE KEY-----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\nCobSt2sklE83MXy+aCWlP5mZqHltyAEVdF6QzN1uVN2rWg3N1SwJ/A==\n-----END RSA PRIVATE KEY-----\n"
+SONAR_TOKEN=sqp_5d4b1372f6e50a541c1004138106d3521ce531cc
+SONAR_HOST_URL=https://sonarqube.sientia.ai
+AZURE_CREDENTIALS={"clientId":"d3522fb7-1eb5-41f4-b981-37b07d5da3d8","clientSecret":"7DM8Q~Ch6I91OgLX143YZ~fJntYU__QpGSOAnc~P","subscriptionId":"38ada0de-addc-4c09-9e7e-eddfab756596","tenantId":"a474959a-eea9-4c10-8298-7ea0c8152c36","activeDirectoryEndpointUrl":"https://login.microsoftonline.com","resourceManagerEndpointUrl":"https://management.azure.com/","activeDirectoryGraphResourceId":"https://graph.windows.net/","sqlManagementEndpointUrl":"https://management.core.windows.net:8443/","galleryEndpointUrl":"https://gallery.azure.com/","managementEndpointUrl":"https://management.core.windows.net/"}
+REGISTRY_LOGIN_SERVER=aignosi.azurecr.io
+REGISTRY_USERNAME=d3522fb7-1eb5-41f4-b981-37b07d5da3d8
+REGISTRY_PASSWORD=7DM8Q~Ch6I91OgLX143YZ~fJntYU__QpGSOAnc~P
+SUSE_RKE2_KUBE_CONFIG=apiVersion: v1\nclusters:\n- cluster:\n    certificate-authority-data: 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\n    server: https://20.121.64.107:6443\n  name: suse-rk2\ncontexts:\n- context:\n    cluster: suse-rk2\n    user: suse-rk2\n  name: suse-rk2\ncurrent-context: suse-rk2\nkind: Config\nusers:\n- name: suse-rk2\n  user:\n    client-certificate-data: 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\n    client-key-data: LS0tLS1CRUdJTiBFQyBQUklWQVRFIEtFWS0tLS0tCk1IY0NBUUVFSUczTUpyWUVlbHhLVHQ1MEtXY3hySVhtKzkzZFhDa3JCeWdBUU1IU1pnc2NvQW9HQ0NxR1NNNDkKQXdFSG9VUURRZ0FFNFN0TWhISktJOWRwYjZuM21lRmdXYmM4c3BhWm9GZzgxVVlZclVJbmlpZ2dUZ3VzL0k1MgorOG9TL2QvRHYzdVpRQ1pna1hEM1pNV0t2amd4UDdzMWpBPT0KLS0tLS1FTkQgRUMgUFJJVkFURSBLRVktLS0tLQo=
+REPO_TOKEN=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
+REPO_USERNAME=bruno-domingues-aignosi
+HELM_REPO_USERNAME=bruno-domingues-aignosi
+HELM_REPO_PASSWORD=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
--- a/.vscode/settings.json
+++ b/.vscode/settings.json
@@ -0,0 +1,14 @@
+{
+  "coverage-gutters.coverageBaseDir": "${workspaceFolder}",
+  "coverage-gutters.coverageFileNames": ["coverage.xml"],
+  "coverage-gutters.coverageReportFileName": "coverage.xml",
+  "coverage-gutters.showLineCoverage": true,
+  "coverage-gutters.showRulerCoverage": true,
+  "coverage-gutters.highlightdark": "rgba(0, 255, 0, 1)",
+  "coverage-gutters.highlightlight": "rgba(0, 200, 0, 1)",
+  "coverage-gutters.partialHighlightDark": "rgba(255, 255, 0, 1)",
+  "coverage-gutters.partialHighlightLight": "rgba(255, 200, 0, 1)",
+  "coverage-gutters.noHighlightDark": "rgba(255, 0, 0, 1)",
+  "coverage-gutters.noHighlightLight": "rgba(255, 0, 0, 1)",
+  "explorer.autoReveal": false
+}
--- a/78
+++ b/78
@@ -0,0 +1,78 @@
+# Multi-stage build for optimized Python application
+FROM python:3.11-slim AS builder
+
+# Set build-time environment variables
+ENV PYTHONDONTWRITEBYTECODE=1 \
+    PYTHONUNBUFFERED=1 \
+    PIP_NO_CACHE_DIR=1 \
+    PIP_DISABLE_PIP_VERSION_CHECK=1
+
+# Install build dependencies only
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    curl \
+    git \
+    && rm -rf /var/lib/apt/lists/* && \
+    apt-get clean
+
+# Configure SSH to trust GitHub host key
+RUN mkdir -p ~/.ssh && \
+    ssh-keyscan -t rsa github.com >> ~/.ssh/known_hosts && \
+    chmod 600 ~/.ssh/known_hosts
+
+# Create virtual environment
+RUN python -m venv /opt/venv
+ENV PATH="/opt/venv/bin:$PATH"
+
+# Upgrade pip and wheel for better caching
+RUN pip install --upgrade pip setuptools wheel
+
+# Copy requirements files for better Docker layer caching
+COPY requirements.txt ./
+
+# Install only production dependencies with no cache
+RUN --mount=type=ssh echo "=== Installing dependencies ===" && \
+    pip install --no-cache-dir -r requirements.txt && \
+    echo "=== Dependencies installed successfully ===" && \
+    pip list | wc -l && \
+    echo "=== Cleaning cache files ===" && \
+    find /opt/venv -type d -name __pycache__ -exec rm -rf {} + 2>/dev/null || true && \
+    find /opt/venv -name "*.pyc" -delete 2>/dev/null || true && \
+    rm -rf /root/.cache/pip/* && \
+    echo "=== Cleaning venv site-packages ===" && \
+    find /opt/venv/lib/python3.11/site-packages/ -type f -name "*.md" -delete 2>/dev/null || true && \
+    echo "=== Stripping .so files ===" && \
+    find /opt/venv -name "*.so" -exec strip {} + 2>/dev/null || true
+
+# Production stage using python-slim for better functionality
+FROM python:3.11-slim AS production
+
+# Set environment variables
+ENV PYTHONDONTWRITEBYTECODE=1 \
+    PYTHONUNBUFFERED=1 \
+    PATH="/opt/venv/bin:$PATH" \
+    POD_ID=unknown \
+    HOME="/app"
+
+# Copy virtual environment from builder stage
+COPY --from=builder /opt/venv /opt/venv
+
+# Set working directory
+WORKDIR /app
+
+# Copy application code
+COPY . .
+
+# Create necessary directories for runtime file creation
+RUN mkdir -p /app/model_manager/reports /app/logs /app/temp /app/models /app/data && \
+    chmod 755 /app/model_manager/reports /app/logs /app/temp /app/models /app/data
+
+# Create non-root user
+RUN groupadd -r appuser && useradd -r -g appuser appuser && \
+    chown -R appuser:appuser /app
+
+# Switch to non-root user
+USER appuser
+
+# Set entrypoint for proper signal handling and PID 1
+ENTRYPOINT ["/opt/venv/bin/python", "-m", "model_manager.worker.worker"]
--- a/21
+++ b/21
@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 aignosi
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
--- a/PIPELINE_PARAMS_CHANGELOG.md
+++ b/PIPELINE_PARAMS_CHANGELOG.md
@@ -0,0 +1,227 @@
+# Changelog de Parâmetros do Pipeline de Treinamento
+
+Este documento descreve as alterações nos parâmetros de entrada do pipeline Temporal para treinamento de modelos.
+
+## Resumo das Alterações
+
+### Parâmetros ALTERADOS (Breaking Changes)
+
+| Parâmetro | Tipo Anterior | Tipo Novo | Descrição |
+|-----------|---------------|-----------|-----------|
+| `lag_train` | `int` | `dict[str, int]` | Agora é um dicionário com lag por variável. Ex: `{"var1": 2, "var2": 3}` |
+| `lag_val` | `int` | `dict[str, int]` | Agora é um dicionário com lag por variável. Ex: `{"var1": 1, "var2": 1}` |
+
+### Parâmetros NOVOS (Obrigatórios)
+
+| Parâmetro | Tipo | Descrição | Valores Válidos |
+|-----------|------|-----------|-----------------|
+| `model_name` | `str` | Nome do tipo de modelo | `"Linear Regression"`, `"Polynomial Regression"` |
+| `degree` | `int` | Grau do polinômio (1 = linear) | `>= 1` |
+| `interaction_only` | `bool` | Apenas termos de interação para polinomial | `true`, `false` |
+| `nan_treatment` | `str` | Tratamento de valores NaN | `"drop"`, `"linear interpolation"`, `"fill linear"` |
+| `scaler_name` | `str` | Nome do scaler a usar | `"Standard Scaler"`, `"None"` |
+
+### Parâmetros NOVOS (Opcionais)
+
+| Parâmetro | Tipo | Descrição | Default |
+|-----------|------|-----------|---------|
+| `start_date` | `str \| null` | Data inicial para filtrar dados (formato: `"YYYY-MM-DD HH:MM:SS"`) | `null` |
+| `end_date` | `str \| null` | Data final para filtrar dados (formato: `"YYYY-MM-DD HH:MM:SS"`) | `null` |
+| `support_filters` | `dict \| null` | Filtros customizados por variável | `{}` |
+| `static_threshold` | `int \| null` | Threshold para remoção de janelas estáticas (1-1000). Só usado quando `rem_static_win` é `true`. | `1` |
+
+---
+
+## Exemplo de Input Completo
+
+### Formato ANTERIOR (não funciona mais):
+
+```json
+{
+  "experiment_run_id": 123,
+  "target_variable": "temperatura",
+  "variable_columns": ["pressao", "umidade", "velocidade"],
+  "lag_train": 2,
+  "lag_val": 1,
+  "rem_static_win": true,
+  "low_lim": {"pressao": 0, "umidade": 0, "velocidade": 0},
+  "upp_lim": {"pressao": 100, "umidade": 100, "velocidade": 50},
+  "window": 0,
+  "use_scaler": true,
+  "include_ar": false,
+  "bucket_name": "training-data",
+  "file_name": "dataset.csv",
+  "line_separator": ";",
+  "decimal_separator": ",",
+  "train_size": 80,
+  "shuffle": false,
+  "experiment_name": "modelo-temperatura",
+  "removed_intervals": []
+}
+```
+
+### Formato NOVO (obrigatório):
+
+```json
+{
+  "experiment_run_id": 123,
+  "target_variable": "temperatura",
+  "variable_columns": ["pressao", "umidade", "velocidade"],
+  
+  "lag_train": {
+    "pressao": 2,
+    "umidade": 2,
+    "velocidade": 2
+  },
+  "lag_val": {
+    "pressao": 1,
+    "umidade": 1,
+    "velocidade": 1
+  },
+  
+  "rem_static_win": true,
+  "static_threshold": null,
+  "low_lim": {"pressao": 0, "umidade": 0, "velocidade": 0},
+  "upp_lim": {"pressao": 100, "umidade": 100, "velocidade": 50},
+  "window": 0,
+  "use_scaler": true,
+  "include_ar": false,
+  "bucket_name": "training-data",
+  "file_name": "dataset.csv",
+  "line_separator": ";",
+  "decimal_separator": ",",
+  "train_size": 80,
+  "shuffle": false,
+  "experiment_name": "modelo-temperatura",
+  "removed_intervals": [],
+  
+  "model_name": "Linear Regression",
+  "degree": 1,
+  "interaction_only": false,
+  "nan_treatment": "drop",
+  "scaler_name": "Standard Scaler",
+  
+  "start_date": null,
+  "end_date": null,
+  "support_filters": {}
+}
+```
+
+---
+
+## Exemplo para Polynomial Regression
+
+```json
+{
+  "experiment_run_id": 124,
+  "target_variable": "temperatura",
+  "variable_columns": ["pressao", "umidade"],
+  
+  "lag_train": {
+    "pressao": 0,
+    "umidade": 0
+  },
+  "lag_val": {
+    "pressao": 0,
+    "umidade": 0
+  },
+  
+  "rem_static_win": false,
+  "low_lim": {"pressao": 0, "umidade": 0},
+  "upp_lim": {"pressao": 100, "umidade": 100},
+  "window": 0,
+  "use_scaler": true,
+  "include_ar": false,
+  "bucket_name": "training-data",
+  "file_name": "dataset.csv",
+  "line_separator": ";",
+  "decimal_separator": ",",
+  "train_size": 80,
+  "shuffle": false,
+  "experiment_name": "modelo-polinomial",
+  "removed_intervals": [],
+  
+  "model_name": "Polynomial Regression",
+  "degree": 2,
+  "interaction_only": false,
+  "nan_treatment": "linear interpolation",
+  "scaler_name": "Standard Scaler",
+  
+  "start_date": "2024-01-01 00:00:00",
+  "end_date": "2024-12-31 23:59:59",
+  "support_filters": {}
+}
+```
+
+---
+
+## Exemplo com Intervalos Removidos
+
+```json
+{
+  "removed_intervals": [
+    ["2024-03-01 00:00:00", "2024-03-15 23:59:59"],
+    ["2024-06-01 00:00:00", "2024-06-30 23:59:59"]
+  ]
+}
+```
+
+---
+
+## Parâmetros Logados no MLflow
+
+Os seguintes parâmetros são agora logados no MLflow:
+
+| Parâmetro MLflow | Descrição |
+|------------------|-----------|
+| `model_name` | Nome do modelo (`Linear Regression` ou `Polynomial Regression`) |
+| `models_params` | `{"degree": int, "interaction_only": bool}` |
+| `target_variable` | Variável alvo |
+| `input_variables` | Lista de variáveis de entrada |
+| `nan_treatment` | Tratamento de NaN |
+| `lag_train` | Dicionário de lags para treino |
+| `lag_transform` | Dicionário de lags para transformação |
+| `static_threshold` | Threshold para janelas estáticas (1 ou null) |
+| `lower_limits` | Limites inferiores por variável |
+| `upper_limits` | Limites superiores por variável |
+| `scaler_name` | Nome do scaler |
+| `scaler_params` | Parâmetros do scaler (mean, variance) |
+| `include_ar` | Se inclui variável autoregressiva |
+| `train_size` | Proporção de treino (0.0 - 1.0) |
+| `test_size` | Proporção de teste (0.0 - 1.0) |
+| `start_date` | Data inicial (ou null) |
+| `end_date` | Data final (ou null) |
+| `removed_intervals` | Lista de intervalos removidos |
+| `retrain` | Sempre `false` para novos modelos |
+| `support_filters` | Filtros customizados |
+
+---
+
+## Validações de Negócio
+
+O sistema valida automaticamente:
+
+1. **`train_size`**: Deve estar entre 10 e 100
+2. **`variable_columns`**: Não pode estar vazio
+3. **`lag_train` / `lag_val`**: Todos os valores devem ser >= 0
+4. **`window`**: Deve ser >= 0
+5. **`degree`**: Deve ser >= 1
+6. **`nan_treatment`**: Deve ser `"drop"`, `"linear interpolation"` ou `"fill linear"`
+7. **`scaler_name`**: Deve ser `"Standard Scaler"` ou `"None"`
+8. **`model_name`**: Deve ser `"Linear Regression"` ou `"Polynomial Regression"`
+9. **`low_lim` / `upp_lim`**: Devem ter as mesmas chaves, e `low_lim[var] < upp_lim[var]`
+10. **`bucket_name` / `file_name` / `experiment_name`**: Não podem estar vazios
+11. **`degree` vs `model_name`**: Se `model_name` = "Polynomial Regression", `degree` deve ser >= 2; se "Linear Regression", `degree` deve ser = 1
+12. **`removed_intervals`**: Cada elemento deve ser lista/tupla com pelo menos 2 elementos (start, end)
+13. **`target_variable`**: Não pode estar vazio
+14. **`static_threshold`**: Se `rem_static_win` = `true` e `static_threshold` tiver valor, deve estar entre 1 e 1000 (inclusive). Se `null`, assume valor `1`.
+
+---
+
+## Arquivos Modificados
+
+- `model_manager/sientia/models.py` - `DataPreprocessor` e `LinearRegressionModel`
+- `model_manager/sientia/metrics.py` - Funções RCE adicionadas
+- `model_manager/utils/models/train_model_params.py` - Novos parâmetros
+- `model_manager/utils/repository/training_repository.py` - Uso dos novos parâmetros
+- `model_manager/utils/repository/model_repository.py` - Logging no MLflow
--- a/README.md
+++ b/README.md
--- a/coverage.xml
+++ b/coverage.xml
--- a/_double_date_column.csv
+++ b/_double_date_column.csv
@@ -0,0 +1,33 @@
+DATA,DATE2,03CV022/CORRENTE_N_M1_PV(Value),303-WIT-230(Value)
+01/05/2022 00:00:00,07-01-2022 01:00:00,170,33
+01/05/2022 00:00:10,07-01-2022 01:00:10,169,605
+01/05/2022 00:00:20,07-01-2022 01:00:20,169,178
+01/05/2022 00:00:30,07-01-2022 01:00:30,166,468
+01/05/2022 00:00:40,07-01-2022 01:00:40,162,136
+01/05/2022 00:00:50,07-01-2022 01:00:50,157,804
+01/05/2022 00:01:00,07-01-2022 01:01:00,155,883
+01/05/2022 00:01:10,07-01-2022 01:01:10,155,684
+01/05/2022 00:01:20,07-01-2022 01:01:20,155,484
+01/05/2022 00:01:30,07-01-2022 01:01:30,155,284
+01/05/2022 00:01:40,07-01-2022 01:01:40,155,85
+01/05/2022 00:01:50,07-01-2022 01:01:50,154,885
+01/05/2022 00:02:00,09-01-2022 02:02:00,154,685
+01/05/2022 00:02:10,09-01-2022 02:02:10,154,486
+01/05/2022 00:02:20,09-01-2022 02:02:20,154,286
+01/05/2022 00:02:30,09-01-2022 02:02:30,154,86
+01/05/2022 00:02:40,09-01-2022 02:02:40,152,866
+01/05/2022 00:02:50,09-01-2022 02:02:50,150,87
+01/05/2022 00:03:00,09-01-2022 02:03:00,148,874
+01/05/2022 00:03:10,09-01-2022 02:03:10,148,2134
+01/05/2022 00:03:20,09-01-2022 02:03:20,148,2068
+01/05/2022 00:03:30,09-01-2022 02:03:30,148,2022
+01/05/2022 00:03:40,09-01-2022 02:03:40,148,1976
+01/05/2022 00:03:50,09-01-2022 02:03:50,154,139
+01/05/2022 00:04:00,11-01-2022 03:04:00,165,112
+01/05/2022 00:04:10,11-01-2022 03:04:10,170,42
+01/05/2022 00:04:20,11-01-2022 03:04:20,170,116
+01/05/2022 00:04:30,11-01-2022 03:04:30,170,191
+01/05/2022 00:04:40,11-01-2022 03:04:40,170,266
+01/05/2022 00:04:50,11-01-2022 03:04:50,170,341
+01/05/2022 00:05:00,11-01-2022 03:05:00,170,416
+01/05/2022 00:05:10,11-01-2022 03:05:10,170,491
--- a/docs/DB_CV022_WIT230.csv
+++ b/docs/DB_CV022_WIT230.csv
@@ -0,0 +1,647 @@
+DATA,03CV022/CORRENTE_N_M1_PV(Value),303-WIT-230(Value)
+01/05/2022 00:00:00,170,33
+01/05/2022 00:00:10,169,605
+01/05/2022 00:00:20,169,178
+01/05/2022 00:00:30,166,468
+01/05/2022 00:00:40,162,136
+01/05/2022 00:00:50,157,804
+01/05/2022 00:01:00,155,883
+01/05/2022 00:01:10,155,684
+01/05/2022 00:01:20,155,484
+01/05/2022 00:01:30,155,284
+01/05/2022 00:01:40,155,85
+01/05/2022 00:01:50,154,885
+01/05/2022 00:02:00,154,685
+01/05/2022 00:02:10,154,486
+01/05/2022 00:02:20,154,286
+01/05/2022 00:02:30,154,86
+01/05/2022 00:02:40,152,866
+01/05/2022 00:02:50,150,87
+01/05/2022 00:03:00,148,874
+01/05/2022 00:03:10,148,2134
+01/05/2022 00:03:20,148,2068
+01/05/2022 00:03:30,148,2022
+01/05/2022 00:03:40,148,1976
+01/05/2022 00:03:50,154,139
+01/05/2022 00:04:00,165,112
+01/05/2022 00:04:10,170,42
+01/05/2022 00:04:20,170,116
+01/05/2022 00:04:30,170,191
+01/05/2022 00:04:40,170,266
+01/05/2022 00:04:50,170,341
+01/05/2022 00:05:00,170,416
+01/05/2022 00:05:10,170,491
+01/05/2022 00:05:20,170,566
+01/05/2022 00:05:30,170,641
+01/05/2022 00:05:40,170,716
+01/05/2022 00:05:50,170,79
+01/05/2022 00:06:00,170,865
+01/05/2022 00:06:10,170,94
+01/05/2022 00:06:20,171,15
+01/05/2022 00:06:30,171,9
+01/05/2022 00:06:40,171,165
+01/05/2022 00:06:50,171,24
+01/05/2022 00:07:00,171,315
+01/05/2022 00:07:10,171,39
+01/05/2022 00:07:20,171,465
+01/05/2022 00:07:30,171,539
+01/05/2022 00:07:40,171,614
+01/05/2022 00:07:50,171,689
+01/05/2022 00:08:00,171,764
+01/05/2022 00:08:10,171,839
+01/05/2022 00:08:20,171,914
+01/05/2022 00:08:30,171,989
+01/05/2022 00:08:40,172,64
+01/05/2022 00:08:50,172,139
+01/05/2022 00:09:00,172,214
+01/05/2022 00:09:10,172,288
+01/05/2022 00:09:20,172,363
+01/05/2022 00:09:30,172,438
+01/05/2022 00:09:40,172,513
+01/05/2022 00:09:50,172,588
+01/05/2022 00:10:00,172,663
+01/05/2022 00:10:10,172,738
+01/05/2022 00:10:20,172,813
+01/05/2022 00:10:30,172,888
+01/05/2022 00:10:40,172,962
+01/05/2022 00:10:50,172,981
+01/05/2022 00:11:00,172,943
+01/05/2022 00:11:10,172,905
+01/05/2022 00:11:20,172,867
+01/05/2022 00:11:30,172,829
+01/05/2022 00:11:40,172,79
+01/05/2022 00:11:50,172,752
+01/05/2022 00:12:00,172,714
+01/05/2022 00:12:10,172,676
+01/05/2022 00:12:20,172,638
+01/05/2022 00:12:30,172,6
+01/05/2022 00:12:40,172,562
+01/05/2022 00:12:50,172,524
+01/05/2022 00:13:00,172,485
+01/05/2022 00:13:10,172,447
+01/05/2022 00:13:20,172,409
+01/05/2022 00:13:30,172,371
+01/05/2022 00:13:40,172,333
+01/05/2022 00:13:50,172,295
+01/05/2022 00:14:00,172,257
+01/05/2022 00:14:10,172,219
+01/05/2022 00:14:20,172,18
+01/05/2022 00:14:30,172,142
+01/05/2022 00:14:40,172,104
+01/05/2022 00:14:50,172,66
+01/05/2022 00:15:00,172,28
+01/05/2022 00:15:10,171,99
+01/05/2022 00:15:20,171,952
+01/05/2022 00:15:30,171,914
+01/05/2022 00:15:40,171,876
+01/05/2022 00:15:50,171,837
+01/05/2022 00:16:00,171,799
+01/05/2022 00:16:10,171,761
+01/05/2022 00:16:20,171,723
+01/05/2022 00:16:30,171,685
+01/05/2022 00:16:40,171,647
+01/05/2022 00:16:50,171,609
+01/05/2022 00:17:00,171,571
+01/05/2022 00:17:10,171,533
+01/05/2022 00:17:20,171,494
+01/05/2022 00:17:30,171,456
+01/05/2022 00:17:40,171,418
+01/05/2022 00:17:50,171,38
+01/05/2022 00:18:00,171,342
+01/05/2022 00:18:10,171,304
+01/05/2022 00:18:20,171,266
+01/05/2022 00:18:30,171,228
+01/05/2022 00:18:40,171,189
+01/05/2022 00:18:50,171,151
+01/05/2022 00:19:00,171,113
+01/05/2022 00:19:10,171,75
+01/05/2022 00:19:20,171,37
+01/05/2022 00:19:30,170,999
+01/05/2022 00:19:40,170,961
+01/05/2022 00:19:50,170,923
+01/05/2022 00:20:00,170,884
+01/05/2022 00:20:10,170,846
+01/05/2022 00:20:20,170,808
+01/05/2022 00:20:30,170,77
+01/05/2022 00:20:40,170,732
+01/05/2022 00:20:50,170,694
+01/05/2022 00:21:00,170,656
+01/05/2022 00:21:10,170,618
+01/05/2022 00:21:20,170,58
+01/05/2022 00:21:30,170,541
+01/05/2022 00:21:40,170,503
+01/05/2022 00:21:50,170,465
+01/05/2022 00:22:00,170,427
+01/05/2022 00:22:10,170,389
+01/05/2022 00:22:20,170,351
+01/05/2022 00:22:30,170,313
+01/05/2022 00:22:40,170,275
+01/05/2022 00:22:50,170,236
+01/05/2022 00:23:00,170,198
+01/05/2022 00:23:10,170,16
+01/05/2022 00:23:20,170,122
+01/05/2022 00:23:30,170,84
+01/05/2022 00:23:40,170,46
+01/05/2022 00:23:50,170,8
+01/05/2022 00:24:00,169,97
+01/05/2022 00:24:10,169,932
+01/05/2022 00:24:20,169,893
+01/05/2022 00:24:30,169,855
+01/05/2022 00:24:40,169,817
+01/05/2022 00:24:50,169,779
+01/05/2022 00:25:00,169,741
+01/05/2022 00:25:10,169,703
+01/05/2022 00:25:20,169,665
+01/05/2022 00:25:30,169,627
+01/05/2022 00:25:40,169,588
+01/05/2022 00:25:50,169,55
+01/05/2022 00:26:00,169,512
+01/05/2022 00:26:10,169,474
+01/05/2022 00:26:20,169,436
+01/05/2022 00:26:30,169,398
+01/05/2022 00:26:40,169,36
+01/05/2022 00:26:50,169,322
+01/05/2022 00:27:00,169,284
+01/05/2022 00:27:10,169,245
+01/05/2022 00:27:20,169,207
+01/05/2022 00:27:30,169,169
+01/05/2022 00:27:40,169,131
+01/05/2022 00:27:50,169,93
+01/05/2022 00:28:00,169,55
+01/05/2022 00:28:10,169,17
+01/05/2022 00:28:20,168,979
+01/05/2022 00:28:30,168,94
+01/05/2022 00:28:40,168,902
+01/05/2022 00:28:50,168,864
+01/05/2022 00:29:00,168,826
+01/05/2022 00:29:10,168,788
+01/05/2022 00:29:20,168,75
+01/05/2022 00:29:30,168,712
+01/05/2022 00:29:40,168,674
+01/05/2022 00:29:50,168,636
+01/05/2022 00:30:00,168,597
+01/05/2022 00:30:10,168,559
+01/05/2022 00:30:20,168,521
+01/05/2022 00:30:30,168,483
+01/05/2022 00:30:40,168,445
+01/05/2022 00:30:50,168,407
+01/05/2022 00:31:00,168,369
+01/05/2022 00:31:10,168,331
+01/05/2022 00:31:20,168,292
+01/05/2022 00:31:30,168,254
+01/05/2022 00:31:40,168,216
+01/05/2022 00:31:50,168,178
+01/05/2022 00:32:00,168,14
+01/05/2022 00:32:10,168,102
+01/05/2022 00:32:20,168,64
+01/05/2022 00:32:30,168,26
+01/05/2022 00:32:40,168,26
+01/05/2022 00:32:50,168,105
+01/05/2022 00:33:00,168,183
+01/05/2022 00:33:10,168,262
+01/05/2022 00:33:20,168,341
+01/05/2022 00:33:30,168,42
+01/05/2022 00:33:40,168,499
+01/05/2022 00:33:50,168,578
+01/05/2022 00:34:00,168,657
+01/05/2022 00:34:10,168,735
+01/05/2022 00:34:20,168,814
+01/05/2022 00:34:30,168,893
+01/05/2022 00:34:40,168,972
+01/05/2022 00:34:50,169,51
+01/05/2022 00:35:00,169,13
+01/05/2022 00:35:10,169,209
+01/05/2022 00:35:20,169,287
+01/05/2022 00:35:30,169,366
+01/05/2022 00:35:40,169,445
+01/05/2022 00:35:50,169,524
+01/05/2022 00:36:00,169,603
+01/05/2022 00:36:10,169,682
+01/05/2022 00:36:20,169,761
+01/05/2022 00:36:30,169,839
+01/05/2022 00:36:40,169,918
+01/05/2022 00:36:50,169,997
+01/05/2022 00:37:00,170,76
+01/05/2022 00:37:10,170,155
+01/05/2022 00:37:20,170,234
+01/05/2022 00:37:30,170,312
+01/05/2022 00:37:40,170,391
+01/05/2022 00:37:50,170,47
+01/05/2022 00:38:00,170,549
+01/05/2022 00:38:10,170,628
+01/05/2022 00:38:20,170,707
+01/05/2022 00:38:30,170,786
+01/05/2022 00:38:40,170,864
+01/05/2022 00:38:50,170,943
+01/05/2022 00:39:00,170,993
+01/05/2022 00:39:10,170,967
+01/05/2022 00:39:20,170,942
+01/05/2022 00:39:30,170,917
+01/05/2022 00:39:40,170,891
+01/05/2022 00:39:50,170,866
+01/05/2022 00:40:00,170,841
+01/05/2022 00:40:10,170,815
+01/05/2022 00:40:20,170,79
+01/05/2022 00:40:30,170,764
+01/05/2022 00:40:40,170,739
+01/05/2022 00:40:50,170,714
+01/05/2022 00:41:00,170,688
+01/05/2022 00:41:10,170,663
+01/05/2022 00:41:20,170,637
+01/05/2022 00:41:30,170,612
+01/05/2022 00:41:40,170,587
+01/05/2022 00:41:50,170,561
+01/05/2022 00:42:00,170,536
+01/05/2022 00:42:10,170,51
+01/05/2022 00:42:20,170,485
+01/05/2022 00:42:30,170,46
+01/05/2022 00:42:40,170,434
+01/05/2022 00:42:50,170,409
+01/05/2022 00:43:00,170,384
+01/05/2022 00:43:10,170,358
+01/05/2022 00:43:20,170,333
+01/05/2022 00:43:30,170,307
+01/05/2022 00:43:40,170,282
+01/05/2022 00:43:50,170,257
+01/05/2022 00:44:00,170,231
+01/05/2022 00:44:10,170,206
+01/05/2022 00:44:20,170,18
+01/05/2022 00:44:30,170,155
+01/05/2022 00:44:40,170,13
+01/05/2022 00:44:50,170,104
+01/05/2022 00:45:00,170,79
+01/05/2022 00:45:10,170,54
+01/05/2022 00:45:20,170,28
+01/05/2022 00:45:30,170,3
+01/05/2022 00:45:40,169,977
+01/05/2022 00:45:50,169,952
+01/05/2022 00:46:00,169,927
+01/05/2022 00:46:10,169,901
+01/05/2022 00:46:20,169,876
+01/05/2022 00:46:30,169,85
+01/05/2022 00:46:40,169,825
+01/05/2022 00:46:50,169,8
+01/05/2022 00:47:00,169,774
+01/05/2022 00:47:10,169,749
+01/05/2022 00:47:20,169,723
+01/05/2022 00:47:30,169,698
+01/05/2022 00:47:40,169,673
+01/05/2022 00:47:50,169,647
+01/05/2022 00:48:00,169,622
+01/05/2022 00:48:10,169,597
+01/05/2022 00:48:20,169,571
+01/05/2022 00:48:30,169,546
+01/05/2022 00:48:40,169,52
+01/05/2022 00:48:50,169,495
+01/05/2022 00:49:00,169,47
+01/05/2022 00:49:10,169,444
+01/05/2022 00:49:20,169,419
+01/05/2022 00:49:30,169,393
+01/05/2022 00:49:40,169,368
+01/05/2022 00:49:50,169,343
+01/05/2022 00:50:00,169,317
+01/05/2022 00:50:10,169,292
+01/05/2022 00:50:20,169,266
+01/05/2022 00:50:30,169,241
+01/05/2022 00:50:40,169,216
+01/05/2022 00:50:50,169,19
+01/05/2022 00:51:00,169,165
+01/05/2022 00:51:10,169,14
+01/05/2022 00:51:20,169,114
+01/05/2022 00:51:30,169,89
+01/05/2022 00:51:40,169,63
+01/05/2022 00:51:50,169,38
+01/05/2022 00:52:00,169,13
+01/05/2022 00:52:10,168,987
+01/05/2022 00:52:20,168,962
+01/05/2022 00:52:30,168,936
+01/05/2022 00:52:40,168,911
+01/05/2022 00:52:50,168,886
+01/05/2022 00:53:00,168,86
+01/05/2022 00:53:10,168,835
+01/05/2022 00:53:20,168,809
+01/05/2022 00:53:30,168,784
+01/05/2022 00:53:40,168,759
+01/05/2022 00:53:50,168,733
+01/05/2022 00:54:00,168,708
+01/05/2022 00:54:10,168,683
+01/05/2022 00:54:20,168,657
+01/05/2022 00:54:30,168,632
+01/05/2022 00:54:40,168,606
+01/05/2022 00:54:50,168,581
+01/05/2022 00:55:00,168,556
+01/05/2022 00:55:10,168,53
+01/05/2022 00:55:20,168,505
+01/05/2022 00:55:30,168,479
+01/05/2022 00:55:40,168,454
+01/05/2022 00:55:50,168,429
+01/05/2022 00:56:00,168,403
+01/05/2022 00:56:10,168,378
+01/05/2022 00:56:20,168,352
+01/05/2022 00:56:30,168,327
+01/05/2022 00:56:40,168,302
+01/05/2022 00:56:50,168,276
+01/05/2022 00:57:00,168,251
+01/05/2022 00:57:10,168,226
+01/05/2022 00:57:20,168,2
+01/05/2022 00:57:30,168,175
+01/05/2022 00:57:40,168,149
+01/05/2022 00:57:50,168,124
+01/05/2022 00:58:00,168,99
+01/05/2022 00:58:10,168,73
+01/05/2022 00:58:20,168,48
+01/05/2022 00:58:30,168,22
+01/05/2022 00:58:40,167,76
+01/05/2022 00:58:50,160,151
+01/05/2022 00:59:00,161,484
+01/05/2022 00:59:10,162,817
+01/05/2022 00:59:20,164,281
+01/05/2022 00:59:30,166,777
+01/05/2022 00:59:40,167,148
+01/05/2022 00:59:50,148,45
+01/05/2022 01:00:00,117,525
+01/05/2022 01:00:10,105,3
+01/05/2022 01:00:20,105,315
+01/05/2022 01:00:30,105,6
+01/05/2022 01:00:40,105,886
+01/05/2022 01:00:50,106,171
+01/05/2022 01:01:00,106,456
+01/05/2022 01:01:10,106,742
+01/05/2022 01:01:20,107,698
+01/05/2022 01:01:30,115,81
+01/05/2022 01:01:40,122,464
+01/05/2022 01:01:50,129,847
+01/05/2022 01:02:00,137,231
+01/05/2022 01:02:10,144,138
+01/05/2022 01:02:20,145,801
+01/05/2022 01:02:30,147,464
+01/05/2022 01:02:40,149,835
+01/05/2022 01:02:50,160,808
+01/05/2022 01:03:00,171,2
+01/05/2022 01:03:10,171,36
+01/05/2022 01:03:20,171,7
+01/05/2022 01:03:30,171,103
+01/05/2022 01:03:40,171,137
+01/05/2022 01:03:50,171,171
+01/05/2022 01:04:00,171,204
+01/05/2022 01:04:10,171,238
+01/05/2022 01:04:20,171,272
+01/05/2022 01:04:30,171,305
+01/05/2022 01:04:40,171,339
+01/05/2022 01:04:50,171,372
+01/05/2022 01:05:00,171,406
+01/05/2022 01:05:10,171,44
+01/05/2022 01:05:20,171,473
+01/05/2022 01:05:30,171,507
+01/05/2022 01:05:40,171,541
+01/05/2022 01:05:50,171,574
+01/05/2022 01:06:00,171,608
+01/05/2022 01:06:10,171,642
+01/05/2022 01:06:20,171,675
+01/05/2022 01:06:30,171,709
+01/05/2022 01:06:40,171,743
+01/05/2022 01:06:50,171,776
+01/05/2022 01:07:00,171,81
+01/05/2022 01:07:10,171,844
+01/05/2022 01:07:20,171,877
+01/05/2022 01:07:30,171,911
+01/05/2022 01:07:40,171,944
+01/05/2022 01:07:50,171,978
+01/05/2022 01:08:00,172,12
+01/05/2022 01:08:10,172,45
+01/05/2022 01:08:20,172,79
+01/05/2022 01:08:30,172,113
+01/05/2022 01:08:40,172,146
+01/05/2022 01:08:50,172,18
+01/05/2022 01:09:00,172,214
+01/05/2022 01:09:10,172,247
+01/05/2022 01:09:20,172,281
+01/05/2022 01:09:30,172,315
+01/05/2022 01:09:40,172,348
+01/05/2022 01:09:50,172,382
+01/05/2022 01:10:00,172,415
+01/05/2022 01:10:10,172,449
+01/05/2022 01:10:20,172,483
+01/05/2022 01:10:30,172,516
+01/05/2022 01:10:40,172,55
+01/05/2022 01:10:50,172,584
+01/05/2022 01:11:00,172,617
+01/05/2022 01:11:10,172,651
+01/05/2022 01:11:20,172,685
+01/05/2022 01:11:30,172,718
+01/05/2022 01:11:40,172,752
+01/05/2022 01:11:50,172,786
+01/05/2022 01:12:00,172,819
+01/05/2022 01:12:10,172,853
+01/05/2022 01:12:20,172,887
+01/05/2022 01:12:30,172,92
+01/05/2022 01:12:40,172,954
+01/05/2022 01:12:50,172,987
+01/05/2022 01:13:00,173,21
+01/05/2022 01:13:10,173,55
+01/05/2022 01:13:20,173,88
+01/05/2022 01:13:30,173,122
+01/05/2022 01:13:40,173,156
+01/05/2022 01:13:50,173,189
+01/05/2022 01:14:00,173,223
+01/05/2022 01:14:10,173,257
+01/05/2022 01:14:20,173,29
+01/05/2022 01:14:30,173,324
+01/05/2022 01:14:40,173,358
+01/05/2022 01:14:50,173,391
+01/05/2022 01:15:00,173,425
+01/05/2022 01:15:10,173,458
+01/05/2022 01:15:20,173,492
+01/05/2022 01:15:30,173,526
+01/05/2022 01:15:40,173,559
+01/05/2022 01:15:50,173,593
+01/05/2022 01:16:00,173,627
+01/05/2022 01:16:10,173,66
+01/05/2022 01:16:20,173,694
+01/05/2022 01:16:30,173,728
+01/05/2022 01:16:40,173,761
+01/05/2022 01:16:50,173,795
+01/05/2022 01:17:00,173,829
+01/05/2022 01:17:10,173,862
+01/05/2022 01:17:20,173,896
+01/05/2022 01:17:30,173,93
+01/05/2022 01:17:40,173,963
+01/05/2022 01:17:50,173,997
+01/05/2022 01:18:00,174,103
+01/05/2022 01:18:10,174,218
+01/05/2022 01:18:20,174,332
+01/05/2022 01:18:30,174,446
+01/05/2022 01:18:40,174,56
+01/05/2022 01:18:50,174,674
+01/05/2022 01:19:00,174,788
+01/05/2022 01:19:10,174,902
+01/05/2022 01:19:20,175,17
+01/05/2022 01:19:30,175,131
+01/05/2022 01:19:40,175,245
+01/05/2022 01:19:50,175,359
+01/05/2022 01:20:00,175,473
+01/05/2022 01:20:10,175,587
+01/05/2022 01:20:20,175,701
+01/05/2022 01:20:30,175,816
+01/05/2022 01:20:40,175,93
+01/05/2022 01:20:50,176,44
+01/05/2022 01:21:00,176,158
+01/05/2022 01:21:10,176,272
+01/05/2022 01:21:20,176,386
+01/05/2022 01:21:30,176,501
+01/05/2022 01:21:40,176,615
+01/05/2022 01:21:50,176,729
+01/05/2022 01:22:00,176,843
+01/05/2022 01:22:10,176,957
+01/05/2022 01:22:20,177,71
+01/05/2022 01:22:30,177,185
+01/05/2022 01:22:40,177,3
+01/05/2022 01:22:50,177,414
+01/05/2022 01:23:00,177,528
+01/05/2022 01:23:10,177,642
+01/05/2022 01:23:20,177,756
+01/05/2022 01:23:30,177,87
+01/05/2022 01:23:40,177,984
+01/05/2022 01:23:50,178,7
+01/05/2022 01:24:00,178,15
+01/05/2022 01:24:10,178,24
+01/05/2022 01:24:20,178,32
+01/05/2022 01:24:30,178,4
+01/05/2022 01:24:40,178,48
+01/05/2022 01:24:50,178,57
+01/05/2022 01:25:00,178,65
+01/05/2022 01:25:10,178,73
+01/05/2022 01:25:20,178,81
+01/05/2022 01:25:30,178,9
+01/05/2022 01:25:40,178,98
+01/05/2022 01:25:50,178,106
+01/05/2022 01:26:00,178,114
+01/05/2022 01:26:10,178,123
+01/05/2022 01:26:20,178,131
+01/05/2022 01:26:30,178,139
+01/05/2022 01:26:40,178,147
+01/05/2022 01:26:50,178,156
+01/05/2022 01:27:00,178,164
+01/05/2022 01:27:10,178,172
+01/05/2022 01:27:20,178,18
+01/05/2022 01:27:30,178,189
+01/05/2022 01:27:40,178,197
+01/05/2022 01:27:50,178,205
+01/05/2022 01:28:00,178,213
+01/05/2022 01:28:10,178,222
+01/05/2022 01:28:20,178,23
+01/05/2022 01:28:30,178,238
+01/05/2022 01:28:40,178,246
+01/05/2022 01:28:50,178,255
+01/05/2022 01:29:00,178,263
+01/05/2022 01:29:10,178,271
+01/05/2022 01:29:20,178,279
+01/05/2022 01:29:30,178,288
+01/05/2022 01:29:40,178,296
+01/05/2022 01:29:50,178,304
+01/05/2022 01:30:00,178,312
+01/05/2022 01:30:10,178,321
+01/05/2022 01:30:20,178,329
+01/05/2022 01:30:30,178,337
+01/05/2022 01:30:40,178,345
+01/05/2022 01:30:50,178,354
+01/05/2022 01:31:00,178,362
+01/05/2022 01:31:10,178,37
+01/05/2022 01:31:20,178,378
+01/05/2022 01:31:30,178,387
+01/05/2022 01:31:40,178,395
+01/05/2022 01:31:50,178,403
+01/05/2022 01:32:00,178,411
+01/05/2022 01:32:10,178,42
+01/05/2022 01:32:20,178,428
+01/05/2022 01:32:30,178,436
+01/05/2022 01:32:40,178,444
+01/05/2022 01:32:50,178,453
+01/05/2022 01:33:00,178,461
+01/05/2022 01:33:10,178,469
+01/05/2022 01:33:20,178,477
+01/05/2022 01:33:30,178,486
+01/05/2022 01:33:40,178,494
+01/05/2022 01:33:50,178,502
+01/05/2022 01:34:00,178,51
+01/05/2022 01:34:10,178,519
+01/05/2022 01:34:20,178,527
+01/05/2022 01:34:30,178,535
+01/05/2022 01:34:40,178,543
+01/05/2022 01:34:50,178,552
+01/05/2022 01:35:00,178,56
+01/05/2022 01:35:10,178,568
+01/05/2022 01:35:20,178,576
+01/05/2022 01:35:30,178,585
+01/05/2022 01:35:40,178,593
+01/05/2022 01:35:50,178,601
+01/05/2022 01:36:00,178,609
+01/05/2022 01:36:10,178,618
+01/05/2022 01:36:20,178,626
+01/05/2022 01:36:30,178,634
+01/05/2022 01:36:40,178,642
+01/05/2022 01:36:50,178,651
+01/05/2022 01:37:00,178,659
+01/05/2022 01:37:10,178,667
+01/05/2022 01:37:20,178,675
+01/05/2022 01:37:30,178,684
+01/05/2022 01:37:40,178,692
+01/05/2022 01:37:50,178,7
+01/05/2022 01:38:00,178,708
+01/05/2022 01:38:10,178,717
+01/05/2022 01:38:20,178,725
+01/05/2022 01:38:30,178,733
+01/05/2022 01:38:40,178,741
+01/05/2022 01:38:50,178,75
+01/05/2022 01:39:00,178,758
+01/05/2022 01:39:10,178,766
+01/05/2022 01:39:20,178,774
+01/05/2022 01:39:30,178,783
+01/05/2022 01:39:40,178,791
+01/05/2022 01:39:50,178,799
+01/05/2022 01:40:00,178,807
+01/05/2022 01:40:10,178,816
+01/05/2022 01:40:20,178,824
+01/05/2022 01:40:30,178,832
+01/05/2022 01:40:40,178,84
+01/05/2022 01:40:50,178,849
+01/05/2022 01:41:00,178,857
+01/05/2022 01:41:10,178,865
+01/05/2022 01:41:20,178,873
+01/05/2022 01:41:30,178,882
+01/05/2022 01:41:40,178,89
+01/05/2022 01:41:50,178,898
+01/05/2022 01:42:00,178,906
+01/05/2022 01:42:10,178,915
+01/05/2022 01:42:20,178,923
+01/05/2022 01:42:30,178,931
+01/05/2022 01:42:40,178,939
+01/05/2022 01:42:50,178,948
+01/05/2022 01:43:00,178,956
+01/05/2022 01:43:10,178,964
+01/05/2022 01:43:20,178,972
+01/05/2022 01:43:30,178,981
+01/05/2022 01:43:40,178,989
+01/05/2022 01:43:50,178,997
+01/05/2022 01:44:00,169,147
+01/05/2022 01:44:10,148,934
+01/05/2022 01:44:20,119,458
+01/05/2022 01:44:30,108,326
+01/05/2022 01:44:40,108,825
+01/05/2022 01:44:50,109,324
+01/05/2022 01:45:00,109,824
+01/05/2022 01:45:10,110,323
+01/05/2022 01:45:20,110,822
+01/05/2022 01:45:30,123,3
+01/05/2022 01:45:40,141,628
+01/05/2022 01:45:50,160,252
+01/05/2022 01:46:00,169,863
+01/05/2022 01:46:10,174,353
+01/05/2022 01:46:20,176,8
+01/05/2022 01:46:30,176,19
+01/05/2022 01:46:40,176,31
+01/05/2022 01:46:50,176,43
+01/05/2022 01:47:00,176,55
+01/05/2022 01:47:10,176,67
+01/05/2022 01:47:20,176,79
+01/05/2022 01:47:30,176,91
--- a/docs/data-1749222138290.csv
+++ b/docs/data-1749222138290.csv
--- a/docs/scenarios.md
+++ b/docs/scenarios.md
@@ -0,0 +1,66 @@
+# E2E Test Scenarios
+
+This document maps the workflow scenarios tested in the E2E suite to their corresponding JSON input files and expected behaviors.
+
+## Infrastructure (second-pass review)
+
+- **Containers:** PostgreSQL, MinIO, MongoDB, and Gitea via testcontainers; real clients and `Activities` code paths.
+- **MLflow:** `file://` tracking URI (real SDK, no remote server).
+- **Temporal:** `WorkflowEnvironment.start_time_skipping()` — official temporalio test runtime; workflows and activities are not stubbed.
+- **Logging/metrics:** `get_logger` + `MetricsController` (sientia_do); no `unittest.mock` for observability in `e2e/conftest.py`.
+- **Unit tests** under `tests/` may still use mocks where appropriate; that policy is separate from this E2E suite.
+
+## 1. TrainModel Workflow (`test_train_model_workflow.py`)
+
+### 1.1 Happy Paths (Successful execution)
+
+| Test Function | Input JSON | Expected Status | Description |
+|---|---|---|---|
+| `test_scenario_1_1_1_linear_regression_basic` | `01-linear-regression-basic.json` | `TRAINING_SUCCESS` | Basic linear regression without scaler. Verifies end-to-end pipeline. |
+| `test_scenario_1_1_2_linear_regression_with_scaler` | `02-linear-regression-with-scaler.json` | `TRAINING_SUCCESS` | Linear regression with `Standard Scaler`. |
+| `test_scenario_1_1_3_polynomial_regression_degree2_with_scaler` | `03-polynomial-regression-degree2.json` | `TRAINING_SUCCESS` | Polynomial regression (degree 2) with Standard Scaler. |
+| `test_scenario_1_1_4_polynomial_regression_degree3_with_scaler` | `04-polynomial-regression-degree3.json` | `TRAINING_SUCCESS` | Polynomial regression (degree 3) with Standard Scaler. |
+| `test_scenario_1_1_5_linear_regression_with_lags` | `05-linear-regression-with-lags.json` | `TRAINING_SUCCESS` | Linear regression with `lag_train`/`lag_val` per variable. |
+| `test_scenario_1_1_6_linear_regression_nan_interpolation` | `06-linear-regression-nan-interpolation.json` | `TRAINING_SUCCESS` | Linear regression with `nan_treatment='linear interpolation'`. |
+| `test_scenario_1_1_7_linear_regression_static_window_removal` | `07-linear-regression-static-window-removal.json` | `TRAINING_SUCCESS` | `rem_static_win=true` with default `static_threshold`. |
+| `test_scenario_1_1_8_linear_regression_with_limits` | `08-linear-regression-with-limits.json` | `TRAINING_SUCCESS` | `support_filters` with `min`/`max` per variable. |
+| `test_scenario_1_1_9_polynomial_degree2_scaler_and_lags` | `09-polynomial-degree2-with-scaler-and-lags.json` | `TRAINING_SUCCESS` | Polynomial (degree 2), Standard Scaler, and lags. |
+| `test_scenario_1_1_10_linear_regression_with_ar_opt_params` | `10-linear-regression-with-ar.json` | `TRAINING_SUCCESS` | `opt_params.include_ar=true` (placeholder for future AR behavior). |
+| `test_scenario_1_1_11_linear_regression_static_threshold_custom` | `11-linear-regression-static-threshold-custom.json` | `TRAINING_SUCCESS` | `rem_static_win=true` with custom `static_threshold`. |
+| `test_scenario_1_1_12_alternate_date_format_dd_mm_yyyy` | `12-angular-test-date-format.json` | `TRAINING_SUCCESS` | `date_column=DATA`, `dd/MM/yyyy` format, object `training_data_dd_mm_yyyy.csv`. |
+| `test_scenario_1_1_13_alternate_csv_narrow_date_window` | `13-angular-test-double-date-column.json` | `TRAINING_SUCCESS` | Same alternate CSV with a bounded `start_date`/`end_date` window. |
+| `test_scenario_1_1_14_polynomial_with_support_filters` | `14-angular-test-polynomial-support-filters.json` | `TRAINING_SUCCESS` | Polynomial (degree 4), scaler, `upper_line`/`lower_line` support filters. |
+| `test_scenario_1_1_15_linear_regression_custom_target_column_name` | `15-linear-regression-custom-target-column.json` | `TRAINING_SUCCESS` | Custom `target_variable` column name (not literal ``target``); Evidently/report columns must match. |
+| `test_scenario_1_1_16_naive_timestamp_header_column` | `16-linear-regression-naive-timestamp-header.json` | `TRAINING_SUCCESS` | `date_column`=`Timestamp`, naive CSV `training_data_timestamp_naive.csv`. |
+| `test_scenario_1_1_17_linear_regression_blank_timestamp_row_dropped` | `17-linear-regression-blank-timestamp-row.json` | `TRAINING_SUCCESS` | One empty timestamp cell; row dropped before index. |
+
+### 1.2 Error Paths
+
+| Test Function | Input JSON | Expected Status | Description |
+|---|---|---|---|
+| `test_scenario_1_2_1_minio_file_not_found` | `01-linear-regression-basic.json` | `TRAINING_ERROR` | MinIO file does not exist. Workflow fails during file download. |
+| `test_scenario_1_2_2_experiment_run_id_not_in_db` | `01-linear-regression-basic.json` | N/A (raises Exception) | `experiment_run_id` does not exist in DB. Workflow fails immediately on status update attempt. |
+
+## 2. Parameter Validation (`test_train_model_validation.py`)
+
+These scenarios test the business rule validations inside `validate_train_params`. All are expected to terminate with `ORCHESTRATOR_VALIDATION_ERROR`.
+
+| Test Function | Modification | Expected Error Substring |
+|---|---|---|
+| `test_scenario_2_1_1_train_size_out_of_range` | `train_size = 5` | `'train_size'` |
+| `test_scenario_2_1_2_empty_variable_columns` | `variable_columns = []` | `'variable_columns'` |
+| `test_scenario_2_1_3_invalid_date_format` | `date_format = 'INVALID'` | `'date_format'` |
+| `test_scenario_2_1_4_whitespace_only_model_name` | `model_name = '   '` | `'model_name'` |
+| `test_scenario_2_1_5_unknown_model_type` | `model_type = 'totally_unknown_model'` | `'totally_unknown_model'` |
+| `test_scenario_2_1_6_missing_target_variable` | `target_variable = ''` | `'target_variable'` |
+| `test_scenario_2_1_7_missing_experiment_run_id` | Missing `experiment_run_id` | N/A (raises ValueError immediately) |
+| `test_scenario_2_1_8_missing_date_column` | Missing `date_column` | N/A (raises ValueError immediately) |
+| `test_scenario_2_1_9_whitespace_date_column` | `date_column = '   '` | `'date_column'` |
+
+## 3. CleanupFiles Workflow (`test_cleanup_files_workflow.py`)
+
+| Test Function | Description |
+|---|---|
+| `test_scenario_3_1_1_cleanup_with_no_temp_dirs` | Temp directory is empty. Activity completes without error. |
+| `test_scenario_3_1_2_cleanup_removes_old_temp_dirs` | Two stale directories matching `name_YYYYMMDD_HHMMSS_microseconds` are removed when older than retention. |
+| `test_scenario_3_1_3_cleanup_nonexistent_temp_path` | Target path does not exist. Handled gracefully without error. |
--- a/docs/test-model-data.csv
+++ b/docs/test-model-data.csv
--- a/docs/test-scenarios/01-linear-regression-basic.json
+++ b/docs/test-scenarios/01-linear-regression-basic.json
@@ -0,0 +1,40 @@
+{
+  "_description": "Cenário básico de regressão linear sem scaler",
+  "experiment_run_id": 1001,
+  "variable_columns": [
+    "303-WIT-200(Value)"
+  ],
+  "target_variable": "03CV020/CORRENTE_N_M1_PV(Value)",
+  "bucket_name": "model-training",
+  "file_name": "training_data.csv",
+  "line_separator": ",",
+  "decimal_separator": ".",
+  "date_column": "timestamp",
+  "date_format": "yyyy-MM-dd HH:mm:ss",
+  "train_size": 80,
+  "shuffle": true,
+  "random_state": 42,
+  "model_name": "Linear Regression",
+  "model_type": "linear_regression",
+  "data_model_kwargs": {
+    "lag_train": {
+      "303-WIT-200(Value)": 0
+    },
+    "lag_val": {
+      "303-WIT-200(Value)": 0
+    },
+    "nan_treatment": "drop",
+    "rem_static_win": false,
+    "static_threshold": null,
+    "start_date": null,
+    "end_date": null,
+    "support_filters": {},
+    "removed_intervals": []
+  },
+  "model_kwargs": {
+    "degree": 1,
+    "interaction_only": false,
+    "scaler_name": "None"
+  },
+  "opt_params": {}
+}
--- a/docs/test-scenarios/02-linear-regression-with-scaler.json
+++ b/docs/test-scenarios/02-linear-regression-with-scaler.json
@@ -0,0 +1,40 @@
+{
+  "_description": "Regressão linear com Standard Scaler habilitado",
+  "experiment_run_id": 1002,
+  "variable_columns": [
+    "303-WIT-200(Value)"
+  ],
+  "target_variable": "03CV020/CORRENTE_N_M1_PV(Value)",
+  "bucket_name": "model-training",
+  "file_name": "training_data.csv",
+  "line_separator": ",",
+  "decimal_separator": ".",
+  "date_column": "timestamp",
+  "date_format": "yyyy-MM-dd HH:mm:ss",
+  "train_size": 80,
+  "shuffle": true,
+  "random_state": 42,
+  "model_name": "Linear Regression",
+  "model_type": "linear_regression",
+  "data_model_kwargs": {
+    "lag_train": {
+      "303-WIT-200(Value)": 0
+    },
+    "lag_val": {
+      "303-WIT-200(Value)": 0
+    },
+    "nan_treatment": "drop",
+    "rem_static_win": false,
+    "static_threshold": null,
+    "start_date": null,
+    "end_date": null,
+    "support_filters": {},
+    "removed_intervals": []
+  },
+  "model_kwargs": {
+    "degree": 1,
+    "interaction_only": false,
+    "scaler_name": "Standard Scaler"
+  },
+  "opt_params": {}
+}
--- a/docs/test-scenarios/03-polynomial-regression-degree2.json
+++ b/docs/test-scenarios/03-polynomial-regression-degree2.json
@@ -0,0 +1,40 @@
+{
+  "_description": "Regressão polinomial de grau 2 com scaler (obrigatório para evitar overflow)",
+  "experiment_run_id": 1003,
+  "variable_columns": [
+    "303-WIT-200(Value)"
+  ],
+  "target_variable": "03CV020/CORRENTE_N_M1_PV(Value)",
+  "bucket_name": "model-training",
+  "file_name": "training_data.csv",
+  "line_separator": ",",
+  "decimal_separator": ".",
+  "date_column": "timestamp",
+  "date_format": "yyyy-MM-dd HH:mm:ss",
+  "train_size": 80,
+  "shuffle": true,
+  "random_state": 42,
+  "model_name": "Polynomial Regression",
+  "model_type": "polynomial_regression",
+  "data_model_kwargs": {
+    "lag_train": {
+      "303-WIT-200(Value)": 0
+    },
+    "lag_val": {
+      "303-WIT-200(Value)": 0
+    },
+    "nan_treatment": "drop",
+    "rem_static_win": false,
+    "static_threshold": null,
+    "start_date": null,
+    "end_date": null,
+    "support_filters": {},
+    "removed_intervals": []
+  },
+  "model_kwargs": {
+    "degree": 2,
+    "interaction_only": false,
+    "scaler_name": "Standard Scaler"
+  },
+  "opt_params": {}
+}
--- a/docs/test-scenarios/04-polynomial-regression-degree3.json
+++ b/docs/test-scenarios/04-polynomial-regression-degree3.json
@@ -0,0 +1,40 @@
+{
+  "_description": "Regressão polinomial de grau 3 com scaler",
+  "experiment_run_id": 1004,
+  "variable_columns": [
+    "303-WIT-200(Value)"
+  ],
+  "target_variable": "03CV020/CORRENTE_N_M1_PV(Value)",
+  "bucket_name": "model-training",
+  "file_name": "training_data.csv",
+  "line_separator": ",",
+  "decimal_separator": ".",
+  "date_column": "timestamp",
+  "date_format": "yyyy-MM-dd HH:mm:ss",
+  "train_size": 80,
+  "shuffle": true,
+  "random_state": 42,
+  "model_name": "Polynomial Regression",
+  "model_type": "polynomial_regression",
+  "data_model_kwargs": {
+    "lag_train": {
+      "303-WIT-200(Value)": 0
+    },
+    "lag_val": {
+      "303-WIT-200(Value)": 0
+    },
+    "nan_treatment": "drop",
+    "rem_static_win": false,
+    "static_threshold": null,
+    "start_date": null,
+    "end_date": null,
+    "support_filters": {},
+    "removed_intervals": []
+  },
+  "model_kwargs": {
+    "degree": 3,
+    "interaction_only": false,
+    "scaler_name": "Standard Scaler"
+  },
+  "opt_params": {}
+}
--- a/docs/test-scenarios/05-linear-regression-with-lags.json
+++ b/docs/test-scenarios/05-linear-regression-with-lags.json
@@ -0,0 +1,40 @@
+{
+  "_description": "Regressão linear com lags de treino e validação",
+  "experiment_run_id": 1005,
+  "variable_columns": [
+    "303-WIT-200(Value)"
+  ],
+  "target_variable": "03CV020/CORRENTE_N_M1_PV(Value)",
+  "bucket_name": "model-training",
+  "file_name": "training_data.csv",
+  "line_separator": ",",
+  "decimal_separator": ".",
+  "date_column": "timestamp",
+  "date_format": "yyyy-MM-dd HH:mm:ss",
+  "train_size": 80,
+  "shuffle": true,
+  "random_state": 42,
+  "model_name": "Linear Regression",
+  "model_type": "linear_regression",
+  "data_model_kwargs": {
+    "lag_train": {
+      "303-WIT-200(Value)": 5
+    },
+    "lag_val": {
+      "303-WIT-200(Value)": 3
+    },
+    "nan_treatment": "drop",
+    "rem_static_win": false,
+    "static_threshold": null,
+    "start_date": null,
+    "end_date": null,
+    "support_filters": {},
+    "removed_intervals": []
+  },
+  "model_kwargs": {
+    "degree": 1,
+    "interaction_only": false,
+    "scaler_name": "None"
+  },
+  "opt_params": {}
+}
--- a/docs/test-scenarios/06-linear-regression-nan-interpolation.json
+++ b/docs/test-scenarios/06-linear-regression-nan-interpolation.json
@@ -0,0 +1,40 @@
+{
+  "_description": "Regressão linear com tratamento de NaN por interpolação linear",
+  "experiment_run_id": 1006,
+  "variable_columns": [
+    "303-WIT-200(Value)"
+  ],
+  "target_variable": "03CV020/CORRENTE_N_M1_PV(Value)",
+  "bucket_name": "model-training",
+  "file_name": "training_data.csv",
+  "line_separator": ",",
+  "decimal_separator": ".",
+  "date_column": "timestamp",
+  "date_format": "yyyy-MM-dd HH:mm:ss",
+  "train_size": 80,
+  "shuffle": true,
+  "random_state": 42,
+  "model_name": "Linear Regression",
+  "model_type": "linear_regression",
+  "data_model_kwargs": {
+    "lag_train": {
+      "303-WIT-200(Value)": 0
+    },
+    "lag_val": {
+      "303-WIT-200(Value)": 0
+    },
+    "nan_treatment": "linear interpolation",
+    "rem_static_win": false,
+    "static_threshold": null,
+    "start_date": null,
+    "end_date": null,
+    "support_filters": {},
+    "removed_intervals": []
+  },
+  "model_kwargs": {
+    "degree": 1,
+    "interaction_only": false,
+    "scaler_name": "None"
+  },
+  "opt_params": {}
+}
--- a/docs/test-scenarios/07-linear-regression-static-window-removal.json
+++ b/docs/test-scenarios/07-linear-regression-static-window-removal.json
@@ -0,0 +1,40 @@
+{
+  "_description": "Regressão linear com remoção de janelas estáticas",
+  "experiment_run_id": 1007,
+  "variable_columns": [
+    "303-WIT-200(Value)"
+  ],
+  "target_variable": "03CV020/CORRENTE_N_M1_PV(Value)",
+  "bucket_name": "model-training",
+  "file_name": "training_data.csv",
+  "line_separator": ",",
+  "decimal_separator": ".",
+  "date_column": "timestamp",
+  "date_format": "yyyy-MM-dd HH:mm:ss",
+  "train_size": 80,
+  "shuffle": true,
+  "random_state": 42,
+  "model_name": "Linear Regression",
+  "model_type": "linear_regression",
+  "data_model_kwargs": {
+    "lag_train": {
+      "303-WIT-200(Value)": 0
+    },
+    "lag_val": {
+      "303-WIT-200(Value)": 0
+    },
+    "nan_treatment": "drop",
+    "rem_static_win": true,
+    "static_threshold": null,
+    "start_date": null,
+    "end_date": null,
+    "support_filters": {},
+    "removed_intervals": []
+  },
+  "model_kwargs": {
+    "degree": 1,
+    "interaction_only": false,
+    "scaler_name": "None"
+  },
+  "opt_params": {}
+}
--- a/docs/test-scenarios/08-linear-regression-with-limits.json
+++ b/docs/test-scenarios/08-linear-regression-with-limits.json
@@ -0,0 +1,45 @@
+{
+  "_description": "Regressão linear com limites inferior e superior para variáveis",
+  "experiment_run_id": 1008,
+  "variable_columns": [
+    "303-WIT-200(Value)"
+  ],
+  "target_variable": "03CV020/CORRENTE_N_M1_PV(Value)",
+  "bucket_name": "model-training",
+  "file_name": "training_data.csv",
+  "line_separator": ",",
+  "decimal_separator": ".",
+  "date_column": "timestamp",
+  "date_format": "yyyy-MM-dd HH:mm:ss",
+  "train_size": 80,
+  "shuffle": true,
+  "random_state": 42,
+  "model_name": "Linear Regression",
+  "model_type": "linear_regression",
+  "data_model_kwargs": {
+    "lag_train": {
+      "303-WIT-200(Value)": 0
+    },
+    "lag_val": {
+      "303-WIT-200(Value)": 0
+    },
+    "nan_treatment": "drop",
+    "rem_static_win": false,
+    "static_threshold": null,
+    "start_date": null,
+    "end_date": null,
+    "support_filters": {
+      "303-WIT-200(Value)": {
+        "min": 0.0,
+        "max": 1000.0
+      }
+    },
+    "removed_intervals": []
+  },
+  "model_kwargs": {
+    "degree": 1,
+    "interaction_only": false,
+    "scaler_name": "None"
+  },
+  "opt_params": {}
+}
--- a/docs/test-scenarios/09-polynomial-degree2-with-scaler-and-lags.json
+++ b/docs/test-scenarios/09-polynomial-degree2-with-scaler-and-lags.json
@@ -0,0 +1,40 @@
+{
+  "_description": "Cenário completo: regressão polinomial grau 2 com scaler e lags",
+  "experiment_run_id": 1009,
+  "variable_columns": [
+    "303-WIT-200(Value)"
+  ],
+  "target_variable": "03CV020/CORRENTE_N_M1_PV(Value)",
+  "bucket_name": "model-training",
+  "file_name": "training_data.csv",
+  "line_separator": ",",
+  "decimal_separator": ".",
+  "date_column": "timestamp",
+  "date_format": "yyyy-MM-dd HH:mm:ss",
+  "train_size": 80,
+  "shuffle": true,
+  "random_state": 42,
+  "model_name": "Polynomial Regression",
+  "model_type": "polynomial_regression",
+  "data_model_kwargs": {
+    "lag_train": {
+      "303-WIT-200(Value)": 3
+    },
+    "lag_val": {
+      "303-WIT-200(Value)": 2
+    },
+    "nan_treatment": "drop",
+    "rem_static_win": false,
+    "static_threshold": null,
+    "start_date": null,
+    "end_date": null,
+    "support_filters": {},
+    "removed_intervals": []
+  },
+  "model_kwargs": {
+    "degree": 2,
+    "interaction_only": false,
+    "scaler_name": "Standard Scaler"
+  },
+  "opt_params": {}
+}
--- a/docs/test-scenarios/10-linear-regression-with-ar.json
+++ b/docs/test-scenarios/10-linear-regression-with-ar.json
@@ -0,0 +1,42 @@
+{
+  "_description": "Linear regression placeholder for autoregressive features; include_ar is reserved for future wrapper support (see opt_params).",
+  "experiment_run_id": 1010,
+  "variable_columns": [
+    "303-WIT-200(Value)"
+  ],
+  "target_variable": "03CV020/CORRENTE_N_M1_PV(Value)",
+  "bucket_name": "model-training",
+  "file_name": "training_data.csv",
+  "line_separator": ",",
+  "decimal_separator": ".",
+  "date_column": "timestamp",
+  "date_format": "yyyy-MM-dd HH:mm:ss",
+  "train_size": 80,
+  "shuffle": true,
+  "random_state": 42,
+  "model_name": "Linear Regression",
+  "model_type": "linear_regression",
+  "data_model_kwargs": {
+    "lag_train": {
+      "303-WIT-200(Value)": 0
+    },
+    "lag_val": {
+      "303-WIT-200(Value)": 0
+    },
+    "nan_treatment": "drop",
+    "rem_static_win": false,
+    "static_threshold": null,
+    "start_date": null,
+    "end_date": null,
+    "support_filters": {},
+    "removed_intervals": []
+  },
+  "model_kwargs": {
+    "degree": 1,
+    "interaction_only": false,
+    "scaler_name": "None"
+  },
+  "opt_params": {
+    "include_ar": true
+  }
+}
--- a/docs/test-scenarios/11-linear-regression-static-threshold-custom.json
+++ b/docs/test-scenarios/11-linear-regression-static-threshold-custom.json
@@ -0,0 +1,40 @@
+{
+  "_description": "Regressão linear com remoção de janelas estáticas e static_threshold customizado",
+  "experiment_run_id": 1011,
+  "variable_columns": [
+    "303-WIT-200(Value)"
+  ],
+  "target_variable": "03CV020/CORRENTE_N_M1_PV(Value)",
+  "bucket_name": "model-training",
+  "file_name": "training_data.csv",
+  "line_separator": ",",
+  "decimal_separator": ".",
+  "date_column": "timestamp",
+  "date_format": "yyyy-MM-dd HH:mm:ss",
+  "train_size": 80,
+  "shuffle": true,
+  "random_state": 42,
+  "model_name": "Linear Regression",
+  "model_type": "linear_regression",
+  "data_model_kwargs": {
+    "lag_train": {
+      "303-WIT-200(Value)": 0
+    },
+    "lag_val": {
+      "303-WIT-200(Value)": 0
+    },
+    "nan_treatment": "drop",
+    "rem_static_win": true,
+    "static_threshold": 100,
+    "start_date": null,
+    "end_date": null,
+    "support_filters": {},
+    "removed_intervals": []
+  },
+  "model_kwargs": {
+    "degree": 1,
+    "interaction_only": false,
+    "scaler_name": "None"
+  },
+  "opt_params": {}
+}
--- a/docs/test-scenarios/12-angular-test-date-format.json
+++ b/docs/test-scenarios/12-angular-test-date-format.json
@@ -0,0 +1,40 @@
+{
+  "_description": "Alternate date column (DATA) and dd/MM/yyyy HH:mm:ss format; uses MinIO object training_data_dd_mm_yyyy.csv from E2E fixtures.",
+  "experiment_run_id": 1012,
+  "variable_columns": [
+    "303-WIT-230(Value)"
+  ],
+  "target_variable": "03CV022/CORRENTE_N_M1_PV(Value)",
+  "bucket_name": "model-training",
+  "file_name": "training_data_dd_mm_yyyy.csv",
+  "line_separator": ",",
+  "decimal_separator": ".",
+  "date_column": "DATA",
+  "date_format": "dd/MM/yyyy HH:mm:ss",
+  "train_size": 80,
+  "shuffle": true,
+  "random_state": 42,
+  "model_name": "Linear Regression",
+  "model_type": "linear_regression",
+  "data_model_kwargs": {
+    "lag_train": {
+      "303-WIT-230(Value)": 3
+    },
+    "lag_val": {
+      "303-WIT-230(Value)": 0
+    },
+    "nan_treatment": "drop",
+    "rem_static_win": false,
+    "static_threshold": null,
+    "start_date": "01/05/2022",
+    "end_date": "31/07/2022",
+    "support_filters": {},
+    "removed_intervals": []
+  },
+  "model_kwargs": {
+    "degree": 1,
+    "interaction_only": false,
+    "scaler_name": "None"
+  },
+  "opt_params": {}
+}
--- a/docs/test-scenarios/13-angular-test-double-date-column.json
+++ b/docs/test-scenarios/13-angular-test-double-date-column.json
@@ -0,0 +1,40 @@
+{
+  "_description": "Same alternate CSV as scenario 12 (DATA + dd/MM/yyyy); narrow date window for regression coverage. Not a multi-date-column dataset.",
+  "experiment_run_id": 1013,
+  "variable_columns": [
+    "303-WIT-230(Value)"
+  ],
+  "target_variable": "03CV022/CORRENTE_N_M1_PV(Value)",
+  "bucket_name": "model-training",
+  "file_name": "training_data_dd_mm_yyyy.csv",
+  "line_separator": ",",
+  "decimal_separator": ".",
+  "date_column": "DATA",
+  "date_format": "dd/MM/yyyy HH:mm:ss",
+  "train_size": 80,
+  "shuffle": true,
+  "random_state": 42,
+  "model_name": "Linear Regression",
+  "model_type": "linear_regression",
+  "data_model_kwargs": {
+    "lag_train": {
+      "303-WIT-230(Value)": 0
+    },
+    "lag_val": {
+      "303-WIT-230(Value)": 0
+    },
+    "nan_treatment": "drop",
+    "rem_static_win": false,
+    "static_threshold": null,
+    "start_date": "01/05/2022 00:00:00",
+    "end_date": "31/05/2022 23:59:59",
+    "support_filters": {},
+    "removed_intervals": []
+  },
+  "model_kwargs": {
+    "degree": 1,
+    "interaction_only": false,
+    "scaler_name": "None"
+  },
+  "opt_params": {}
+}
--- a/docs/test-scenarios/14-angular-test-polynomial-support-filters.json
+++ b/docs/test-scenarios/14-angular-test-polynomial-support-filters.json
@@ -0,0 +1,51 @@
+{
+  "_description": "Cenário angular-test-01: regressão polinomial degree 4, scaler, support filters em 303-WIT-200",
+  "experiment_run_id": 1014,
+  "variable_columns": [
+    "303-WIT-200(Value)"
+  ],
+  "target_variable": "03CV020/CORRENTE_N_M1_PV(Value)",
+  "bucket_name": "model-training",
+  "file_name": "training_data.csv",
+  "line_separator": ",",
+  "decimal_separator": ".",
+  "date_column": "timestamp",
+  "date_format": "yyyy-MM-dd HH:mm:ss",
+  "train_size": 80,
+  "shuffle": true,
+  "random_state": 42,
+  "model_name": "Polynomial Regression",
+  "model_type": "polynomial_regression",
+  "data_model_kwargs": {
+    "lag_train": {
+      "303-WIT-200(Value)": 0
+    },
+    "lag_val": {
+      "303-WIT-200(Value)": 0
+    },
+    "nan_treatment": "drop",
+    "rem_static_win": false,
+    "static_threshold": null,
+    "start_date": "2025-06-02 00:00:00",
+    "end_date": "2025-06-08 23:59:59",
+    "support_filters": {
+      "303-WIT-200(Value)": {
+        "upper_line": {
+          "intercept": 40.400002,
+          "angle": 0
+        },
+        "lower_line": {
+          "intercept": 30.5,
+          "angle": 0
+        }
+      }
+    },
+    "removed_intervals": []
+  },
+  "model_kwargs": {
+    "degree": 4,
+    "interaction_only": false,
+    "scaler_name": "Standard Scaler"
+  },
+  "opt_params": {}
+}
--- a/docs/test-scenarios/15-linear-regression-custom-target-column.json
+++ b/docs/test-scenarios/15-linear-regression-custom-target-column.json
@@ -0,0 +1,40 @@
+{
+  "_description": "Target column name is not ``target``; report/Evidently sections must use params.target_variable.",
+  "experiment_run_id": 1015,
+  "variable_columns": [
+    "303-WIT-200(Value)"
+  ],
+  "target_variable": "MY_CUSTOM_TARGET_COLUMN",
+  "bucket_name": "model-training",
+  "file_name": "training_data_custom_target.csv",
+  "line_separator": ",",
+  "decimal_separator": ".",
+  "date_column": "timestamp",
+  "date_format": "yyyy-MM-dd HH:mm:ss",
+  "train_size": 80,
+  "shuffle": true,
+  "random_state": 42,
+  "model_name": "Linear Regression",
+  "model_type": "linear_regression",
+  "data_model_kwargs": {
+    "lag_train": {
+      "303-WIT-200(Value)": 0
+    },
+    "lag_val": {
+      "303-WIT-200(Value)": 0
+    },
+    "nan_treatment": "drop",
+    "rem_static_win": false,
+    "static_threshold": null,
+    "start_date": null,
+    "end_date": null,
+    "support_filters": {},
+    "removed_intervals": []
+  },
+  "model_kwargs": {
+    "degree": 1,
+    "interaction_only": false,
+    "scaler_name": "None"
+  },
+  "opt_params": {}
+}
--- a/docs/test-scenarios/16-linear-regression-naive-timestamp-header.json
+++ b/docs/test-scenarios/16-linear-regression-naive-timestamp-header.json
@@ -0,0 +1,40 @@
+{
+  "_description": "Naive Timestamp column header; snake_case date_column/date_format and training_data_timestamp_naive.csv.",
+  "experiment_run_id": 1016,
+  "variable_columns": [
+    "303-WIT-200(Value)"
+  ],
+  "target_variable": "03CV020/CORRENTE_N_M1_PV(Value)",
+  "bucket_name": "model-training",
+  "file_name": "training_data_timestamp_naive.csv",
+  "line_separator": ",",
+  "decimal_separator": ".",
+  "date_column": "Timestamp",
+  "date_format": "yyyy-MM-dd HH:mm:ss",
+  "train_size": 80,
+  "shuffle": true,
+  "random_state": 42,
+  "model_name": "Linear Regression",
+  "model_type": "linear_regression",
+  "data_model_kwargs": {
+    "lag_train": {
+      "303-WIT-200(Value)": 0
+    },
+    "lag_val": {
+      "303-WIT-200(Value)": 0
+    },
+    "nan_treatment": "drop",
+    "rem_static_win": false,
+    "static_threshold": null,
+    "start_date": null,
+    "end_date": null,
+    "support_filters": {},
+    "removed_intervals": []
+  },
+  "model_kwargs": {
+    "degree": 1,
+    "interaction_only": false,
+    "scaler_name": "None"
+  },
+  "opt_params": {}
+}
--- a/docs/test-scenarios/17-linear-regression-blank-timestamp-row.json
+++ b/docs/test-scenarios/17-linear-regression-blank-timestamp-row.json
@@ -0,0 +1,40 @@
+{
+  "_description": "One CSV row has an empty timestamp; pipeline should drop it and continue training.",
+  "experiment_run_id": 1017,
+  "variable_columns": [
+    "303-WIT-200(Value)"
+  ],
+  "target_variable": "03CV020/CORRENTE_N_M1_PV(Value)",
+  "bucket_name": "model-training",
+  "file_name": "training_data_blank_timestamp_row.csv",
+  "line_separator": ",",
+  "decimal_separator": ".",
+  "date_column": "timestamp",
+  "date_format": "yyyy-MM-dd HH:mm:ss",
+  "train_size": 80,
+  "shuffle": true,
+  "random_state": 42,
+  "model_name": "Linear Regression",
+  "model_type": "linear_regression",
+  "data_model_kwargs": {
+    "lag_train": {
+      "303-WIT-200(Value)": 0
+    },
+    "lag_val": {
+      "303-WIT-200(Value)": 0
+    },
+    "nan_treatment": "drop",
+    "rem_static_win": false,
+    "static_threshold": null,
+    "start_date": null,
+    "end_date": null,
+    "support_filters": {},
+    "removed_intervals": []
+  },
+  "model_kwargs": {
+    "degree": 1,
+    "interaction_only": false,
+    "scaler_name": "None"
+  },
+  "opt_params": {}
+}
--- a/docs/train-model-workflow-io-diff-main-vs-current-branch.md
+++ b/docs/train-model-workflow-io-diff-main-vs-current-branch.md
@@ -0,0 +1,417 @@
+# Train Model Workflow IO Diff (`main` vs current branch)
+
+Base comparison: `git diff main...HEAD`
+Workflow analyzed: `train_model`
+
+## 1) Executive overview
+
+This branch introduces a structural refactor of the training stack and a contract update for workflow input/output.
+
+Main impacts:
+
+- The old in-house training stack (`TrainingRepository`, `ModelRepository`, `StorageRepository`, `model_manager.sientia.models`) was replaced by:
+  - `DataManagerRepository` (data prep + metrics + report generation)
+  - `SientiaModel` wrapper from plugin store (`sientia_model`)
+  - `SientiaMLflowRepository` (MLflow integration)
+  - `MinioRepository` (storage integration)
+- Input contract moved from many fixed legacy ML params to a plugin/wrapper-oriented schema (`model_type`, `*_kwargs`, `model_metadata`, optional `val_file_name`).
+- Workflow return changed from `None` to a serializable result object (`dict[str, Any] | None`) containing training execution metadata.
+- Queue naming and worker bootstrap architecture now depend on runtime (`train_model-<runtime>-queue`).
+
+---
+
+## 2) Input contract diff (before vs now)
+
+### 2.1 Previous contract (`main`)
+
+`TrainModelParams` in `main` required a large set of explicit fields for the old preprocessing/model pipeline, focused only in linear regression model:
+
+- Core:
+  - `experiment_run_id`, `variable_columns`, `target_variable`
+  - `bucket_name`, `file_name`, `line_separator`, `decimal_separator`
+  - `train_size`, `shuffle`
+- Legacy preprocessing/model fields focused only in linear regression model (required in `from_dict`):
+  - `lag_train`, `lag_val`
+  - `rem_static_win`, `low_lim`, `upp_lim`, `window`
+  - `use_scaler`, `include_ar`, `scaler_name`
+  - `removed_intervals`, `start_date`, `end_date`, `nan_treatment`
+  - `degree`, `interaction_only`
+  - `experiment_name`, `model_name`
+  - `support_filters` (optional dict), `static_threshold` (optional int)
+
+Validation was strongly tied to this structure (lag ranges, limits consistency, polynomial/scaler constraints, etc.).
+
+### 2.2 Current contract (this branch)
+
+`TrainModelParams` now supports a plugin-driven schema and wrapper kwargs:
+
+- Kept/mandatory core fields:
+  - `experiment_run_id` (now accepts numeric string too; coerced to int)
+  - `variable_columns`, `target_variable`
+  - `bucket_name`, `file_name`, `line_separator`, `decimal_separator`
+  - `train_size`, `shuffle`
+  - `model_name`
+  - `model_type`
+  - `data_model_kwargs`, `model_kwargs`, `opt_params` (required as dict by current `from_dict`)
+- New/updated fields:
+  - `random_state` (default `42`)
+  - `val_file_name` (optional explicit validation file)
+  - `model_id` (currently optional, but needs discussion, since the model metadata in MongoDB should be created before the model training)
+- Removed from required input contract:
+  - `lag_train`, `lag_val`, `rem_static_win`, `low_lim`, `upp_lim`, `window`
+  - `use_scaler`, `include_ar`
+  - `degree`, `interaction_only`, `nan_treatment`
+  - `start_date`, `end_date`, `scaler_name`
+  - `removed_intervals`, `support_filters`, `static_threshold`
+- Parameters internally derived:
+  - `model_metadata` model type info from plugin store.
+  - `run_name` is internally derived from experiment name and datetime.
+  - `experiment_name` is internally derived from `model_name`.
+
+### 2.3 Validation behavior changes
+
+Before:
+- Validation was mostly hardcoded business checks tied to legacy linear/polynomial stack.
+
+Now:
+- Validation still checks core constraints (`train_size`, non-empty strings, etc.), but model-specific validation moved to JSON Schema driven checks, using OpenAPI/JSON Schema definitions from plugin store:
+  - `model_metadata.schemas.components.schemas.data_model`
+  - `model_metadata.schemas.components.schemas.model`
+  - `model_metadata.schemas.components.schemas.opt_params`
+- `model_metadata` is now a required semantic dependency for `validate_business_rules()`.
+- Date format validation remains, but allowed formats are defined locally in `train_model_params.py`.
+
+### 2.4 Input loading pipeline changes in workflow
+
+Before:
+- `validate_train_params` directly consumed workflow input.
+
+Now:
+1. `load_model_metadata` runs first (fetches model index/schema from plugin store and injects `model_metadata`).
+2. `validate_train_params` runs with enriched payload.
+
+This means IO preprocessing now depends on plugin-store metadata resolution before final validation.
+
+---
+
+## 3) Output contract diff (before vs now)
+
+### 3.1 Workflow return (`train_model.run`)
+
+Before (`main`):
+- Return type: `None`
+- Workflow side effects were persisted mainly via DB status updates and MLflow artifacts.
+
+Now:
+- Return type: `dict[str, Any] | None`
+- Workflow returns the training activity summary when successful.
+
+### 3.2 Activity-level training result payload
+
+Before (from `Training.train_model` in `main` path):
+- Returned minimal dict:
+  - `run_name`
+  - `run_dir`
+
+Now:
+- Returns extended dict:
+  - `run_name`
+  - `experiment_name`
+  - `run_id`
+  - `run_dir`
+
+### 3.3 Persistence map by destination (DB, MLflow, MinIO, local filesystem)
+
+This section maps where each artifact/metadata goes, in which format, and how that changed from `main`.
+
+#### 3.3.1 PostgreSQL (`experiment_run` table)
+
+## Before (`main`)
+
+- Update path: `update_experiment_run` activity with `UpdateType.MODEL_SAVED`.
+- Persisted on success:
+  - `status` transition to `TRAINING_SUCCESS`
+  - `run_name` (MLflow run identifier used by current implementation)
+- Persisted on failures:
+  - `status` transition to validation/training error statuses
+  - `error_message`
+
+## Now (current branch)
+
+- Same update path and status/error behavior.
+- Even though train activity now returns more metadata (`run_id`, `experiment_name`), current workflow update for `MODEL_SAVED` still forwards mainly `run_name`.
+- Practical effect:
+  - DB remains status-centric and run-name-centric
+  - richer identifiers exist in workflow return payload, not fully mirrored to DB columns in current flow
+
+#### 3.3.2 MLflow (tracking server/artifact store)
+
+## Before (`main`)
+
+- Persistence orchestration lived in `ModelRepository.save_model()` + `_save_run()`.
+- Typical persisted content:
+  - model params (many legacy params such as lags, limits, scaler config, removed intervals)
+  - regression metrics (`MSE`, `R2`, `MAE`)
+  - model objects:
+    - `data_model`
+    - `prediction_model`
+  - artifacts:
+    - `report.html`
+    - `train_data.csv`
+    - `test_data.csv`
+    - optional `model_equation.json`
+- Run naming:
+  - computed by querying existing runs and appending sequence (`<experiment>-<n>` style)
+
+## Now (current branch)
+
+- Persistence orchestrated in `Training._persist_training_artifacts()` and MLflow run context is opened by `SientiaMLflowRepository.start_run(...)`.
+- Persisted content now:
+  - model wrapper itself via `wrapper.store_model(name=train_params.model_name)`
+  - regression metrics also logged as MLflow params via `mlflow.log_param(...)`:
+    - `mse_val`
+    - `mae_val`
+    - `r2_val`
+  - artifacts explicitly logged with `mlflow.log_artifact(...)`:
+    - `report.html`
+    - `train_data.csv`
+    - `test_data.csv`
+  - metrics are computed before save (`mse_val`, `mae_val`, `r2_val`) and persisted in the run as params
+- Run identifiers now exposed back to workflow:
+  - `experiment_name`
+  - `run_name`
+  - `run_id`
+- Notable behavioral change:
+  - `wrapper._input_example` is cleared (`None`) before storing model.
+
+#### 3.3.3 MinIO object storage
+
+## Before (`main`)
+
+- Read path:
+  - single source object downloaded via `StorageRepository.fetch_file(bucket_name, file_name)`
+- Write path:
+  - training workflow did not write generated outputs to MinIO in this code path
+  - generated artifacts were persisted to MLflow, not uploaded back to MinIO
+- Location:
+  - source data in input bucket/key provided by workflow input (`bucket_name` + `file_name`)
+
+## Now (current branch)
+
+- Read path migrated to `MinioRepository.download_file(...)`.
+- Supports two input objects:
+  - mandatory training object: `bucket_name` + `file_name`
+  - optional validation object: same `bucket_name` + `val_file_name`
+- Write path:
+  - still no artifact upload to MinIO in this workflow path
+  - report/CSV outputs continue to flow to MLflow artifacts
+- Location details:
+  - bucket resolved from payload (`bucket_name`)
+  - object key exactly from payload (`file_name`, optional `val_file_name`)
+  - default bucket in env/config is `MINIO_DEFAULT_BUCKET`, but runtime payload can override via `bucket_name`
+
+#### 3.3.4 Local filesystem (ephemeral runtime workspace)
+
+## Before (`main`)
+
+- Temporary run dir created under reports root using run name + timestamp suffix.
+- Artifacts generated locally in that directory:
+  - `report.html`
+  - `train_data.csv`
+  - `test_data.csv`
+  - optional `model_equation.json`
+- After MLflow logging, cleanup activity removed temp directory.
+
+## Now (current branch)
+
+- Temporary run dir managed by `DataManagerRepository` under runtime reports root (`.../reports/temp/<run_name>`).
+- Same artifact family generated locally:
+  - `report.html`
+  - `train_data.csv`
+  - `test_data.csv`
+  - optional `model_equation.json` (for `linear_regression`)
+- Cleanup behavior is now tolerant:
+  - cleanup runs in guarded `finally`
+  - training success is not reverted if cleanup later fails
+
+#### 3.3.5 Quick matrix (before vs now)
+
+- **Postgres**
+  - before: status + run_name + errors
+  - now: same persisted shape; workflow return contains extra IDs
+- **MLflow**
+  - before: legacy model objects + params/metrics + report/data artifacts
+  - now: wrapper-based model persistence + `mse_val`/`mae_val`/`r2_val` as params + report/data artifacts + run_id exposed
+- **MinIO**
+  - before: reads 1 CSV input object
+  - now: reads 1 or 2 CSV input objects (train + optional validation), still no output upload
+- **Local temp**
+  - before: generated artifacts, then cleanup
+  - now: generated artifacts, then best-effort cleanup (non-blocking for success result)
+
+### 3.4 Cleanup behavior impact on output semantics
+
+Before:
+- Cleanup was called directly after training result; failures propagated straightforwardly.
+
+Now:
+- Cleanup is in a guarded `finally`.
+- If training succeeded but cleanup fails, workflow warns and does not rollback success semantics.
+- Effective output semantics: successful training result can be returned even if temp cleanup fails.
+
+---
+
+## 4) Detailed field mapping (old -> new)
+
+## Kept (or equivalent role)
+
+- `experiment_run_id` -> kept (broader accepted types: int or numeric string)
+- `variable_columns` -> kept
+- `target_variable` -> kept
+- `bucket_name` -> kept
+- `file_name` -> kept
+- `line_separator` -> kept
+- `decimal_separator` -> kept
+- `date_column` -> required (snake_case key; must exist in CSV)
+- `date_format` -> optional in payload; omitted/null/blank resolves to default `yyyy-MM-dd HH:mm:ss`
+- `train_size` -> kept
+- `shuffle` -> kept
+- `model_name` -> kept (now less coupled to legacy model enum)
+
+## Added
+
+- `model_type` (primary selector for plugin wrapper/index lookup)
+- `data_model_kwargs`
+- `model_kwargs`
+- `opt_params`
+- `val_file_name` (optional second dataset input)
+- `model_id` (optional metadata)
+- `model_metadata` (loaded/required for schema validation)
+- `random_state` (explicit split reproducibility control)
+
+## Removed from new required contract
+
+- `lag_train`, `lag_val`
+- `rem_static_win`, `static_threshold`
+- `low_lim`, `upp_lim`
+- `window`
+- `use_scaler`, `include_ar`
+- `degree`, `interaction_only`
+- `nan_treatment`
+- `start_date`, `end_date`
+- `scaler_name`
+- `removed_intervals`
+- `support_filters`
+- `experiment_name` (no longer required as top-level client input)
+
+---
+
+## 5) Internal architecture update notes
+
+### 5.1 Repository layer redesign
+
+Removed:
+- `model_manager/utils/repository/model_repository.py`
+- `model_manager/utils/repository/training_repository.py`
+- `model_manager/utils/repository/storage_repository.py`
+
+Added:
+- `model_manager/utils/repository/data_manager_repository.py`
+
+Interpretation:
+- Data preprocessing/report/metrics responsibilities were consolidated into `DataManagerRepository`.
+- Training/model persistence shifted to wrapper + plugin store + MLflow repository integrations.
+
+### 5.2 Model engine abstraction migration
+
+Before:
+- Strong coupling to local classes in `model_manager.sientia.models` and custom preprocessing/model objects in `TrainModelResult`.
+
+Now:
+- Training uses `SientiaModel` wrapper dynamically obtained by `plugin_store.get_model(model_type=...)`.
+- Contract is wrapper-driven (`train`, `transform`, `predict`, `store_model`).
+- The codebase removed `model_manager/sientia/models.py`, `model_serving.py`, and `utils.py`, indicating full migration to externalized model runtime abstraction.
+
+### 5.3 Worker/runtime architecture changes
+
+- New `prepare_worker.py` centralizes worker setup and autoscaling parameters.
+- Queue names are now runtime-derived:
+  - `train_model-<runtime>-queue`
+  - `cleanup_files-<runtime>-queue`
+- `worker.py` now installs runtime via plugin store (`plugin_store.install_runtime(runtime_name=...)`) before starting workers.
+- This introduces environment/runtime-aware deployment and model packaging behavior.
+
+### 5.4 Synchronous activity and tracking adjustments
+
+- `experiment_tracking` migrated from async postgres helper to sync postgres client path (`postgres_sync`).
+- Several activities switched to sync method signatures.
+- Error handling in workflow and DB status update paths is more defensive (secondary failures while persisting error status are logged and do not mask primary failure cause).
+
+### 5.5 `TrainModelResult` shape update
+
+Before:
+- Stored classic split artifacts (`x_train`, `x_test`, `y_train`, `y_test`) + concrete preprocessing/model objects (`process_data`, `regr`, `scaler_dict`).
+
+Now:
+- Stores `train_data`, `val_data` and prediction DataFrames, plus tracking identifiers (`experiment_name`, `run_id`).
+- Result object is less tied to internal estimator classes and more aligned with serializable workflow/model-store integration.
+
+---
+
+## 6) Net IO compatibility assessment
+
+## Input compatibility
+
+Not backward compatible with old payloads without adaptation.
+
+Key reasons:
+- Legacy required fields removed/ignored by new path.
+- New required fields introduced (`model_type`, `*_kwargs` dicts, runtime metadata flow dependency).
+- Validation pipeline now expects model metadata semantics.
+
+## Output compatibility
+
+Behavior changed:
+- Workflow now returns a result object (previously `None`).
+- Training summary includes `experiment_name` and `run_id` in addition to `run_name` and `run_dir`.
+- DB update still centered on `run_name`; callers relying only on DB may not see all new output info unless workflow return is consumed.
+
+---
+
+## 7) Practical migration guidance (client side)
+
+To call `train_model` in this branch:
+
+1. Send snake_case payload aligned to new `TrainModelParams`.
+2. Always provide:
+   - `model_name` slugified model name (ex.: `test_model_name or test-model-name`)
+   - `model_type`
+   - `data_model_kwargs` (dict)
+   - `model_kwargs` (dict)
+   - `opt_params` (dict)
+3. Keep `experiment_run_id` numeric (int or numeric string).
+4. Use runtime queue naming consistent with worker runtime:
+   - `train_model-<runtime>-queue`
+5. If you need explicit validation split file, send `val_file_name`; otherwise split uses `train_size`/`shuffle`/`random_state`.
+
+---
+
+## 8) Source references used for this document
+
+Primary diffs:
+- `model_manager/workflows/train_model.py`
+- `model_manager/utils/models/train_model_params.py`
+- `model_manager/utils/models/train_model_result.py`
+- `model_manager/activities/training.py`
+- `model_manager/activities/activities.py`
+- `model_manager/activities/experiment_tracking.py`
+- `model_manager/utils/repository/data_manager_repository.py`
+- `model_manager/utils/repository/model_repository.py` (removed)
+- `model_manager/utils/repository/training_repository.py` (removed)
+- `model_manager/utils/repository/storage_repository.py` (removed)
+- `model_manager/worker/worker.py`
+- `model_manager/worker/prepare_worker.py`
+- `README.md`
+- `input-sample.md`
+- `scripts/run_training_test.py`
+
--- a/e2e/init.py
+++ b/e2e/init.py
@@ -0,0 +1,3 @@
+"""
+End-to-end tests for the Model Manager Temporal workflows.
+"""
--- a/e2e/conftest.py
+++ b/e2e/conftest.py
@@ -0,0 +1,697 @@
+"""
+Pytest configuration and fixtures for E2E tests.
+
+External dependencies use testcontainers or real SDK integrations (no mocks of
+model_manager or other first-party code):
+
+- PostgreSQL, MinIO, MongoDB, Gitea: testcontainers.
+- MLflow: real client with ``file://`` tracking URI (no MLflow server process).
+- Temporal: ``WorkflowEnvironment.start_time_skipping()`` — official in-process
+  test runtime from temporalio; exercises real workflows and activity code, not
+  stubs of business logic.
+- Observability: ``Logger`` (``get_logger`` from ``model_manager.utils.logger_helper``)
+  and ``MetricsController`` from sientia_do, same stack as production.
+"""
+
+from concurrent.futures import ThreadPoolExecutor
+import base64
+import csv
+import io
+import os
+import shutil
+import tempfile
+import time
+
+import mlflow
+import pytest
+import pytest_asyncio
+import requests
+from minio import Minio
+from sqlalchemy import create_engine, text
+from testcontainers.core.container import DockerContainer  # type: ignore[import,import-untyped]
+from testcontainers.minio import MinioContainer  # type: ignore[import-untyped]
+from testcontainers.mongodb import MongoDbContainer  # type: ignore[import-untyped]
+from testcontainers.postgres import PostgresContainer  # type: ignore[import,import-untyped]
+from temporalio.testing import WorkflowEnvironment
+from temporalio.worker import Worker
+
+from model_manager.activities.activities import Activities
+from model_manager.utils.logger_helper import get_logger
+from model_manager.workflows.cleanup_files import CleanupFiles
+from model_manager.workflows.train_model import TrainModel
+from sientia_do.notifications.handlers import CoreNotificationHandler
+from sientia_do.observability.metrics_controller import MetricsController
+from sientia_model.model_repository.plugin_store import PluginStore
+
+# ---------------------------------------------------------------------------
+# CSV training data: columns must match the variable_columns and target_variable
+# used across all test scenarios.
+_TRAIN_CSV_COLUMNS = [
+    'timestamp',
+    '303-WIT-200(Value)',
+    '03CV020/CORRENTE_N_M1_PV(Value)',
+    '303-WIT-230(Value)',
+    '03CV022/CORRENTE_N_M1_PV(Value)',
+]
+_MINIO_BUCKET = 'model-training'
+_MINIO_OBJECT = 'training_data.csv'
+
+# ---------------------------------------------------------------------------
+# Helpers – CSV generation
+# ---------------------------------------------------------------------------
+
+def _build_training_csv() -> bytes:
+    """
+    Generate a 150-row CSV with all columns needed by test scenarios.
+
+    The numeric values cycle deterministically so lags and static-window
+    removal always find enough rows in both train and validation splits.
+    """
+    output = io.StringIO()
+    writer = csv.writer(output)
+    writer.writerow(_TRAIN_CSV_COLUMNS)
+    for i in range(150):
+        ts = f'2025-06-{(i // 24) + 2:02d} {i % 24:02d}:00:00'
+        wit200 = round(30.0 + (i % 20) * 0.5, 2)
+        cv020 = round(100.0 + (i % 15) * 0.3, 2)
+        wit230 = round(25.0 + (i % 18) * 0.4, 2)
+        cv022 = round(90.0 + (i % 12) * 0.25, 2)
+        writer.writerow([ts, wit200, cv020, wit230, cv022])
+    return output.getvalue().encode('utf-8')
+
+
+def _build_training_csv_dd_mm_yyyy() -> bytes:
+    """
+    Generate a 150-row CSV with dd/MM/yyyy HH:mm:ss timestamps and
+    a DATA column header, for scenarios 12/13 that use a different date format.
+    """
+    output = io.StringIO()
+    writer = csv.writer(output)
+    writer.writerow([
+        'DATA',
+        '303-WIT-230(Value)',
+        '03CV022/CORRENTE_N_M1_PV(Value)',
+    ])
+    for i in range(150):
+        day = (i % 30) + 1
+        ts = f'{day:02d}/05/2022 {i % 24:02d}:00:00'
+        wit230 = round(25.0 + (i % 18) * 0.4, 2)
+        cv022 = round(90.0 + (i % 12) * 0.25, 2)
+        writer.writerow([ts, wit230, cv022])
+    return output.getvalue().encode('utf-8')
+
+
+def _build_training_csv_custom_target_column() -> bytes:
+    """
+    Same layout as the standard CSV but the target column has a non-default name
+    (not ``target``) to exercise report and metrics paths.
+    """
+    output = io.StringIO()
+    writer = csv.writer(output)
+    writer.writerow([
+        'timestamp',
+        '303-WIT-200(Value)',
+        'MY_CUSTOM_TARGET_COLUMN',
+    ])
+    for i in range(150):
+        ts = f'2025-06-{(i // 24) + 2:02d} {i % 24:02d}:00:00'
+        wit200 = round(30.0 + (i % 20) * 0.5, 2)
+        target_val = round(100.0 + (i % 15) * 0.3, 2)
+        writer.writerow([ts, wit200, target_val])
+    return output.getvalue().encode('utf-8')
+
+
+def _build_training_csv_timestamp_header_naive() -> bytes:
+    """
+    Naive datetimes under column ``Timestamp`` (common UI export) for scenario 16.
+    """
+    output = io.StringIO()
+    writer = csv.writer(output)
+    writer.writerow([
+        'Timestamp',
+        '303-WIT-200(Value)',
+        '03CV020/CORRENTE_N_M1_PV(Value)',
+    ])
+    for i in range(150):
+        ts = f'2025-06-{(i // 24) + 2:02d} {i % 24:02d}:00:00'
+        wit200 = round(30.0 + (i % 20) * 0.5, 2)
+        cv020 = round(100.0 + (i % 15) * 0.3, 2)
+        writer.writerow([ts, wit200, cv020])
+    return output.getvalue().encode('utf-8')
+
+
+def _build_training_csv_blank_timestamp_row() -> bytes:
+    """Standard columns with one row where ``timestamp`` is empty (NaN after parse)."""
+    output = io.StringIO()
+    writer = csv.writer(output)
+    writer.writerow(_TRAIN_CSV_COLUMNS)
+    for i in range(150):
+        wit200 = round(30.0 + (i % 20) * 0.5, 2)
+        cv020 = round(100.0 + (i % 15) * 0.3, 2)
+        wit230 = round(25.0 + (i % 18) * 0.4, 2)
+        cv022 = round(90.0 + (i % 12) * 0.25, 2)
+        if i == 17:
+            writer.writerow(['', wit200, cv020, wit230, cv022])
+        else:
+            ts = f'2025-06-{(i // 24) + 2:02d} {i % 24:02d}:00:00'
+            writer.writerow([ts, wit200, cv020, wit230, cv022])
+    return output.getvalue().encode('utf-8')
+
+
+# ---------------------------------------------------------------------------
+# Helpers – Gitea seed
+# ---------------------------------------------------------------------------
+
+def _wait_for_gitea(base_url: str, timeout: int = 120) -> None:
+    """Poll Gitea until it responds to HTTP requests."""
+    deadline = time.time() + timeout
+    last_err = None
+    while time.time() < deadline:
+        try:
+            resp = requests.get(f'{base_url}/', timeout=3)
+            if resp.status_code in (200, 404, 302):
+                return
+        except Exception as e:
+            last_err = e
+        time.sleep(2)
+    raise TimeoutError(f'Gitea did not start within {timeout}s at {base_url}. Last error: {last_err}')
+
+
+def _gitea_api(method: str, url: str, auth: tuple, **kwargs) -> requests.Response:
+    resp = requests.request(method, url, auth=auth, timeout=30, **kwargs)
+    try:
+        resp.raise_for_status()
+    except requests.exceptions.HTTPError as e:
+        raise RuntimeError(f"Gitea API error {resp.status_code}: {resp.text}") from e
+    return resp
+
+
+def _seed_gitea(base_url: str, admin_user: str, admin_pass: str) -> None:
+    """
+    Create a fictitious model-store repository with dummy models.
+    """
+    auth = (admin_user, admin_pass)
+    api = f'{base_url}/api/v1'
+
+    # Create repository
+    _gitea_api(
+        'POST', f'{api}/user/repos', auth,
+        json={'name': 'model-store', 'private': False, 'auto_init': False},
+    )
+
+    # Root index.yaml
+    root_index = """
+store_name: "E2E Test Store"
+version: 1
+models:
+  - name: "linear_regression"
+    version: 1
+    runtime: "basic"
+  - name: "polynomial_regression"
+    version: 1
+    runtime: "basic"
+runtimes:
+  basic:
+    version: "1.0.0"
+    libraries:
+      - name: "pandas"
+      - name: "numpy"
+"""
+
+    # Model index.yaml (shared for all dummies)
+    model_index = """
+name: "{model_name}"
+version: 1
+runtime: "basic"
+path: "wrapper.py"
+class: "DummyWrapper"
+model:
+  class: "DummyModel"
+  path: "model_logic.py"
+  external: false
+data_model:
+  class: "DummyTransformer"
+  path: "model_logic.py"
+  external: false
+"""
+
+    # schemas.yaml
+    schemas_yaml = """
+model:
+  type: object
+  properties: {}
+data_model:
+  type: object
+  properties: {}
+opt_params:
+  type: object
+  properties: {}
+"""
+
+    # wrapper.py
+    wrapper_py = """
+from sientia_model.wrappers.sientia_model import SientiaModel
+import pandas as pd
+import numpy as np
+from typing import Any
+
+class DummyWrapper(SientiaModel):
+    def _predict(self, data: pd.DataFrame) -> tuple[pd.DataFrame, dict[str, Any]]:
+        self._log("info", f"Predicting dummy model for {self.model_type}")
+        # Return a simple prediction (mean or 0.5) to allow metrics computation
+        preds = pd.DataFrame({self.target: [0.5] * len(data)}, index=data.index)
+        return preds, {}
+        
+    def _transform(self, data: pd.DataFrame) -> tuple[pd.DataFrame, dict[str, Any]]:
+        return data, {}
+        
+    def _train_transformer(self, train_data: pd.DataFrame, val_data: pd.DataFrame) -> None:
+        pass
+        
+    def _train_model(self, x: pd.DataFrame, y: pd.DataFrame, x_val: pd.DataFrame | None = None, y_val: pd.DataFrame | None = None) -> None:
+        self.target = y.columns[0]
+        
+    def _retrain_transformer(self, data: pd.DataFrame) -> None:
+        pass
+        
+    def _retrain_model(self, x: pd.DataFrame, y: pd.DataFrame | None) -> None:
+        pass
+"""
+
+    # model_logic.py
+    model_logic_py = """
+class DummyModel:
+    def __init__(self, **kwargs):
+        pass
+
+class DummyTransformer:
+    def __init__(self, **kwargs):
+        pass
+"""
+
+    # requirements.txt required by current model packaging path in training activity.
+    requirements_txt = """
+pandas
+numpy
+"""
+
+    def push_file(path: str, content: str):
+        encoded = base64.b64encode(content.encode()).decode()
+        _gitea_api(
+            'POST',
+            f'{api}/repos/{admin_user}/model-store/contents/{path}',
+            auth,
+            json={'message': f'seed: {path}', 'content': encoded},
+        )
+
+    # Push root index
+    push_file('index.yaml', root_index)
+
+    # Push files for both models used in tests
+    for model_name in ['linear_regression', 'polynomial_regression']:
+        prefix = f'models/{model_name}'
+        push_file(f'{prefix}/index.yaml', model_index.format(model_name=model_name))
+        push_file(f'{prefix}/schemas.yaml', schemas_yaml)
+        push_file(f'{prefix}/wrapper.py', wrapper_py)
+        push_file(f'{prefix}/model_logic.py', model_logic_py)
+        push_file(f'{prefix}/requirements.txt', requirements_txt.strip() + '\n')
+        push_file(f'{prefix}/__init__.py', "")
+
+    # Push runtime
+    push_file('runtime/basic.yaml', 'name: basic\nversion: "1.0.0"\nlibraries: []')
+
+
+# ---------------------------------------------------------------------------
+# Session-scoped containers
+# ---------------------------------------------------------------------------
+
+@pytest.fixture(scope='session')
+def postgres_container():
+    """PostgreSQL 15 container for experiment_run table."""
+    container = PostgresContainer('postgres:15')
+    container.start()
+    yield container
+    container.stop()
+
+
+@pytest.fixture(scope='session')
+def minio_container():
+    """MinIO container for training CSV storage."""
+    container = MinioContainer()
+    container.start()
+    yield container
+    container.stop()
+
+
+@pytest.fixture(scope='session')
+def mongodb_container():
+    """MongoDB container for CoreNotificationHandler."""
+    container = MongoDbContainer('mongo:7')
+    container.start()
+    yield container
+    container.stop()
+
+
+@pytest.fixture(scope='session')
+def gitea_container():
+    """
+    Gitea container with a ``model-store`` repo seeded via REST API
+    (``index.yaml``, dummy model files, ``_seed_gitea``).
+
+    The container starts with INSTALL_LOCK so no setup wizard is needed.
+    An admin user is created via Gitea's CLI before the HTTP API is used.
+    """
+    admin_user = 'gitea_admin'
+    admin_pass = 'gitea_admin_pass'  # noqa: S105
+
+    container = (
+        DockerContainer('gitea/gitea:latest')
+        .with_env('GITEA__security__INSTALL_LOCK', 'true')
+        .with_env('GITEA__server__HTTP_PORT', '3000')
+        .with_env('GITEA__log__LEVEL', 'Warn')
+        .with_exposed_ports(3000)
+    )
+    container.start()
+
+    port = container.get_exposed_port(3000)
+    base_url = f'http://localhost:{port}'
+
+    _wait_for_gitea(base_url)
+    time.sleep(5)  # Wait a bit for DB to fully initialize after HTTP is up
+
+    # Create admin user via Gitea CLI inside the container
+    # Must run after Gitea is fully initialized
+    gitea_cmd = (
+        f'gitea admin user create '
+        f'--username {admin_user} '
+        f'--password {admin_pass} '
+        f'--email admin@test.local '
+        f'--admin '
+        f'--must-change-password=false'
+    )
+    exec_result = container.exec(f"su git -c '{gitea_cmd}'")
+    if exec_result.exit_code != 0:
+        raise RuntimeError(f"Failed to create Gitea admin user: {exec_result.output.decode('utf-8')}")
+
+    _seed_gitea(base_url, admin_user, admin_pass)
+
+    yield {
+        'container': container,
+        'base_url': base_url,
+        'admin_user': admin_user,
+        'admin_pass': admin_pass,
+    }
+
+    container.stop()
+
+
+@pytest.fixture(scope='session')
+def mlflow_tracking_dir():
+    """Local MLflow filesystem tracking directory (no network needed)."""
+    tmpdir = tempfile.mkdtemp(prefix='mlflow-e2e-')
+    mlflow.set_tracking_uri(f'file://{tmpdir}')
+    yield tmpdir
+    shutil.rmtree(tmpdir, ignore_errors=True)
+
+
+@pytest.fixture(scope='session', autouse=True)
+def e2e_runtime_reports_dir():
+    """
+    Route runtime report artifacts to a writable temp directory during E2E.
+
+    Production defaults point to /var/lib/model-manager; in local CI/dev runs this
+    path may be unavailable. This fixture keeps the same code paths while avoiding
+    host permission issues.
+    """
+    import model_manager.runtime_paths as runtime_paths
+    import model_manager.utils.repository.data_manager_repository as data_repo_module
+
+    base_dir = tempfile.mkdtemp(prefix='model-manager-e2e-runtime-')
+    reports_root = f'{base_dir}/reports'
+    reports_temp_dir = f'{reports_root}/temp'
+    project_base_path = os.path.abspath(os.path.join(os.path.dirname(__file__), '..', 'model_manager'))
+
+    old_runtime_reports_root = runtime_paths.REPORTS_ROOT
+    old_runtime_reports_temp = runtime_paths.REPORTS_TEMP_DIR
+    old_runtime_project_base = runtime_paths.PROJECT_BASE_PATH
+    old_repo_reports_root = data_repo_module.REPORTS_ROOT
+    old_repo_project_base = data_repo_module.PROJECT_BASE_PATH
+
+    runtime_paths.REPORTS_ROOT = reports_root
+    runtime_paths.REPORTS_TEMP_DIR = reports_temp_dir
+    runtime_paths.PROJECT_BASE_PATH = project_base_path
+    data_repo_module.REPORTS_ROOT = reports_root
+    data_repo_module.PROJECT_BASE_PATH = project_base_path
+
+    try:
+        yield reports_root
+    finally:
+        runtime_paths.REPORTS_ROOT = old_runtime_reports_root
+        runtime_paths.REPORTS_TEMP_DIR = old_runtime_reports_temp
+        runtime_paths.PROJECT_BASE_PATH = old_runtime_project_base
+        data_repo_module.REPORTS_ROOT = old_repo_reports_root
+        data_repo_module.PROJECT_BASE_PATH = old_repo_project_base
+        shutil.rmtree(base_dir, ignore_errors=True)
+
+
+# ---------------------------------------------------------------------------
+# Session-scoped: seed MinIO with training CSV
+# ---------------------------------------------------------------------------
+
+@pytest.fixture(scope='session', autouse=True)
+def upload_training_csv(minio_container, mlflow_tracking_dir):  # noqa: ARG001
+    """
+    Upload training CSV files to the MinIO container before any test runs.
+    Depends on mlflow_tracking_dir to ensure the MLflow URI is set at session start.
+    """
+    port = minio_container.get_exposed_port(9000)
+    client = Minio(
+        f'localhost:{port}',
+        access_key='minioadmin',
+        secret_key='minioadmin',
+        secure=False,
+    )
+
+    if not client.bucket_exists(_MINIO_BUCKET):
+        client.make_bucket(_MINIO_BUCKET)
+
+    # Standard training CSV
+    csv_bytes = _build_training_csv()
+    client.put_object(
+        _MINIO_BUCKET,
+        _MINIO_OBJECT,
+        io.BytesIO(csv_bytes),
+        length=len(csv_bytes),
+        content_type='text/csv',
+    )
+
+    # dd/MM/yyyy format CSV for scenarios 12/13
+    alt_csv_bytes = _build_training_csv_dd_mm_yyyy()
+    client.put_object(
+        _MINIO_BUCKET,
+        'training_data_dd_mm_yyyy.csv',
+        io.BytesIO(alt_csv_bytes),
+        length=len(alt_csv_bytes),
+        content_type='text/csv',
+    )
+
+    custom_target = _build_training_csv_custom_target_column()
+    client.put_object(
+        _MINIO_BUCKET,
+        'training_data_custom_target.csv',
+        io.BytesIO(custom_target),
+        length=len(custom_target),
+        content_type='text/csv',
+    )
+
+    ts_header = _build_training_csv_timestamp_header_naive()
+    client.put_object(
+        _MINIO_BUCKET,
+        'training_data_timestamp_naive.csv',
+        io.BytesIO(ts_header),
+        length=len(ts_header),
+        content_type='text/csv',
+    )
+
+    blank_ts = _build_training_csv_blank_timestamp_row()
+    client.put_object(
+        _MINIO_BUCKET,
+        'training_data_blank_timestamp_row.csv',
+        io.BytesIO(blank_ts),
+        length=len(blank_ts),
+        content_type='text/csv',
+    )
+
+
+# ---------------------------------------------------------------------------
+# Function-scoped: database engine + schema setup
+# ---------------------------------------------------------------------------
+
+@pytest.fixture
+def postgres_engine(postgres_container):
+    """SQLAlchemy engine connected to the test PostgreSQL container."""
+    engine = create_engine(postgres_container.get_connection_url())
+    yield engine
+    engine.dispose()
+
+
+@pytest.fixture(autouse=True)
+def setup_experiment_run_table(postgres_engine):
+    """
+    Create the experiment_run table before each test and drop it afterwards
+    to guarantee full isolation between tests.
+    """
+    with postgres_engine.begin() as conn:
+        conn.execute(text("""
+            CREATE TABLE IF NOT EXISTS public.experiment_run (
+                id              INT PRIMARY KEY,
+                experiment_name TEXT NOT NULL,
+                run_name        TEXT,
+                username        TEXT,
+                status          TEXT NOT NULL DEFAULT 'ORCHESTRATOR_WAITING_PROC',
+                error_message   TEXT,
+                created_at      TIMESTAMPTZ NOT NULL DEFAULT NOW(),
+                updated_at      TIMESTAMPTZ NOT NULL DEFAULT NOW(),
+                bucket_name     TEXT,
+                file_name       TEXT
+            )
+        """))
+    yield
+    with postgres_engine.begin() as conn:
+        conn.execute(text('DROP TABLE IF EXISTS public.experiment_run'))
+
+
+# ---------------------------------------------------------------------------
+# Observability (real sientia_do implementations)
+# ---------------------------------------------------------------------------
+
+@pytest.fixture(scope='session')
+def e2e_logger():
+    """Shared production-style Logger for the whole E2E session."""
+    return get_logger('model-manager-e2e')
+
+
+@pytest.fixture
+def metrics_controller(e2e_logger):
+    """MetricsController bound to the E2E logger (fresh instance per test)."""
+    return MetricsController(logger=e2e_logger)
+
+
+# ---------------------------------------------------------------------------
+# Application fixtures
+# ---------------------------------------------------------------------------
+
+@pytest.fixture
+def notification_handler(mongodb_container, e2e_logger):
+    """
+    Real CoreNotificationHandler connected to the MongoDB testcontainer.
+    """
+    connection_url = mongodb_container.get_connection_url()
+    handler = CoreNotificationHandler(
+        connection_string=connection_url,
+        database='test_notifications',
+        logger=e2e_logger,
+        project_name='model-manager-e2e',
+    )
+    yield handler
+    handler.shutdown()
+
+
+@pytest.fixture
+def plugin_store(gitea_container, e2e_logger, metrics_controller, notification_handler):
+    """
+    Real PluginStore pointed at the Gitea testcontainer.
+    cache_ttl_seconds=0 forces a fresh download every test.
+    """
+    store = PluginStore(
+        base_url=gitea_container['base_url'],
+        owner=gitea_container['admin_user'],
+        repo='model-store',
+        username=gitea_container['admin_user'],
+        password=gitea_container['admin_pass'],
+        cache_ttl_seconds=0,
+        logger=e2e_logger,
+        notification_handler=notification_handler,
+        metrics_controller=metrics_controller,
+    )
+    yield store
+
+
+@pytest.fixture
+def test_activities(
+    postgres_container,
+    minio_container,
+    mlflow_tracking_dir,  # noqa: ARG001 – ensures MLflow URI is set
+    plugin_store,
+    e2e_logger,
+    notification_handler,
+    metrics_controller,
+):
+    """
+    Real Activities instance wired to all testcontainers.
+    """
+    pg_port = postgres_container.get_exposed_port(5432)
+    minio_port = minio_container.get_exposed_port(9000)
+
+    activities = Activities(
+        postgres_config={
+            'host': 'localhost',
+            'port': int(pg_port),
+            'user': 'test',
+            'password': 'test',
+            'dbname': 'test',
+            'min_connections': 1,
+            'max_connections': 5,
+        },
+        mlflow_config={
+            'url': mlflow.get_tracking_uri(),
+            'username': None,
+            'password': None,
+        },
+        minio_config={
+            'endpoint_url': f'http://localhost:{minio_port}',
+            'access_key': 'minioadmin',
+            'secret_key': 'minioadmin',
+            'use_ssl': False,
+            'default_bucket': _MINIO_BUCKET,
+        },
+        plugin_store=plugin_store,
+        logger=e2e_logger,
+        notification_handler=notification_handler,
+        metrics_controller=metrics_controller,
+    )
+    yield activities
+    activities.shutdown()
+
+
+def _activity_list(activities: Activities) -> list:
+    return [
+        activities.update_experiment_run,
+        activities.load_model_metadata,
+        activities.validate_train_params,
+        activities.train_model,
+        activities.cleanup_resources,
+        activities.cleanup_temp_directories,
+    ]
+
+
+@pytest_asyncio.fixture(scope='function')
+async def temporal_test_env():
+    """Temporal SDK test environment (time-skipping); runs real workflow/activity code."""
+    env = await WorkflowEnvironment.start_time_skipping()
+    async with env:
+        yield env
+
+
+@pytest_asyncio.fixture(scope='function')
+async def temporal_worker(temporal_test_env, test_activities):
+    """Temporal worker registered with all workflows and activities."""
+    with ThreadPoolExecutor() as executor:
+        async with Worker(
+            temporal_test_env.client,
+            task_queue='test-queue',
+            workflows=[TrainModel, CleanupFiles],
+            activities=_activity_list(test_activities),
+            activity_executor=executor,
+        ) as worker:
+            yield worker
--- a/e2e/helpers.py
+++ b/e2e/helpers.py
@@ -0,0 +1,195 @@
+"""
+Shared helpers for E2E tests (Temporal workflows + PostgreSQL).
+"""
+
+import asyncio
+import json
+from datetime import datetime
+from pathlib import Path
+from typing import Any
+
+import pytest
+from sqlalchemy import text
+from sqlalchemy.engine import Engine
+
+
+async def start_and_await_workflow(
+    client,
+    workflow_run,
+    input_data: dict,
+    workflow_id: str,
+    timeout: float = 600.0,
+):
+    """
+    Start a Temporal workflow and wait for its result.
+
+    Args:
+        client: Temporal client from WorkflowEnvironment.
+        workflow_run: Workflow run method (e.g. TrainModel.run).
+        input_data: Workflow input payload.
+        workflow_id: Unique workflow id.
+        timeout: Max seconds to wait for completion (default allows cold testcontainer startup).
+
+    Returns:
+        Workflow result value.
+    """
+    handle = await client.start_workflow(
+        workflow_run,
+        input_data,
+        id=workflow_id,
+        task_queue='test-queue',
+    )
+    return await asyncio.wait_for(handle.result(), timeout=timeout)
+
+
+def make_workflow_id(prefix: str) -> str:
+    """Build a unique workflow id using a prefix and current timestamp."""
+    return f'{prefix}-{datetime.now().timestamp()}'
+
+
+def insert_experiment_run(
+    engine: Engine,
+    experiment_run_id: int,
+    experiment_name: str = 'test_experiment',
+    status: str = 'ORCHESTRATOR_WAITING_PROC',
+    bucket_name: str = 'model-training',
+    file_name: str = 'training_data.csv',
+) -> None:
+    """
+    Insert a minimal experiment_run row to satisfy foreign-key-style lookups.
+
+    Args:
+        engine: SQLAlchemy engine connected to the test database.
+        experiment_run_id: Primary key for the row.
+        experiment_name: Human-readable experiment name.
+        status: Initial status string.
+        bucket_name: MinIO bucket name.
+        file_name: Training file name inside the bucket.
+    """
+    with engine.begin() as conn:
+        conn.execute(
+            text("""
+                INSERT INTO public.experiment_run
+                    (id, experiment_name, status, bucket_name, file_name)
+                VALUES
+                    (:id, :experiment_name, :status, :bucket_name, :file_name)
+                ON CONFLICT (id) DO NOTHING
+            """),
+            {
+                'id': experiment_run_id,
+                'experiment_name': experiment_name,
+                'status': status,
+                'bucket_name': bucket_name,
+                'file_name': file_name,
+            },
+        )
+
+
+def assert_experiment_status(
+    engine: Engine,
+    experiment_run_id: int,
+    expected_status: str,
+) -> None:
+    """
+    Assert the final status of an experiment_run row.
+
+    Args:
+        engine: SQLAlchemy engine.
+        experiment_run_id: Row primary key.
+        expected_status: Expected status string.
+    """
+    with engine.connect() as conn:
+        row = conn.execute(
+            text('SELECT status FROM public.experiment_run WHERE id = :id'),
+            {'id': experiment_run_id},
+        ).fetchone()
+
+    assert row is not None, (
+        f'No experiment_run row found for id={experiment_run_id}'
+    )
+    assert row[0] == expected_status, (
+        f'Expected status={expected_status!r}, got {row[0]!r} '
+        f'for experiment_run id={experiment_run_id}'
+    )
+
+
+def assert_experiment_run_name_set(
+    engine: Engine,
+    experiment_run_id: int,
+) -> None:
+    """Assert that run_name is not null/empty after a successful training."""
+    with engine.connect() as conn:
+        row = conn.execute(
+            text('SELECT run_name FROM public.experiment_run WHERE id = :id'),
+            {'id': experiment_run_id},
+        ).fetchone()
+
+    assert row is not None, (
+        f'No experiment_run row found for id={experiment_run_id}'
+    )
+    assert row[0] is not None and row[0].strip() != '', (
+        f'Expected run_name to be set for experiment_run id={experiment_run_id}, got {row[0]!r}'
+    )
+
+
+def assert_experiment_error(
+    engine: Engine,
+    experiment_run_id: int,
+    expected_status: str,
+    error_substr: str,
+) -> None:
+    """
+    Assert status and that error_message contains a given substring.
+
+    Args:
+        engine: SQLAlchemy engine.
+        experiment_run_id: Row primary key.
+        expected_status: Expected status string.
+        error_substr: Substring that must appear in error_message.
+    """
+    with engine.connect() as conn:
+        row = conn.execute(
+            text(
+                'SELECT status, error_message FROM public.experiment_run WHERE id = :id'
+            ),
+            {'id': experiment_run_id},
+        ).fetchone()
+
+    assert row is not None, (
+        f'No experiment_run row found for id={experiment_run_id}'
+    )
+    assert row[0] == expected_status, (
+        f'Expected status={expected_status!r}, got {row[0]!r}'
+    )
+    assert row[1] is not None and error_substr.lower() in row[1].lower(), (
+        f'Expected error_message to contain {error_substr!r}, got {row[1]!r}'
+    )
+
+
+def assert_no_experiment_row(engine: Engine, experiment_run_id: int) -> None:
+    """Assert that no experiment_run row exists for the given id."""
+    with engine.connect() as conn:
+        count = conn.execute(
+            text('SELECT COUNT(*) FROM public.experiment_run WHERE id = :id'),
+            {'id': experiment_run_id},
+        ).scalar()
+    assert count == 0, (
+        f'Expected no experiment_run row for id={experiment_run_id}, found {count}'
+    )
+
+
+def load_scenario(scenario_filename: str) -> dict[str, Any]:
+    """
+    Load a test scenario JSON file from docs/test-scenarios/.
+
+    Args:
+        scenario_filename: Filename without path (e.g. '01-linear-regression-basic.json').
+
+    Returns:
+        dict: Parsed scenario payload.
+    """
+    scenario_path = (
+        Path(__file__).parent.parent / 'docs' / 'test-scenarios' / scenario_filename
+    )
+    with open(scenario_path) as f:
+        return json.load(f)
--- a/e2e/test_cleanup_files_workflow.py
+++ b/e2e/test_cleanup_files_workflow.py
@@ -0,0 +1,108 @@
+"""
+End-to-end tests for CleanupFiles workflow.
+
+Covers scenarios 3.x: cleanup of temporary local directories.
+"""
+
+import pytest
+from temporalio.testing import WorkflowEnvironment
+from temporalio.worker import Worker
+
+from e2e.helpers import make_workflow_id, start_and_await_workflow
+from model_manager.workflows.cleanup_files import CleanupFiles
+
+# Matches Cleanup.dir_timestamp_pattern: name_YYYYMMDD_HHMMSS_microseconds
+_STALE_DIR_OLD = 'stale_run_20200102_030405_000001'
+_STALE_DIR_OLDER = 'stale_run_20191231_235959_999999'
+
+
+@pytest.mark.asyncio
+@pytest.mark.integration
+async def test_scenario_3_1_1_cleanup_with_no_temp_dirs(
+    temporal_test_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    tmp_path,
+):
+    """Scenario 3.1.1 – Cleanup when the temp directory is empty.
+
+    The cleanup_temp_directories activity should complete without error
+    and the workflow should finish successfully.
+    """
+    # Use an empty temp directory as the reports path
+    empty_dir = tmp_path / 'reports_temp'
+    empty_dir.mkdir()
+
+    result = await start_and_await_workflow(
+        temporal_test_env.client,
+        CleanupFiles.run,
+        {'temp_path': str(empty_dir)},
+        make_workflow_id('test-s3-1-1'),
+    )
+
+    # Workflow returns None on success
+    assert result is None
+
+
+@pytest.mark.asyncio
+@pytest.mark.integration
+async def test_scenario_3_1_2_cleanup_removes_old_temp_dirs(
+    temporal_test_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    tmp_path,
+):
+    """Scenario 3.1.2 – Cleanup removes stale subdirectories from the temp dir.
+
+    Creates two subdirectories with timestamp suffixes inside the reports
+    temp directory and verifies the activity removes them.
+    """
+    reports_dir = tmp_path / 'reports_temp'
+    reports_dir.mkdir()
+
+    # Create two stale run directories (names must match cleanup activity regex)
+    stale1 = reports_dir / _STALE_DIR_OLD
+    stale2 = reports_dir / _STALE_DIR_OLDER
+    stale1.mkdir()
+    stale2.mkdir()
+    (stale1 / 'model.pkl').write_bytes(b'fake-model-data')
+    (stale2 / 'report.json').write_bytes(b'{"status": "old"}')
+
+    result = await start_and_await_workflow(
+        temporal_test_env.client,
+        CleanupFiles.run,
+        {'temp_path': str(reports_dir)},
+        make_workflow_id('test-s3-1-2'),
+    )
+
+    assert result is None
+
+    # The activity should have cleaned up the stale directories
+    remaining = list(reports_dir.iterdir())
+    assert len(remaining) == 0, (
+        f'Expected all stale dirs to be removed, but found: {remaining}'
+    )
+
+
+@pytest.mark.asyncio
+@pytest.mark.integration
+async def test_scenario_3_1_3_cleanup_nonexistent_temp_path(
+    temporal_test_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    tmp_path,
+):
+    """Scenario 3.1.3 – Cleanup with a temp_path that does not exist.
+
+    The activity must handle a missing directory gracefully without
+    raising an unhandled exception, since the directory may have already
+    been cleaned by a previous run.
+    """
+    nonexistent = str(tmp_path / 'does_not_exist' / 'reports')
+
+    # Should not raise — the activity is expected to handle a missing path
+    result = await start_and_await_workflow(
+        temporal_test_env.client,
+        CleanupFiles.run,
+        {'temp_path': nonexistent},
+        make_workflow_id('test-s3-1-3'),
+    )
+
+    assert result is None
--- a/e2e/test_train_model_validation.py
+++ b/e2e/test_train_model_validation.py
@@ -0,0 +1,298 @@
+"""
+End-to-end tests for TrainModel parameter validation paths.
+
+Covers scenarios 2.1.x: workflows that must terminate with
+ORCHESTRATOR_VALIDATION_ERROR due to invalid parameter values.
+"""
+
+import pytest
+from temporalio.client import WorkflowFailureError
+from temporalio.testing import WorkflowEnvironment
+from temporalio.worker import Worker
+
+from e2e.helpers import (
+    assert_experiment_error,
+    insert_experiment_run,
+    load_scenario,
+    make_workflow_id,
+    start_and_await_workflow,
+)
+from model_manager.workflows.train_model import TrainModel
+
+# Base experiment_run ids for validation test scenarios (offset to avoid collision)
+_VALIDATION_ID_BASE = 3000
+
+
+def _exception_chain_text(exc: BaseException) -> str:
+    """Concatenate messages from an exception __cause__/__context__ chain."""
+    parts: list[str] = []
+    cur: BaseException | None = exc
+    seen: set[int] = set()
+    while cur is not None and id(cur) not in seen:
+        seen.add(id(cur))
+        text = str(cur).strip()
+        if text:
+            parts.append(text)
+        cur = cur.__cause__ or getattr(cur, '__context__', None)
+    return ' | '.join(parts).lower()
+
+
+@pytest.mark.asyncio
+@pytest.mark.integration
+async def test_scenario_2_1_1_train_size_out_of_range(
+    temporal_test_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    postgres_engine,
+):
+    """Scenario 2.1.1 – train_size=5 violates the 10–100 business rule.
+
+    Expected: workflow updates status → ORCHESTRATOR_VALIDATION_ERROR
+    and error_message references 'train_size'.
+    """
+    experiment_run_id = _VALIDATION_ID_BASE + 1
+    scenario = load_scenario('01-linear-regression-basic.json')
+    scenario = {**scenario, 'experiment_run_id': experiment_run_id, 'train_size': 5}
+    insert_experiment_run(postgres_engine, experiment_run_id)
+
+    with pytest.raises(Exception):
+        await start_and_await_workflow(
+            temporal_test_env.client,
+            TrainModel.run,
+            scenario,
+            make_workflow_id('test-s2-1-1'),
+        )
+
+    assert_experiment_error(
+        postgres_engine,
+        experiment_run_id,
+        expected_status='ORCHESTRATOR_VALIDATION_ERROR',
+        error_substr='train_size',
+    )
+
+
+@pytest.mark.asyncio
+@pytest.mark.integration
+async def test_scenario_2_1_2_empty_variable_columns(
+    temporal_test_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    postgres_engine,
+):
+    """Scenario 2.1.2 – variable_columns=[] → ORCHESTRATOR_VALIDATION_ERROR."""
+    experiment_run_id = _VALIDATION_ID_BASE + 2
+    scenario = load_scenario('01-linear-regression-basic.json')
+    scenario = {**scenario, 'experiment_run_id': experiment_run_id, 'variable_columns': []}
+    insert_experiment_run(postgres_engine, experiment_run_id)
+
+    with pytest.raises(Exception):
+        await start_and_await_workflow(
+            temporal_test_env.client,
+            TrainModel.run,
+            scenario,
+            make_workflow_id('test-s2-1-2'),
+        )
+
+    assert_experiment_error(
+        postgres_engine,
+        experiment_run_id,
+        expected_status='ORCHESTRATOR_VALIDATION_ERROR',
+        error_substr='variable_columns',
+    )
+
+
+@pytest.mark.asyncio
+@pytest.mark.integration
+async def test_scenario_2_1_3_invalid_date_format(
+    temporal_test_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    postgres_engine,
+):
+    """Scenario 2.1.3 – date_format='INVALID' is not in the allowed list."""
+    experiment_run_id = _VALIDATION_ID_BASE + 3
+    scenario = load_scenario('01-linear-regression-basic.json')
+    scenario = {**scenario, 'experiment_run_id': experiment_run_id, 'date_format': 'INVALID'}
+    insert_experiment_run(postgres_engine, experiment_run_id)
+
+    with pytest.raises(Exception):
+        await start_and_await_workflow(
+            temporal_test_env.client,
+            TrainModel.run,
+            scenario,
+            make_workflow_id('test-s2-1-3'),
+        )
+
+    assert_experiment_error(
+        postgres_engine,
+        experiment_run_id,
+        expected_status='ORCHESTRATOR_VALIDATION_ERROR',
+        error_substr='date_format',
+    )
+
+
+@pytest.mark.asyncio
+@pytest.mark.integration
+async def test_scenario_2_1_4_whitespace_only_model_name(
+    temporal_test_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    postgres_engine,
+):
+    """Scenario 2.1.4 – model_name='   ' (whitespace) → ORCHESTRATOR_VALIDATION_ERROR."""
+    experiment_run_id = _VALIDATION_ID_BASE + 4
+    scenario = load_scenario('01-linear-regression-basic.json')
+    scenario = {**scenario, 'experiment_run_id': experiment_run_id, 'model_name': '   '}
+    insert_experiment_run(postgres_engine, experiment_run_id)
+
+    with pytest.raises(Exception):
+        await start_and_await_workflow(
+            temporal_test_env.client,
+            TrainModel.run,
+            scenario,
+            make_workflow_id('test-s2-1-4'),
+        )
+
+    assert_experiment_error(
+        postgres_engine,
+        experiment_run_id,
+        expected_status='ORCHESTRATOR_VALIDATION_ERROR',
+        error_substr='model_name',
+    )
+
+
+@pytest.mark.asyncio
+@pytest.mark.integration
+async def test_scenario_2_1_5_unknown_model_type(
+    temporal_test_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    postgres_engine,
+):
+    """Scenario 2.1.5 – model_type='totally_unknown' → ORCHESTRATOR_VALIDATION_ERROR.
+
+    The PluginStore will not find this model in the Gitea repo, causing
+    load_model_metadata to fail before validate_train_params is even called.
+    """
+    experiment_run_id = _VALIDATION_ID_BASE + 5
+    scenario = load_scenario('01-linear-regression-basic.json')
+    scenario = {
+        **scenario,
+        'experiment_run_id': experiment_run_id,
+        'model_type': 'totally_unknown_model',
+    }
+    insert_experiment_run(postgres_engine, experiment_run_id)
+
+    with pytest.raises(Exception):
+        await start_and_await_workflow(
+            temporal_test_env.client,
+            TrainModel.run,
+            scenario,
+            make_workflow_id('test-s2-1-5'),
+        )
+
+    assert_experiment_error(
+        postgres_engine,
+        experiment_run_id,
+        expected_status='ORCHESTRATOR_VALIDATION_ERROR',
+        error_substr='totally_unknown_model',
+    )
+
+
+@pytest.mark.asyncio
+@pytest.mark.integration
+async def test_scenario_2_1_6_missing_target_variable(
+    temporal_test_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    postgres_engine,
+):
+    """Scenario 2.1.6 – target_variable='' (empty string) → ORCHESTRATOR_VALIDATION_ERROR."""
+    experiment_run_id = _VALIDATION_ID_BASE + 6
+    scenario = load_scenario('01-linear-regression-basic.json')
+    scenario = {**scenario, 'experiment_run_id': experiment_run_id, 'target_variable': ''}
+    insert_experiment_run(postgres_engine, experiment_run_id)
+
+    with pytest.raises(Exception):
+        await start_and_await_workflow(
+            temporal_test_env.client,
+            TrainModel.run,
+            scenario,
+            make_workflow_id('test-s2-1-6'),
+        )
+
+    assert_experiment_error(
+        postgres_engine,
+        experiment_run_id,
+        expected_status='ORCHESTRATOR_VALIDATION_ERROR',
+        error_substr='target_variable',
+    )
+
+
+@pytest.mark.asyncio
+@pytest.mark.integration
+async def test_scenario_2_1_7_missing_experiment_run_id(
+    temporal_test_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+):
+    """Scenario 2.1.7 – experiment_run_id missing → workflow raises ValueError immediately.
+
+    No DB row is inserted because experiment_run_id is mandatory to even
+    know which row to update. The workflow should raise before any DB call.
+    """
+    scenario = load_scenario('01-linear-regression-basic.json')
+    scenario = {k: v for k, v in scenario.items() if k != 'experiment_run_id'}
+
+    with pytest.raises(WorkflowFailureError) as excinfo:
+        await start_and_await_workflow(
+            temporal_test_env.client,
+            TrainModel.run,
+            scenario,
+            make_workflow_id('test-s2-1-7'),
+        )
+    combined = _exception_chain_text(excinfo.value)
+    assert 'experiment_run_id' in combined
+
+
+@pytest.mark.asyncio
+@pytest.mark.integration
+async def test_scenario_2_1_8_missing_date_column(
+    temporal_test_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+):
+    """Scenario 2.1.8 – date_column missing in payload raises before workflow business validation."""
+    scenario = load_scenario('01-linear-regression-basic.json')
+    scenario = {k: v for k, v in scenario.items() if k != 'date_column'}
+
+    with pytest.raises(WorkflowFailureError) as excinfo:
+        await start_and_await_workflow(
+            temporal_test_env.client,
+            TrainModel.run,
+            scenario,
+            make_workflow_id('test-s2-1-8'),
+        )
+    combined = _exception_chain_text(excinfo.value)
+    assert 'date_column' in combined
+
+
+@pytest.mark.asyncio
+@pytest.mark.integration
+async def test_scenario_2_1_9_whitespace_date_column(
+    temporal_test_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    postgres_engine,
+):
+    """Scenario 2.1.9 – date_column='   ' must produce ORCHESTRATOR_VALIDATION_ERROR."""
+    experiment_run_id = _VALIDATION_ID_BASE + 9
+    scenario = load_scenario('01-linear-regression-basic.json')
+    scenario = {**scenario, 'experiment_run_id': experiment_run_id, 'date_column': '   '}
+    insert_experiment_run(postgres_engine, experiment_run_id)
+
+    with pytest.raises(Exception):
+        await start_and_await_workflow(
+            temporal_test_env.client,
+            TrainModel.run,
+            scenario,
+            make_workflow_id('test-s2-1-9'),
+        )
+
+    assert_experiment_error(
+        postgres_engine,
+        experiment_run_id,
+        expected_status='ORCHESTRATOR_VALIDATION_ERROR',
+        error_substr='date_column',
+    )
--- a/e2e/test_train_model_workflow.py
+++ b/e2e/test_train_model_workflow.py
@@ -0,0 +1,493 @@
+"""
+End-to-end tests for TrainModel workflow – main workflow scenarios.
+
+Covers:
+  1.1.x – Happy-path training (various scenarios from docs/test-scenarios/)
+  1.2.x – Error paths (MinIO failure, missing DB row)
+"""
+
+import pytest
+from temporalio.testing import WorkflowEnvironment
+from temporalio.worker import Worker
+
+from e2e.helpers import (
+    assert_experiment_error,
+    assert_experiment_run_name_set,
+    assert_experiment_status,
+    assert_no_experiment_row,
+    insert_experiment_run,
+    load_scenario,
+    make_workflow_id,
+    start_and_await_workflow,
+)
+from model_manager.workflows.train_model import TrainModel
+
+
+# ---------------------------------------------------------------------------
+# 1.1 – Happy paths
+# ---------------------------------------------------------------------------
+
+@pytest.mark.asyncio
+@pytest.mark.integration
+async def test_scenario_1_1_1_linear_regression_basic(
+    temporal_test_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    postgres_engine,
+):
+    """Scenario 1.1.1 – Linear Regression Basic (cenário 01).
+
+    Validates the complete training pipeline end-to-end:
+    load_model_metadata → validate_train_params → train_model →
+    update_experiment_run (TRAINING_SUCCESS).
+    """
+    scenario = load_scenario('01-linear-regression-basic.json')
+    experiment_run_id = scenario['experiment_run_id']
+    insert_experiment_run(postgres_engine, experiment_run_id)
+
+    await start_and_await_workflow(
+        temporal_test_env.client,
+        TrainModel.run,
+        scenario,
+        make_workflow_id('test-s1-1-1'),
+    )
+
+    assert_experiment_status(postgres_engine, experiment_run_id, 'TRAINING_SUCCESS')
+    assert_experiment_run_name_set(postgres_engine, experiment_run_id)
+
+
+@pytest.mark.asyncio
+@pytest.mark.integration
+async def test_scenario_1_1_2_linear_regression_with_scaler(
+    temporal_test_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    postgres_engine,
+):
+    """Scenario 1.1.2 – Linear regression with Standard Scaler (cenário 02)."""
+    scenario = load_scenario('02-linear-regression-with-scaler.json')
+    experiment_run_id = scenario['experiment_run_id']
+    insert_experiment_run(postgres_engine, experiment_run_id)
+
+    await start_and_await_workflow(
+        temporal_test_env.client,
+        TrainModel.run,
+        scenario,
+        make_workflow_id('test-s1-1-2'),
+    )
+
+    assert_experiment_status(postgres_engine, experiment_run_id, 'TRAINING_SUCCESS')
+    assert_experiment_run_name_set(postgres_engine, experiment_run_id)
+
+
+@pytest.mark.asyncio
+@pytest.mark.integration
+async def test_scenario_1_1_3_polynomial_regression_degree2_with_scaler(
+    temporal_test_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    postgres_engine,
+):
+    """Scenario 1.1.3 – Polynomial Regression Degree 2 with Standard Scaler (cenário 03)."""
+    scenario = load_scenario('03-polynomial-regression-degree2.json')
+    experiment_run_id = scenario['experiment_run_id']
+    insert_experiment_run(postgres_engine, experiment_run_id)
+
+    await start_and_await_workflow(
+        temporal_test_env.client,
+        TrainModel.run,
+        scenario,
+        make_workflow_id('test-s1-1-3'),
+    )
+
+    assert_experiment_status(postgres_engine, experiment_run_id, 'TRAINING_SUCCESS')
+    assert_experiment_run_name_set(postgres_engine, experiment_run_id)
+
+
+@pytest.mark.asyncio
+@pytest.mark.integration
+async def test_scenario_1_1_4_polynomial_regression_degree3_with_scaler(
+    temporal_test_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    postgres_engine,
+):
+    """Scenario 1.1.4 – Polynomial regression degree 3 with Standard Scaler (cenário 04)."""
+    scenario = load_scenario('04-polynomial-regression-degree3.json')
+    experiment_run_id = scenario['experiment_run_id']
+    insert_experiment_run(postgres_engine, experiment_run_id)
+
+    await start_and_await_workflow(
+        temporal_test_env.client,
+        TrainModel.run,
+        scenario,
+        make_workflow_id('test-s1-1-4'),
+    )
+
+    assert_experiment_status(postgres_engine, experiment_run_id, 'TRAINING_SUCCESS')
+    assert_experiment_run_name_set(postgres_engine, experiment_run_id)
+
+
+@pytest.mark.asyncio
+@pytest.mark.integration
+async def test_scenario_1_1_5_linear_regression_with_lags(
+    temporal_test_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    postgres_engine,
+):
+    """Scenario 1.1.5 – Linear Regression with lag_train/lag_val per variable (cenário 05)."""
+    scenario = load_scenario('05-linear-regression-with-lags.json')
+    experiment_run_id = scenario['experiment_run_id']
+    insert_experiment_run(postgres_engine, experiment_run_id)
+
+    await start_and_await_workflow(
+        temporal_test_env.client,
+        TrainModel.run,
+        scenario,
+        make_workflow_id('test-s1-1-5'),
+    )
+
+    assert_experiment_status(postgres_engine, experiment_run_id, 'TRAINING_SUCCESS')
+    assert_experiment_run_name_set(postgres_engine, experiment_run_id)
+
+
+@pytest.mark.asyncio
+@pytest.mark.integration
+async def test_scenario_1_1_6_linear_regression_nan_interpolation(
+    temporal_test_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    postgres_engine,
+):
+    """Scenario 1.1.6 – nan_treatment='linear interpolation' (cenário 06)."""
+    scenario = load_scenario('06-linear-regression-nan-interpolation.json')
+    experiment_run_id = scenario['experiment_run_id']
+    insert_experiment_run(postgres_engine, experiment_run_id)
+
+    await start_and_await_workflow(
+        temporal_test_env.client,
+        TrainModel.run,
+        scenario,
+        make_workflow_id('test-s1-1-6'),
+    )
+
+    assert_experiment_status(postgres_engine, experiment_run_id, 'TRAINING_SUCCESS')
+
+
+@pytest.mark.asyncio
+@pytest.mark.integration
+async def test_scenario_1_1_7_linear_regression_static_window_removal(
+    temporal_test_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    postgres_engine,
+):
+    """Scenario 1.1.7 – rem_static_win=true with default static_threshold (cenário 07)."""
+    scenario = load_scenario('07-linear-regression-static-window-removal.json')
+    experiment_run_id = scenario['experiment_run_id']
+    insert_experiment_run(postgres_engine, experiment_run_id)
+
+    await start_and_await_workflow(
+        temporal_test_env.client,
+        TrainModel.run,
+        scenario,
+        make_workflow_id('test-s1-1-7'),
+    )
+
+    assert_experiment_status(postgres_engine, experiment_run_id, 'TRAINING_SUCCESS')
+
+
+@pytest.mark.asyncio
+@pytest.mark.integration
+async def test_scenario_1_1_8_linear_regression_with_limits(
+    temporal_test_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    postgres_engine,
+):
+    """Scenario 1.1.8 – support_filters with min/max limits per variable (cenário 08)."""
+    scenario = load_scenario('08-linear-regression-with-limits.json')
+    experiment_run_id = scenario['experiment_run_id']
+    insert_experiment_run(postgres_engine, experiment_run_id)
+
+    await start_and_await_workflow(
+        temporal_test_env.client,
+        TrainModel.run,
+        scenario,
+        make_workflow_id('test-s1-1-8'),
+    )
+
+    assert_experiment_status(postgres_engine, experiment_run_id, 'TRAINING_SUCCESS')
+
+
+@pytest.mark.asyncio
+@pytest.mark.integration
+async def test_scenario_1_1_9_polynomial_degree2_scaler_and_lags(
+    temporal_test_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    postgres_engine,
+):
+    """Scenario 1.1.9 – Polynomial degree 2, Standard Scaler and lags (cenário 09)."""
+    scenario = load_scenario('09-polynomial-degree2-with-scaler-and-lags.json')
+    experiment_run_id = scenario['experiment_run_id']
+    insert_experiment_run(postgres_engine, experiment_run_id)
+
+    await start_and_await_workflow(
+        temporal_test_env.client,
+        TrainModel.run,
+        scenario,
+        make_workflow_id('test-s1-1-9'),
+    )
+
+    assert_experiment_status(postgres_engine, experiment_run_id, 'TRAINING_SUCCESS')
+    assert_experiment_run_name_set(postgres_engine, experiment_run_id)
+
+
+@pytest.mark.asyncio
+@pytest.mark.integration
+async def test_scenario_1_1_10_linear_regression_with_ar_opt_params(
+    temporal_test_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    postgres_engine,
+):
+    """Scenario 1.1.10 – Linear regression with include_ar in opt_params (cenário 10)."""
+    scenario = load_scenario('10-linear-regression-with-ar.json')
+    experiment_run_id = scenario['experiment_run_id']
+    insert_experiment_run(postgres_engine, experiment_run_id)
+
+    await start_and_await_workflow(
+        temporal_test_env.client,
+        TrainModel.run,
+        scenario,
+        make_workflow_id('test-s1-1-10'),
+    )
+
+    assert_experiment_status(postgres_engine, experiment_run_id, 'TRAINING_SUCCESS')
+    assert_experiment_run_name_set(postgres_engine, experiment_run_id)
+
+
+@pytest.mark.asyncio
+@pytest.mark.integration
+async def test_scenario_1_1_11_linear_regression_static_threshold_custom(
+    temporal_test_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    postgres_engine,
+):
+    """Scenario 1.1.11 – rem_static_win=true with custom static_threshold (cenário 11)."""
+    scenario = load_scenario('11-linear-regression-static-threshold-custom.json')
+    experiment_run_id = scenario['experiment_run_id']
+    insert_experiment_run(postgres_engine, experiment_run_id)
+
+    await start_and_await_workflow(
+        temporal_test_env.client,
+        TrainModel.run,
+        scenario,
+        make_workflow_id('test-s1-1-11'),
+    )
+
+    assert_experiment_status(postgres_engine, experiment_run_id, 'TRAINING_SUCCESS')
+
+
+@pytest.mark.asyncio
+@pytest.mark.integration
+async def test_scenario_1_1_12_alternate_date_format_dd_mm_yyyy(
+    temporal_test_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    postgres_engine,
+):
+    """Scenario 1.1.12 – DATA column and dd/MM/yyyy format CSV (cenário 12)."""
+    scenario = load_scenario('12-angular-test-date-format.json')
+    experiment_run_id = scenario['experiment_run_id']
+    insert_experiment_run(
+        postgres_engine,
+        experiment_run_id,
+        file_name='training_data_dd_mm_yyyy.csv',
+    )
+
+    await start_and_await_workflow(
+        temporal_test_env.client,
+        TrainModel.run,
+        scenario,
+        make_workflow_id('test-s1-1-12'),
+    )
+
+    assert_experiment_status(postgres_engine, experiment_run_id, 'TRAINING_SUCCESS')
+    assert_experiment_run_name_set(postgres_engine, experiment_run_id)
+
+
+@pytest.mark.asyncio
+@pytest.mark.integration
+async def test_scenario_1_1_13_alternate_csv_narrow_date_window(
+    temporal_test_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    postgres_engine,
+):
+    """Scenario 1.1.13 – Same alternate CSV as 12 with date window (cenário 13)."""
+    scenario = load_scenario('13-angular-test-double-date-column.json')
+    experiment_run_id = scenario['experiment_run_id']
+    insert_experiment_run(
+        postgres_engine,
+        experiment_run_id,
+        file_name='training_data_dd_mm_yyyy.csv',
+    )
+
+    await start_and_await_workflow(
+        temporal_test_env.client,
+        TrainModel.run,
+        scenario,
+        make_workflow_id('test-s1-1-13'),
+    )
+
+    assert_experiment_status(postgres_engine, experiment_run_id, 'TRAINING_SUCCESS')
+
+
+@pytest.mark.asyncio
+@pytest.mark.integration
+async def test_scenario_1_1_14_polynomial_with_support_filters(
+    temporal_test_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    postgres_engine,
+):
+    """Scenario 1.1.14 – Polynomial degree 4, Standard Scaler, line support filters (cenário 14)."""
+    scenario = load_scenario('14-angular-test-polynomial-support-filters.json')
+    experiment_run_id = scenario['experiment_run_id']
+    insert_experiment_run(postgres_engine, experiment_run_id)
+
+    await start_and_await_workflow(
+        temporal_test_env.client,
+        TrainModel.run,
+        scenario,
+        make_workflow_id('test-s1-1-14'),
+    )
+
+    assert_experiment_status(postgres_engine, experiment_run_id, 'TRAINING_SUCCESS')
+
+
+@pytest.mark.asyncio
+@pytest.mark.integration
+async def test_scenario_1_1_15_linear_regression_custom_target_column_name(
+    temporal_test_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    postgres_engine,
+):
+    """Scenario 1.1.15 – Target column is not named ``target``; report path uses target_variable."""
+    scenario = load_scenario('15-linear-regression-custom-target-column.json')
+    experiment_run_id = scenario['experiment_run_id']
+    insert_experiment_run(
+        postgres_engine,
+        experiment_run_id,
+        file_name='training_data_custom_target.csv',
+    )
+
+    await start_and_await_workflow(
+        temporal_test_env.client,
+        TrainModel.run,
+        scenario,
+        make_workflow_id('test-s1-1-15'),
+    )
+
+    assert_experiment_status(postgres_engine, experiment_run_id, 'TRAINING_SUCCESS')
+    assert_experiment_run_name_set(postgres_engine, experiment_run_id)
+
+
+@pytest.mark.asyncio
+@pytest.mark.integration
+async def test_scenario_1_1_16_naive_timestamp_header_column(
+    temporal_test_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    postgres_engine,
+):
+    """Scenario 1.1.16 – CSV uses ``Timestamp`` header; snake_case date_column/date_format."""
+    scenario = load_scenario('16-linear-regression-naive-timestamp-header.json')
+    experiment_run_id = scenario['experiment_run_id']
+    insert_experiment_run(
+        postgres_engine,
+        experiment_run_id,
+        file_name='training_data_timestamp_naive.csv',
+    )
+
+    await start_and_await_workflow(
+        temporal_test_env.client,
+        TrainModel.run,
+        scenario,
+        make_workflow_id('test-s1-1-16'),
+    )
+
+    assert_experiment_status(postgres_engine, experiment_run_id, 'TRAINING_SUCCESS')
+    assert_experiment_run_name_set(postgres_engine, experiment_run_id)
+
+
+@pytest.mark.asyncio
+@pytest.mark.integration
+async def test_scenario_1_1_17_linear_regression_blank_timestamp_row_dropped(
+    temporal_test_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    postgres_engine,
+):
+    """Scenario 1.1.17 – CSV has one empty timestamp cell; row is dropped and training succeeds."""
+    scenario = load_scenario('17-linear-regression-blank-timestamp-row.json')
+    experiment_run_id = scenario['experiment_run_id']
+    insert_experiment_run(
+        postgres_engine,
+        experiment_run_id,
+        file_name='training_data_blank_timestamp_row.csv',
+    )
+
+    await start_and_await_workflow(
+        temporal_test_env.client,
+        TrainModel.run,
+        scenario,
+        make_workflow_id('test-s1-1-17'),
+    )
+
+    assert_experiment_status(postgres_engine, experiment_run_id, 'TRAINING_SUCCESS')
+    assert_experiment_run_name_set(postgres_engine, experiment_run_id)
+
+
+# ---------------------------------------------------------------------------
+# 1.2 – Error paths
+# ---------------------------------------------------------------------------
+
+@pytest.mark.asyncio
+@pytest.mark.integration
+async def test_scenario_1_2_1_minio_file_not_found(
+    temporal_test_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    postgres_engine,
+):
+    """Scenario 1.2.1 – Training file does not exist in MinIO → TRAINING_ERROR."""
+    scenario = load_scenario('01-linear-regression-basic.json')
+    scenario = {**scenario, 'experiment_run_id': 2001, 'file_name': 'does_not_exist.csv'}
+    experiment_run_id = 2001
+    insert_experiment_run(postgres_engine, experiment_run_id)
+
+    with pytest.raises(Exception):
+        await start_and_await_workflow(
+            temporal_test_env.client,
+            TrainModel.run,
+            scenario,
+            make_workflow_id('test-s1-2-1'),
+        )
+
+    assert_experiment_error(
+        postgres_engine,
+        experiment_run_id,
+        expected_status='TRAINING_ERROR',
+        error_substr='does_not_exist',
+    )
+
+
+@pytest.mark.asyncio
+@pytest.mark.integration
+async def test_scenario_1_2_2_experiment_run_id_not_in_db(
+    temporal_test_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    postgres_engine,
+):
+    """Scenario 1.2.2 – experiment_run_id row absent → update_experiment_run raises."""
+    scenario = load_scenario('01-linear-regression-basic.json')
+    scenario = {**scenario, 'experiment_run_id': 9999}
+    # Intentionally NOT inserting the row
+
+    with pytest.raises(Exception):
+        await start_and_await_workflow(
+            temporal_test_env.client,
+            TrainModel.run,
+            scenario,
+            make_workflow_id('test-s1-2-2'),
+        )
+
+    assert_no_experiment_row(postgres_engine, 9999)
--- a/git_requirements_mapping.txt
+++ b/git_requirements_mapping.txt
@@ -0,0 +1,2 @@
+sientia_do: git+ssh://git@github.com/Aignosi/sientia-dataops-library.git
+sientia_model: git+ssh://git@github.com/Aignosi/sientia-model-library.git
--- a/input-sample.json
+++ b/input-sample.json
@@ -0,0 +1,38 @@
+{
+  "experiment_run_id": 1001,
+  "variable_columns": ["feature_a", "feature_b"],
+  "target_variable": "target",
+  "bucket_name": "model-training",
+  "file_name": "training_data.csv",
+  "line_separator": ",",
+  "decimal_separator": ".",
+  "date_column": "timestamp",
+  "train_size": 80,
+  "shuffle": true,
+  "random_state": 42,
+  "model_name": "Linear Regression",
+  "model_type": "linear_regression",
+  "data_model_kwargs": {
+    "lag_train": {
+      "feature_a": 0,
+      "feature_b": 0
+    },
+    "lag_val": {
+      "feature_a": 0,
+      "feature_b": 0
+    },
+    "nan_treatment": "drop",
+    "rem_static_win": false,
+    "static_threshold": null,
+    "start_date": null,
+    "end_date": null,
+    "support_filters": {},
+    "removed_intervals": []
+  },
+  "model_kwargs": {
+    "degree": 1,
+    "interaction_only": false,
+    "scaler_name": "Standard Scaler"
+  },
+  "opt_params": {}
+}
--- a/input-sample.md
+++ b/input-sample.md
@@ -0,0 +1,76 @@
+##### Insert a new experiment run
+
+```sql
+-- Optional: remove a previous run with the same id
+DELETE FROM public.experiment_run WHERE experiment_run_id = 1001;
+```
+
+```sql
+INSERT INTO public.experiment_run
+(experiment_name, run_name, username, status, error_message, created_at,
+updated_at, bucket_name, file_name, request_data, orchestrator_response_data)
+VALUES(
+	'test-experiment-name',
+	'test-run-name',
+	'test-username',
+	'ORCHESTRATOR_WAITING_PROC',
+	null,
+	now(),
+	now(),
+	'model-training',
+	'training_data.csv',
+	'{"experiment_run_id":1001,"variable_columns":["feature_a","feature_b"],"target_variable":"target","bucket_name":"model-training","file_name":"training_data.csv","line_separator":",","decimal_separator":".","train_size":80,"shuffle":true,"model_name":"Linear Regression","model_type":"linear_regression","data_model_kwargs":{"lag_train":{"feature_a":0,"feature_b":0},"lag_val":{"feature_a":0,"feature_b":0},"nan_treatment":"drop"},"model_kwargs":{"degree":1,"scaler_name":"Standard Scaler"},"opt_params":{}}',
+  null
+);
+```
+
+##### Upload the input dataset to MinIO
+
+```bash
+mc cp input_dataset.csv suse/model-training/training-sample-dataset-1001.csv
+```
+
+##### Temporal input payload sample
+
+Keys match `TrainModelParams.from_dict` in `model_manager/utils/models/train_model_params.py`: every field passed to `_check_none` must be present, including **`date_column`**; `model_metadata` must be non-empty for `validate_business_rules()`. You may omit **`date_format`** (defaults to `yyyy-MM-dd HH:mm:ss`). Omit optional keys (`random_state`, `val_file_name`, `model_id`) when defaults or `None` apply.
+
+```json
+{
+  "experiment_run_id": 1001,
+  "variable_columns": ["feature_a", "feature_b"],
+  "target_variable": "target",
+  "bucket_name": "model-training",
+  "file_name": "training-sample-dataset-1001.csv",
+  "line_separator": ",",
+  "decimal_separator": ".",
+  "date_column": "timestamp",
+  "train_size": 80,
+  "shuffle": true,
+  "random_state": 42,
+  "model_name": "test-runtime-linear-regression-model",
+  "model_type": "linear_regression",
+  "data_model_kwargs": {
+    "lag_train": {
+      "feature_a": 0,
+      "feature_b": 0
+    },
+    "lag_val": {
+      "feature_a": 0,
+      "feature_b": 0
+    },
+    "nan_treatment": "drop",
+    "rem_static_win": false,
+    "static_threshold": null,
+    "start_date": null,
+    "end_date": null,
+    "support_filters": {},
+    "removed_intervals": []
+  },
+  "model_kwargs": {
+    "degree": 1,
+    "interaction_only": false,
+    "scaler_name": "Standard Scaler"
+  },
+  "opt_params": {}
+}
+```
--- a/input_dataset.csv
+++ b/input_dataset.csv
@@ -0,0 +1,11 @@
+timestamp,Counter,Rollout,Square
+2026-01-01 00:00:00,1.0,2.0,5.1
+2026-01-01 00:01:00,2.0,2.0,5.9
+2026-01-01 00:02:00,2.0,3.0,8.3
+2026-01-01 00:03:00,3.0,3.0,9.2
+2026-01-01 00:04:00,3.0,4.0,10.8
+2026-01-01 00:05:00,4.0,4.0,11.7
+2026-01-01 00:06:00,4.0,5.0,14.1
+2026-01-01 00:07:00,5.0,5.0,15.15
+2026-01-01 00:08:00,5.0,6.0,17.2
+2026-01-01 00:09:00,6.0,6.0,17.9
--- a/model-manager-plugin-store-migration-plan.md
+++ b/model-manager-plugin-store-migration-plan.md
@@ -0,0 +1,385 @@
+---
+tags:
+  - engineering
+  - sientia
+  - runtime-system
+  - model-manager
+  - plugin-store
+  - migration-plan
+created: 2026-03-02
+modified: 2026-03-02
+created_by: Vitor Pimentel
+modified_by: Vitor Pimentel
+status: draft
+---
+
+# Sientia Model Manager — PluginStore Migration Plan
+
+> Implementation plan for migrating `sientia-dataops-model-manager` to use the Sientia PluginStore for runtime installation and model retrieval, aligned with the runtime architecture described in `analytics.md`.
+
+## Summary
+
+1. [[#Objectives and Scope|Objectives and Scope]] — What this migration must achieve
+2. [[#Existing State Overview (model-manager)|Existing State Overview]] — Current responsibilities and coupling points
+3. [[#Requirements Mapping|Requirements Mapping]] — Functional and non-functional requirements
+4. [[#Target Architecture|Target Architecture]] — Desired runtime and model-loading architecture
+5. [[#Implementation Plan|Implementation Plan]] — Phased, detailed changes to apply
+6. [[#Testing Strategy|Testing Strategy]] — How to validate the new behavior
+7. [[#Rollout and Migration Strategy|Rollout and Migration Strategy]] — How to safely roll out and deprecate old paths
+8. [[#Potential Model Library Changes|Potential Model Library Changes]] — Expected impact on `sientia-model-library`
+9. [[#Related Documents|Related Documents]] — Cross-links to supporting documents
+
+---
+
+## Objectives and Scope
+
+The goal of this work is to evolve `sientia-dataops-model-manager` so that:
+
+- It **detects the runtime** before the worker starts, using the `RUNTIME` environment variable.
+- It **installs the selected runtime** using the PluginStore runtime interface from `sientia_model.model_repository.plugin_store`:
+  - `PluginStore.install_runtime(runtime_name)`.
+- It **uses PluginStore to obtain models from the store**, instead of constructing them from the local ML template / mlops library:
+  - Pipelines call `PluginStore.get_model(...)` to obtain `SientiaModel` instances.
+  - The previous “in-repo model implementation plus mlops library” path is removed.
+
+Out of scope:
+
+- Changing Temporal workflow semantics (queues, retry policies, etc.).
+- Replacing the existing MLflow-based tracking and reporting; these remain the responsibility of `ModelRepository` and the reporting utilities.
+
+---
+
+## Existing State Overview (model-manager)
+
+The `sientia-dataops-model-manager` application currently:
+
+- **Worker orchestration** (`model_manager/worker/worker.py`)
+  - Reads Temporal configuration from env (`TEMPORAL_HOST`, `TEMPORAL_NAMESPACE`, task queues).
+  - Sets up observability (Prometheus, metrics, Sientia logger).
+  - Builds connector configs for Postgres, MLflow, MinIO, MongoDB.
+  - Instantiates `Activities` and schedules, then starts Temporal workers.
+  - Does not validate or install any “runtime” concept before worker startup.
+
+- **Training pipeline**
+  - `Training` activity (`model_manager/activities/training.py`) coordinates:
+    - Parameter validation (`validate_train_params`).
+    - Training execution via `TrainingRepository`.
+    - Saving trained models and artifacts via `ModelRepository` to MLflow.
+  - `TrainingRepository` (`model_manager/utils/repository/training_repository.py`):
+    - Loads and preprocesses CSV data (via `DataPreprocessor`).
+    - Trains a local `LinearRegressionModel` defined in `model_manager.sientia.models`.
+    - Computes metrics and builds a `TrainModelResult` for downstream steps.
+  - `ModelRepository` (`model_manager/utils/repository/model_repository.py`):
+    - Uses `ModelServing` and `Reports` to:
+      - Generate reports and CSV artifacts.
+      - Log parameters, metrics and models into MLflow.
+      - Today, production models are identified using **stages** (for example `Production`) in the Model Registry; aliases like `@production` are not yet used.
+      - MLflow-related logic here overlaps conceptually with the MLflow interactions implemented in `sientia-dataops-laborious_temporal`, which motivates extracting a **shared MLflow repository** into `sientia-dataops-library` (see `mlflow-shared-repository-migration-plan`).
+
+- **Coupling to models and runtimes**
+  - Training is tightly coupled to internal classes (`DataPreprocessor`, `LinearRegressionModel`).
+  - No runtime installation; env assumed ready.
+  - The system does not yet use PluginStore’s `get_model` or `install_runtime` capabilities.
+
+**MLflow:** All MLflow operations (lookup, promotion, etc.) → [[mlflow-shared-repository-migration-plan|shared repository]]. Model Manager uses the interface; it does not implement these concepts.
+
+### Current vs Target — High-level Flow
+
+```mermaid
+flowchart LR
+    subgraph currentState [Current State — Model Manager]
+        direction TB
+        WorkerMM["Temporal Worker\n(model_manager/worker.py)"]
+        ActivitiesMM["Activities\n(training, cleanup, etc.)"]
+        TrainRepo["TrainingRepository\n(local DataPreprocessor + LinearRegressionModel)"]
+        ModelRepoMM["ModelRepository\n(MLflow + reports)"]
+
+        WorkerMM -->|"Temporal tasks"| ActivitiesMM
+        ActivitiesMM -->|"train_model activity"| TrainRepo
+        TrainRepo -->|"TrainModelResult"| ModelRepoMM
+        ModelRepoMM -->|"experiments, runs, artifacts"| MLflowMM["MLflow Server"]
+    end
+
+    subgraph targetState [Target State — Model Manager]
+        direction TB
+        WorkerMM2["Temporal Worker\n+ Runtime bootstrap\n(read RUNTIME, install runtime)"]
+        ActivitiesMM2["Activities\n(+ ModelProvider)"]
+        PluginStoreNode["PluginStore\n(Gitea model store)"]
+        SientiaWrapper["SientiaModel wrapper\n(from store.get_model)"]
+        ModelRepoMM2["ModelRepository\n(MLflow + reports)"]
+
+        WorkerMM2 -->|"install_runtime(RUNTIME)"| PluginStoreNode
+        WorkerMM2 -->|"Temporal tasks"| ActivitiesMM2
+        ActivitiesMM2 -->|"get_training_model"| PluginStoreNode
+        PluginStoreNode -->|"SientiaModel instance"| SientiaWrapper
+        ActivitiesMM2 -->|"call train(...) on wrapper"| SientiaWrapper
+        SientiaWrapper -->|"TrainModelResult-compatible data"| ModelRepoMM2
+        ModelRepoMM2 -->|"experiments, runs, artifacts"| MLflowMM2["MLflow Server"]
+    end
+```
+
+### Current vs Target — Training Hot Path (Code Sketch)
+
+Current hot path in `TrainingRepository.train` (simplified):
+
+```python
+data = load_data(uploaded_file, params.line_separator, params.decimal_separator)
+data = _ensure_date_column_parsed(data, params)
+data = self._configure_datetime_index(data, params)
+
+process_data = self._init_data_preprocessor(params)
+process_data.fit(data)
+data_view = process_data.transform(data)
+
+x_train, x_test, y_train, y_test = split_train_test(...)
+
+regr = LinearRegressionModel(
+    target_variable=params.target_variable,
+    variable_columns=params.variable_columns,
+    degree=params.degree,
+    interaction_only=params.interaction_only,
+)
+regr.fit(pd.concat([x_train, y_train], axis=1))
+```
+
+Target hot path with PluginStore + `SientiaModel` (conceptual):
+
+```python
+data = load_and_preprocess(uploaded_file, params)          # keep existing preprocessing
+train_df, val_df = build_train_val_splits(data, params)   # explicit train/val
+
+wrapper = model_provider.get_training_model(
+    model_name=params.model_name,
+    runtime=os.environ["RUNTIME"],
+    opt_params={"env": params.environment},
+    model_kwargs={},
+    data_model_kwargs={},
+)
+
+wrapper.train(
+    train_data=train_df,
+    val_data=val_df,
+    target=params.target_variable,
+)
+
+# From here, metrics and artifacts are computed based on wrapper outputs
+```
+
+---
+
+## Requirements Mapping
+
+### Functional Requirements
+
+| ID    | Requirement                                  | Description                                                                                          | Impacted Areas                                                                 |
+|-------|----------------------------------------------|------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------|
+| FR-01 | Runtime detection via env var                | Before starting workers, read `RUNTIME` env var and fail fast if missing or empty                   | `model_manager/worker/worker.py`                                               |
+| FR-02 | Runtime installation via PluginStore         | Install the runtime defined in `RUNTIME` using `PluginStore.install_runtime(runtime_name)`          | `worker.py`, `sientia_model.model_repository.plugin_store.PluginStore`        |
+| FR-03 | PluginStore-based model retrieval            | Use `PluginStore.get_model(...)` to obtain `SientiaModel` instances for training                    | `TrainingRepository` (or new adapter), `Training` activity                     |
+| FR-04 | Remove mlops-library-based construction      | Do not construct models directly from `model_manager.sientia.models`; remove the mlops path  | `TrainingRepository`, `model_manager.sientia.models`, dependency graph        |
+| FR-05 | Use shared MLflow repository                | Delegate all MLflow ops (runs, metrics, artifacts, production lookup) to `SientiaMLflowRepository`; keep reports and `TrainModelResult` in Model Manager | `ModelRepository`, [[mlflow-shared-repository-migration-plan]] |
+| FR-06 | Centralized PluginStore configuration       | Configure PluginStore (Gitea URL, repo, auth, PyPI mirror) via env/config | Config helper, `worker.py`                                    |
+
+### Non-Functional Requirements
+
+| ID     | Requirement                              | Description                                                                                                       | Impacted Areas                                             |
+|--------|------------------------------------------|-------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------|
+| NFR-01 | Robust runtime bootstrap                 | If runtime installation fails, the worker must not start; errors must be explicit in logs/metrics                 | `worker.py`, PluginStore error handling                    |
+| NFR-02 | Single path                          | Use PluginStore + SientiaModel path only; no toggling or parallel old path | `worker.py`, Training activities                         |
+| NFR-03 | Observability and debuggability          | Logs and metrics must cover runtime detection, install attempts and PluginStore interactions                      | Logging around runtime and PluginStore                     |
+| NFR-04 | Testability                              | Unit and integration tests must cover runtime detection, install, and model retrieval                             | `tests/worker`, `tests/activities`, new PluginStore tests |
+| NFR-05 | Security                                 | No credentials hard-coded in source; rely on env/secret management                                                | Config helpers, deployment manifests                       |
+
+---
+
+## Target Architecture
+
+### Runtime bootstrap
+
+- **New required env var:** `RUNTIME` (name of the runtime; must match a runtime in the store index).
+- **New PluginStore configuration env vars** (names to be finalized):
+  - `STORE_BASE_URL`, `STORE_OWNER`, `STORE_REPO`
+  - Optional: `STORE_BRANCH`, `STORE_USERNAME`, `STORE_PASSWORD`, `PYPI_INDEX_URL`, `PYPI_USERNAME`, `PYPI_PASSWORD`
+- **Worker startup sequence** in `main()`:
+  1. Initialize logger and basic metadata as today.
+  2. Read `RUNTIME` from env; if missing/empty → log critical error and exit.
+  3. Build `PluginStore` instance using configuration env vars.
+  4. Call `store.install_runtime(runtime_name=RUNTIME)`; on failure → log error, set `APP_UP` metric to 0 and exit.
+  5. Only after successful runtime installation → build connector configs, instantiate Activities, connect to Temporal.
+
+### PluginStore usage in training
+
+- **ModelProvider abstraction** (e.g. `model_manager/utils/model_provider.py`):
+  - Holds a `PluginStore` instance and logger.
+  - Exposes `get_training_model(model_name, runtime, opt_params, model_kwargs, data_model_kwargs) -> SientiaModel` via `store.get_model(...)`.
+- **TrainingRepository integration:**
+  - Prepare input data using existing preprocessing logic.
+  - Ask ModelProvider for a `SientiaModel` instance (`model_name` from params, `runtime` from `RUNTIME`).
+  - Call the public `train(...)` method of the wrapper; collect outputs and metadata only through the public API.
+  - Build `TrainModelResult` from train/test splits, predictions, and artifacts required by `ModelRepository`.
+  - Model behavior lives in `SientiaModel`; manager focuses on orchestration and reports.
+
+---
+
+## Implementation Plan
+
+### Phase 0 — Design Alignment
+
+- **P0-01**: Confirm with stakeholders:
+  - The expected values and semantics for `RUNTIME` (naming convention, mapping to store runtimes).
+  - Whether the manager will ever need to support more than one runtime per process (current assumption: no).
+- **P0-02**: Decide the config strategy:
+  - Pure environment variables vs a config file + env overrides.
+- **P0-03**: Validate how `model_name` will be passed into the training workflow:
+  - Confirm or extend `TrainModelParams` to carry `model_name` and runtime-related fields as needed.
+
+### Phase 1 — Runtime Detection and Installation
+
+- **P1-01**: Extend `worker.py` docs and configuration:
+  - Add `RUNTIME` to the environment variables list in the module docstring.
+  - Document failure behavior when `RUNTIME` is missing or empty.
+- **P1-02**: Implement `build_plugin_store_from_env` helper:
+  - New function that:
+    - Reads `STORE_*` and `PYPI_*` env vars.
+    - Creates and returns a `PluginStore` instance with appropriate logger.
+  - Place it either in `worker.py` or in a dedicated utility module (e.g. `model_manager/utils/plugin_store_config.py`).
+- **P1-03**: Integrate runtime installation into `main()`:
+  - Before any Temporal client initialization:
+    - Read `runtime_name = os.getenv("RUNTIME")`.
+    - Build PluginStore via the helper.
+    - Call `install_runtime(runtime_name)`.
+  - Log:
+    - Start and end of runtime installation.
+    - List of installed requirements (name and version).
+  - On failure:
+    - Emit a clear message (including runtime name and store repo).
+    - Mark the app as DOWN in metrics.
+    - Exit with non-zero status.
+
+### Phase 2 — ModelProvider and Training Integration
+
+- **P2-01**: Introduce `ModelProvider` abstraction:
+  - Implement `ModelProvider` with:
+    - A reference to the shared `PluginStore`.
+    - Methods for retrieving models for training:
+      - `get_training_model(model_name, runtime, opt_params, model_kwargs, data_model_kwargs)`.
+  - Ensure it logs:
+    - Model and runtime names.
+    - Cache hits/misses when appropriate.
+- **P2-02**: Wire ModelProvider into Activities:
+  - Update the construction of `Activities` in `worker.py` to accept:
+    - A `ModelProvider` or a `PluginStore` that can be wrapped inside the `Training` activity.
+  - Update `Training.__init__` signature to accept this new dependency and store it as an attribute.
+- **P2-03**: Adjust `TrainingRepository` to use `SientiaModel`:
+  - In `train`:
+    1. Keep or refine current CSV loading and preprocessing pipeline (DataPreprocessor, split into train/test).
+    2. Use `ModelProvider` to retrieve the model:
+       - `model_name` from `TrainModelParams`.
+       - `runtime` from `RUNTIME`.
+       - `opt_params` mirroring how `test_plugin_store.py` interacts with models.
+    3. Call the model’s `train` method and produce the same core artifacts the current code expects:
+       - Train/test splits.
+       - Metrics and predictions for `TrainModelResult`.
+  - In `after_train_calculation`:
+    - Either re-use metrics from the SientiaModel, or continue calculating MSE/MAE/R² as a verification step.
+
+### Phase 3 — Removing mlops Dependencies
+
+- **P3-01**: Identify all usage points of:
+  - `LinearRegressionModel`.
+  - `DataPreprocessor` where behavior overlaps with what SientiaModel already does.
+- **P3-02**: Remove mlops-based code:
+  - Remove unused mlops-library-based training hooks.
+  - Simplify `TrainingRepository` to delegate as much as possible to SientiaModel logic.
+  - Use PluginStore + `SientiaModel` path only (no migration flag or parallel old path).
+
+### Phase 4 — ModelRepository, Shared MLflow Repository and Reporting Alignment
+
+- **P4-01**: Ensure `TrainModelResult` is correctly populated:
+  - Confirm that:
+    - `x_train`, `x_test`, `y_train`, `y_test`, `y_pred`, `y_train_pred` are provided by the new flow.
+    - Any fields required by `_generate_report` and `_save_run` remain available.
+- **P4-02**: Delegate all MLflow operations to `SientiaMLflowRepository` (see [[mlflow-shared-repository-migration-plan]]); keep in Model Manager only reporting orchestration and `TrainModelResult` construction.
+- **P4-03**: Validate that MLflow reports remain consistent:
+  - Run a side-by-side comparison between:
+    - A run from the previous (mlops-based) pipeline.
+    - A PluginStore-based run for the same dataset/experiment using the shared repository.
+  - Compare:
+    - Logged parameters.
+    - Metrics.
+    - Artifacts (reports, CSVs, equation JSON).
+
+---
+
+## Testing Strategy
+
+- **T1 — Unit tests**
+  - Worker: Test behavior when `RUNTIME` is missing or empty; test that `install_runtime` is called with the correct runtime name (mock PluginStore).
+  - ModelProvider: Test that it calls `PluginStore.get_model` with the expected arguments.
+  - TrainingRepository: Test that it uses the model returned by PluginStore instead of `LinearRegressionModel`.
+- **T2 — Integration tests**
+  - Set up a test store with a minimal model and runtime.
+  - Run a full training workflow: verify runtime installation first; confirm model is retrieved and training completes; validate metrics and artifacts via MLflow.
+- **T3 — Regression tests**
+  - Run the same experiment once with the old pipeline and once with the PluginStore-based pipeline.
+  - Compare key results (metrics and artifacts) to ensure differences are understood and acceptable.
+
+---
+
+## Rollout and Migration Strategy
+
+- **R1 — Criar modelos com a nova arquitetura**
+  - Garantir que o pipeline de modelagem (Factory/Warehouse/Store) consiga produzir modelos:
+    - Encapsulados em wrappers que estendem `SientiaModel`.
+    - Com interface estável para `train`, `retrain` (quando existir), `predict`/`transform` e `store_model`.
+  - Publicar um conjunto inicial de modelos “pilot” no store que será consumido pelo Model Manager.
+
+- **R2 — Subir um ou mais runtimes para esses modelos**
+  - Configurar e instalar runtimes específicos para os novos modelos, alinhados ao `RUNTIME` esperado pelo Model Manager:
+    - Verificar que cada runtime contém todas as dependências necessárias (via PluginStore / runtime installer).
+    - Validar que, em um ambiente de teste, o runtime consegue:
+      - Instalar bibliotecas.
+      - Carregar o wrapper via PluginStore e executar pelo menos um ciclo de treino de ponta a ponta.
+
+- **R3 — Colocar os novos modelos para rodar no Model Manager**
+  - Integrar o uso de `PluginStore.get_model(...)` na pipeline de treino:
+    - Direcionar um subconjunto de fluxos de treinamento para os modelos “pilot” oriundos do store.
+    - Monitorar:
+      - Estabilidade dos workers.
+      - Tempo de treino e consumo de recursos.
+      - Artefatos e métricas geradas no MLflow.
+  - Quando estáveis, coordenar com as equipes de produto/negócio para considerar esses modelos como candidatos a produção e, quando já estiverem usando MLflow 3+ com wrappers, promover esses modelos para produção usando aliases (`@production`).
+
+- **R4 — Migrar progressivamente os demais modelos**
+  - Definir uma ordem de migração por domínio/família de modelo (por exemplo: modelos de predição de série temporal, modelos de classificação, etc.):
+    - Para cada modelo legado:
+      - Criar/ajustar o wrapper `SientiaModel` correspondente no Factory/Warehouse.
+      - Garantir que o modelo passe a ser entregue pelo store e consumido via PluginStore.
+      - Executar o ciclo de testes (T1–T3) descrito na seção anterior.
+  - Após migrar todas as famílias de modelo:
+    - Remover o caminho de código que instancia diretamente `LinearRegressionModel` e demais classes locais.
+    - Limpar variáveis de configuração relacionadas à pipeline antiga (mlops library local).
+    - Assumir como padrão único: Model Manager treinando apenas modelos vindos do store, via wrappers `SientiaModel` e, quando aplicável, com resolução de produção por aliases em MLflow 3+.
+
+---
+
+## Potential Model Library Changes
+
+- **Clarifying the SientiaModel training interface:**
+  - Ensure that `SientiaModel` provides a stable way to train (including validation split handling).
+  - A clear contract for returning predictions and metrics.
+  - Access to any internal state needed for `TrainModelResult` construction.
+- **Improving PluginStore ergonomics:**
+  - Optionally add a helper to build `PluginStore` from environment variables (reusable across applications).
+  - More structured exceptions for missing runtime definitions, missing models, network and authentication issues.
+- These changes should be coordinated so that model manager and any other consumers can rely on a consistent, documented behavior.
+
+---
+
+## Related Documents
+
+- [[mlflow-shared-repository-migration-plan|MLflow Shared Repository Migration Plan]] — Concepts implemented in the common interface (production lookup, wrapper loading, promotion, etc.)
+- [[analytics-implementation-plan|Runtime Analytics Helm Implementation Plan]]
+- [[analytics|Runtime Analytics Architecture and Analysis]]
+- [[../model-plugin-system/06-end-to-end-flow|Model Plugin System — End-to-End Flow]]
+
--- a/model_manager/init.py
+++ b/model_manager/init.py
--- a/model_manager/activities/init.py
+++ b/model_manager/activities/init.py
--- a/model_manager/activities/activities.py
+++ b/model_manager/activities/activities.py
@@ -0,0 +1,166 @@
+from temporalio import workflow
+
+with workflow.unsafe.imports_passed_through():
+    from typing import Any
+
+    from sientia_do.notifications.handlers import CoreNotificationHandler as NotificationHandler
+    from sientia_do.observability.logger import Logger
+    from sientia_do.observability.metrics_controller import MetricsController
+    from sientia_do.observability.sientia_monitoring import SientiaMonitoring
+    from sientia_do.repository.minio_repository_sync import MinioRepository
+    from sientia_model.model_repository.mlflow_repository import SientiaMLflowRepository
+    from sientia_model.model_repository.plugin_store import PluginStore
+
+    from model_manager.activities.cleanup import Cleanup
+    from model_manager.activities.experiment_tracking import ExperimentTracking
+    from model_manager.activities.training import Training
+
+
+class Activities(ExperimentTracking, Training, Cleanup):
+    """
+    Main activities orchestrator for the Model Manager system.
+
+    This class combines functionality from multiple activity classes to provide
+    a unified interface for all workflow operations. It manages database connections,
+    MLFlow model interactions, MinIO storage operations, and cleanup operations.
+
+    The class implements multiple inheritance to combine specialized functionality:
+    - ExperimentTracking: ML experiment lifecycle tracking and database operations
+    - Training: ML model training operations with MLFlow and MinIO integration
+    - Cleanup: File and directory cleanup operations for MinIO and local filesystem
+
+    Attributes:
+        postgres_config (dict): PostgreSQL connection configuration
+        mlflow_config (dict): MLFlow server configuration
+        minio_config (dict): MinIO storage configuration
+        logger (Logger): Logging and observability instance
+        notification_handler (NotificationHandler): Notification management instance
+    """
+
+    def __init__(
+        self,
+        postgres_config: dict[str, Any],
+        mlflow_config: dict[str, Any],
+        minio_config: dict[str, Any],
+        plugin_store: PluginStore,
+        logger: Logger,
+        notification_handler: NotificationHandler,
+        metrics_controller: MetricsController,
+    ):
+        """
+        Initialize the Activities orchestrator with all required configurations.
+
+        This constructor initializes all parent classes with their respective
+        configurations and sets up the foundation for all activity operations.
+
+        Args:
+            postgres_config: PostgreSQL connection configuration dictionary
+                Required keys: host, port, user, password, dbname, min_connections, max_connections
+            mlflow_config: MLFlow server configuration dictionary
+                Required keys: host, port, username, password
+            minio_config: MinIO storage configuration dictionary
+                Required keys: endpoint_url, access_key, secret_key, region, use_ssl, default_bucket
+            logger: Logger instance for observability and debugging
+            notification_handler: Notification handler for alerts and monitoring
+
+        Raises:
+            Exception: If any parent class initialization fails
+        """
+
+        ExperimentTracking.__init__(
+            self,
+            host=postgres_config['host'],
+            port=postgres_config['port'],
+            user=postgres_config['user'],
+            password=postgres_config['password'],
+            dbname=postgres_config['dbname'],
+            min_connections=postgres_config['min_connections'],
+            max_connections=postgres_config['max_connections'],
+            logger=logger,
+            notification_handler=notification_handler,
+            metrics_controller=metrics_controller,
+        )
+
+        self.mlflow_repository = SientiaMLflowRepository(
+            host=mlflow_config['url'],
+            username=mlflow_config['username'],
+            password=mlflow_config['password'],
+            logger=logger,
+            notification_handler=notification_handler,
+            metrics_controller=metrics_controller,
+        )
+
+        # MinIO repository used for all object storage operations
+        endpoint_url = minio_config['endpoint_url']
+        # MinioRepository expects the endpoint without scheme
+        if endpoint_url.startswith('http://'):
+            endpoint = endpoint_url.removeprefix('http://')
+        elif endpoint_url.startswith('https://'):
+            endpoint = endpoint_url.removeprefix('https://')
+        else:
+            endpoint = endpoint_url
+
+        self.minio_repository = MinioRepository(
+            endpoint=endpoint,
+            access_key=minio_config['access_key'],
+            secret_key=minio_config['secret_key'],
+            logger=logger,
+            notification_handler=notification_handler,
+            metrics_controller=metrics_controller,
+            secure=minio_config['use_ssl'],
+            bucket=minio_config['default_bucket'],
+        )
+
+        Training.__init__(
+            self,
+            mlflow_repository=self.mlflow_repository,
+            plugin_store=plugin_store,
+            minio_repository=self.minio_repository,
+            logger=logger,
+            notification_handler=notification_handler,
+            metrics_controller=metrics_controller,
+        )
+
+        Cleanup.__init__(
+            self,
+            logger=logger,
+            notification_handler=notification_handler,
+            metrics_controller=metrics_controller,
+        )
+
+    def __del__(self):
+        """
+        Destructor to safely handle cleanup during garbage collection.
+
+        This prevents AttributeError when the parent Postgres.__del__ tries to access
+        self.engine in objects with multiple inheritance. Only attempts cleanup if
+        the engine attribute exists.
+        """
+        # Only call parent __del__ if engine attribute exists
+        # This prevents AttributeError in multiple inheritance scenarios
+        if hasattr(self, 'engine'):
+            try:
+                # Call parent class __del__ if it exists
+                if hasattr(super(), '__del__'):  # pragma: no cover
+                    super().__del__()  # pragma: no cover
+            except Exception:  # noqa: S110, BLE001  # pragma: no cover
+                # Silently ignore errors during garbage collection
+                # Logging here could cause issues if logger is already destroyed
+                pass
+
+    def shutdown(self):
+        """
+        Gracefully shutdown all activities and clean up resources.
+
+        This method ensures proper cleanup of all resources including:
+        - PostgreSQL connection pools (via ExperimentTracking)
+        - Any other resources that need explicit cleanup
+
+        The method should be called before the application terminates to ensure
+        proper resource cleanup and prevent resource leaks.
+
+        Prefer calling this method explicitly rather than relying on __del__.
+        """
+        ExperimentTracking.close(self)
+        self.info('Postgres client closed')
+        SientiaMonitoring.shutdown(self)
--- a/model_manager/activities/cleanup.py
+++ b/model_manager/activities/cleanup.py
@@ -0,0 +1,221 @@
+"""
+Cleanup activities for removing stale files from local filesystem.
+
+This module provides activities for cleaning up temporary files and directories
+that are older than the configured retention period. It operates independently
+of the database, using timestamps embedded in filenames.
+"""
+
+from temporalio import activity, workflow
+
+with workflow.unsafe.imports_passed_through():
+    import os
+    import re
+    import shutil
+    import traceback
+    from datetime import datetime, timedelta
+    from typing import Any
+
+    from sientia_do.notifications.handlers import CoreNotificationHandler as NotificationHandler
+    from sientia_do.notifications.models import NotificationLevel
+    from sientia_do.observability.logger import Logger
+    from sientia_do.observability.metrics_controller import MetricsController
+    from sientia_do.observability.sientia_monitoring import SientiaMonitoring
+
+    from model_manager.metrics import ACTIVITY_EXECUTION_TOTAL, WORKFLOW_EXECUTION_TOTAL
+    from model_manager.runtime_paths import REPORTS_TEMP_DIR
+
+    RETENTION_HOURS = int(os.getenv('CLEANUP_RETENTION_HOURS', '24'))
+    DRY_RUN = os.getenv('CLEANUP_DRY_RUN', 'false').lower() == 'true'
+
+
+class Cleanup(SientiaMonitoring):
+    """
+    Activity for cleaning up stale files and directories.
+
+    This activity extends SientiaMonitoring and handles cleanup of:
+    - Local temporary directories with timestamp suffixes
+    """
+
+    def __init__(
+        self,
+        logger: Logger,
+        notification_handler: NotificationHandler,
+        metrics_controller: MetricsController,
+    ):
+        """
+        Initialize Cleanup activity.
+
+        Args:
+            logger: Logger instance for observability
+            notification_handler: Handler for sending notifications
+            metrics_controller: Controller for metrics emission
+        """
+        SientiaMonitoring.__init__(self, logger, notification_handler, metrics_controller)
+
+        # Configuration from environment variables
+        self.retention_hours = RETENTION_HOURS
+        self.dry_run = DRY_RUN
+
+        # Regex patterns for timestamp extraction
+        self.dir_timestamp_pattern = re.compile(
+            r'^(.+)_(\d{8}_\d{6}_\d{6})$'
+        )  # name_YYYYMMDD_HHMMSS_microseconds
+
+    @activity.defn(name='cleanup_temp_directories')
+    def cleanup_temp_directories(self, input_data: dict[str, Any]) -> None:
+        """
+        Clean up stale temporary directories based on timestamp in directory name.
+
+        This activity scans the reports/temp directory for subdirectories following
+        the pattern '{name}_{timestamp}' where timestamp is in YYYYMMDD_HHMMSS_microseconds format.
+        Directories older than the retention period are deleted.
+
+        Args:
+            input_data: Cleanup configuration containing:
+                - metadata (dict): Workflow execution metadata
+                - temp_path (str): Path to temp directory (optional, defaults to reports/temp)
+
+        Returns:
+            None: Results are logged and tracked via metrics
+
+        Raises:
+            Exception: If cleanup fails (after sending notification)
+        """
+        metadata = input_data.get('metadata', {})
+        temp_path = input_data.get('temp_path', REPORTS_TEMP_DIR)
+        metrics_status = 'success'
+
+        cutoff_time = datetime.now() - timedelta(hours=self.retention_hours)
+
+        try:
+            self.info(
+                f'Starting local directory cleanup - Path: {temp_path}, '
+                f'Retention: {self.retention_hours}h, Dry run: {self.dry_run}',
+                metadata,
+            )
+
+            if not os.path.exists(temp_path):
+                self.warning(f'Temp directory does not exist: {temp_path}', metadata)
+                return
+
+            directories_scanned = 0
+            directories_deleted = 0
+            errors = []
+
+            for item_name in os.listdir(temp_path):
+                item_path = os.path.join(temp_path, item_name)
+
+                if not os.path.isdir(item_path):
+                    continue
+
+                directories_scanned += 1
+
+                # Extract timestamp from directory name
+                match = self.dir_timestamp_pattern.match(item_name)
+                if not match:
+                    self.debug(
+                        f'Skipping directory without timestamp pattern: {item_name}', metadata
+                    )
+                    continue
+
+                timestamp_str = match.group(2)
+                try:
+                    # Parse YYYYMMDD_HHMMSS_microseconds
+                    dir_time = datetime.strptime(timestamp_str, '%Y%m%d_%H%M%S_%f')
+
+                    if dir_time < cutoff_time:
+                        age_hours = (datetime.now() - dir_time).total_seconds() / 3600
+
+                        if self.dry_run:
+                            self.info(
+                                f'[DRY RUN] Would delete directory: {item_name} (age: {age_hours:.1f}h)',
+                                metadata,
+                            )
+                            directories_deleted += 1
+                        else:
+                            try:
+                                shutil.rmtree(item_path)
+                                self.info(
+                                    f'Deleted stale directory: {item_name} (age: {age_hours:.1f}h)',
+                                    metadata,
+                                )
+                                directories_deleted += 1
+                            except OSError as e:
+                                error_msg = f'Failed to delete directory {item_name}: {str(e)}'
+                                errors.append(error_msg)
+                                self.error(error_msg, metadata)
+                    else:
+                        age_hours = (datetime.now() - dir_time).total_seconds() / 3600
+                        self.debug(
+                            f'Keeping recent directory: {item_name} (age: {age_hours:.1f}h)',
+                            metadata,
+                        )
+
+                except ValueError as e:
+                    error_msg = f'Invalid timestamp format in directory {item_name}: {str(e)}'
+                    errors.append(error_msg)
+                    self.error(error_msg, metadata)
+
+            self.info(
+                f'Directory cleanup completed - Scanned: {directories_scanned}, '
+                f'Deleted: {directories_deleted}, Errors: {len(errors)}',
+                metadata,
+            )
+
+        except Exception as e:
+            metrics_status = 'error'
+            error_msg = f'Error in directory cleanup: {str(e)}'
+            trace = traceback.format_exc()
+
+            self.send_notification(
+                metadata=metadata,
+                notification_id='CLEANUP_DIRECTORIES_ERROR',
+                message=error_msg,
+                block='cleanup_temp_directories',
+                level=NotificationLevel.ERROR,
+                attachment_content=trace,
+            )
+
+            raise
+        finally:
+            self._emit_metrics(
+                metadata=metadata,
+                metrics_status=metrics_status,
+                activity_name='cleanup_temp_directories',
+                emit_workflow_metric=True,
+            )
+
+    def _emit_metrics(
+        self,
+        metadata: dict[str, Any],
+        metrics_status: str,
+        activity_name: str,
+        emit_workflow_metric: bool,
+    ) -> None:
+        """
+        Emit workflow and activity execution metrics.
+
+        Args:
+            metadata: Activity metadata containing pod_id and workflow_name
+            metrics_status: Execution status ('success' or 'error')
+            activity_name: Name of the activity being executed
+        """
+        if emit_workflow_metric:
+            self.emit_metric_sync(
+                metric_object=WORKFLOW_EXECUTION_TOTAL,
+                tags={
+                    'pod_id': metadata.get('pod_id'),
+                    'workflow_name': metadata.get('workflow_name'),
+                    'status': metrics_status,
+                },
+            )
+
+        self.emit_metric_sync(
+            metric_object=ACTIVITY_EXECUTION_TOTAL,
+            tags={
+                'pod_id': metadata.get('pod_id'),
+                'activity_name': activity_name,
+                'status': metrics_status,
+            },
+        )
--- a/model_manager/activities/experiment_tracking.py
+++ b/model_manager/activities/experiment_tracking.py
@@ -0,0 +1,280 @@
+"""
+Experiment tracking activities for managing ML experiment lifecycle.
+
+This module provides activities for tracking and updating experiment run status
+in the PostgreSQL database, extending the synchronous Postgres client with specialized
+methods for experiment management.
+"""
+
+import enum
+
+from temporalio import activity, workflow
+
+with workflow.unsafe.imports_passed_through():
+    import traceback
+    from collections.abc import Mapping
+    from datetime import UTC, datetime
+    from typing import Any
+
+    from sientia_do.notifications.handlers import CoreNotificationHandler as NotificationHandler
+    from sientia_do.notifications.models import NotificationLevel
+    from sientia_do.observability.logger import Logger
+    from sientia_do.observability.metrics_controller import MetricsController
+    from sientia_do.temporal.activities.postgres_sync import Postgres
+    from sqlalchemy import text
+
+
+class UpdateType(enum.StrEnum):
+    """Types of experiment run updates."""
+
+    STATUS = 'status'
+    STATUS_WITH_ERROR = 'status_with_error'
+    MODEL_SAVED = 'model_saved'
+
+
+class ExperimentTracking(Postgres):
+    """
+    Activity for tracking ML experiment lifecycle and status updates.
+
+    This activity extends the Postgres activity to provide specialized methods
+    for managing experiment runs, including status updates, error tracking, and
+    model registration. It maintains the experiment lifecycle from initialization
+    through training, model saving, and cleanup.
+
+    The activity uses a SQLAlchemy engine / connection pool and adds experiment-specific
+    operations with proper error handling and notifications.
+    """
+
+    def __init__(
+        self,
+        host: str,
+        port: int,
+        user: str,
+        password: str,
+        dbname: str,
+        min_connections: int,
+        max_connections: int,
+        logger: Logger,
+        notification_handler: NotificationHandler,
+        metrics_controller: MetricsController,
+    ):
+        """
+        Initialize ExperimentTracking activity with database configuration.
+
+        Args:
+            host: PostgreSQL server hostname
+            port: PostgreSQL server port
+            user: Database user
+            password: Database password
+            dbname: Database name
+            min_connections: Minimum connections in pool
+            max_connections: Maximum connections in pool
+            logger: Logger instance for observability
+            notification_handler: Notification handler for alerts
+            metrics_controller: Metrics controller for observability
+
+        Raises:
+            ConnectionError: If database connection cannot be established
+        """
+        Postgres.__init__(
+            self,
+            host=host,
+            port=port,
+            user=user,
+            password=password,
+            dbname=dbname,
+            min_connections=min_connections,
+            max_connections=max_connections,
+            logger=logger,
+            notification_handler=notification_handler,
+            metrics_controller=metrics_controller,
+        )
+
+        self.info(f'Postgres client initialized at {host}:{port}')
+
+    def __del__(self):
+        """
+        Destructor to safely handle cleanup during garbage collection.
+
+        This prevents AttributeError when used in multiple inheritance scenarios
+        where the parent Postgres.__del__ might be called on objects without
+        the engine attribute.
+        """
+        # Only call parent __del__ if engine attribute exists
+        if hasattr(self, 'engine'):
+            try:
+                if hasattr(super(), '__del__'):
+                    super().__del__()
+            except Exception:  # noqa: S110, BLE001
+                # Silently ignore errors during garbage collection
+                pass
+
+    def _execute_update(self, query: str, params: Mapping[str, Any]) -> dict[str, Any]:
+        """
+        Execute an UPDATE SQL statement.
+
+        Args:
+            query: Parameterized SQL string to execute.
+            params: Mapping of parameters for the SQL query.
+
+        Returns:
+            dict: A dictionary containing the affected row count: {'rowcount': int}.
+        """
+
+        with self.engine.begin() as connection:
+            result = connection.execute(text(query), params)
+            return {'rowcount': result.rowcount}
+
+    def _build_status_update_query(
+        self, status: str | None, experiment_run_id: int
+    ) -> tuple[str, dict[str, Any]]:
+        """Build SQL query for simple status update."""
+        if not isinstance(status, str) or not status:
+            raise ValueError('status is required for STATUS update type')
+
+        sql_query = """
+            UPDATE experiment_run
+            SET status = :status, updated_at = :updated_at
+            WHERE id = :experiment_run_id
+        """
+
+        query_params = {
+            'status': status,
+            'updated_at': datetime.now(UTC),
+            'experiment_run_id': experiment_run_id,
+        }
+
+        return sql_query, query_params
+
+    def _build_status_with_error_query(
+        self, status: str | None, error_message: str | None, experiment_run_id: int
+    ) -> tuple[str, dict[str, Any]]:
+        """Build SQL query for status update with error message."""
+        if not isinstance(status, str) or not status:
+            raise ValueError('status is required for STATUS_WITH_ERROR update type')
+
+        if not isinstance(error_message, str) or not error_message:
+            raise ValueError('error_message is required for STATUS_WITH_ERROR update type')
+
+        # Truncate error message if too long
+        truncated_error = error_message[:1024] if len(error_message) > 1024 else error_message
+
+        sql_query = """
+            UPDATE experiment_run
+            SET status = :status, error_message = :error_message, updated_at = :updated_at
+            WHERE id = :experiment_run_id
+        """
+
+        query_params = {
+            'status': status,
+            'error_message': truncated_error,
+            'updated_at': datetime.now(UTC),
+            'experiment_run_id': experiment_run_id,
+        }
+
+        return sql_query, query_params
+
+    def _build_model_saved_query(
+        self, run_name: str | None, status: str | None, experiment_run_id: int
+    ) -> tuple[str, dict[str, Any]]:
+        """Build SQL query for model saved update."""
+        if not isinstance(run_name, str) or not run_name:
+            raise ValueError('run_name is required for MODEL_SAVED update type')
+
+        if not isinstance(status, str) or not status:
+            raise ValueError('status is required for MODEL_SAVED update type')
+
+        sql_query = """
+            UPDATE experiment_run
+            SET run_name = :run_name, status = :status, updated_at = :updated_at
+            WHERE id = :experiment_run_id
+        """
+
+        query_params = {
+            'run_name': run_name,
+            'status': status,
+            'updated_at': datetime.now(UTC),
+            'experiment_run_id': experiment_run_id,
+        }
+
+        return sql_query, query_params
+
+    def _get_update_query_and_params(
+        self, update_type: str, experiment_run_id: int, input_data: dict[str, Any]
+    ) -> tuple[str, dict[str, Any]]:
+        """Get SQL query and parameters based on update type."""
+        status = input_data.get('status')
+        error_message = input_data.get('error_message')
+        run_name = input_data.get('run_name')
+
+        if update_type == UpdateType.STATUS:
+            return self._build_status_update_query(status, experiment_run_id)
+
+        if update_type == UpdateType.STATUS_WITH_ERROR:
+            return self._build_status_with_error_query(status, error_message, experiment_run_id)
+
+        if update_type == UpdateType.MODEL_SAVED:
+            return self._build_model_saved_query(run_name, status, experiment_run_id)
+
+        raise ValueError(f'Invalid update_type: {update_type}')
+
+    @activity.defn(name='update_experiment_run')
+    def update_experiment_run(self, input_data: dict[str, Any]) -> None:
+        """
+        Update experiment run with status, errors, or model information.
+
+        This activity provides a unified interface for all experiment run updates,
+        supporting different update types through a single method. It automatically
+        selects the appropriate SQL query based on the update type and parameters.
+
+        Args:
+            input_data: Configuration for experiment run update operation
+                Required keys:
+                    - metadata (dict): Workflow execution metadata
+                    - experiment_run_id (int): Unique identifier for the experiment run
+                    - update_type (str): Type of update (status, status_with_error, model_saved)
+                Optional keys:
+                    - status (str): New status for the experiment run
+                    - error_message (str): Error message if update failed
+                    - run_name (str): MLFlow run name if model was saved
+
+        Raises:
+            ValueError: If required parameters are missing for the update type
+            RuntimeError: If update operation fails
+        """
+        metadata = input_data.get('metadata')
+        experiment_run_id = input_data['experiment_run_id']
+        update_type = input_data['update_type']
+        status = input_data.get('status')
+
+        try:
+            sql_query, query_params = self._get_update_query_and_params(
+                update_type, experiment_run_id, input_data
+            )
+
+            result = self._execute_update(sql_query, query_params)
+
+            if result.get('rowcount', 0) == 0:
+                error_msg = (
+                    f'No experiment_run row updated for id={experiment_run_id} '
+                    f'(row missing or id mismatch). update_type={update_type!r}, status={status!r}.'
+                )
+                raise ValueError(error_msg)
+
+            self.info(
+                f'Successfully updated experiment run {experiment_run_id} with status {status}',
+                metadata,
+            )
+        except Exception as e:  # noqa: BLE001
+            error_msg = f'Error updating experiment run - ID: {experiment_run_id}, Status: {status}, Error: {str(e)}'
+            trace = traceback.format_exc()
+
+            self.send_notification(
+                metadata=metadata or {},
+                notification_id='UPDATE_EXPERIMENT_RUN_ERROR',
+                message=error_msg,
+                block='update_experiment_run',
+                level=NotificationLevel.ERROR,
+                attachment_content=trace,
+            )
+            raise RuntimeError(error_msg) from e
--- a/model_manager/activities/training.py
+++ b/model_manager/activities/training.py
@@ -0,0 +1,399 @@
+"""
+Training activities for ML model training operations.
+
+This module provides activities for training machine learning models.
+The activity extends BaseActivity and receives pre-downloaded files
+and raises `ModelTrainingError` when training fails.
+"""
+
+from sientia_model.wrappers.sientia_model import SientiaModel
+from temporalio import activity, workflow
+
+with workflow.unsafe.imports_passed_through():
+    import traceback
+    from typing import Any
+
+    import mlflow
+    from sientia_do.notifications.handlers import CoreNotificationHandler as NotificationHandler
+    from sientia_do.notifications.models import NotificationLevel
+    from sientia_do.observability.logger import Logger
+    from sientia_do.observability.metrics_controller import MetricsController
+    from sientia_do.observability.sientia_monitoring import SientiaMonitoring
+    from sientia_do.repository.minio_repository_sync import MinioRepository
+    from sientia_model.model_repository.mlflow_repository import SientiaMLflowRepository
+    from sientia_model.model_repository.plugin_store import PluginStore
+
+    from model_manager.utils.models.train_model_params import TrainModelParams
+    from model_manager.utils.models.train_model_result import TrainModelResult
+    from model_manager.utils.repository.data_manager_repository import DataManagerRepository
+
+
+class Training(SientiaMonitoring):
+    """
+    Activity for ML model training operations.
+
+    This activity extends SientiaMonitoring and handles machine learning model
+    training with comprehensive error handling. It receives pre-downloaded
+    files from the workflow and raises `ModelTrainingError` on failure so the
+    workflow can map the correct experiment status.
+    """
+
+    def __init__(
+        self,
+        mlflow_repository: SientiaMLflowRepository,
+        plugin_store: PluginStore,
+        minio_repository: MinioRepository,
+        logger: Logger,
+        notification_handler: NotificationHandler,
+        metrics_controller: MetricsController,
+    ):
+        """
+        Initialize Training activity.
+
+        Args:
+            logger: Logger instance for observability
+            notification_handler: Handler for sending notifications
+        """
+        SientiaMonitoring.__init__(self, logger, notification_handler, metrics_controller)
+        self.data_manager_repository = DataManagerRepository(logger)
+        self.mlflow_repository = mlflow_repository
+        self.plugin_store = plugin_store
+        self.minio_repository = minio_repository
+
+    @activity.defn(name='load_model_metadata')
+    def load_model_metadata(self, input_data: dict[str, Any]) -> dict[str, Any]:
+        """
+        Load model metadata/schemas from the model store.
+
+        This activity is responsible for fetching model metadata/schemas from the
+        model store index and extracting a serializable `model_metadata` dict that
+        `TrainModelParams.validate_business_rules()` depends on.
+
+        Args:
+            input_data: Workflow input at the same level as `validate_train_params`,
+                including at least `model_name` and the fields required by
+                `TrainModelParams.from_dict` to build wrapper kwargs.
+
+        Return:
+            dict[str, Any]: Updated `input_data` containing `input_data['model_metadata']`.
+        """
+        metadata = input_data.get('metadata', {})
+
+        self.info(f'Loading model metadata for {input_data}', metadata)
+
+        try:
+            train_params = TrainModelParams.from_dict(input_data)
+            model_metadata = self.plugin_store.get_model_index(
+                model_type=train_params.model_type,
+                metadata=metadata,
+            )
+
+            train_params.model_metadata = model_metadata
+            self.info(f'Model metadata loaded successfully for {input_data}', metadata)
+            self.debug(f'Model metadata: {model_metadata}', metadata)
+            return train_params.to_dict()
+        except Exception as exc:
+            trace = traceback.format_exc()
+            self.send_notification(
+                metadata=metadata,
+                notification_id='LOAD_MODEL_METADATA_ERROR',
+                message=f'Error loading model metadata: {str(exc)}',
+                block='load_model_metadata',
+                level=NotificationLevel.ERROR,
+                attachment_content=trace,
+            )
+            raise
+
+    @activity.defn(name='validate_train_params')
+    def validate_train_params(self, input_data: dict[str, Any]) -> dict[str, Any]:
+        """
+        Validate and convert training parameters from dict to TrainModelParams.
+
+        This activity validates the input training parameters and converts them
+        to a TrainModelParams object.
+
+        Args:
+            input_data: Training parameters and metadata at the same level
+                Required keys:
+                    - metadata (dict): Workflow execution metadata
+                    - All TrainModelParams fields (experiment_run_id, target_variable, etc.)
+
+        Returns:
+            dict[str, Any]: Validated and converted training parameters as dictionary
+
+        Raises:
+            Exception: If validation fails (after sending notification)
+        """
+        metadata = input_data.get('metadata', {})
+
+        self.info(f'Validating training parameters for {input_data}', metadata)
+
+        try:
+            train_params = TrainModelParams.from_dict(input_data)
+
+            train_params.validate_business_rules()
+
+            self.info(
+                f'Training parameters validated successfully - '
+                f'Target: {train_params.target_variable}, '
+                f'Experiment: {train_params.experiment_name}',
+                metadata,
+            )
+
+            self.debug(
+                f'Training parameters validated successfully: {train_params.to_dict()}', metadata
+            )
+
+            return train_params.to_dict()
+        except Exception as e:
+            error_msg = f'Error validating training parameters: {str(e)}'
+            trace = traceback.format_exc()
+
+            self.send_notification(
+                metadata=metadata,
+                notification_id='VALIDATE_TRAIN_PARAMS_ERROR',
+                message=error_msg,
+                block='validate_train_params',
+                level=NotificationLevel.ERROR,
+                attachment_content=trace,
+            )
+            raise
+
+    @activity.defn(name='train_model')
+    def train_model(self, input_data: dict[str, Any]) -> dict[str, Any]:
+        """
+        Train a machine learning model.
+
+        This activity orchestrates the ML training pipeline:
+        1. Validate input parameters.
+        2. Prepare data via DataManagerRepository.
+        3. Train the model and compute metrics.
+
+        Args:
+            input_data: Training configuration containing:
+                - metadata (dict): Workflow execution metadata.
+                - uploaded_file (BytesIO): Training data already downloaded from MinIO.
+                - train_params (dict): Training parameters.
+
+        Returns:
+            dict[str, Any]: Serializable summary (run identifiers, run_dir for cleanup, regression metrics).
+
+        Raises:
+            ValueError: If input validation fails.
+            Exception: If training fails (after sending notification).
+        """
+        metadata = input_data.get('metadata')
+        train_params = TrainModelParams.from_dict(input_data['train_params'])
+
+        self.info('Starting train_model process', metadata)
+
+        try:
+            # Download training file bytes from MinIO
+
+            self.info(
+                f'Downloading training file from MinIO for {train_params.file_name}', metadata
+            )
+            train_bytes = self.minio_repository.download_file(
+                object_name=train_params.file_name,
+                bucket=train_params.bucket_name,
+                metadata=metadata,
+            )
+
+            # Download optional validation file bytes from the same bucket
+            val_bytes: bytes | None = None
+            validation_name = train_params.val_file_name
+            if validation_name is not None:
+                self.info(f'Downloading validation file from MinIO for {validation_name}', metadata)
+                val_bytes = self.minio_repository.download_file(
+                    object_name=validation_name,
+                    bucket=train_params.bucket_name,
+                    metadata=metadata,
+                )
+
+            self.info(f'Preparing training data for {train_params.file_name}', metadata)
+            train_result = self.data_manager_repository.prepare_training_data(
+                train_file_bytes=train_bytes,
+                validation_file_bytes=val_bytes,
+                params=train_params,
+                metadata=metadata,
+            )
+
+            self.info(f'Getting model wrapper for {train_params.model_type}', metadata)
+            wrapper = self.plugin_store.get_model(
+                model_type=train_params.model_type,
+                force_download=False,
+                opt_params=train_params.opt_params or {},
+                model_kwargs=train_params.model_kwargs or {},
+                data_model_kwargs=train_params.data_model_kwargs or {},
+                metadata=metadata,
+            )
+
+            if self.logger is not None:
+                wrapper.logger = self.logger.base_logger
+
+            self.info(f'Training model for {train_params.model_type}', metadata)
+            train_data = train_result.train_data
+            val_data = train_result.val_data
+
+            self.debug(
+                f'train_model prepared data (head 10):\ntrain:\n{train_data.head(10).to_string()}'
+                f'\nval:\n{val_data.head(10).to_string()}',
+                metadata,
+            )
+
+            wrapper.train(
+                train_data=train_data,
+                val_data=val_data,
+                target=train_params.target_variable,
+            )
+
+            self.info(
+                f'Generating predictions using the trained wrapper for {train_params.model_type}',
+                metadata,
+            )
+            # Generate predictions using the trained wrapper
+            transformed_train, _ = wrapper.transform(train_data)
+            transformed_val, _ = wrapper.transform(val_data)
+
+            self.debug(
+                f'train_model transform (head 10):\ntrain:\n{transformed_train.head(10).to_string()}'
+                f'\nval:\n{transformed_val.head(10).to_string()}',
+                metadata,
+            )
+
+            y_train_pred_df, _ = wrapper.predict({}, transformed_train)
+            y_val_pred_df, _ = wrapper.predict({}, transformed_val)
+
+            self.debug(
+                f'train_model predict (head 10):\ntrain:\n{y_train_pred_df.head(10).to_string()}'
+                f'\nval:\n{y_val_pred_df.head(10).to_string()}',
+                metadata,
+            )
+
+            y_train_pred_df.sort_index(inplace=True, ascending=False)
+            y_val_pred_df.sort_index(inplace=True, ascending=False)
+
+            train_result.y_train_pred = y_train_pred_df
+            train_result.y_pred = y_val_pred_df
+
+            self.info(f'Computing regression metrics for {train_params.model_type}', metadata)
+            train_result = self.data_manager_repository.compute_regression_metrics(
+                train_result,
+                wrapper,
+                metadata=metadata,
+            )
+
+            self.info(f'Starting MLflow run for {train_params.model_type}', metadata)
+            with self.mlflow_repository.start_run(
+                model_name=train_params.model_name,
+                run_name=train_result.run_name,
+                experiment_name=train_result.experiment_name,
+                tags=None,
+                metadata=metadata,
+            ) as run_info:
+                train_result.run_id = run_info.run_id
+                self._persist_training_artifacts(train_result, train_params, wrapper, metadata)
+
+            return {
+                'run_name': train_result.run_name,
+                'experiment_name': train_result.experiment_name,
+                'run_id': train_result.run_id,
+                'run_dir': train_result.run_dir,
+            }
+        except Exception as e:  # noqa: BLE001
+            error_msg = f'Error training model - error: {str(e)}'
+
+            trace = traceback.format_exc()
+
+            self.send_notification(
+                metadata=metadata or {},
+                notification_id='TRAIN_MODEL_ERROR',
+                message=error_msg,
+                block='train_model',
+                level=NotificationLevel.ERROR,
+                attachment_content=trace,
+            )
+
+            raise e
+
+    def _persist_training_artifacts(
+        self,
+        train_result: TrainModelResult,
+        train_params: TrainModelParams,
+        wrapper: SientiaModel,
+        metadata: dict[str, Any] | None,
+    ) -> None:
+        self.info(f'Generating report for {train_params.model_type}', metadata)
+        train_result = self.data_manager_repository.generate_report(
+            train_result,
+            metadata=metadata,
+        )
+
+        if (
+            train_result.report_path is None
+            or train_result.train_data_path is None
+            or train_result.test_data_path is None
+        ):
+            raise ValueError('Report path, train data path, or test data path is not set')
+
+        self.info(f'Storing model for {train_params.model_type}', metadata)
+        wrapper._input_example = None
+        wrapper.store_model(name=train_params.model_name)
+        self._log_regression_metrics_as_params(train_result)
+        self.info(f'Logging artifacts for {train_params.model_type}', metadata)
+        mlflow.log_artifact(train_result.report_path)
+        mlflow.log_artifact(train_result.train_data_path)
+        mlflow.log_artifact(train_result.test_data_path)
+        if train_result.equation_path is not None:
+            mlflow.log_artifact(train_result.equation_path)
+
+    def _log_regression_metrics_as_params(self, train_result: TrainModelResult) -> None:
+        """
+        Persist computed regression metrics as MLflow params.
+
+        Args:
+            train_result: Training output containing computed regression metrics.
+        """
+        metric_params = {
+            'mse_val': train_result.mse_val,
+            'mae_val': train_result.mae_val,
+            'r2_val': train_result.r2_val,
+        }
+
+        for key, value in metric_params.items():
+            if value is not None:
+                mlflow.log_param(key, value)
+
+    @activity.defn(name='cleanup_resources')
+    def cleanup_resources(self, input_data: dict[str, Any]) -> None:
+        """
+        Cleanup temporary resources created during training.
+
+        Args:
+            input_data: Cleanup configuration containing:
+                - metadata (dict): Workflow execution metadata.
+                - run_dir (str): Temporary directory to remove.
+
+        Raises:
+            Exception: If cleanup fails (after sending notification).
+        """
+        metadata = input_data.get('metadata', {})
+        run_dir = input_data.get('run_dir', '')
+
+        try:
+            self.data_manager_repository.cleanup_run_directory(run_dir, metadata)
+        except Exception as e:  # noqa: BLE001
+            error_msg = f'Error cleaning up resources - Run directory: {run_dir}, Error: {str(e)}'
+
+            trace = traceback.format_exc()
+
+            self.send_notification(
+                metadata=metadata,
+                notification_id='CLEANUP_RESOURCES_ERROR',
+                message=error_msg,
+                block='cleanup_resources',
+                level=NotificationLevel.ERROR,
+                attachment_content=trace,
+            )
+
+            raise
--- a/model_manager/metrics.py
+++ b/model_manager/metrics.py
@@ -0,0 +1,38 @@
+"""
+Model Manager Metrics Module
+
+This module defines all Prometheus metrics used by the Sientia DataOps Model Manager system
+for monitoring and observability. The metrics provide insights into system performance,
+training operations, and operational health.
+
+The metrics are designed to be scraped by Prometheus and can be visualized in
+Grafana or other monitoring dashboards to provide real-time visibility into
+the system's operation.
+
+Key Metric Categories:
+- Application Health: Overall system status and availability
+
+Metric Labels:
+- pod_id: Kubernetes pod identifier for multi-instance deployments
+"""
+
+from prometheus_client import Counter, Gauge
+
+# Application health metric
+APP_UP = Gauge(
+    'app_up',
+    'Indicates if the application is running (1) or shutting down (0)',
+    ['pod_id'],
+)
+
+WORKFLOW_EXECUTION_TOTAL = Counter(
+    'model_manager_workflow_executions_total',
+    'Total number of workflow executions',
+    ['pod_id', 'workflow_name', 'status'],  # status: success, error
+)
+
+ACTIVITY_EXECUTION_TOTAL = Counter(
+    'model_manager_activity_executions_total',
+    'Total number of activity executions',
+    ['pod_id', 'activity_name', 'status'],  # status: success, error
+)
--- a/model_manager/reports/header.html
+++ b/model_manager/reports/header.html
@@ -0,0 +1,167 @@
+<!DOCTYPE html>
+<html lang="en">
+  <head>
+    <meta charset="UTF-8" />
+    <meta http-equiv="X-UA-Compatible" content="IE=edge" />
+    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+    <link rel="stylesheet" href="style.css" />
+
+    <title>Report</title>
+
+    <style>
+      * {
+        font-family: "Franklin Gothic Medium", "Arial Narrow", Arial, sans-serif;
+        margin: 0;
+        padding: 0;
+        box-sizing: border-box;
+      }
+
+      .logo {
+        padding-top: 70;
+        padding-bottom: 70;
+        position: absolute;
+        margin-left: -48px;
+      }
+
+      h1 {
+        color: #fff;
+        position: absolute;
+        margin-left: 45%;
+      }
+
+      html,
+      body {
+        scroll-behavior: smooth;
+      }
+
+      section {
+        padding-top: 90px;
+        width: 100%;
+        display: fixed;
+        justify-content: center;
+        align-items: center;
+        background-color: rgb(217, 217, 214, 0.7);
+      }
+
+      .material-symbols-outlined {
+        font-variation-settings: "FILL" 0, "wght" 400, "GRAD" 0, "opsz" 24;
+        color: #ffff;
+      }
+
+      /* Tooltip text */
+      .tooltiptext {
+        visibility: hidden;
+        background-color: rgb(0, 30, 96, 0.9);
+        padding: 10px;
+        margin-left: -90px;
+        font-size: 16px;
+        position: absolute;
+        top: 85px;
+        border-bottom-left-radius: 12px;
+        border-bottom-right-radius: 12px;
+      }
+
+      /* Show the tooltip text when you mouse over the tooltip container */
+      .material-symbols-outlined:hover .tooltiptext {
+        visibility: visible;
+      }
+
+      header {
+        position: fixed;
+        top: 0;
+        width: 100%;
+        height: 85px;
+        background: rgb(0, 30, 96, 0.95);
+        display: flex;
+        justify-content: space-between;
+        align-items: center;
+        padding: 10px 50px 0;
+      }
+
+      header nav {
+        display: absolute;
+        margin-left: 80%;
+        gap: 10px;
+      }
+
+      header nav a {
+        position: relative;
+        text-decoration: none;
+        padding: 12px 18px;
+        color: #fff;
+        font-weight: 500;
+      }
+
+      header nav a.active {
+        background-color: #001540;
+        position: relative;
+        border-radius: 12px;
+      }
+    </style>
+
+    <link
+      rel="stylesheet"
+      href="https://fonts.googleapis.com/css2?family=Material+Symbols+Outlined:opsz,wght,FILL,GRAD@20..48,100..700,0..1,-50..200"
+    />
+  </head>
+  <body>
+    <main>
+      <header>
+        <a href="#" class="logo">
+          <img
+            src="https://aignosi.blob.core.windows.net/sientia/20231016-Aignosi_Logo_WHITE.png"
+            alt="Aignosi Logo"
+            width="247"
+            height="70"
+          />
+        </a>
+        <h1>Report</h1>
+        <nav>
+          <a href="#data_quality" class="active"> Summary </a>
+          <a href="#data_drift"> Drift </a>
+          <a href="#regression"> Regression </a>
+        </nav>
+        <div class="material-symbols-outlined">
+          info
+          <p class="tooltiptext">
+            Note that "current" <br />
+            is related to the test <br />
+            set while "reference" <br />
+            refers to the training <br />
+            set
+          </p>
+        </div>
+      </header>
+      <div class="quality_div">
+        <section id="data_quality"></section>
+      </div>
+      <div class="data_drift_div">
+        <section id="data_drift"></section>
+      </div>
+      <div class="regression_div">
+        <section id="regression"></section>
+      </div>
+    </main>
+
+    <script>
+      let sec = document.querySelectorAll("section");
+      let links = document.querySelectorAll("nav  a");
+
+      window.onscroll = () => {
+        sec.forEach((section) => {
+          let top = window.scrollY;
+          let offset = section.offsetTop;
+          let height = section.offsetHeight;
+          let id = section.getAttribute("id");
+
+          if (top >= offset && top < offset + height) {
+            links.forEach((link) => {
+              link.classList.remove("active");
+              document.querySelector("nav a[href*=" + id + "]").classList.add("active");
+            });
+          }
+        });
+      };
+    </script>
+  </body>
+</html>
--- a/model_manager/reports/temp/.gitkeep
+++ b/model_manager/reports/temp/.gitkeep
--- a/model_manager/reports/temp/test-linear-regression-basic-5_20260119_124123_695140/data_drift.html
+++ b/model_manager/reports/temp/test-linear-regression-basic-5_20260119_124123_695140/data_drift.html
--- a/model_manager/reports/temp/test-linear-regression-basic-5_20260119_124123_695140/data_quality.html
+++ b/model_manager/reports/temp/test-linear-regression-basic-5_20260119_124123_695140/data_quality.html
--- a/model_manager/reports/temp/test-linear-regression-basic-5_20260119_124123_695140/header.html
+++ b/model_manager/reports/temp/test-linear-regression-basic-5_20260119_124123_695140/header.html
@@ -0,0 +1,167 @@
+<!DOCTYPE html>
+<html lang="en">
+  <head>
+    <meta charset="UTF-8" />
+    <meta http-equiv="X-UA-Compatible" content="IE=edge" />
+    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+    <link rel="stylesheet" href="style.css" />
+
+    <title>Report</title>
+
+    <style>
+      * {
+        font-family: "Franklin Gothic Medium", "Arial Narrow", Arial, sans-serif;
+        margin: 0;
+        padding: 0;
+        box-sizing: border-box;
+      }
+
+      .logo {
+        padding-top: 70;
+        padding-bottom: 70;
+        position: absolute;
+        margin-left: -48px;
+      }
+
+      h1 {
+        color: #fff;
+        position: absolute;
+        margin-left: 45%;
+      }
+
+      html,
+      body {
+        scroll-behavior: smooth;
+      }
+
+      section {
+        padding-top: 90px;
+        width: 100%;
+        display: fixed;
+        justify-content: center;
+        align-items: center;
+        background-color: rgb(217, 217, 214, 0.7);
+      }
+
+      .material-symbols-outlined {
+        font-variation-settings: "FILL" 0, "wght" 400, "GRAD" 0, "opsz" 24;
+        color: #ffff;
+      }
+
+      /* Tooltip text */
+      .tooltiptext {
+        visibility: hidden;
+        background-color: rgb(0, 30, 96, 0.9);
+        padding: 10px;
+        margin-left: -90px;
+        font-size: 16px;
+        position: absolute;
+        top: 85px;
+        border-bottom-left-radius: 12px;
+        border-bottom-right-radius: 12px;
+      }
+
+      /* Show the tooltip text when you mouse over the tooltip container */
+      .material-symbols-outlined:hover .tooltiptext {
+        visibility: visible;
+      }
+
+      header {
+        position: fixed;
+        top: 0;
+        width: 100%;
+        height: 85px;
+        background: rgb(0, 30, 96, 0.95);
+        display: flex;
+        justify-content: space-between;
+        align-items: center;
+        padding: 10px 50px 0;
+      }
+
+      header nav {
+        display: absolute;
+        margin-left: 80%;
+        gap: 10px;
+      }
+
+      header nav a {
+        position: relative;
+        text-decoration: none;
+        padding: 12px 18px;
+        color: #fff;
+        font-weight: 500;
+      }
+
+      header nav a.active {
+        background-color: #001540;
+        position: relative;
+        border-radius: 12px;
+      }
+    </style>
+
+    <link
+      rel="stylesheet"
+      href="https://fonts.googleapis.com/css2?family=Material+Symbols+Outlined:opsz,wght,FILL,GRAD@20..48,100..700,0..1,-50..200"
+    />
+  </head>
+  <body>
+    <main>
+      <header>
+        <a href="#" class="logo">
+          <img
+            src="https://aignosi.blob.core.windows.net/sientia/20231016-Aignosi_Logo_WHITE.png"
+            alt="Aignosi Logo"
+            width="247"
+            height="70"
+          />
+        </a>
+        <h1>Report</h1>
+        <nav>
+          <a href="#data_quality" class="active"> Summary </a>
+          <a href="#data_drift"> Drift </a>
+          <a href="#regression"> Regression </a>
+        </nav>
+        <div class="material-symbols-outlined">
+          info
+          <p class="tooltiptext">
+            Note that "current" <br />
+            is related to the test <br />
+            set while "reference" <br />
+            refers to the training <br />
+            set
+          </p>
+        </div>
+      </header>
+      <div class="quality_div">
+        <section id="data_quality"></section>
+      </div>
+      <div class="data_drift_div">
+        <section id="data_drift"></section>
+      </div>
+      <div class="regression_div">
+        <section id="regression"></section>
+      </div>
+    </main>
+
+    <script>
+      let sec = document.querySelectorAll("section");
+      let links = document.querySelectorAll("nav  a");
+
+      window.onscroll = () => {
+        sec.forEach((section) => {
+          let top = window.scrollY;
+          let offset = section.offsetTop;
+          let height = section.offsetHeight;
+          let id = section.getAttribute("id");
+
+          if (top >= offset && top < offset + height) {
+            links.forEach((link) => {
+              link.classList.remove("active");
+              document.querySelector("nav a[href*=" + id + "]").classList.add("active");
+            });
+          }
+        });
+      };
+    </script>
+  </body>
+</html>
--- a/model_manager/reports/temp/test-linear-regression-basic-5_20260119_124123_695140/model_equation.json
+++ b/model_manager/reports/temp/test-linear-regression-basic-5_20260119_124123_695140/model_equation.json
@@ -0,0 +1,15 @@
+{
+  "target_variable": "03CV020/CORRENTE_N_M1_PV(Value)",
+  "coefficients": {
+    "303-WIT-200(Value)": 0.0125579833984375
+  },
+  "intercept": 37.25,
+  "equation_string": "03CV020/CORRENTE_N_M1_PV(Value) = 37.250000 + 0.012558 * 303-WIT-200(Value)",
+  "latex_equation": "03CV020/CORRENTE_N_M1_PV(Value) = 37.250000 + 0.012558 \\cdot 303-WIT-200(Value)",
+  "model_type": "Linear Regression",
+  "degree": 1,
+  "interaction_only": false,
+  "original_features": [
+    "303-WIT-200(Value)"
+  ]
+}
--- a/model_manager/reports/temp/test-linear-regression-basic-5_20260119_124123_695140/regression.html
+++ b/model_manager/reports/temp/test-linear-regression-basic-5_20260119_124123_695140/regression.html
--- a/model_manager/reports/temp/test-linear-regression-basic-5_20260119_124123_695140/report.html
+++ b/model_manager/reports/temp/test-linear-regression-basic-5_20260119_124123_695140/report.html
--- a/model_manager/reports/temp/test-linear-regression-basic-5_20260119_124123_695140/test_data.csv
+++ b/model_manager/reports/temp/test-linear-regression-basic-5_20260119_124123_695140/test_data.csv
--- a/model_manager/reports/temp/test-linear-regression-basic-5_20260119_124123_695140/train_data.csv
+++ b/model_manager/reports/temp/test-linear-regression-basic-5_20260119_124123_695140/train_data.csv
--- a/model_manager/reports/temp/test-linear-regression-basic-6_20260119_124358_804790/data_drift.html
+++ b/model_manager/reports/temp/test-linear-regression-basic-6_20260119_124358_804790/data_drift.html
--- a/model_manager/reports/temp/test-linear-regression-basic-6_20260119_124358_804790/data_quality.html
+++ b/model_manager/reports/temp/test-linear-regression-basic-6_20260119_124358_804790/data_quality.html
--- a/model_manager/reports/temp/test-linear-regression-basic-6_20260119_124358_804790/header.html
+++ b/model_manager/reports/temp/test-linear-regression-basic-6_20260119_124358_804790/header.html
@@ -0,0 +1,167 @@
+<!DOCTYPE html>
+<html lang="en">
+  <head>
+    <meta charset="UTF-8" />
+    <meta http-equiv="X-UA-Compatible" content="IE=edge" />
+    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+    <link rel="stylesheet" href="style.css" />
+
+    <title>Report</title>
+
+    <style>
+      * {
+        font-family: "Franklin Gothic Medium", "Arial Narrow", Arial, sans-serif;
+        margin: 0;
+        padding: 0;
+        box-sizing: border-box;
+      }
+
+      .logo {
+        padding-top: 70;
+        padding-bottom: 70;
+        position: absolute;
+        margin-left: -48px;
+      }
+
+      h1 {
+        color: #fff;
+        position: absolute;
+        margin-left: 45%;
+      }
+
+      html,
+      body {
+        scroll-behavior: smooth;
+      }
+
+      section {
+        padding-top: 90px;
+        width: 100%;
+        display: fixed;
+        justify-content: center;
+        align-items: center;
+        background-color: rgb(217, 217, 214, 0.7);
+      }
+
+      .material-symbols-outlined {
+        font-variation-settings: "FILL" 0, "wght" 400, "GRAD" 0, "opsz" 24;
+        color: #ffff;
+      }
+
+      /* Tooltip text */
+      .tooltiptext {
+        visibility: hidden;
+        background-color: rgb(0, 30, 96, 0.9);
+        padding: 10px;
+        margin-left: -90px;
+        font-size: 16px;
+        position: absolute;
+        top: 85px;
+        border-bottom-left-radius: 12px;
+        border-bottom-right-radius: 12px;
+      }
+
+      /* Show the tooltip text when you mouse over the tooltip container */
+      .material-symbols-outlined:hover .tooltiptext {
+        visibility: visible;
+      }
+
+      header {
+        position: fixed;
+        top: 0;
+        width: 100%;
+        height: 85px;
+        background: rgb(0, 30, 96, 0.95);
+        display: flex;
+        justify-content: space-between;
+        align-items: center;
+        padding: 10px 50px 0;
+      }
+
+      header nav {
+        display: absolute;
+        margin-left: 80%;
+        gap: 10px;
+      }
+
+      header nav a {
+        position: relative;
+        text-decoration: none;
+        padding: 12px 18px;
+        color: #fff;
+        font-weight: 500;
+      }
+
+      header nav a.active {
+        background-color: #001540;
+        position: relative;
+        border-radius: 12px;
+      }
+    </style>
+
+    <link
+      rel="stylesheet"
+      href="https://fonts.googleapis.com/css2?family=Material+Symbols+Outlined:opsz,wght,FILL,GRAD@20..48,100..700,0..1,-50..200"
+    />
+  </head>
+  <body>
+    <main>
+      <header>
+        <a href="#" class="logo">
+          <img
+            src="https://aignosi.blob.core.windows.net/sientia/20231016-Aignosi_Logo_WHITE.png"
+            alt="Aignosi Logo"
+            width="247"
+            height="70"
+          />
+        </a>
+        <h1>Report</h1>
+        <nav>
+          <a href="#data_quality" class="active"> Summary </a>
+          <a href="#data_drift"> Drift </a>
+          <a href="#regression"> Regression </a>
+        </nav>
+        <div class="material-symbols-outlined">
+          info
+          <p class="tooltiptext">
+            Note that "current" <br />
+            is related to the test <br />
+            set while "reference" <br />
+            refers to the training <br />
+            set
+          </p>
+        </div>
+      </header>
+      <div class="quality_div">
+        <section id="data_quality"></section>
+      </div>
+      <div class="data_drift_div">
+        <section id="data_drift"></section>
+      </div>
+      <div class="regression_div">
+        <section id="regression"></section>
+      </div>
+    </main>
+
+    <script>
+      let sec = document.querySelectorAll("section");
+      let links = document.querySelectorAll("nav  a");
+
+      window.onscroll = () => {
+        sec.forEach((section) => {
+          let top = window.scrollY;
+          let offset = section.offsetTop;
+          let height = section.offsetHeight;
+          let id = section.getAttribute("id");
+
+          if (top >= offset && top < offset + height) {
+            links.forEach((link) => {
+              link.classList.remove("active");
+              document.querySelector("nav a[href*=" + id + "]").classList.add("active");
+            });
+          }
+        });
+      };
+    </script>
+  </body>
+</html>
--- a/model_manager/reports/temp/test-linear-regression-basic-6_20260119_124358_804790/model_equation.json
+++ b/model_manager/reports/temp/test-linear-regression-basic-6_20260119_124358_804790/model_equation.json
@@ -0,0 +1,15 @@
+{
+  "target_variable": "03CV020/CORRENTE_N_M1_PV(Value)",
+  "coefficients": {
+    "303-WIT-200(Value)": 0.0125579833984375
+  },
+  "intercept": 37.25,
+  "equation_string": "03CV020/CORRENTE_N_M1_PV(Value) = 37.250000 + 0.012558 * 303-WIT-200(Value)",
+  "latex_equation": "03CV020/CORRENTE_N_M1_PV(Value) = 37.250000 + 0.012558 \\cdot 303-WIT-200(Value)",
+  "model_type": "Linear Regression",
+  "degree": 1,
+  "interaction_only": false,
+  "original_features": [
+    "303-WIT-200(Value)"
+  ]
+}
--- a/model_manager/reports/temp/test-linear-regression-basic-6_20260119_124358_804790/regression.html
+++ b/model_manager/reports/temp/test-linear-regression-basic-6_20260119_124358_804790/regression.html
--- a/Show More
+++ b/Show More
				`@@ -0,0 +1 @@`
				`Signature: 8a477f597d28d172789f06886806bc55`