[DPE-8884] Add charm refresh (#39)

* [DPE-8884] Implement charm refreshing

* [DPE-8884] Implement charm refreshing

* [DPE-8884] Implement charm refreshing

* [DPE-8884] Implement charm refreshing

* [DPE-8884] Implement charm refreshing

* [DPE-8884] Implement charm refreshing

* [DPE-8884] Implement charm refreshing

* fix lint

* fix tests

* fix lint

* fix build

* Fixes

* Improvements.

* Improvements.

* Unit tests

* fix unit

* fix CI build

* Rebase.

* Improve refresh scaling capabilities.

* Fix tests

* fix lint

* Remove unused code.

* logger fixes

* fixes

* fixes

---------

Co-authored-by: Vladyslav Tarasenko <vladyslav.tarasenko@canonical.com>

Author: BON4

.github/workflows/ci.yaml

@@ -67,7 +67,7 @@ jobs:
           - .
           - tests/integration/application-charm
     name: Build charm
-    uses: canonical/data-platform-workflows/.github/workflows/build_charm.yaml@v29.0.0
+    uses: canonical/data-platform-workflows/.github/workflows/build_charm.yaml@v32.1.0
     with:
       path-to-charm-directory: ${{ matrix.path }}
       cache: false

actions.yaml

@@ -1,2 +1,57 @@
 # Copyright 2025 Canonical Ltd.
 # See LICENSE file for licensing details.
+pre-refresh-check:
+  description: Check if charm is ready to refresh
+  additionalProperties: false
+force-refresh-start:
+  description: |
+    Potential of data loss and downtime
+
+    Force refresh of first unit
+
+    Must run with at least one of the parameters `=false`
+  params:
+    check-compatibility:
+      type: boolean
+      default: true
+      description: |
+        Potential of data loss and downtime
+
+        If `false`, force refresh if new version of Cassandra and/or charm is not compatible with previous version
+    run-pre-refresh-checks:
+      type: boolean
+      default: true
+      description: |
+        Potential of data loss and downtime
+
+        If `false`, force refresh if app is unhealthy or not ready to refresh (and unit status shows "Pre-refresh check failed")
+    check-workload-container:
+      type: boolean
+      default: true
+      description: |
+        Potential of data loss and downtime during and after refresh
+
+        If `false`, allow refresh to Cassandra container version that has not been validated to work with the charm revision
+  additionalProperties: false
+resume-refresh:
+  description: |
+    Refresh next unit(s) (after you have manually verified that refreshed units are healthy)
+
+    If the `pause-after-unit-refresh` config is set to `all`, this action will refresh the next unit.
+
+    If `pause-after-unit-refresh` is set to `first`, this action will refresh all remaining units.
+    Exception: if automatic health checks fail after a unit has refreshed, the refresh will pause.
+
+    If `pause-after-unit-refresh` is set to `none`, this action will have no effect unless it is called with `check-health-of-refreshed-units` as `false`.
+  params:
+    check-health-of-refreshed-units:
+      type: boolean
+      default: true
+      description: |
+        Potential of data loss and downtime
+
+        If `false`, force refresh (of next unit) if 1 or more refreshed units are unhealthy
+
+        Warning: if first unit to refresh is unhealthy, consider running `force-refresh-start` action on that unit instead of using this parameter.
+        If first unit to refresh is unhealthy because compatibility checks, pre-refresh checks, or workload container checks are failing, this parameter is more destructive than the `force-refresh-start` action.
+  additionalProperties: false

charmcraft.yaml

@@ -74,9 +74,22 @@ parts:
       # Include requirements.txt in *.charm artifact for easier debugging
       cp requirements.txt "$CRAFT_PART_INSTALL/requirements.txt"
 
-  # "files" part name is arbitrary; use for consistency
   files:
     plugin: dump
     source: .
+    after:
+      - poetry-deps  # Ensure poetry is installed
+    build-packages:
+      - git
+    override-build: |
+      # Set `charm_version` in refresh_versions.toml from git tag
+      # Create venv in `..` so that git working tree is not dirty
+      python3 -m venv ../refresh-version-venv
+      source ../refresh-version-venv/bin/activate
+      poetry install --only build-refresh-version
+      write-charm-version
+
+      craftctl default
     stage:
       - LICENSE
+      - refresh_versions.toml

config.yaml

@@ -17,3 +17,11 @@ options:
       Configure the internal system user password. The password will be auto-generated
       if this option is not set. This needs to be a Juju Secret URI pointing to an
       accessible secret that contains the following content: `operator: <password>`.
+
+  pause-after-unit-refresh:
+    description: |
+      Wait for manual confirmation to resume refresh after these units refresh
+
+      Allowed values: "all", "first", "none"
+    type: string
+    default: first

metadata.yaml

@@ -34,6 +34,8 @@ peers:
     interface: cassandra_peers
   bootstrap:
     interface: rolling_op
+  refresh-v-three:
+    interface: refresh    
 
 requires:
   client-certificates: