refactor: overhaul health check system architecture including collect…

.github/workflows/ci.yml

@@ -24,6 +24,9 @@ jobs:
           python -m pip install --upgrade pip
           pip install -e ".[dev]"
 
+      - name: Code quality - Ruff formatter
+        run: ruff format --check .
+
       - name: Run health test suite
         run: |
           pytest tests/unit/health/ tests/integration/test_health_*.py -q

.github/workflows/release.yml

@@ -27,7 +27,7 @@ jobs:
     - name: Install build dependencies
       run: |
         python -m pip install --upgrade pip
-        pip install build twine black mypy pip-audit types-requests types-PyYAML types-setuptools
+        pip install build twine ruff mypy pip-audit types-requests types-PyYAML types-setuptools
 
     - name: Set up Node.js
       uses: actions/setup-node@v4
@@ -40,8 +40,8 @@ jobs:
         npm ci
         npm run build
 
-    - name: Code Quality - Black Formatter
-      run: black --check .
+    - name: Code Quality - Ruff Formatter
+      run: ruff format --check .
 
     - name: Code Quality - Type Safety (Mypy)
       run: mypy .

CONTRIBUTING.md

@@ -21,10 +21,10 @@ pip install -e ".[dev]"
 We enforce strict quality gates. All checks must pass before merging.
 
 ### Formatting & Linting
-We use **Black** (formatter) and **Isort** (import sorter).
+We use **Ruff** for formatting and linting.
 ```bash
-black .
-isort .
+ruff format .
+ruff check --fix .
 ```
 
 ### Static Type Checking

README.md

@@ -12,7 +12,7 @@
 
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 [![Python 3.8+](https://img.shields.io/badge/python-3.8+-blue.svg)](https://www.python.org/downloads/)
-[![Code Style: Black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
+[![Code style: Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
 
 
 A comprehensive Python module for managing Elasticsearch operations within pipeline processes.

elastro/cli/commands/health.py

@@ -158,22 +158,38 @@ def health_group() -> None:
     default=False,
     help="With --fix, show planned API calls without executing",
 )
-@click.option("--yes", is_flag=True, default=False, help="With --fix, auto-confirm CONFIRM actions")
+@click.option(
+    "--yes",
+    is_flag=True,
+    default=False,
+    help="With --fix, auto-confirm CONFIRM actions",
+)
 @click.option(
     "--force",
     is_flag=True,
     default=False,
     help="With --fix and --yes, allow DESTRUCTIVE actions in non-interactive mode",
 )
-@click.option("--index", "index_pattern", type=str, default=None, help="Limit fixes to an index pattern")
+@click.option(
+    "--index",
+    "index_pattern",
+    type=str,
+    default=None,
+    help="Limit fixes to an index pattern",
+)
 @click.option(
     "--action",
     "action_filter",
     type=click.Choice(CATALOG_ACTION_IDS, case_sensitive=False),
     default=None,
     help="Limit fixes to a single remediation action",
 )
-@click.option("--target-replicas", type=int, default=None, help="Explicit replica target for reduce_replicas")
+@click.option(
+    "--target-replicas",
+    type=int,
+    default=None,
+    help="Explicit replica target for reduce_replicas",
+)
 @click.option(
     "--history/--no-history",
     default=False,
@@ -386,7 +402,13 @@ def _render_health_fix(
     default=False,
     help="With --yes, allow DESTRUCTIVE actions in non-interactive mode",
 )
-@click.option("--index", "index_pattern", type=str, default=None, help="Limit fixes to an index pattern")
+@click.option(
+    "--index",
+    "index_pattern",
+    type=str,
+    default=None,
+    help="Limit fixes to an index pattern",
+)
 @click.option(
     "--action",
     "action_filter",
@@ -846,7 +868,9 @@ def health_nodes(
 
 
 @health_group.command("shards")
-@click.option("--index", type=str, default=None, help="Limit to a specific index pattern")
+@click.option(
+    "--index", type=str, default=None, help="Limit to a specific index pattern"
+)
 @click.option(
     "--analyze",
     is_flag=True,
@@ -977,7 +1001,9 @@ def health_shards(
     default=False,
     help="Show only indices with failed or stuck ILM lifecycle steps",
 )
-@click.option("--index", "index_pattern", type=str, default=None, help="Limit to an index pattern")
+@click.option(
+    "--index", "index_pattern", type=str, default=None, help="Limit to an index pattern"
+)
 @click.pass_context
 def health_ilm(
     ctx: click.Context,
@@ -1203,9 +1229,7 @@ def health_rollback_list(ctx: click.Context, last: int) -> None:
                 f"{record.action_id}  {record.applied_at.isoformat()}"
             )
     else:
-        payload = {
-            "rollbacks": [record.model_dump(mode="json") for record in records]
-        }
+        payload = {"rollbacks": [record.model_dump(mode="json") for record in records]}
         click.echo(format_output(payload, output_format=output_fmt))
 
 
@@ -1251,10 +1275,14 @@ def _run_health_rollback(
         rollback_id,
         dry_run,
     )
-    audit = None if dry_run else HealthAuditLogger(
-        client,
-        profile=_cli_profile(ctx),
-        host=_client_host(client),
+    audit = (
+        None
+        if dry_run
+        else HealthAuditLogger(
+            client,
+            profile=_cli_profile(ctx),
+            host=_client_host(client),
+        )
     )
     executor = RemediationExecutor(
         client,
@@ -1395,4 +1423,4 @@ def health_report(
         click.echo(format_output(result, output_format="json"))
     except OperationError as e:
         click.echo(f"Error fetching health report: {str(e)}", err=True)
-        raise SystemExit(1) from e
+        raise SystemExit(1) from e

elastro/cli/commands/index.py

@@ -186,7 +186,9 @@ def update_index(client: ElasticsearchClient, name: str, settings: Any) -> None:
     help="Preview deletion without executing (scriptable with -o json)",
 )
 @click.pass_obj
-def delete_index(client: ElasticsearchClient, name: str, force: bool, dry_run: bool) -> None:
+def delete_index(
+    client: ElasticsearchClient, name: str, force: bool, dry_run: bool
+) -> None:
     """
     Delete an index.
 
@@ -210,7 +212,11 @@ def delete_index(client: ElasticsearchClient, name: str, force: bool, dry_run: b
     elastro index delete my-logs --force
     ```
     """
-    from elastro.cli.deletion import emit_delete_preview, preview_index_delete, should_prompt_for_delete
+    from elastro.cli.deletion import (
+        emit_delete_preview,
+        preview_index_delete,
+        should_prompt_for_delete,
+    )
 
     if dry_run:
         emit_delete_preview(preview_index_delete(client, name))
@@ -337,7 +343,9 @@ def list_indices(client: ElasticsearchClient, pattern: str) -> None:
             color = (
                 "green"
                 if health == "green"
-                else "yellow" if health == "yellow" else "red"
+                else "yellow"
+                if health == "yellow"
+                else "red"
             )
 
             table.add_row(
@@ -603,7 +611,9 @@ def fix_indices(client: ElasticsearchClient) -> None:
         fix_result = run_health_fix(
             client,
             interactive=True,
-            confirm=lambda prompt, default: Confirm.ask(f"   {prompt}", default=default),
+            confirm=lambda prompt, default: Confirm.ask(
+                f"   {prompt}", default=default
+            ),
             prompt=lambda message: Prompt.ask(f"   {message}"),
         )
         render_fix_run_result(fix_result, output_format="table")

elastro/cli/commands/snapshot.py

@@ -140,7 +140,10 @@ def delete_repository(
     elastro -o json snapshot repo delete my_backup --dry-run
     ```
     """
-    from elastro.cli.deletion import emit_delete_preview, preview_snapshot_repository_delete
+    from elastro.cli.deletion import (
+        emit_delete_preview,
+        preview_snapshot_repository_delete,
+    )
 
     if dry_run:
         emit_delete_preview(preview_snapshot_repository_delete(client, name))
@@ -307,7 +310,7 @@ def restore_snapshot(
         if not repository:
             console.print("\nAvailable Repositories:")
             for i, r in enumerate(repo_names):
-                console.print(f"  {i+1}. {r}")
+                console.print(f"  {i + 1}. {r}")
 
             repo_idx = int(Prompt.ask("Select Repository", default="1")) - 1
             repository = repo_names[repo_idx]
@@ -334,7 +337,7 @@ def restore_snapshot(
             for i in range(limit):
                 s = snaps[i]
                 console.print(
-                    f"  {i+1}. {s['snapshot']} ({s['state']}, {len(s['indices'])} indices)"
+                    f"  {i + 1}. {s['snapshot']} ({s['state']}, {len(s['indices'])} indices)"
                 )
 
             snap_idx = int(Prompt.ask("Select Snapshot", default="1")) - 1

elastro/cli/deletion.py

@@ -79,10 +79,15 @@ def emit_delete_preview(preview: DeletePreview) -> None:
             click.echo(f"  {key}: {value}")
         return
 
-    click.echo(format_output(delete_preview_payload(preview), output_format=output_fmt), nl=False)
+    click.echo(
+        format_output(delete_preview_payload(preview), output_format=output_fmt),
+        nl=False,
+    )
 
 
-def should_prompt_for_delete(*, dry_run: bool, force: bool = False, yes: bool = False) -> bool:
+def should_prompt_for_delete(
+    *, dry_run: bool, force: bool = False, yes: bool = False
+) -> bool:
     """Return True when interactive confirmation is required."""
     if dry_run:
         return False
@@ -325,7 +330,9 @@ def preview_script_delete(client: ElasticsearchClient, script_id: str) -> Delete
     )
 
 
-def preview_pipeline_delete(client: ElasticsearchClient, pipeline_id: str) -> DeletePreview:
+def preview_pipeline_delete(
+    client: ElasticsearchClient, pipeline_id: str
+) -> DeletePreview:
     exists = False
     try:
         client._ensure_connected()
@@ -344,4 +351,4 @@ def preview_pipeline_delete(client: ElasticsearchClient, pipeline_id: str) -> De
             if exists
             else f"Ingest pipeline '{pipeline_id}' does not exist; delete would fail."
         ),
-    )
+    )

elastro/core/errors.py

@@ -48,6 +48,10 @@ class ElasticIndexError(OperationError):
     pass
 
 
+# Backward-compatible alias used by tests and docs.
+IndexError = ElasticIndexError
+
+
 class DocumentError(OperationError):
     """Raised when a document operation fails."""
 

elastro/core/ilm.py

@@ -182,4 +182,6 @@ def retry_lifecycle(self, index: str) -> bool:
             return True
         except Exception as e:
             logger.error("Failed to retry ILM lifecycle for '%s': %s", index, e)
-            raise OperationError(f"Failed to retry ILM lifecycle for '{index}': {e}") from e
+            raise OperationError(
+                f"Failed to retry ILM lifecycle for '{index}': {e}"
+            ) from e

elastro/core/logger.py

@@ -120,9 +120,7 @@ def configure_logging(log_level: Optional[str] = None) -> logging.Logger:
         )
         package_logger.addHandler(file_handler)
     except Exception:
-        sys.stderr.write(
-            f"Warning: Could not set up file logging to {LOG_FILE_PATH}\n"
-        )
+        sys.stderr.write(f"Warning: Could not set up file logging to {LOG_FILE_PATH}\n")
 
     if _logloom_handler is not None:
         try:
@@ -158,4 +156,4 @@ def get_logger(name: str, log_level: Optional[str] = None) -> logging.Logger:
         logger.handlers.clear()
     if log_level is not None:
         logger.setLevel(_resolve_level(log_level))
-    return logger
+    return logger

elastro/health/__init__.py

@@ -9,7 +9,10 @@
     Severity,
 )
 from elastro.health.assessor import HealthAssessor
-from elastro.health.collectors.health_report import HealthReportCollector, map_indicators
+from elastro.health.collectors.health_report import (
+    HealthReportCollector,
+    map_indicators,
+)
 from elastro.health.manager import HealthManager
 from elastro.health.remediation import RemediationCatalog, RemediationExecutor
 
@@ -26,4 +29,4 @@
     "RemediationExecutor",
     "RemediationSafety",
     "Severity",
-]
+]

elastro/health/assessor.py

@@ -119,7 +119,8 @@ def run(
                             title="Health report unavailable",
                             status=FindingStatus.SKIPPED,
                             severity=Severity.LOW,
-                            summary=result.error or "Health report collector was skipped.",
+                            summary=result.error
+                            or "Health report collector was skipped.",
                             source="collector",
                         )
                     )
@@ -131,7 +132,9 @@ def run(
             if result.name == "health_report":
                 report_data = result.data
                 raw_health_report = report_data.get("report")
-                cluster_name = report_data.get("cluster_name", cluster_name) or cluster_name
+                cluster_name = (
+                    report_data.get("cluster_name", cluster_name) or cluster_name
+                )
                 indicators = report_data.get("indicators", {})
                 overall_score = compute_weighted_score(indicators)
                 findings.extend(non_passing_findings(report_data.get("findings", [])))
@@ -225,9 +228,7 @@ def run(
                     overall_score = max(0, overall_score - deduction)
 
         collector_data = {
-            result.name: result.data
-            for result in results
-            if result.status == "ok"
+            result.name: result.data for result in results if result.status == "ok"
         }
         disk_data = collector_data.get("disk") or {}
         if isinstance(disk_data, dict) and disk_data.get("cluster_settings"):
@@ -395,4 +396,4 @@ def _run_collectors(
 
         results.append(result)
 
-    return results
+    return results

elastro/health/audit.py

@@ -156,4 +156,4 @@ def log_rollback(
             record.session_id,
             payload,
             cluster_name=record.cluster_name,
-        )
+        )

elastro/health/collectors/__init__.py

@@ -12,4 +12,4 @@
     "Collector",
     "CollectorRegistry",
     "CollectorResult",
-]
+]

elastro/health/collectors/base.py

@@ -102,4 +102,4 @@ def run(
                 )
             results.append(result)
 
-        return results
+        return results