chore(nicegui): bump to 3.3.1

.github/workflows/_claude-code.yml

@@ -26,6 +26,11 @@ on:
         required: false
         default: true
         type: boolean
+      use_sticky_comment:
+        description: 'Use just one comment to deliver PR comments (only applies for pull_request event workflows)'
+        required: false
+        default: false
+        type: boolean
     secrets:
       ANTHROPIC_API_KEY:
         required: true
@@ -85,13 +90,15 @@ jobs:
             --model claude-sonnet-4-5-20250929
             --allowed-tools "${{ inputs.allowed_tools }}"
             --system-prompt "Read the CLAUDE.md file in the root folder of this repository and explicitely acknowledge you will apply **all** guidance therein and in **all** linked documents."
+
       - name: Run Claude Code (Automation Mode)
         if: inputs.mode == 'automation'
         uses: anthropics/claude-code-action@v1.0.22
         with:
           github_token: ${{ secrets.GITHUB_TOKEN }}
           anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
           track_progress: ${{ inputs.track_progress }}
+          use_sticky_comment: ${{ inputs.use_sticky_comment }}
           additional_permissions: |
             actions: read
           allowed_bots: "dependabot[bot],renovate[bot]"

.github/workflows/_package-publish.yml

@@ -32,15 +32,15 @@ jobs:
         experimental: [false]
         include:
           - runner: ubuntu-24.04-arm
-            experimental: true
+            experimental: false
           - runner: macos-latest
-            experimental: true
+            experimental: false
           - runner: macos-13
-            experimental: true
+            experimental: false
           - runner: windows-latest
-            experimental: true
+            experimental: false
           - runner: windows-11-arm
-            experimental: true
+            experimental: false
 
     permissions:
       attestations: write

.github/workflows/claude-code-automation-pr-review.yml

@@ -11,206 +11,211 @@
 
 jobs:
   claude-review:
+    if: |
+      contains(github.event.pull_request.labels.*.name, 'claude') ||
+      github.event.action == 'ready_for_review'
     uses: ./.github/workflows/_claude-code.yml
     with:
       mode: 'automation'
+      allowed_tools: 'mcp__github_inline_comment__create_inline_comment,Read,Write,Edit,MultiEdit,Glob,Grep,LS,WebFetch,WebSearch,Bash(git:*),Bash(bun:*),Bash(npm:*),Bash(npx:*),Bash(gh:*),Bash(uv:*),Bash(make:*)'
       track_progress: ${{ github.event_name == 'pull_request' && contains(fromJSON('["opened", "synchronize", "ready_for_review", "reopened"]'), github.event.action) }}
+      use_sticky_comment: true
       prompt: |
         # PR REVIEW FOR AIGNOSTICS PYTHON SDK
 
         **REPO**: ${{ github.repository }}
         **PR**: #${{ github.event.pull_request.number }}
         **BRANCH**: ${{ github.head_ref }}
 
         ## Context
 
         This is a **medical device software SDK** for computational pathology. You are reviewing code that:
         - Processes whole slide images (WSI) - gigapixel medical images
         - Integrates with FDA/MDR regulated AI/ML applications
         - Handles sensitive medical data (HIPAA compliance required)
         - Follows a **modulith architecture** with strict module boundaries
 
         ## Documentation References
 
         **IMPORTANT**: This repository has comprehensive documentation you MUST reference:
         - **CLAUDE.md** (root) - Architecture, testing workflow, development standards
         - **.github/CLAUDE.md** - Complete CI/CD guide (19 workflows, test strategy)
         - **src/aignostics/*/CLAUDE.md** - Module-specific implementation guides
 
         Read these files and apply their guidance throughout your review.
 
         ## CRITICAL CHECKS (BLOCKING - Must Pass)
 
         ### 1. Test Markers (CRITICAL!)
 
         **EVERY test MUST have at least one marker: `unit`, `integration`, or `e2e`**
 
         Tests without these markers will **NOT run in CI** because the pipeline explicitly filters by markers.
 
         ```bash
         # Find unmarked tests (should return 0 tests):
         uv run pytest -m "not unit and not integration and not e2e" --collect-only
 
         # If unmarked tests found, check the specific files changed in this PR:
         uv run pytest tests/aignostics/<module>/<file>_test.py --collect-only
         ```
 
         **Action if violations found**:
         - List all test files missing markers with file paths and line numbers
         - Provide exact decorator to add (e.g., `@pytest.mark.unit`)
         - Reference `.github/CLAUDE.md` test categorization guide
 
         ### 2. Test Coverage (85% Minimum)
 
         If coverage drops below 85%, identify which new code lacks tests.
 
         ### 3. Code Quality (Must Pass)
 
         ```bash
         # Check linting:
         make lint
         # Runs: ruff format, ruff check, pyright (basic), mypy (strict)
         ```
 
         All 4 checks must pass. If failures occur, provide specific fixes.
 
         ### 4. Conventional Commits
 
         All commits must follow: `type(scope): description`
 
         Valid types: `feat`, `fix`, `docs`, `refactor`, `test`, `chore`, `ci`, `perf`, `build`
 
         ```bash
         # Check commit messages:
         git log --oneline origin/main..HEAD
         ```
 
         ## Repository-Specific Review Areas
 
         ### 5. Architecture Compliance
 
         **Modulith Principles**:
         - Each module is self-contained (Service + optional CLI + optional GUI)
         - **CRITICAL**: CLI and GUI must NEVER depend on each other
         - Both depend on Service layer only
         - No circular dependencies between modules
 
         **Service Pattern**:
         - All services inherit from `BaseService` (from `utils`)
         - Must implement `health()` → `Health` and `info()` → `dict`
         - Use dependency injection via `locate_implementations(BaseService)`
         - No decorator-based DI
 
         **Check**:
         ```bash
         # Find all service implementations:
         grep -r "class.*Service.*BaseService" src/aignostics/
 
         # Check for circular imports:
         # Look for cross-module imports that shouldn't exist
         ```
 
         ### 6. Testing Strategy
 
         **Test Categories** (see `.github/CLAUDE.md` for full details):
         - `unit`: Isolated, no external deps, <10s timeout, sequential (XDIST_WORKER_FACTOR=0.0)
         - `integration`: Mocked external services, <5min, limited parallel (0.2)
         - `e2e`: Real API calls, staging environment, full parallel (1.0)
         - `long_running`: E2E tests ≥5min, aggressive parallel (2.0), opt-out with label
         - `very_long_running`: E2E tests ≥60min, only run when explicitly enabled
 
         **For new tests, verify**:
         - Correct marker applied based on test characteristics
         - Timeout set if >10s (use `@pytest.mark.timeout(60)`)
         - E2E tests only run against staging (never production in PR CI)
 
         ### 7. Medical Device & Security
 
         **Check for**:
         - Secrets/tokens in code or commits (use .env, never hardcode)
         - Sensitive data masking in logs (use `mask_secrets=True`)
         - Medical data handling (DICOM compliance, proper anonymization)
         - OAuth token management (refresh before 5min expiry)
 
         **WSI Processing**:
         - Large images processed in tiles (never load full image in memory)
         - Proper cleanup of temp files
         - Progress tracking for long operations
 
         ### 8. Breaking Changes
 
         **Check if PR introduces**:
         - API client method signature changes
         - CLI command changes (breaking user scripts)
         - Environment variable changes
         - Configuration file format changes
         - OpenAPI model changes (from codegen)
 
         If breaking changes detected, verify:
         - Proper deprecation warnings added
         - Migration guide in PR description
         - Version bump appropriate (major vs minor)
 
         ### 9. CI/CD Impact
 
         **If workflow files changed** (`.github/workflows/*.yml`):
         - Verify syntax is correct
         - Check reusable workflow inputs/secrets match
         - Validate test marker filtering logic
         - Ensure BetterStack heartbeats still work
 
         **If new tests added**:
         - Are they categorized correctly for CI execution?
         - Do they need to be scheduled tests?
         - Is XDIST_WORKER_FACTOR appropriate?
 
         ### 10. Documentation Updates
 
         **If new features added**:
         - Is CLAUDE.md updated? (root or module-specific)
         - Are docstrings added (Google style)?
         - Is README updated if user-facing change?
         - Are type hints complete?
 
         ## Code Quality Standards
 
         - **Type Checking**: Dual checking (MyPy strict + PyRight basic) - both must pass
         - **Line Length**: 120 chars max
         - **Imports**: stdlib → 3rd-party → local, use relative imports within modules
         - **Docstrings**: Google style for all public APIs
         - **Error Handling**: Custom exceptions from `system/_exceptions.py`
         - **Logging**: Structured logging via `get_logger(__name__)`
 
         ## Review Output Format
 
         For each issue found, provide:
 
         1. **Location**: `file_path:line_number` (e.g., `src/aignostics/platform/_client.py:123`)
         2. **Issue**: Clear description with reference to CLAUDE.md section
         3. **Reproduce**: Exact command to reproduce (e.g., `uv run pytest tests/...`)
         4. **Fix**: Concrete code example or command
         5. **Verify**: Command to verify fix works (e.g., `make lint && make test`)
 
         **Use inline comments** for specific code issues.
         **Use PR-level comment** for:
         - Summary of findings (blocking vs suggestions)
         - Overall architecture feedback
         - Praise for excellent work
         - Missing CLAUDE.md updates needed
 
         ## Final Steps
 
         After completing your review:
 
         1. **Summarize findings** in PR comment using `gh pr comment`
         2. **Categorize issues**: Blocking (must fix) vs Suggestions (nice to have)
         3. **Provide commands** to fix all blocking issues in one go if possible
         4. **Reference documentation**: Link to relevant CLAUDE.md sections
 
         Use `gh pr comment` with your Bash tool to leave your comprehensive review as a comment on the PR.
 
         ---
 
         **Remember**: This is medical device software. Insist on highest standards. Be thorough, actionable, and kind.
     secrets:
       ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}

CLI_REFERENCE.md

@@ -14,7 +14,7 @@ $ aignostics [OPTIONS] COMMAND [ARGS]...
 * `--show-completion`: Show completion for the current shell, to copy it or customize the installation.
 * `--help`: Show this message and exit.
 
-🔬 Aignostics Python SDK v0.2.226 - built with love in Berlin 🐻
+🔬 Aignostics Python SDK v0.2.226 - built with love in Berlin 🐻 // Python v3.14.1
 
 **Commands**:
 

pyproject.toml

@@ -77,7 +77,7 @@ dependencies = [
     # From Template
     "fastapi[all,standard]>=0.123.10",
     "humanize>=4.14.0,<5",
-    "nicegui[native]>=3.1.0,<3.2.0", # Regression in 3.2.0
+    "nicegui[native]>=3.3.1,<4",
     "packaging>=25.0,<26",
     "platformdirs>=4.5.1,<5",
     "psutil>=7.1.3,<8",
@@ -153,7 +153,7 @@ dev = [
     "pip-licenses @ git+https://github.com/neXenio/pip-licenses.git@master", # https://github.com/raimon49/pip-licenses/pull/224
     "pre-commit>=4.5.0,<5",
     "pyright>=1.1.406,<1.1.407", # Regression in 1.1.407, see https://github.com/microsoft/pyright/issues/11060
-    "pytest>=9.0.1,<10",
+    "pytest>=9.0.2,<10",
     "pytest-asyncio>=1.3.0,<2",
     "pytest-cov>=7.0.0,<8",
     "pytest-docker>=3.2.5,<4",

src/aignostics/application/_cli.py

@@ -746,7 +746,7 @@ def run_submit(  # noqa: PLR0913, PLR0917
         )
     except ValueError as e:
         logger.warning(
-            "Bad input to create run for application '%s' (version: '%s'): %s", application_id, application_version, e
+            "Bad input to create run for application '{}' (version: '{}'): {}", application_id, application_version, e
         )
         console.print(
             f"[warning]Warning:[/warning] Bad input to create run for application "
@@ -755,7 +755,7 @@ def run_submit(  # noqa: PLR0913, PLR0917
         sys.exit(2)
     except NotFoundException as e:
         logger.warning(
-            "Could not find application version '%s' (version: '%s'): %s", application_id, application_version, e
+            "Could not find application version '{}' (version: '{}'): {}", application_id, application_version, e
         )
         console.print(
             f"[warning]Warning:[/warning] Could not find application '{application_id} "
@@ -773,10 +773,10 @@ def run_submit(  # noqa: PLR0913, PLR0917
     try:
         metadata_dict = read_metadata_csv_to_dict(metadata_csv_file=metadata_csv_file)
         if not metadata_dict:
-            console.print("Could mot read metadata file '%s'", metadata_csv_file)
+            console.print(f"Could not read metadata file '{metadata_csv_file}'")
             sys.exit(2)
         logger.trace(
-            "Submitting run for application '%s' (version: '%s') with metadata: %s",
+            "Submitting run for application '{}' (version: '{}') with metadata: {}",
             application_id,
             app_version.version_number,
             metadata_dict,
@@ -809,7 +809,7 @@ def run_submit(  # noqa: PLR0913, PLR0917
         return application_run.run_id
     except ValueError as e:
         logger.warning(
-            "Bad input to create run for application '%s' (version: %s): %s",
+            "Bad input to create run for application '{}' (version: {}): {}",
             application_id,
             app_version.version_number,
             e,
@@ -821,7 +821,7 @@ def run_submit(  # noqa: PLR0913, PLR0917
         sys.exit(2)
     except Exception as e:
         logger.exception(
-            "Failed to create run for application '%s' (version: %s)", application_id, app_version.version_number
+            "Failed to create run for application '{}' (version: {})", application_id, app_version.version_number
         )
         console.print(
             f"[error]Error:[/error] Failed to create run for application "
@@ -1059,7 +1059,7 @@ def run_cancel_by_filter(  # noqa: C901, PLR0912, PLR0915
         sys.exit(1)
 
     logger.trace(
-        "Canceling runs with filters: tags=%s, application_id=%s, application_version=%s, limit=%s, dry_run=%s",
+        "Canceling runs with filters: tags={}, application_id={}, application_version={}, limit={}, dry_run={}",
         tags,
         application_id,
         application_version,
@@ -1207,7 +1207,7 @@ def run_update_item_metadata(
         sys.exit(2)
     except ValueError as e:
         logger.warning(
-            "Run ID '%s' or item external ID '%s' invalid or metadata invalid: %s",
+            "Run ID '{}' or item external ID '{}' invalid or metadata invalid: {}",
             run_id,
             external_id,
             e,
@@ -1219,7 +1219,7 @@ def run_update_item_metadata(
         sys.exit(2)
     except Exception as e:
         logger.exception(
-            "Failed to update custom metadata for item '%s' in run with ID '%s'",
+            "Failed to update custom metadata for item '{}' in run with ID '{}'",
             external_id,
             run_id,
         )
@@ -1278,8 +1278,8 @@ def result_download(  # noqa: C901, PLR0913, PLR0915, PLR0917
 ) -> None:
     """Download results of a run."""
     logger.trace(
-        "Downloading results for run with ID '%s' to '%s' with options: "
-        "create_subdirectory_for_run=%s, create_subdirectory_per_item=%s, wait_for_completion=%s, qupath_project=%r",
+        "Downloading results for run with ID '{}' to '{}' with options: "
+        "create_subdirectory_for_run={}, create_subdirectory_per_item={}, wait_for_completion={}, qupath_project={}",
         run_id,
         destination_directory,
         create_subdirectory_for_run,