Add V2 UI packaging and Docker integration

[tomerqodo]

Benchmark PR from agentic-review-benchmarks#8

[qodo-code-review]

Code Review by Qodo

🐞 Bugs (1) 📘 Rule violations (3) 📎 Requirement gaps (0)

1. Missing future import in __init__.py 📘 Rule violation ✓ Correctness

Description

• src/prefect/__init__.py contains type annotations (e.g., __ui_v2_static_path__: pathlib.Path)
  but does not include from __future__ import annotations as the first import.
• This violates the requirement for src/ Python files with type hints to enable forward-reference
  resolution and consistent type-checking behavior.

Code

src/prefect/init.py[R67-72]

+# The absolute path to the built V2 UI within the Python module, used by
+# `prefect server start` to serve a dynamic build of the V2 UI
+__ui_v2_static_subpath__: pathlib.Path = __module_path__ / "server" / "ui_v2_build"
+
+# The absolute path to the built V2 UI within the Python module
+__ui_v2_static_path__: pathlib.Path = __module_path__ / "server" / "ui_v2"

Evidence

The checklist requires from __future__ import annotations as the first import in any src/ Python
file that uses type annotations. src/prefect/__init__.py has annotated variables added/maintained,
but its import block begins with normal imports instead of the required future import.

AGENTS.md
src/prefect/init.py[1-10]
src/prefect/init.py[55-72]

Agent prompt

The issue below was found during a code review. Follow the provided context and guidance below and implement a solution

## Issue description
`src/prefect/__init__.py` uses type annotations but does not have `from __future__ import annotations` as the first import, violating the project rule for typed files under `src/`.

## Issue Context
This file contains annotated constants (e.g., `__ui_v2_static_path__: pathlib.Path`) and imports from `typing`, so it must include the future annotations import as the first import statement.

## Fix Focus Areas
- src/prefect/__init__.py[1-10]
- src/prefect/__init__.py[55-72]

ⓘ Copy this prompt and use it to remediate the issue with your preferred AI generation tools

---

2. Missing future import in ui.py 📘 Rule violation ✓ Correctness

Description

• src/prefect/settings/models/server/ui.py contains type annotations (e.g., `model_config:
  ClassVar[...], v2_enabled: bool) but lacks from __future__ import annotations` as the first
  import.
• This violates the required typing import convention for src/ modules and can lead to
  inconsistent annotation evaluation across the codebase.

Code

src/prefect/settings/models/server/ui.py[R22-25]

+    v2_enabled: bool = Field(
+        default=True,
+        description="Whether to serve the experimental V2 UI instead of the default V1 UI.",
+    )

Evidence

The compliance rule requires from __future__ import annotations to be present as the first import
in any typed Python file under src/. This file begins with from typing ... and defines annotated
settings fields, but has no future import at all.

AGENTS.md
src/prefect/settings/models/server/ui.py[1-7]
src/prefect/settings/models/server/ui.py[9-29]

Agent prompt

The issue below was found during a code review. Follow the provided context and guidance below and implement a solution

## Issue description
`src/prefect/settings/models/server/ui.py` defines type annotations but does not include `from __future__ import annotations` as the first import.

## Issue Context
The file defines annotated fields and class variables; the project rule requires future annotations import first for all typed files under `src/`.

## Fix Focus Areas
- src/prefect/settings/models/server/ui.py[1-7]
- src/prefect/settings/models/server/ui.py[9-29]

ⓘ Copy this prompt and use it to remediate the issue with your preferred AI generation tools

---

3. logging.getLogger() used for ui_logger 📘 Rule violation ✧ Quality

Description

• The new code creates ui_logger via logging.getLogger("ui_server") rather than the required
  standardized get_logger(...) pattern with a logging.Logger type annotation.
• This breaks logging consistency/type-safety expectations and violates the project’s logger
  instantiation standard.

Code

src/prefect/server/api/server.py[R529-532]

+        # Log which UI version is being served
+        if v2_enabled:
+            ui_logger = logging.getLogger("ui_server")
+            ui_logger.info("Serving experimental V2 UI")

Evidence

The compliance rule mandates using logger: "logging.Logger" = get_logger("module_name") instead of
logging.getLogger() directly. In create_ui_app, the new ui_logger is instantiated with
logging.getLogger without the standardized pattern or type annotation.

AGENTS.md
src/prefect/server/api/server.py[529-533]
src/prefect/server/api/server.py[51-52]

Agent prompt

The issue below was found during a code review. Follow the provided context and guidance below and implement a solution

## Issue description
A new logger is created via `logging.getLogger("ui_server")` inside `create_ui_app`, which violates the standardized logger initialization pattern that requires `get_logger(...)` and a `logging.Logger` type annotation.

## Issue Context
This module already imports `get_logger` and defines a module-level `logger: "logging.Logger" = get_logger("server")`.

## Fix Focus Areas
- src/prefect/server/api/server.py[529-533]

ⓘ Copy this prompt and use it to remediate the issue with your preferred AI generation tools

---

View more (1)

4. V2 UI path mismatch 🐞 Bug ✓ Correctness

Description

• Python runtime looks for V2 UI assets in a different directory name than the build/packaging steps
  produce (underscore vs hyphen).
• When V2 is enabled, os.path.exists(source_static_path) will fail and the server will not mount
  any UI routes, effectively disabling the UI.
• This is likely to reproduce in Docker builds and release packaging because both Dockerfile and
  hatch artifacts use the hyphenated directory name.

Code

src/prefect/init.py[R67-72]

+# The absolute path to the built V2 UI within the Python module, used by
+# `prefect server start` to serve a dynamic build of the V2 UI
+__ui_v2_static_subpath__: pathlib.Path = __module_path__ / "server" / "ui_v2_build"
+
+# The absolute path to the built V2 UI within the Python module
+__ui_v2_static_path__: pathlib.Path = __module_path__ / "server" / "ui_v2"

Evidence

The PR introduces __ui_v2_static_path__ pointing to server/ui_v2, and server UI mounting checks
that path. However, the Docker build and hatch packaging place V2 assets under server/ui-v2
(hyphen). That mismatch means the V2 asset directory the server checks for will not exist in the
packaged artifact/image.

src/prefect/init.py[60-73]
src/prefect/server/api/server.py[455-469]
src/prefect/server/api/server.py[524-543]
Dockerfile[102-107]
pyproject.toml[231-233]
.github/workflows/python-package.yaml[46-52]

Agent prompt

The issue below was found during a code review. Follow the provided context and guidance below and implement a solution

### Issue description
V2 UI assets are built/copied into `src/prefect/server/ui-v2`, but the Python runtime expects them in `src/prefect/server/ui_v2`.

### Issue Context
When `server.ui.v2_enabled` is true, `create_ui_app` checks `os.path.exists(prefect.__ui_v2_static_path__)` and mounts the UI only if that directory exists. Because the packaged assets land in a different directory name, V2 UI serving will silently not mount.

### Fix Focus Areas
- src/prefect/__init__.py[67-72]
- Dockerfile[102-107]
- pyproject.toml[231-233]
- .github/workflows/python-package.yaml[46-52]
- src/prefect/server/api/server.py[459-469]

ⓘ Copy this prompt and use it to remediate the issue with your preferred AI generation tools

---

ⓘ The new review experience is currently in Beta. Learn more

[qodo-code-review]

1. Missing future import in init.py 📘 Rule violation ✓ Correctness

• src/prefect/__init__.py contains type annotations (e.g., __ui_v2_static_path__: pathlib.Path)
  but does not include from __future__ import annotations as the first import.
• This violates the requirement for src/ Python files with type hints to enable forward-reference
  resolution and consistent type-checking behavior.

Agent prompt

## Issue description
`src/prefect/__init__.py` uses type annotations but does not have `from __future__ import annotations` as the first import, violating the project rule for typed files under `src/`.

## Issue Context
This file contains annotated constants (e.g., `__ui_v2_static_path__: pathlib.Path`) and imports from `typing`, so it must include the future annotations import as the first import statement.

## Fix Focus Areas
- src/prefect/__init__.py[1-10]
- src/prefect/__init__.py[55-72]

ⓘ Copy this prompt and use it to remediate the issue with your preferred AI generation tools

[qodo-code-review]

2. Missing future import in ui.py 📘 Rule violation ✓ Correctness

• src/prefect/settings/models/server/ui.py contains type annotations (e.g., `model_config:
  ClassVar[...], v2_enabled: bool) but lacks from __future__ import annotations` as the first
  import.
• This violates the required typing import convention for src/ modules and can lead to
  inconsistent annotation evaluation across the codebase.

Agent prompt

## Issue description
`src/prefect/settings/models/server/ui.py` defines type annotations but does not include `from __future__ import annotations` as the first import.

## Issue Context
The file defines annotated fields and class variables; the project rule requires future annotations import first for all typed files under `src/`.

## Fix Focus Areas
- src/prefect/settings/models/server/ui.py[1-7]
- src/prefect/settings/models/server/ui.py[9-29]

ⓘ Copy this prompt and use it to remediate the issue with your preferred AI generation tools

[qodo-code-review]

3. logging.getlogger() used for ui_logger 📘 Rule violation ✧ Quality

• The new code creates ui_logger via logging.getLogger("ui_server") rather than the required
  standardized get_logger(...) pattern with a logging.Logger type annotation.
• This breaks logging consistency/type-safety expectations and violates the project’s logger
  instantiation standard.

Agent prompt

## Issue description
A new logger is created via `logging.getLogger("ui_server")` inside `create_ui_app`, which violates the standardized logger initialization pattern that requires `get_logger(...)` and a `logging.Logger` type annotation.

## Issue Context
This module already imports `get_logger` and defines a module-level `logger: "logging.Logger" = get_logger("server")`.

## Fix Focus Areas
- src/prefect/server/api/server.py[529-533]

ⓘ Copy this prompt and use it to remediate the issue with your preferred AI generation tools

[qodo-code-review]

4. V2 ui path mismatch 🐞 Bug ✓ Correctness

• Python runtime looks for V2 UI assets in a different directory name than the build/packaging steps
  produce (underscore vs hyphen).
• When V2 is enabled, os.path.exists(source_static_path) will fail and the server will not mount
  any UI routes, effectively disabling the UI.
• This is likely to reproduce in Docker builds and release packaging because both Dockerfile and
  hatch artifacts use the hyphenated directory name.

Agent prompt

### Issue description
V2 UI assets are built/copied into `src/prefect/server/ui-v2`, but the Python runtime expects them in `src/prefect/server/ui_v2`.

### Issue Context
When `server.ui.v2_enabled` is true, `create_ui_app` checks `os.path.exists(prefect.__ui_v2_static_path__)` and mounts the UI only if that directory exists. Because the packaged assets land in a different directory name, V2 UI serving will silently not mount.

### Fix Focus Areas
- src/prefect/__init__.py[67-72]
- Dockerfile[102-107]
- pyproject.toml[231-233]
- .github/workflows/python-package.yaml[46-52]
- src/prefect/server/api/server.py[459-469]

ⓘ Copy this prompt and use it to remediate the issue with your preferred AI generation tools