Metadata-Version: 2.4
Name: autourgos-cua-coordinate-tool
Version: 1.0.3
Summary: LLM-grounded UI coordinate finding for Autourgos computer-use agents — locates a described UI element in a screenshot and returns its position normalized to a 0-1000 scale (Gemini computer-use's coordinate convention).
Author-email: Jitin Kumar Sengar <devxjitin@gmail.com>
Maintainer: Sonia, Vishwanil Suman
License:                                  Apache License
                                   Version 2.0, January 2004
                                http://www.apache.org/licenses/
        
           TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
        
           1. Definitions.
        
              "License" shall mean the terms and conditions for use, reproduction,
              and distribution as defined by Sections 1 through 9 of this document.
        
              "Licensor" shall mean the copyright owner or entity authorized by
              the copyright owner that is granting the License.
        
              "Legal Entity" shall mean the union of the acting entity and all
              other entities that control, are controlled by, or are under common
              control with that entity. For the purposes of this definition,
              "control" means (i) the power, direct or indirect, to cause the
              direction or management of such entity, whether by contract or
              otherwise, or (ii) ownership of fifty percent (50%) or more of the
              outstanding shares, or (iii) beneficial ownership of such entity.
        
              "You" (or "Your") shall mean an individual or Legal Entity
              exercising permissions granted by this License.
        
              "Source" form shall mean the preferred form for making modifications,
              including but not limited to software source code, documentation
              source, and configuration files.
        
              "Object" form shall mean any form resulting from mechanical
              transformation or translation of a Source form, including but
              not limited to compiled object code, generated documentation,
              and conversions to other media types.
        
              "Work" shall mean the work of authorship, whether in Source or
              Object form, made available under the License, as indicated by a
              copyright notice that is included in or attached to the work
              (an example is provided in the Appendix below).
        
              "Derivative Works" shall mean any work, whether in Source or Object
              form, that is based on (or derived from) the Work and for which the
              editorial revisions, annotations, elaborations, or other modifications
              represent, as a whole, an original work of authorship. For the
              purposes of this License, Derivative Works shall not include works
              that remain separable from, or merely link (or bind by name) to the
              interfaces of, the Work and Derivative Works thereof.
        
              "Contribution" shall mean any work of authorship, including the
              original version of the Work and any modifications or additions
              to that Work or Derivative Works thereof, that is intentionally
              submitted to Licensor for inclusion in the Work by the copyright owner
              or by an individual or Legal Entity authorized to submit on behalf of
              the copyright owner. For the purposes of this definition, "submitted"
              means any form of electronic, verbal, or written communication sent
              to the Licensor or its representatives, including but not limited to
              communication on electronic mailing lists, source code control systems,
              and issue tracking systems that are managed by, or on behalf of, the
              Licensor for the purpose of discussing and improving the Work, but
              excluding communication that is conspicuously marked or otherwise
              designated in writing by the copyright owner as "Not a Contribution."
        
              "Contributor" shall mean Licensor and any individual or Legal Entity
              on behalf of whom a Contribution has been received by Licensor and
              subsequently incorporated within the Work.
        
           2. Grant of Copyright License. Subject to the terms and conditions of
              this License, each Contributor hereby grants to You a perpetual,
              worldwide, non-exclusive, no-charge, royalty-free, irrevocable
              copyright license to reproduce, prepare Derivative Works of,
              publicly display, publicly perform, sublicense, and distribute the
              Work and such Derivative Works in Source or Object form.
        
           3. Grant of Patent License. Subject to the terms and conditions of
              this License, each Contributor hereby grants to You a perpetual,
              worldwide, non-exclusive, no-charge, royalty-free, irrevocable
              (except as stated in this section) patent license to make, have made,
              use, offer to sell, sell, import, and otherwise transfer the Work,
              where such license applies only to those patent claims licensable
              by such Contributor that are necessarily infringed by their
              Contribution(s) alone or by combination of their Contribution(s)
              with the Work to which such Contribution(s) was submitted. If You
              institute patent litigation against any entity (including a
              cross-claim or counterclaim in a lawsuit) alleging that the Work
              or a Contribution incorporated within the Work constitutes direct
              or contributory patent infringement, then any patent licenses
              granted to You under this License for that Work shall terminate
              as of the date such litigation is filed.
        
           4. Redistribution. You may reproduce and distribute copies of the
              Work or Derivative Works thereof in any medium, with or without
              modifications, and in Source or Object form, provided that You
              meet the following conditions:
        
              (a) You must give any other recipients of the Work or
                  Derivative Works a copy of this License; and
        
              (b) You must cause any modified files to carry prominent notices
                  stating that You changed the files; and
        
              (c) You must retain, in the Source form of any Derivative Works
                  that You distribute, all copyright, patent, trademark, and
                  attribution notices from the Source form of the Work,
                  excluding those notices that do not pertain to any part of
                  the Derivative Works; and
        
              (d) If the Work includes a "NOTICE" text file as part of its
                  distribution, then any Derivative Works that You distribute must
                  include a readable copy of the attribution notices contained
                  within such NOTICE file, excluding those notices that do not
                  pertain to any part of the Derivative Works, in at least one
                  of the following places: within a NOTICE text file distributed
                  as part of the Derivative Works; within the Source form or
                  documentation, if provided along with the Derivative Works; or,
                  within a display generated by the Derivative Works, if and
                  wherever such third-party notices normally appear. The contents
                  of the NOTICE file are for informational purposes only and
                  do not modify the License. You may add Your own attribution
                  notices within Derivative Works that You distribute, alongside
                  or as an addendum to the NOTICE text from the Work, provided
                  that such additional attribution notices cannot be construed
                  as modifying the License.
        
              You may add Your own copyright statement to Your modifications and
              may provide additional or different license terms and conditions
              for use, reproduction, or distribution of Your modifications, or
              for any such Derivative Works as a whole, provided Your use,
              reproduction, and distribution of the Work otherwise complies with
              the conditions stated in this License.
        
           5. Submission of Contributions. Unless You explicitly state otherwise,
              any Contribution intentionally submitted for inclusion in the Work
              by You to the Licensor shall be under the terms and conditions of
              this License, without any additional terms or conditions.
              Notwithstanding the above, nothing herein shall supersede or modify
              the terms of any separate license agreement you may have executed
              with Licensor regarding such Contributions.
        
           6. Trademarks. This License does not grant permission to use the trade
              names, trademarks, service marks, or product names of the Licensor,
              except as required for reasonable and customary use in describing
              the origin of the Work and reproducing the content of the NOTICE file.
        
           7. Disclaimer of Warranty. Unless required by applicable law or
              agreed to in writing, Licensor provides the Work (and each
              Contributor provides its Contributions) on an "AS IS" BASIS,
              WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
              implied, including, without limitation, any warranties or conditions
              of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
              PARTICULAR PURPOSE. You are solely responsible for determining the
              appropriateness of using or redistributing the Work and assume any
              risks associated with Your exercise of permissions under this License.
        
           8. Limitation of Liability. In no event and under no legal theory,
              whether in tort (including negligence), contract, or otherwise,
              unless required by applicable law (such as deliberate and grossly
              negligent acts) or agreed to in writing, shall any Contributor be
              liable to You for damages, including any direct, indirect, special,
              incidental, or consequential damages of any character arising as a
              result of this License or out of the use or inability to use the
              Work (including but not limited to damages for loss of goodwill,
              work stoppage, computer failure or malfunction, or any and all
              other commercial damages or losses), even if such Contributor
              has been advised of the possibility of such damages.
        
           9. Accepting Warranty or Additional Liability. While redistributing
              the Work or Derivative Works thereof, You may choose to offer,
              and charge a fee for, acceptance of support, warranty, indemnity,
              or other liability obligations and/or rights consistent with this
              License. However, in accepting such obligations, You may act only
              on Your own behalf and on Your sole responsibility, not on behalf
              of any other Contributor, and only if You agree to indemnify,
              defend, and hold each Contributor harmless for any liability
              incurred by, or claims asserted against, such Contributor by reason
              of your accepting any such warranty or additional liability.
        
           END OF TERMS AND CONDITIONS
        
           APPENDIX: How to apply the Apache License to your work.
        
              To apply the Apache License to your work, attach the following
              boilerplate notice, with the fields enclosed by brackets "[]"
              replaced with your own identifying information. (Don't include
              the brackets!)  The text should be enclosed in the appropriate
              comment syntax for the file format. We also recommend that a
              file or class name and description of purpose be included on the
              same "printed page" as the copyright notice for easier
              identification within third-party archives.
        
           Copyright 2026 Jitin Kumar Sengar
        
           Licensed under the Apache License, Version 2.0 (the "License");
           you may not use this file except in compliance with the License.
           You may obtain a copy of the License at
        
               http://www.apache.org/licenses/LICENSE-2.0
        
           Unless required by applicable law or agreed to in writing, software
           distributed under the License is distributed on an "AS IS" BASIS,
           WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
           See the License for the specific language governing permissions and
           limitations under the License.
        
Project-URL: Homepage, https://github.com/devxjitin/autourgos-cua-coordinate-tool
Project-URL: Repository, https://github.com/devxjitin/autourgos-cua-coordinate-tool
Project-URL: Issues, https://github.com/devxjitin/autourgos-cua-coordinate-tool/issues
Keywords: autourgos,agent,computer-use,cua,coordinates,grounding,vision,llm,gui-automation
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: autourgos-agent>=3.1.1
Requires-Dist: autourgos-core>=0.4.0
Provides-Extra: images
Requires-Dist: Pillow>=9.0; extra == "images"
Provides-Extra: capture
Requires-Dist: mss>=9.0; extra == "capture"
Provides-Extra: all
Requires-Dist: Pillow>=9.0; extra == "all"
Requires-Dist: mss>=9.0; extra == "all"
Provides-Extra: dev
Requires-Dist: pytest>=7.0; extra == "dev"
Requires-Dist: Pillow>=9.0; extra == "dev"
Requires-Dist: mss>=9.0; extra == "dev"
Dynamic: license-file

# autourgos-cua-coordinate-tool

[![Framework: Autourgos](https://img.shields.io/badge/Framework-Autourgos-orange.svg)](https://github.com/devxjitin)
[![Python](https://img.shields.io/badge/python-3.9%2B-blue.svg)](https://pypi.org/project/autourgos-cua-coordinate-tool/)
[![License: Apache 2.0](https://img.shields.io/badge/license-Apache%202.0-green.svg)](https://github.com/devxjitin/autourgos-cua-coordinate-tool/blob/main/LICENSE)
[![Author](https://img.shields.io/badge/Author-Jitin%20Kumar%20Sengar-blue.svg)](https://github.com/devxjitin)

LLM-grounded UI coordinate finding for [Autourgos](https://github.com/devxjitin) computer-use agents.
Give it a description ("the Submit button") and it returns where that element is —
normalized to a 0-1000 scale, the same convention
[Gemini's computer-use API](https://ai.google.dev/gemini-api/docs/computer-use) uses. It can
auto-capture the current screen and auto-detect screen dimensions, or take an explicit
screenshot/dimensions instead — both paths are always available.

```python
from autourgos_cua_coordinate_tool import CoordinateFinder
from autourgos_openaichat import OpenAIChatModel

llm = OpenAIChatModel(model="gpt-4o")
finder = CoordinateFinder(llm)

# Automatic: capture the current screen and auto-detect its dimensions.
coord = finder.find("the Submit button")
x_px, y_px = coord.to_pixels()

# Custom: a specific screenshot and explicit dimensions.
coord = finder.find("the Submit button", "screenshot.png")
x_px, y_px = coord.to_pixels(1920, 1080)
```

---

## Features

- **Provider-agnostic grounding** — drives any vision-capable LLM shaped like
  [`autourgos-openaichat`](https://github.com/devxjitin/autourgos-openaichat)'s or
  [`autourgos-responses`](https://github.com/devxjitin/autourgos-responses)'s `BaseLLM`
  (`invoke(prompt, files=, **overrides)` / `ainvoke(...)`). No hard dependency on either
  package, and no coupling to one vision API.
- **Automatic *and* custom screenshots** — omit `image` to auto-capture the current
  screen (optional `mss` dependency), or pass a specific file path/bytes yourself.
- **Automatic *and* custom screen dimensions** — omit `screen_width`/`screen_height` to
  auto-detect them (free from an auto-capture, or via optional `Pillow` for a
  caller-supplied image), or pass them explicitly to force a specific conversion.
- **Gemini-style normalized coordinates** — output is always 0-1000 on both axes
  regardless of screenshot resolution, matching Gemini computer-use's own convention,
  with `.to_pixels()` doing the documented denormalization.
- **Fails closed** — an element the model can't find, or a response that can't be
  parsed, raises `CoordinateNotFoundError` instead of returning a fabricated coordinate.
- **Ready-made agent tool** — `make_find_coordinates_tool()` wraps a `CoordinateFinder`
  as a standard [`autourgos-agent`](https://github.com/devxjitin/autourgos-agent) `Tool`
  for `agent.add_tools(...)`.
- **Sync and async** — `find()` / `afind()`.

---

## Table of Contents

- [Install](#install)
- [Quick Start](#quick-start)
- [Automatic vs Custom](#automatic-vs-custom)
- [Async](#async)
- [As an Agent Tool](#as-an-agent-tool)
- [Coordinate System](#coordinate-system)
- [Error Handling](#error-handling)
- [API Reference](#api-reference)
- [License](#license)

---

## Install

```bash
pip install autourgos-cua-coordinate-tool
```

For automatic screen capture (`mss`) and/or automatic image dimension detection
(`Pillow`):

```bash
pip install 'autourgos-cua-coordinate-tool[capture]'   # auto-capture the screen
pip install 'autourgos-cua-coordinate-tool[images]'    # auto-detect a given image's size
pip install 'autourgos-cua-coordinate-tool[all]'       # both
```

Neither is required for the fully custom (caller-supplied image + dimensions) path.

---

## Quick Start

```python
from autourgos_cua_coordinate_tool import CoordinateFinder, CoordinateNotFoundError
from autourgos_openaichat import OpenAIChatModel

llm = OpenAIChatModel(model="gpt-4o")
finder = CoordinateFinder(llm)

try:
    coord = finder.find("the search input box")   # auto-captures the current screen
except CoordinateNotFoundError as exc:
    print("not found:", exc)
else:
    x_px, y_px = coord.to_pixels()                 # dimensions auto-detected from the capture
    print(f"click at ({x_px}, {y_px})")
```

Works the same with `autourgos-responses` model instances, or any object that
exposes `invoke(prompt, files=, **overrides)` / `ainvoke(...)`.

---

## Automatic vs Custom

`find(description, image=None, *, screen_width=None, screen_height=None, **overrides)`
supports both, and you can mix them freely:

| `image` | `screen_width`/`screen_height` | Behavior |
|---|---|---|
| omitted (`None`) | omitted | **Fully automatic** — captures the current screen (`mss`), dimensions come free from the capture. |
| omitted (`None`) | given | Auto-captures the screen, but forces pixel conversion against the dimensions you passed. |
| given | omitted | **Custom screenshot**, dimensions auto-detected from it via Pillow if installed (falls back to `None` if not — `to_pixels()` then needs explicit dimensions). |
| given | given | **Fully custom** — no auto-capture, no auto-detection. |

```python
# Fully automatic
coord = finder.find("the Submit button")

# Custom screenshot, automatic dimensions (via Pillow)
coord = finder.find("the Submit button", "screenshot.png")

# Automatic screenshot, custom (forced) dimensions
coord = finder.find("the Submit button", screen_width=2560, screen_height=1440)

# Fully custom
coord = finder.find("the Submit button", "screenshot.png", screen_width=1920, screen_height=1080)
```

---

## Async

```python
coord = await finder.afind("the Submit button")   # auto-capture works here too
```

---

## As an Agent Tool

```python
from autourgos_agent import Agent
from autourgos_cua_coordinate_tool import CoordinateFinder, make_find_coordinates_tool

finder = CoordinateFinder(llm)

# Fully automatic (auto-captures the screen, auto-detects dimensions):
find_coordinates = make_find_coordinates_tool(finder)

# Custom instead:
find_coordinates = make_find_coordinates_tool(
    finder,
    screen_width=1920,
    screen_height=1080,
    screenshot_path="/tmp/screen.png",  # default when the agent omits image_path;
                                         # can also be a zero-arg callable for a
                                         # fresh path each call
)

agent = Agent(llm=my_llm)
agent.add_tools(find_coordinates)
result = agent.invoke("Click the Submit button")
```

The tool returns a dict: `{"found": True, "x_norm": ..., "y_norm": ..., "x": ..., "y": ...}`
(pixel `x`/`y` only present when dimensions were configured or auto-detected), or
`{"found": False, "error": "..."}` — including when auto-capture is requested but
`mss` isn't installed.

---

## Coordinate System

Every `Coordinate` is normalized to **0-1000** on both axes, independent of the
screenshot's actual resolution — the same convention documented for Gemini's
computer-use API:

```python
actual_x = int(x_norm / 1000 * screen_width)
actual_y = int(y_norm / 1000 * screen_height)
```

`Coordinate.to_pixels(screen_width=None, screen_height=None)` implements this exactly —
pass dimensions explicitly to force them (custom), or omit both to use whatever was
auto-detected when the `Coordinate` was found (automatic).

---

## Error Handling

`CoordinateFinder.find()`/`afind()` raise `CoordinateNotFoundError` — never a
guessed coordinate — when:

- the model explicitly reports the element isn't visible,
- the response can't be parsed into a coordinate at all, or
- a parsed coordinate falls outside the 0-1000 range.

Auto-capture (`image=None`) raises `CaptureError` instead if the optional `mss`
dependency isn't installed.

---

## API Reference

### `CoordinateFinder(llm, *, image_detail=None)`

- `find(description, image=None, *, screen_width=None, screen_height=None, **overrides) -> Coordinate`
- `afind(description, image=None, *, screen_width=None, screen_height=None, **overrides) -> Coordinate` (async)

`image` is a file path or bytes, or omit it to auto-capture the current screen.
`**overrides` are forwarded to the underlying `llm.invoke()`/`ainvoke()` call (e.g.
`temperature=`).

### `Coordinate`

- `x_norm: float`, `y_norm: float` — 0-1000 normalized position
- `raw_response: str` — the model's raw text, for debugging
- `screen_width`, `screen_height: Optional[int]` — auto-detected (or explicitly
  passed) dimensions at find() time, if any
- `to_pixels(screen_width=None, screen_height=None) -> (int, int)`

### `make_find_coordinates_tool(finder, *, screenshot_path=None, screen_width=None, screen_height=None, name="find_coordinates") -> Tool`

Builds a `find_coordinates(description, image_path=None)` tool bound to `finder`.
`image_path` omitted (and no `screenshot_path` configured) auto-captures the screen.

### `capture_screen() -> ScreenCapture` / `detect_image_size(image) -> Optional[(int, int)]`

Lower-level helpers `CoordinateFinder` uses internally; exposed directly for other uses.
`capture_screen()` raises `CaptureError` if `mss` isn't installed. `detect_image_size()`
never raises — returns `None` if Pillow isn't installed or the image can't be read.

---

## License

Apache License 2.0. See [LICENSE](LICENSE).
