chore: import upstream snapshot with attribution

2026-07-13 13:03:19 +08:00
commit 91e75e620b
3227 changed files with 1307078 additions and 0 deletions
@@ -0,0 +1,10 @@
+[bumpversion]
+current_version = 0.1.4
+commit = True
+tag = True
+tag_name = som-v{new_version}
+message = Bump cua-som to v{new_version}
+
+[bumpversion:file:pyproject.toml]
+search = version = "{current_version}"
+replace = version = "{new_version}"
@@ -0,0 +1,661 @@
+                    GNU AFFERO GENERAL PUBLIC LICENSE
+                       Version 3, 19 November 2007
+
+ Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/>
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+                            Preamble
+
+  The GNU Affero General Public License is a free, copyleft license for
+software and other kinds of works, specifically designed to ensure
+cooperation with the community in the case of network server software.
+
+  The licenses for most software and other practical works are designed
+to take away your freedom to share and change the works.  By contrast,
+our General Public Licenses are intended to guarantee your freedom to
+share and change all versions of a program--to make sure it remains free
+software for all its users.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+them if you wish), that you receive source code or can get it if you
+want it, that you can change the software or use pieces of it in new
+free programs, and that you know you can do these things.
+
+  Developers that use our General Public Licenses protect your rights
+with two steps: (1) assert copyright on the software, and (2) offer
+you this License which gives you legal permission to copy, distribute
+and/or modify the software.
+
+  A secondary benefit of defending all users' freedom is that
+improvements made in alternate versions of the program, if they
+receive widespread use, become available for other developers to
+incorporate.  Many developers of free software are heartened and
+encouraged by the resulting cooperation.  However, in the case of
+software used on network servers, this result may fail to come about.
+The GNU General Public License permits making a modified version and
+letting the public access it on a server without ever releasing its
+source code to the public.
+
+  The GNU Affero General Public License is designed specifically to
+ensure that, in such cases, the modified source code becomes available
+to the community.  It requires the operator of a network server to
+provide the source code of the modified version running there to the
+users of that server.  Therefore, public use of a modified version, on
+a publicly accessible server, gives the public access to the source
+code of the modified version.
+
+  An older license, called the Affero General Public License and
+published by Affero, was designed to accomplish similar goals.  This is
+a different license, not a version of the Affero GPL, but Affero has
+released a new version of the Affero GPL which permits relicensing under
+this license.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.
+
+                       TERMS AND CONDITIONS
+
+  0. Definitions.
+
+  "This License" refers to version 3 of the GNU Affero General Public License.
+
+  "Copyright" also means copyright-like laws that apply to other kinds of
+works, such as semiconductor masks.
+
+  "The Program" refers to any copyrightable work licensed under this
+License.  Each licensee is addressed as "you".  "Licensees" and
+"recipients" may be individuals or organizations.
+
+  To "modify" a work means to copy from or adapt all or part of the work
+in a fashion requiring copyright permission, other than the making of an
+exact copy.  The resulting work is called a "modified version" of the
+earlier work or a work "based on" the earlier work.
+
+  A "covered work" means either the unmodified Program or a work based
+on the Program.
+
+  To "propagate" a work means to do anything with it that, without
+permission, would make you directly or secondarily liable for
+infringement under applicable copyright law, except executing it on a
+computer or modifying a private copy.  Propagation includes copying,
+distribution (with or without modification), making available to the
+public, and in some countries other activities as well.
+
+  To "convey" a work means any kind of propagation that enables other
+parties to make or receive copies.  Mere interaction with a user through
+a computer network, with no transfer of a copy, is not conveying.
+
+  An interactive user interface displays "Appropriate Legal Notices"
+to the extent that it includes a convenient and prominently visible
+feature that (1) displays an appropriate copyright notice, and (2)
+tells the user that there is no warranty for the work (except to the
+extent that warranties are provided), that licensees may convey the
+work under this License, and how to view a copy of this License.  If
+the interface presents a list of user commands or options, such as a
+menu, a prominent item in the list meets this criterion.
+
+  1. Source Code.
+
+  The "source code" for a work means the preferred form of the work
+for making modifications to it.  "Object code" means any non-source
+form of a work.
+
+  A "Standard Interface" means an interface that either is an official
+standard defined by a recognized standards body, or, in the case of
+interfaces specified for a particular programming language, one that
+is widely used among developers working in that language.
+
+  The "System Libraries" of an executable work include anything, other
+than the work as a whole, that (a) is included in the normal form of
+packaging a Major Component, but which is not part of that Major
+Component, and (b) serves only to enable use of the work with that
+Major Component, or to implement a Standard Interface for which an
+implementation is available to the public in source code form.  A
+"Major Component", in this context, means a major essential component
+(kernel, window system, and so on) of the specific operating system
+(if any) on which the executable work runs, or a compiler used to
+produce the work, or an object code interpreter used to run it.
+
+  The "Corresponding Source" for a work in object code form means all
+the source code needed to generate, install, and (for an executable
+work) run the object code and to modify the work, including scripts to
+control those activities.  However, it does not include the work's
+System Libraries, or general-purpose tools or generally available free
+programs which are used unmodified in performing those activities but
+which are not part of the work.  For example, Corresponding Source
+includes interface definition files associated with source files for
+the work, and the source code for shared libraries and dynamically
+linked subprograms that the work is specifically designed to require,
+such as by intimate data communication or control flow between those
+subprograms and other parts of the work.
+
+  The Corresponding Source need not include anything that users
+can regenerate automatically from other parts of the Corresponding
+Source.
+
+  The Corresponding Source for a work in source code form is that
+same work.
+
+  2. Basic Permissions.
+
+  All rights granted under this License are granted for the term of
+copyright on the Program, and are irrevocable provided the stated
+conditions are met.  This License explicitly affirms your unlimited
+permission to run the unmodified Program.  The output from running a
+covered work is covered by this License only if the output, given its
+content, constitutes a covered work.  This License acknowledges your
+rights of fair use or other equivalent, as provided by copyright law.
+
+  You may make, run and propagate covered works that you do not
+convey, without conditions so long as your license otherwise remains
+in force.  You may convey covered works to others for the sole purpose
+of having them make modifications exclusively for you, or provide you
+with facilities for running those works, provided that you comply with
+the terms of this License in conveying all material for which you do
+not control copyright.  Those thus making or running the covered works
+for you must do so exclusively on your behalf, under your direction
+and control, on terms that prohibit them from making any copies of
+your copyrighted material outside their relationship with you.
+
+  Conveying under any other circumstances is permitted solely under
+the conditions stated below.  Sublicensing is not allowed; section 10
+makes it unnecessary.
+
+  3. Protecting Users' Legal Rights From Anti-Circumvention Law.
+
+  No covered work shall be deemed part of an effective technological
+measure under any applicable law fulfilling obligations under article
+11 of the WIPO copyright treaty adopted on 20 December 1996, or
+similar laws prohibiting or restricting circumvention of such
+measures.
+
+  When you convey a covered work, you waive any legal power to forbid
+circumvention of technological measures to the extent such circumvention
+is effected by exercising rights under this License with respect to
+the covered work, and you disclaim any intention to limit operation or
+modification of the work as a means of enforcing, against the work's
+users, your or third parties' legal rights to forbid circumvention of
+technological measures.
+
+  4. Conveying Verbatim Copies.
+
+  You may convey verbatim copies of the Program's source code as you
+receive it, in any medium, provided that you conspicuously and
+appropriately publish on each copy an appropriate copyright notice;
+keep intact all notices stating that this License and any
+non-permissive terms added in accord with section 7 apply to the code;
+keep intact all notices of the absence of any warranty; and give all
+recipients a copy of this License along with the Program.
+
+  You may charge any price or no price for each copy that you convey,
+and you may offer support or warranty protection for a fee.
+
+  5. Conveying Modified Source Versions.
+
+  You may convey a work based on the Program, or the modifications to
+produce it from the Program, in the form of source code under the
+terms of section 4, provided that you also meet all of these conditions:
+
+    a) The work must carry prominent notices stating that you modified
+    it, and giving a relevant date.
+
+    b) The work must carry prominent notices stating that it is
+    released under this License and any conditions added under section
+    7.  This requirement modifies the requirement in section 4 to
+    "keep intact all notices".
+
+    c) You must license the entire work, as a whole, under this
+    License to anyone who comes into possession of a copy.  This
+    License will therefore apply, along with any applicable section 7
+    additional terms, to the whole of the work, and all its parts,
+    regardless of how they are packaged.  This License gives no
+    permission to license the work in any other way, but it does not
+    invalidate such permission if you have separately received it.
+
+    d) If the work has interactive user interfaces, each must display
+    Appropriate Legal Notices; however, if the Program has interactive
+    interfaces that do not display Appropriate Legal Notices, your
+    work need not make them do so.
+
+  A compilation of a covered work with other separate and independent
+works, which are not by their nature extensions of the covered work,
+and which are not combined with it such as to form a larger program,
+in or on a volume of a storage or distribution medium, is called an
+"aggregate" if the compilation and its resulting copyright are not
+used to limit the access or legal rights of the compilation's users
+beyond what the individual works permit.  Inclusion of a covered work
+in an aggregate does not cause this License to apply to the other
+parts of the aggregate.
+
+  6. Conveying Non-Source Forms.
+
+  You may convey a covered work in object code form under the terms
+of sections 4 and 5, provided that you also convey the
+machine-readable Corresponding Source under the terms of this License,
+in one of these ways:
+
+    a) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by the
+    Corresponding Source fixed on a durable physical medium
+    customarily used for software interchange.
+
+    b) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by a
+    written offer, valid for at least three years and valid for as
+    long as you offer spare parts or customer support for that product
+    model, to give anyone who possesses the object code either (1) a
+    copy of the Corresponding Source for all the software in the
+    product that is covered by this License, on a durable physical
+    medium customarily used for software interchange, for a price no
+    more than your reasonable cost of physically performing this
+    conveying of source, or (2) access to copy the
+    Corresponding Source from a network server at no charge.
+
+    c) Convey individual copies of the object code with a copy of the
+    written offer to provide the Corresponding Source.  This
+    alternative is allowed only occasionally and noncommercially, and
+    only if you received the object code with such an offer, in accord
+    with subsection 6b.
+
+    d) Convey the object code by offering access from a designated
+    place (gratis or for a charge), and offer equivalent access to the
+    Corresponding Source in the same way through the same place at no
+    further charge.  You need not require recipients to copy the
+    Corresponding Source along with the object code.  If the place to
+    copy the object code is a network server, the Corresponding Source
+    may be on a different server (operated by you or a third party)
+    that supports equivalent copying facilities, provided you maintain
+    clear directions next to the object code saying where to find the
+    Corresponding Source.  Regardless of what server hosts the
+    Corresponding Source, you remain obligated to ensure that it is
+    available for as long as needed to satisfy these requirements.
+
+    e) Convey the object code using peer-to-peer transmission, provided
+    you inform other peers where the object code and Corresponding
+    Source of the work are being offered to the general public at no
+    charge under subsection 6d.
+
+  A separable portion of the object code, whose source code is excluded
+from the Corresponding Source as a System Library, need not be
+included in conveying the object code work.
+
+  A "User Product" is either (1) a "consumer product", which means any
+tangible personal property which is normally used for personal, family,
+or household purposes, or (2) anything designed or sold for incorporation
+into a dwelling.  In determining whether a product is a consumer product,
+doubtful cases shall be resolved in favor of coverage.  For a particular
+product received by a particular user, "normally used" refers to a
+typical or common use of that class of product, regardless of the status
+of the particular user or of the way in which the particular user
+actually uses, or expects or is expected to use, the product.  A product
+is a consumer product regardless of whether the product has substantial
+commercial, industrial or non-consumer uses, unless such uses represent
+the only significant mode of use of the product.
+
+  "Installation Information" for a User Product means any methods,
+procedures, authorization keys, or other information required to install
+and execute modified versions of a covered work in that User Product from
+a modified version of its Corresponding Source.  The information must
+suffice to ensure that the continued functioning of the modified object
+code is in no case prevented or interfered with solely because
+modification has been made.
+
+  If you convey an object code work under this section in, or with, or
+specifically for use in, a User Product, and the conveying occurs as
+part of a transaction in which the right of possession and use of the
+User Product is transferred to the recipient in perpetuity or for a
+fixed term (regardless of how the transaction is characterized), the
+Corresponding Source conveyed under this section must be accompanied
+by the Installation Information.  But this requirement does not apply
+if neither you nor any third party retains the ability to install
+modified object code on the User Product (for example, the work has
+been installed in ROM).
+
+  The requirement to provide Installation Information does not include a
+requirement to continue to provide support service, warranty, or updates
+for a work that has been modified or installed by the recipient, or for
+the User Product in which it has been modified or installed.  Access to a
+network may be denied when the modification itself materially and
+adversely affects the operation of the network or violates the rules and
+protocols for communication across the network.
+
+  Corresponding Source conveyed, and Installation Information provided,
+in accord with this section must be in a format that is publicly
+documented (and with an implementation available to the public in
+source code form), and must require no special password or key for
+unpacking, reading or copying.
+
+  7. Additional Terms.
+
+  "Additional permissions" are terms that supplement the terms of this
+License by making exceptions from one or more of its conditions.
+Additional permissions that are applicable to the entire Program shall
+be treated as though they were included in this License, to the extent
+that they are valid under applicable law.  If additional permissions
+apply only to part of the Program, that part may be used separately
+under those permissions, but the entire Program remains governed by
+this License without regard to the additional permissions.
+
+  When you convey a copy of a covered work, you may at your option
+remove any additional permissions from that copy, or from any part of
+it.  (Additional permissions may be written to require their own
+removal in certain cases when you modify the work.)  You may place
+additional permissions on material, added by you to a covered work,
+for which you have or can give appropriate copyright permission.
+
+  Notwithstanding any other provision of this License, for material you
+add to a covered work, you may (if authorized by the copyright holders of
+that material) supplement the terms of this License with terms:
+
+    a) Disclaiming warranty or limiting liability differently from the
+    terms of sections 15 and 16 of this License; or
+
+    b) Requiring preservation of specified reasonable legal notices or
+    author attributions in that material or in the Appropriate Legal
+    Notices displayed by works containing it; or
+
+    c) Prohibiting misrepresentation of the origin of that material, or
+    requiring that modified versions of such material be marked in
+    reasonable ways as different from the original version; or
+
+    d) Limiting the use for publicity purposes of names of licensors or
+    authors of the material; or
+
+    e) Declining to grant rights under trademark law for use of some
+    trade names, trademarks, or service marks; or
+
+    f) Requiring indemnification of licensors and authors of that
+    material by anyone who conveys the material (or modified versions of
+    it) with contractual assumptions of liability to the recipient, for
+    any liability that these contractual assumptions directly impose on
+    those licensors and authors.
+
+  All other non-permissive additional terms are considered "further
+restrictions" within the meaning of section 10.  If the Program as you
+received it, or any part of it, contains a notice stating that it is
+governed by this License along with a term that is a further
+restriction, you may remove that term.  If a license document contains
+a further restriction but permits relicensing or conveying under this
+License, you may add to a covered work material governed by the terms
+of that license document, provided that the further restriction does
+not survive such relicensing or conveying.
+
+  If you add terms to a covered work in accord with this section, you
+must place, in the relevant source files, a statement of the
+additional terms that apply to those files, or a notice indicating
+where to find the applicable terms.
+
+  Additional terms, permissive or non-permissive, may be stated in the
+form of a separately written license, or stated as exceptions;
+the above requirements apply either way.
+
+  8. Termination.
+
+  You may not propagate or modify a covered work except as expressly
+provided under this License.  Any attempt otherwise to propagate or
+modify it is void, and will automatically terminate your rights under
+this License (including any patent licenses granted under the third
+paragraph of section 11).
+
+  However, if you cease all violation of this License, then your
+license from a particular copyright holder is reinstated (a)
+provisionally, unless and until the copyright holder explicitly and
+finally terminates your license, and (b) permanently, if the copyright
+holder fails to notify you of the violation by some reasonable means
+prior to 60 days after the cessation.
+
+  Moreover, your license from a particular copyright holder is
+reinstated permanently if the copyright holder notifies you of the
+violation by some reasonable means, this is the first time you have
+received notice of violation of this License (for any work) from that
+copyright holder, and you cure the violation prior to 30 days after
+your receipt of the notice.
+
+  Termination of your rights under this section does not terminate the
+licenses of parties who have received copies or rights from you under
+this License.  If your rights have been terminated and not permanently
+reinstated, you do not qualify to receive new licenses for the same
+material under section 10.
+
+  9. Acceptance Not Required for Having Copies.
+
+  You are not required to accept this License in order to receive or
+run a copy of the Program.  Ancillary propagation of a covered work
+occurring solely as a consequence of using peer-to-peer transmission
+to receive a copy likewise does not require acceptance.  However,
+nothing other than this License grants you permission to propagate or
+modify any covered work.  These actions infringe copyright if you do
+not accept this License.  Therefore, by modifying or propagating a
+covered work, you indicate your acceptance of this License to do so.
+
+  10. Automatic Licensing of Downstream Recipients.
+
+  Each time you convey a covered work, the recipient automatically
+receives a license from the original licensors, to run, modify and
+propagate that work, subject to this License.  You are not responsible
+for enforcing compliance by third parties with this License.
+
+  An "entity transaction" is a transaction transferring control of an
+organization, or substantially all assets of one, or subdividing an
+organization, or merging organizations.  If propagation of a covered
+work results from an entity transaction, each party to that
+transaction who receives a copy of the work also receives whatever
+licenses to the work the party's predecessor in interest had or could
+give under the previous paragraph, plus a right to possession of the
+Corresponding Source of the work from the predecessor in interest, if
+the predecessor has it or can get it with reasonable efforts.
+
+  You may not impose any further restrictions on the exercise of the
+rights granted or affirmed under this License.  For example, you may
+not impose a license fee, royalty, or other charge for exercise of
+rights granted under this License, and you may not initiate litigation
+(including a cross-claim or counterclaim in a lawsuit) alleging that
+any patent claim is infringed by making, using, selling, offering for
+sale, or importing the Program or any portion of it.
+
+  11. Patents.
+
+  A "contributor" is a copyright holder who authorizes use under this
+License of the Program or a work on which the Program is based.  The
+work thus licensed is called the contributor's "contributor version".
+
+  A contributor's "essential patent claims" are all patent claims
+owned or controlled by the contributor, whether already acquired or
+hereafter acquired, that would be infringed by some manner, permitted
+by this License, of making, using, or selling its contributor version,
+but do not include claims that would be infringed only as a
+consequence of further modification of the contributor version.  For
+purposes of this definition, "control" includes the right to grant
+patent sublicenses in a manner consistent with the requirements of
+this License.
+
+  Each contributor grants you a non-exclusive, worldwide, royalty-free
+patent license under the contributor's essential patent claims, to
+make, use, sell, offer for sale, import and otherwise run, modify and
+propagate the contents of its contributor version.
+
+  In the following three paragraphs, a "patent license" is any express
+agreement or commitment, however denominated, not to enforce a patent
+(such as an express permission to practice a patent or covenant not to
+sue for patent infringement).  To "grant" such a patent license to a
+party means to make such an agreement or commitment not to enforce a
+patent against the party.
+
+  If you convey a covered work, knowingly relying on a patent license,
+and the Corresponding Source of the work is not available for anyone
+to copy, free of charge and under the terms of this License, through a
+publicly available network server or other readily accessible means,
+then you must either (1) cause the Corresponding Source to be so
+available, or (2) arrange to deprive yourself of the benefit of the
+patent license for this particular work, or (3) arrange, in a manner
+consistent with the requirements of this License, to extend the patent
+license to downstream recipients.  "Knowingly relying" means you have
+actual knowledge that, but for the patent license, your conveying the
+covered work in a country, or your recipient's use of the covered work
+in a country, would infringe one or more identifiable patents in that
+country that you have reason to believe are valid.
+
+  If, pursuant to or in connection with a single transaction or
+arrangement, you convey, or propagate by procuring conveyance of, a
+covered work, and grant a patent license to some of the parties
+receiving the covered work authorizing them to use, propagate, modify
+or convey a specific copy of the covered work, then the patent license
+you grant is automatically extended to all recipients of the covered
+work and works based on it.
+
+  A patent license is "discriminatory" if it does not include within
+the scope of its coverage, prohibits the exercise of, or is
+conditioned on the non-exercise of one or more of the rights that are
+specifically granted under this License.  You may not convey a covered
+work if you are a party to an arrangement with a third party that is
+in the business of distributing software, under which you make payment
+ to the third party based on the extent of your activity of conveying
+ the work, and under which the third party grants, to any of the
+ parties who would receive the covered work from you, a discriminatory
+ patent license (a) in connection with copies of the covered work
+ conveyed by you (or copies made from those copies), or (b) primarily
+ for and in connection with specific products or compilations that
+ contain the covered work, unless you entered into that arrangement,
+ or that patent license was granted, prior to 28 March 2007.
+
+  Nothing in this License shall be construed as excluding or limiting
+ any implied license or other defenses to infringement that may
+ otherwise be available to you under applicable patent law.
+
+  12. No Surrender of Others' Freedom.
+
+  If conditions are imposed on you (whether by court order, agreement or
+ otherwise) that contradict the conditions of this License, they do not
+ excuse you from the conditions of this License.  If you cannot convey a
+ covered work so as to satisfy simultaneously your obligations under this
+ License and any other pertinent obligations, then as a consequence you may
+ not convey it at all.  For example, if you agree to terms that obligate you
+ to collect a royalty for further conveying from those to whom you convey
+ the Program, the only way you could satisfy both those terms and this
+ License would be to refrain entirely from conveying the Program.
+
+  13. Remote Network Interaction; Use with the GNU General Public License.
+
+  Notwithstanding any other provision of this License, if you modify the
+ Program, your modified version must prominently offer all users
+ interacting with it remotely through a computer network (if your version
+ supports such interaction) an opportunity to receive the Corresponding
+ Source of your version by providing access to the Corresponding Source
+ from a network server at no charge, through some standard or customary
+ means of facilitating copying of software.  This Corresponding Source
+ shall include the Corresponding Source for any work covered by version 3
+ of the GNU General Public License that is incorporated pursuant to the
+ following paragraph.
+
+  Notwithstanding any other provision of this License, you have
+ permission to link or combine any covered work with a work licensed
+ under version 3 of the GNU General Public License into a single
+ combined work, and to convey the resulting work.  The terms of this
+ License will continue to apply to the part which is the covered work,
+ but the work with which it is combined will remain governed by version
+ 3 of the GNU General Public License.
+
+  14. Revised Versions of this License.
+
+  The Free Software Foundation may publish revised and/or new versions of
+ the GNU Affero General Public License from time to time.  Such new versions
+ will be similar in spirit to the present version, but may differ in detail to
+ address new problems or concerns.
+
+  Each version is given a distinguishing version number.  If the
+ Program specifies that a certain numbered version of the GNU Affero General
+ Public License "or any later version" applies to it, you have the
+ option of following the terms and conditions either of that numbered
+ version or of any later version published by the Free Software
+ Foundation.  If the Program does not specify a version number of the
+ GNU Affero General Public License, you may choose any version ever published
+ by the Free Software Foundation.
+
+  If the Program specifies that a proxy can decide which future
+ versions of the GNU Affero General Public License can be used, that proxy's
+ public statement of acceptance of a version permanently authorizes you
+ to choose that version for the Program.
+
+  Later license versions may give you additional or different
+ permissions.  However, no additional obligations are imposed on any
+ author or copyright holder as a result of your choosing to follow a
+ later version.
+
+  15. Disclaimer of Warranty.
+
+  THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
+ APPLICABLE LAW.  EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
+ HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
+ OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
+ THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+ PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
+ IS WITH YOU.  SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
+ ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+  16. Limitation of Liability.
+
+  IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+ WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
+ THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
+ GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
+ USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
+ DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
+ PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
+ EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
+ SUCH DAMAGES.
+
+  17. Interpretation of Sections 15 and 16.
+
+  If the disclaimer of warranty and limitation of liability provided
+ above cannot be given local legal effect according to their terms,
+ reviewing courts shall apply local law that most closely approximates
+ an absolute waiver of all civil liability in connection with the
+ Program, unless a warranty or assumption of liability accompanies a
+ copy of the Program in return for a fee.
+
+                     END OF TERMS AND CONDITIONS
+
+            How to Apply These Terms to Your New Programs
+
+  If you develop a new program, and you want it to be of the greatest
+ possible use to the public, the best way to achieve this is to make it
+ free software which everyone can redistribute and change under these terms.
+
+  To do so, attach the following notices to the program.  It is safest
+ to attach them to the start of each source file to most effectively
+ state the exclusion of warranty; and each file should have at least
+ the "copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the program's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This program is free software: you can redistribute it and/or modify
+    it under the terms of the GNU Affero General Public License as published by
+    the Free Software Foundation, either version 3 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Affero General Public License for more details.
+
+    You should have received a copy of the GNU Affero General Public License
+    along with this program.  If not, see <https://www.gnu.org/licenses/>.
+
+Also add information on how to contact you by electronic and paper mail.
+
+  If your software can interact with users remotely through a computer
+ network, you should also make sure that it provides a way for users to
+ get its source.  For example, if your program is a web application, its
+ interface could display a "Source" link that leads users to an archive
+ of the code.  There are many ways you could offer source, and different
+ solutions will be better for different programs; see section 13 for the
+ specific requirements.
+
+  You should also get your employer (if you work as a programmer) or school,
+ if any, to sign a "copyright disclaimer" for the program, if necessary.
+ For more information on this, and how to apply and follow the GNU AGPL, see
+ <https://www.gnu.org/licenses/>.
@@ -0,0 +1,84 @@
+<div align="center">
+<h1>
+  <div class="image-wrapper" style="display: inline-block;">
+    <picture>
+      <source media="(prefers-color-scheme: dark)" alt="logo" height="150" srcset="https://raw.githubusercontent.com/trycua/cua/main/img/logo_white.svg" style="display: block; margin: auto;">
+      <source media="(prefers-color-scheme: light)" alt="logo" height="150" srcset="https://raw.githubusercontent.com/trycua/cua/main/img/logo_black.svg" style="display: block; margin: auto;">
+      <img alt="Shows my svg">
+    </picture>
+  </div>
+
+[![Python](https://img.shields.io/badge/Python-333333?logo=python&logoColor=white&labelColor=333333)](#)
+[![macOS](https://img.shields.io/badge/macOS-000000?logo=apple&logoColor=F0F0F0)](#)
+[![Discord](https://img.shields.io/badge/Discord-%235865F2.svg?&logo=discord&logoColor=white)](https://discord.com/invite/mVnXXpdE85)
+[![PyPI](https://img.shields.io/pypi/v/cua-computer?color=333333)](https://pypi.org/project/cua-computer/)
+
+</h1>
+</div>
+
+**Som** (Set-of-Mark) is a visual grounding component for the Computer-Use Agent (Cua) framework powering Cua, for detecting and analyzing UI elements in screenshots. Optimized for macOS Silicon with Metal Performance Shaders (MPS), it combines YOLO-based icon detection with EasyOCR text recognition to provide comprehensive UI element analysis.
+
+## Features
+
+- Optimized for Apple Silicon with MPS acceleration
+- Icon detection using YOLO with multi-scale processing
+- Text recognition using EasyOCR (GPU-accelerated)
+- Automatic hardware detection (MPS → CUDA → CPU)
+- Smart detection parameters tuned for UI elements
+- Detailed visualization with numbered annotations
+- Performance benchmarking tools
+
+## System Requirements
+
+- **Recommended**: macOS with Apple Silicon
+  - Uses Metal Performance Shaders (MPS)
+  - Multi-scale detection enabled
+  - ~0.4s average detection time
+- **Supported**: Any Python 3.11+ environment
+  - Falls back to CPU if no GPU available
+  - Single-scale detection on CPU
+  - ~1.3s average detection time
+
+## Installation
+
+```bash
+# Using PDM (recommended)
+pdm install
+
+# Using pip
+pip install -e .
+```
+
+## Quick Start
+
+```python
+from som import OmniParser
+from PIL import Image
+
+# Initialize parser
+parser = OmniParser()
+
+# Process an image
+image = Image.open("screenshot.png")
+result = parser.parse(
+    image,
+    box_threshold=0.3,    # Confidence threshold
+    iou_threshold=0.1,    # Overlap threshold
+    use_ocr=True         # Enable text detection
+)
+
+# Access results
+for elem in result.elements:
+    if elem.type == "icon":
+        print(f"Icon: confidence={elem.confidence:.3f}, bbox={elem.bbox.coordinates}")
+    else:  # text
+        print(f"Text: '{elem.content}', confidence={elem.confidence:.3f}")
+```
+
+## Docs
+
+- [Configuration](http://localhost:8090/docs/libraries/som/configuration)
+
+## License
+
+MIT License - See LICENSE file for details.
@@ -0,0 +1,2 @@
+[virtualenvs]
+in-project = true
@@ -0,0 +1,58 @@
+[build-system]
+requires = ["pdm-backend"]
+build-backend = "pdm.backend"
+
+[project]
+name = "cua-som"
+version = "0.1.4"
+description = "Computer Vision and OCR library for detecting and analyzing UI elements"
+authors = [
+    { name = "TryCua", email = "gh@trycua.com" }
+]
+dependencies = [
+    "torch>=2.2.1",
+    "torchvision>=0.17.1",
+    "ultralytics>=8.1.28",
+    "easyocr>=1.7.1",
+    "numpy>=1.26.4",
+    "pillow>=10.2.0",
+    "setuptools>=75.8.1",
+    "opencv-python-headless>=4.11.0.86",
+    "matplotlib>=3.8.3",
+    "huggingface-hub>=0.21.4",
+    "supervision>=0.25.1",
+    "typing-extensions>=4.9.0",
+    "pydantic>=2.6.3"
+]
+requires-python = ">=3.12,<3.14"
+readme = "README.md"
+license = {text = "AGPL-3.0-or-later"}
+keywords = ["computer-vision", "ocr", "ui-analysis", "icon-detection"]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "License :: OSI Approved :: GNU Affero General Public License v3 or later (AGPLv3+)",
+    "Intended Audience :: Developers",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.11",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Topic :: Scientific/Engineering :: Image Recognition"
+]
+
+[project.urls]
+Homepage = "https://github.com/trycua/cua"
+Repository = "https://github.com/trycua/cua"
+Documentation = "https://github.com/trycua/cua/tree/main/docs"
+
+[tool.pdm]
+distribution = true
+package-type = "library"
+src-layout = false
+
+[tool.pdm.build]
+includes = ["som/"]
+source-includes = ["tests/", "README.md", "LICENSE"]
+
+[tool.pytest.ini_options]
+asyncio_mode = "auto"
+testpaths = ["tests"]
+python_files = "test_*.py"
@@ -0,0 +1,23 @@
+"""SOM - Computer Vision and OCR library for detecting and analyzing UI elements."""
+
+__version__ = "0.1.0"
+
+from .detect import OmniParser
+from .models import (
+    BoundingBox,
+    IconElement,
+    ParseResult,
+    ParserMetadata,
+    TextElement,
+    UIElement,
+)
+
+__all__ = [
+    "OmniParser",
+    "BoundingBox",
+    "UIElement",
+    "IconElement",
+    "TextElement",
+    "ParserMetadata",
+    "ParseResult",
+]
@@ -0,0 +1,490 @@
+import argparse
+import base64
+import io
+import logging
+import signal
+import time
+from contextlib import contextmanager
+from pathlib import Path
+from typing import Any, Dict, List, Optional, Tuple, Union, cast
+
+import cv2
+import numpy as np
+import supervision as sv
+import torch
+import torchvision.ops
+import torchvision.transforms as T
+from huggingface_hub import hf_hub_download
+from PIL import Image
+from supervision.detection.core import Detections
+from ultralytics import YOLO
+
+from .detection import DetectionProcessor
+from .models import (
+    BoundingBox,
+    IconElement,
+    ParseResult,
+    ParserMetadata,
+    TextElement,
+    UIElement,
+)
+from .ocr import OCRProcessor
+from .visualization import BoxAnnotator
+
+logger = logging.getLogger(__name__)
+
+
+class TimeoutException(Exception):
+    pass
+
+
+@contextmanager
+def timeout(seconds: int):
+    def timeout_handler(signum, frame):
+        raise TimeoutException("OCR process timed out")
+
+    # Register the signal handler
+    original_handler = signal.signal(signal.SIGALRM, timeout_handler)
+    signal.alarm(seconds)
+
+    try:
+        yield
+    finally:
+        signal.alarm(0)
+        signal.signal(signal.SIGALRM, original_handler)
+
+
+def process_text_box(box, image):
+    """Process a single text box with OCR."""
+    try:
+        from typing import Any, List, Sequence, Tuple
+
+        import easyocr
+
+        x1 = int(min(point[0] for point in box))
+        y1 = int(min(point[1] for point in box))
+        x2 = int(max(point[0] for point in box))
+        y2 = int(max(point[1] for point in box))
+
+        # Add padding
+        pad = 2
+        x1 = max(0, x1 - pad)
+        y1 = max(0, y1 - pad)
+        x2 = min(image.shape[1], x2 + pad)
+        y2 = min(image.shape[0], y2 + pad)
+
+        region = image[y1:y2, x1:x2]
+        if region.size > 0:
+            reader = easyocr.Reader(["en"])
+            results = reader.readtext(region)
+            if results and len(results) > 0:
+                # EasyOCR returns a list of tuples (bbox, text, confidence)
+                first_result = results[0]
+                if isinstance(first_result, (list, tuple)) and len(first_result) >= 3:
+                    text = str(first_result[1])
+                    confidence = float(first_result[2])
+                    if confidence > 0.5:
+                        return text, [x1, y1, x2, y2], confidence
+    except Exception:
+        pass
+    return None
+
+
+def check_ocr_box(image_path: Union[str, Path]) -> Tuple[List[str], List[List[float]]]:
+    """Check OCR box using EasyOCR."""
+    # Read image once
+    if isinstance(image_path, str):
+        image_path = Path(image_path)
+
+    # Read image into memory
+    image_cv = cv2.imread(str(image_path))
+    if image_cv is None:
+        logger.error(f"Failed to read image: {image_path}")
+        return [], []
+
+    # Get image dimensions
+    img_height, img_width = image_cv.shape[:2]
+    confidence_threshold = 0.5
+
+    # Use EasyOCR
+    import ssl
+
+    import easyocr
+
+    # Create unverified SSL context for development
+    ssl._create_default_https_context = ssl._create_unverified_context
+    try:
+        reader = easyocr.Reader(["en"])
+        with timeout(5):  # 5 second timeout for EasyOCR
+            results = reader.readtext(image_cv, paragraph=False, text_threshold=0.5)
+    except TimeoutException:
+        logger.warning("EasyOCR timed out, returning no results")
+        return [], []
+    except Exception as e:
+        logger.warning(f"EasyOCR failed: {str(e)}")
+        return [], []
+    finally:
+        # Restore default SSL context
+        ssl._create_default_https_context = ssl.create_default_context
+
+    texts = []
+    boxes = []
+
+    for box, text, conf in results:
+        # Convert box format to [x1, y1, x2, y2]
+        x1 = min(point[0] for point in box)
+        y1 = min(point[1] for point in box)
+        x2 = max(point[0] for point in box)
+        y2 = max(point[1] for point in box)
+
+        if float(conf) > 0.5:  # Only keep higher confidence detections
+            texts.append(text)
+            boxes.append([x1, y1, x2, y2])
+
+    return texts, boxes
+
+
+class OmniParser:
+    """Enhanced UI parser using computer vision and OCR for detecting interactive elements."""
+
+    def __init__(
+        self,
+        model_path: Optional[Union[str, Path]] = None,
+        cache_dir: Optional[Union[str, Path]] = None,
+        force_device: Optional[str] = None,
+    ):
+        """Initialize the OmniParser.
+
+        Args:
+            model_path: Optional path to the YOLO model
+            cache_dir: Optional directory to cache model files
+            force_device: Force specific device (cpu/cuda/mps)
+        """
+        self.detector = DetectionProcessor(
+            model_path=Path(model_path) if model_path else None,
+            cache_dir=Path(cache_dir) if cache_dir else None,
+            force_device=force_device,
+        )
+        self.ocr = OCRProcessor()
+        self.visualizer = BoxAnnotator()
+
+    def process_image(
+        self,
+        image: Image.Image,
+        box_threshold: float = 0.3,
+        iou_threshold: float = 0.1,
+        use_ocr: bool = True,
+    ) -> Tuple[Image.Image, List[UIElement]]:
+        """Process an image to detect UI elements and optionally text.
+
+        Args:
+            image: Input PIL Image
+            box_threshold: Confidence threshold for detection
+            iou_threshold: IOU threshold for NMS
+            use_ocr: Whether to enable OCR processing
+
+        Returns:
+            Tuple of (annotated image, list of detections)
+        """
+        try:
+            logger.info("Starting UI element detection...")
+
+            # Detect icons
+            icon_detections = self.detector.detect_icons(
+                image=image, box_threshold=box_threshold, iou_threshold=iou_threshold
+            )
+            logger.info(f"Found {len(icon_detections)} interactive elements")
+
+            # Convert icon detections to typed objects
+            elements: List[UIElement] = cast(
+                List[UIElement],
+                [
+                    IconElement(
+                        id=i + 1,
+                        bbox=BoundingBox(
+                            x1=det["bbox"][0],
+                            y1=det["bbox"][1],
+                            x2=det["bbox"][2],
+                            y2=det["bbox"][3],
+                        ),
+                        confidence=det["confidence"],
+                        scale=det.get("scale"),
+                    )
+                    for i, det in enumerate(icon_detections)
+                ],
+            )
+
+            # Run OCR if enabled
+            if use_ocr:
+                logger.info("Running OCR detection...")
+                text_detections = self.ocr.detect_text(image=image, confidence_threshold=0.5)
+                if text_detections is None:
+                    text_detections = []
+                logger.info(f"Found {len(text_detections)} text regions")
+
+                # Convert text detections to typed objects
+                text_elements = cast(
+                    List[UIElement],
+                    [
+                        TextElement(
+                            id=len(elements) + i + 1,
+                            bbox=BoundingBox(
+                                x1=det["bbox"][0],
+                                y1=det["bbox"][1],
+                                x2=det["bbox"][2],
+                                y2=det["bbox"][3],
+                            ),
+                            content=det["content"],
+                            confidence=det["confidence"],
+                        )
+                        for i, det in enumerate(text_detections)
+                    ],
+                )
+
+                if elements and text_elements:
+                    # Filter out non-OCR elements that have OCR elements with center points colliding with them
+                    filtered_elements = []
+                    for elem in elements:  # elements at this point contains only non-OCR elements
+                        should_keep = True
+                        for text_elem in text_elements:
+                            # Calculate center point of the text element
+                            center_x = (text_elem.bbox.x1 + text_elem.bbox.x2) / 2
+                            center_y = (text_elem.bbox.y1 + text_elem.bbox.y2) / 2
+
+                            # Check if this center point is inside the non-OCR element
+                            if (
+                                center_x >= elem.bbox.x1
+                                and center_x <= elem.bbox.x2
+                                and center_y >= elem.bbox.y1
+                                and center_y <= elem.bbox.y2
+                            ):
+                                should_keep = False
+                                break
+
+                        if should_keep:
+                            filtered_elements.append(elem)
+                    elements = filtered_elements
+
+                    # Merge detections using NMS
+                    all_elements = elements + text_elements
+                    boxes = torch.tensor([elem.bbox.coordinates for elem in all_elements])
+                    scores = torch.tensor([elem.confidence for elem in all_elements])
+                    keep_indices = torchvision.ops.nms(boxes, scores, iou_threshold)
+                    elements = [all_elements[i] for i in keep_indices]
+                else:
+                    # Just add text elements to the list if IOU doesn't need to be applied
+                    elements.extend(text_elements)
+
+            # Calculate drawing parameters based on image size
+            box_overlay_ratio = max(image.size) / 3200
+            draw_config = {
+                "font_size": int(12 * box_overlay_ratio),
+                "box_thickness": max(int(2 * box_overlay_ratio), 1),
+                "text_padding": max(int(3 * box_overlay_ratio), 1),
+            }
+
+            # Convert elements back to dict format for visualization
+            detection_dicts = [
+                {
+                    "type": elem.type,
+                    "bbox": elem.bbox.coordinates,
+                    "confidence": elem.confidence,
+                    "content": elem.content if isinstance(elem, TextElement) else None,
+                }
+                for elem in elements
+            ]
+
+            # Create visualization
+            logger.info("Creating visualization...")
+            annotated_image = self.visualizer.draw_boxes(
+                image=image.copy(), detections=detection_dicts, draw_config=draw_config
+            )
+            logger.info("Visualization complete")
+
+            return annotated_image, elements
+
+        except Exception as e:
+            logger.error(f"Error in process_image: {str(e)}")
+            import traceback
+
+            logger.error(traceback.format_exc())
+            raise
+
+    def parse(
+        self,
+        screenshot_data: Union[bytes, str],
+        box_threshold: float = 0.3,
+        iou_threshold: float = 0.1,
+        use_ocr: bool = True,
+    ) -> ParseResult:
+        """Parse a UI screenshot to detect interactive elements and text.
+
+        Args:
+            screenshot_data: Raw bytes or base64 string of the screenshot
+            box_threshold: Confidence threshold for detection
+            iou_threshold: IOU threshold for NMS
+            use_ocr: Whether to enable OCR processing
+
+        Returns:
+            ParseResult object containing elements, annotated image, and metadata
+        """
+        try:
+            start_time = time.time()
+
+            # Convert input to PIL Image
+            if isinstance(screenshot_data, str):
+                screenshot_data = base64.b64decode(screenshot_data)
+            image = Image.open(io.BytesIO(screenshot_data)).convert("RGB")
+
+            # Process image
+            annotated_image, elements = self.process_image(
+                image=image,
+                box_threshold=box_threshold,
+                iou_threshold=iou_threshold,
+                use_ocr=use_ocr,
+            )
+
+            # Convert annotated image to base64
+            buffered = io.BytesIO()
+            annotated_image.save(buffered, format="PNG")
+            annotated_image_base64 = base64.b64encode(buffered.getvalue()).decode("utf-8")
+
+            # Generate screen info text
+            screen_info = []
+            parsed_content_list = []
+
+            # Set element IDs and generate human-readable descriptions
+            for i, elem in enumerate(elements):
+                # Set the ID (1-indexed)
+                elem.id = i + 1
+
+                if isinstance(elem, IconElement):
+                    screen_info.append(
+                        f"Box #{i+1}: Icon (confidence={elem.confidence:.3f}, bbox={elem.bbox.coordinates})"
+                    )
+                    parsed_content_list.append(
+                        {
+                            "id": i + 1,
+                            "type": "icon",
+                            "bbox": elem.bbox.coordinates,
+                            "confidence": elem.confidence,
+                            "content": None,
+                        }
+                    )
+                elif isinstance(elem, TextElement):
+                    screen_info.append(
+                        f"Box #{i+1}: Text '{elem.content}' (confidence={elem.confidence:.3f}, bbox={elem.bbox.coordinates})"
+                    )
+                    parsed_content_list.append(
+                        {
+                            "id": i + 1,
+                            "type": "text",
+                            "bbox": elem.bbox.coordinates,
+                            "confidence": elem.confidence,
+                            "content": elem.content,
+                        }
+                    )
+
+            # Calculate metadata
+            latency = time.time() - start_time
+            width, height = image.size
+
+            # Create ParseResult object with enhanced properties
+            result = ParseResult(
+                elements=elements,
+                annotated_image_base64=annotated_image_base64,
+                screen_info=screen_info,
+                parsed_content_list=parsed_content_list,
+                metadata=ParserMetadata(
+                    image_size=(width, height),
+                    num_icons=len([e for e in elements if isinstance(e, IconElement)]),
+                    num_text=len([e for e in elements if isinstance(e, TextElement)]),
+                    device=self.detector.device,
+                    ocr_enabled=use_ocr,
+                    latency=latency,
+                ),
+            )
+
+            # Return the ParseResult object directly
+            return result
+
+        except Exception as e:
+            logger.error(f"Error in parse: {str(e)}")
+            import traceback
+
+            logger.error(traceback.format_exc())
+            raise
+
+
+def main():
+    """Command line interface for UI element detection."""
+    parser = argparse.ArgumentParser(description="Detect UI elements and text in images")
+    parser.add_argument("image_path", help="Path to the input image")
+    parser.add_argument("--model-path", help="Path to YOLO model")
+    parser.add_argument(
+        "--box-threshold", type=float, default=0.3, help="Box confidence threshold (default: 0.3)"
+    )
+    parser.add_argument(
+        "--iou-threshold", type=float, default=0.1, help="IOU threshold (default: 0.1)"
+    )
+    parser.add_argument(
+        "--ocr", action="store_true", default=True, help="Enable OCR processing (default: True)"
+    )
+    parser.add_argument("--output", help="Output path for annotated image")
+    args = parser.parse_args()
+
+    # Setup logging
+    logging.basicConfig(level=logging.INFO)
+
+    try:
+        # Initialize parser
+        parser = OmniParser(model_path=args.model_path)
+
+        # Load and process image
+        logger.info(f"Loading image from: {args.image_path}")
+        image = Image.open(args.image_path).convert("RGB")
+        logger.info(f"Image loaded successfully, size: {image.size}")
+
+        # Process image
+        annotated_image, elements = parser.process_image(
+            image=image,
+            box_threshold=args.box_threshold,
+            iou_threshold=args.iou_threshold,
+            use_ocr=args.ocr,
+        )
+
+        # Save output image
+        output_path = args.output or str(
+            Path(args.image_path).parent
+            / f"{Path(args.image_path).stem}_analyzed{Path(args.image_path).suffix}"
+        )
+        logger.info(f"Saving annotated image to: {output_path}")
+
+        Path(output_path).parent.mkdir(parents=True, exist_ok=True)
+        annotated_image.save(output_path)
+        logger.info(f"Image saved successfully to {output_path}")
+
+        # Print detections
+        logger.info("\nDetections:")
+        for i, elem in enumerate(elements):
+            if isinstance(elem, IconElement):
+                logger.info(
+                    f"Interactive element {i}: confidence={elem.confidence:.3f}, bbox={elem.bbox.coordinates}"
+                )
+            elif isinstance(elem, TextElement):
+                logger.info(f"Text {i}: '{elem.content}', bbox={elem.bbox.coordinates}")
+
+    except Exception as e:
+        logger.error(f"Error processing image: {str(e)}")
+        import traceback
+
+        logger.error(traceback.format_exc())
+        return 1
+
+    return 0
+
+
+if __name__ == "__main__":
+    import sys
+
+    sys.exit(main())
@@ -0,0 +1,241 @@
+import logging
+from pathlib import Path
+from typing import Any, Dict, List, Optional, Tuple
+
+import numpy as np
+import torch
+import torchvision
+from huggingface_hub import hf_hub_download
+from PIL import Image
+from ultralytics import YOLO
+
+logger = logging.getLogger(__name__)
+
+
+class DetectionProcessor:
+    """Class for handling YOLO-based icon detection."""
+
+    def __init__(
+        self,
+        model_path: Optional[Path] = None,
+        cache_dir: Optional[Path] = None,
+        force_device: Optional[str] = None,
+    ):
+        """Initialize the detection processor.
+
+        Args:
+            model_path: Path to YOLOv8 model
+            cache_dir: Directory to cache downloaded models
+            force_device: Force specific device (cuda, cpu, mps)
+        """
+        self.model_path = model_path
+        self.cache_dir = cache_dir
+        self.model = None  # type: Any  # Will be set to YOLO model in load_model
+
+        # Set device
+        self.device = "cpu"
+        if torch.cuda.is_available() and force_device != "cpu":
+            self.device = "cuda"
+        elif (
+            hasattr(torch, "backends")
+            and hasattr(torch.backends, "mps")
+            and torch.backends.mps.is_available()
+            and force_device != "cpu"
+        ):
+            self.device = "mps"
+
+        if force_device:
+            self.device = force_device
+
+        logger.info(f"Using device: {self.device}")
+
+    def load_model(self) -> None:
+        """Load or download the YOLO model."""
+        try:
+            # Set default model path if none provided
+            if self.model_path is None:
+                self.model_path = Path(__file__).parent / "weights" / "icon_detect" / "model.pt"
+
+            # Check if the model file already exists
+            if not self.model_path.exists():
+                logger.info(
+                    "Model not found locally, downloading from Microsoft OmniParser-v2.0..."
+                )
+
+                # Create directory
+                self.model_path.parent.mkdir(parents=True, exist_ok=True)
+
+                try:
+                    # Check if the model exists in cache
+                    cache_path = None
+                    if self.cache_dir:
+                        # Try to find the model in the cache
+                        potential_paths = list(Path(self.cache_dir).glob("**/model.pt"))
+                        if potential_paths:
+                            cache_path = str(potential_paths[0])
+                            logger.info(f"Found model in cache: {cache_path}")
+
+                    if not cache_path:
+                        # Download from HuggingFace
+                        downloaded_path = hf_hub_download(
+                            repo_id="microsoft/OmniParser-v2.0",
+                            filename="icon_detect/model.pt",
+                            cache_dir=self.cache_dir,
+                        )
+                        cache_path = downloaded_path
+                        logger.info(f"Model downloaded to cache: {cache_path}")
+
+                    # Copy to package directory
+                    import shutil
+
+                    shutil.copy2(cache_path, self.model_path)
+                    logger.info(f"Model copied to: {self.model_path}")
+                except Exception as e:
+                    raise FileNotFoundError(
+                        f"Failed to download model: {str(e)}\n"
+                        "Please ensure you have internet connection and huggingface-hub installed."
+                    ) from e
+
+            # Make sure the model path exists before loading
+            if not self.model_path.exists():
+                raise FileNotFoundError(f"Model file not found at: {self.model_path}")
+
+            # If model is already loaded, skip reloading
+            if self.model is not None:
+                logger.info("Model already loaded, skipping reload")
+                return
+
+            logger.info(f"Loading YOLOv8 model from {self.model_path}")
+            from ultralytics import YOLO
+
+            self.model = YOLO(str(self.model_path))  # Convert Path to string for compatibility
+
+            # Verify model loaded successfully
+            if self.model is None:
+                raise ValueError("Model failed to initialize but didn't raise an exception")
+
+            if self.device in ["cuda", "mps"]:
+                self.model.to(self.device)
+
+            logger.info(f"Model loaded successfully with device: {self.device}")
+        except Exception as e:
+            logger.error(f"Failed to load model: {str(e)}")
+            # Re-raise with more informative message but preserve the model as None
+            self.model = None
+            raise RuntimeError(f"Failed to initialize detection model: {str(e)}") from e
+
+    def detect_icons(
+        self,
+        image: Image.Image,
+        box_threshold: float = 0.05,
+        iou_threshold: float = 0.1,
+        multi_scale: bool = True,
+    ) -> List[Dict[str, Any]]:
+        """Detect icons in an image using YOLO.
+
+        Args:
+            image: PIL Image to process
+            box_threshold: Confidence threshold for detection
+            iou_threshold: IOU threshold for NMS
+            multi_scale: Whether to use multi-scale detection
+
+        Returns:
+            List of icon detection dictionaries
+        """
+        # Load model if not already loaded
+        if self.model is None:
+            self.load_model()
+
+        # Double-check the model was successfully loaded
+        if self.model is None:
+            logger.error("Model failed to load and is still None")
+            return []  # Return empty list instead of crashing
+
+        img_width, img_height = image.size
+        all_detections = []
+
+        # Define detection scales
+        scales = (
+            [{"size": 1280, "conf": box_threshold}]  # Single scale for CPU
+            if self.device == "cpu"
+            else [
+                {"size": 640, "conf": box_threshold},  # Base scale
+                {"size": 1280, "conf": box_threshold},  # Medium scale
+                {"size": 1920, "conf": box_threshold},  # Large scale
+            ]
+        )
+
+        if not multi_scale:
+            scales = [scales[0]]
+
+        # Run detection at each scale
+        for scale in scales:
+            try:
+                if self.model is None:
+                    logger.error("Model is None, skipping detection")
+                    continue
+
+                results = self.model.predict(
+                    source=image,
+                    conf=scale["conf"],
+                    iou=iou_threshold,
+                    max_det=1000,
+                    verbose=False,
+                    augment=self.device != "cpu",
+                    agnostic_nms=True,
+                    imgsz=scale["size"],
+                    device=self.device,
+                )
+
+                # Process results
+                for r in results:
+                    boxes = r.boxes
+                    if not hasattr(boxes, "conf") or not hasattr(boxes, "xyxy"):
+                        logger.warning("Boxes object missing expected attributes")
+                        continue
+
+                    confidences = boxes.conf
+                    coords = boxes.xyxy
+
+                    # Handle different types of tensors (PyTorch, NumPy, etc.)
+                    if hasattr(confidences, "cpu"):
+                        confidences = confidences.cpu()
+                    if hasattr(coords, "cpu"):
+                        coords = coords.cpu()
+
+                    for conf, bbox in zip(confidences, coords):
+                        # Normalize coordinates
+                        x1, y1, x2, y2 = bbox.tolist()
+                        norm_bbox = [
+                            x1 / img_width,
+                            y1 / img_height,
+                            x2 / img_width,
+                            y2 / img_height,
+                        ]
+
+                        all_detections.append(
+                            {
+                                "type": "icon",
+                                "confidence": conf.item(),
+                                "bbox": norm_bbox,
+                                "scale": scale["size"],
+                                "interactivity": True,
+                            }
+                        )
+
+            except Exception as e:
+                logger.warning(f"Detection failed at scale {scale['size']}: {str(e)}")
+                continue
+
+        # Merge detections using NMS
+        if len(all_detections) > 0:
+            boxes = torch.tensor([d["bbox"] for d in all_detections])
+            scores = torch.tensor([d["confidence"] for d in all_detections])
+
+            keep_indices = torchvision.ops.nms(boxes, scores, iou_threshold)
+
+            merged_detections = [all_detections[i] for i in keep_indices]
+        else:
+            merged_detections = []
+
+        return merged_detections
@@ -0,0 +1,120 @@
+from typing import Any, Dict, List, Literal, Optional, Tuple, Union
+
+from pydantic import BaseModel, Field, validator
+
+
+class BoundingBox(BaseModel):
+    """Normalized bounding box coordinates."""
+
+    x1: float = Field(..., description="Normalized left coordinate")
+    y1: float = Field(..., description="Normalized top coordinate")
+    x2: float = Field(..., description="Normalized right coordinate")
+    y2: float = Field(..., description="Normalized bottom coordinate")
+
+    @property
+    def coordinates(self) -> List[float]:
+        """Get coordinates as a list [x1, y1, x2, y2]."""
+        return [self.x1, self.y1, self.x2, self.y2]
+
+
+class UIElement(BaseModel):
+    """Base class for UI elements."""
+
+    id: Optional[int] = Field(None, description="Unique identifier for the element (1-indexed)")
+    type: Literal["icon", "text"]
+    bbox: BoundingBox
+    interactivity: bool = Field(default=False, description="Whether the element is interactive")
+    confidence: float = Field(default=1.0, description="Detection confidence score")
+
+
+class IconElement(UIElement):
+    """An interactive icon element."""
+
+    type: Literal["icon"] = "icon"
+    interactivity: bool = True
+    scale: Optional[int] = Field(None, description="Detection scale used")
+
+
+class TextElement(UIElement):
+    """A text element."""
+
+    type: Literal["text"] = "text"
+    content: str = Field(..., description="The text content")
+    interactivity: bool = False
+
+
+class ImageData(BaseModel):
+    """Image data with dimensions."""
+
+    base64: str = Field(..., description="Base64 encoded image data")
+    width: int = Field(..., description="Image width in pixels")
+    height: int = Field(..., description="Image height in pixels")
+
+    @validator("width", "height")
+    def dimensions_must_be_positive(cls, v):
+        if v <= 0:
+            raise ValueError("Dimensions must be positive")
+        return v
+
+
+class ParserMetadata(BaseModel):
+    """Metadata about the parsing process."""
+
+    image_size: Tuple[int, int] = Field(
+        ..., description="Original image dimensions (width, height)"
+    )
+    num_icons: int = Field(..., description="Number of icons detected")
+    num_text: int = Field(..., description="Number of text elements detected")
+    device: str = Field(..., description="Device used for detection (cpu/cuda/mps)")
+    ocr_enabled: bool = Field(..., description="Whether OCR was enabled")
+    latency: float = Field(..., description="Total processing time in seconds")
+
+    @property
+    def width(self) -> int:
+        """Get image width from image_size."""
+        return self.image_size[0]
+
+    @property
+    def height(self) -> int:
+        """Get image height from image_size."""
+        return self.image_size[1]
+
+
+class ParseResult(BaseModel):
+    """Result of parsing a UI screenshot."""
+
+    elements: List[UIElement] = Field(..., description="Detected UI elements")
+    annotated_image_base64: str = Field(..., description="Base64 encoded annotated image")
+    metadata: ParserMetadata = Field(..., description="Processing metadata")
+    screen_info: Optional[List[str]] = Field(
+        None, description="Human-readable descriptions of elements"
+    )
+    parsed_content_list: Optional[List[Dict[str, Any]]] = Field(
+        None, description="Parsed elements as dictionaries"
+    )
+
+    @property
+    def image(self) -> ImageData:
+        """Get image data as a convenience property."""
+        return ImageData(
+            base64=self.annotated_image_base64,
+            width=self.metadata.width,
+            height=self.metadata.height,
+        )
+
+    @property
+    def width(self) -> int:
+        """Get image width from metadata."""
+        return self.metadata.width
+
+    @property
+    def height(self) -> int:
+        """Get image height from metadata."""
+        return self.metadata.height
+
+    def model_dump(self) -> Dict[str, Any]:
+        """Convert model to dict for compatibility with older code."""
+        result = super().model_dump()
+        # Add image data dict for backward compatibility
+        result["image"] = self.image.model_dump()
+        return result
@@ -0,0 +1,172 @@
+import logging
+import signal
+from contextlib import contextmanager
+from pathlib import Path
+from typing import Any, Dict, List, Tuple, Union
+
+import easyocr
+import numpy as np
+import torch
+from PIL import Image
+
+logger = logging.getLogger(__name__)
+
+
+class TimeoutException(Exception):
+    pass
+
+
+@contextmanager
+def timeout(seconds: int):
+    import threading
+
+    # Check if we're in the main thread
+    if threading.current_thread() is threading.main_thread():
+
+        def timeout_handler(signum, frame):
+            raise TimeoutException("OCR process timed out")
+
+        original_handler = signal.signal(signal.SIGALRM, timeout_handler)
+        signal.alarm(seconds)
+
+        try:
+            yield
+        finally:
+            signal.alarm(0)
+            signal.signal(signal.SIGALRM, original_handler)
+    else:
+        # In a non-main thread, we can't use signal
+        logger.warning(
+            "Timeout function called from non-main thread; signal-based timeout disabled"
+        )
+        try:
+            yield
+        finally:
+            pass
+
+
+class OCRProcessor:
+    """Class for handling OCR text detection."""
+
+    _shared_reader = None  # Class-level shared reader instance
+
+    def __init__(self):
+        """Initialize the OCR processor."""
+        self.reader = None
+        # Determine best available device
+        self.device = "cpu"
+        if torch.cuda.is_available():
+            self.device = "cuda"
+        elif (
+            hasattr(torch, "backends")
+            and hasattr(torch.backends, "mps")
+            and torch.backends.mps.is_available()
+        ):
+            self.device = "mps"
+        logger.info(f"OCR processor initialized with device: {self.device}")
+
+    def _ensure_reader(self):
+        """Ensure EasyOCR reader is initialized.
+
+        Uses a class-level cached reader to avoid reinitializing on every instance.
+        """
+        # First check if we already have a class-level reader
+        if OCRProcessor._shared_reader is not None:
+            self.reader = OCRProcessor._shared_reader
+            return
+
+        # Otherwise initialize a new one
+        if self.reader is None:
+            try:
+                logger.info("Initializing EasyOCR reader...")
+                import easyocr
+
+                # Use GPU if available
+                use_gpu = self.device in ["cuda", "mps"]
+                self.reader = easyocr.Reader(["en"], gpu=use_gpu)
+
+                # Verify reader initialization
+                if self.reader is None:
+                    raise ValueError("Failed to initialize EasyOCR reader")
+
+                # Cache the reader at class level
+                OCRProcessor._shared_reader = self.reader
+
+                logger.info(f"EasyOCR reader initialized successfully with GPU={use_gpu}")
+            except Exception as e:
+                logger.error(f"Failed to initialize EasyOCR reader: {str(e)}")
+                # Set to a placeholder that will be checked
+                self.reader = None
+                raise RuntimeError(f"EasyOCR initialization failed: {str(e)}") from e
+
+    def detect_text(
+        self, image: Image.Image, confidence_threshold: float = 0.5, timeout_seconds: int = 5
+    ) -> List[Dict[str, Any]]:
+        """Detect text in an image using EasyOCR.
+
+        Args:
+            image: PIL Image to process
+            confidence_threshold: Minimum confidence for text detection
+            timeout_seconds: Maximum time to wait for OCR
+
+        Returns:
+            List of text detection dictionaries
+        """
+        try:
+            # Try to initialize reader, catch any exceptions
+            try:
+                self._ensure_reader()
+            except Exception as e:
+                logger.error(f"Failed to initialize OCR reader: {str(e)}")
+                return []
+
+            # Ensure reader was properly initialized
+            if self.reader is None:
+                logger.error("OCR reader is None after initialization")
+                return []
+
+            # Convert PIL Image to numpy array
+            image_np = np.array(image)
+
+            try:
+                with timeout(timeout_seconds):
+                    results = self.reader.readtext(
+                        image_np, paragraph=False, text_threshold=confidence_threshold
+                    )
+            except TimeoutException:
+                logger.warning("OCR timed out")
+                return []
+            except Exception as e:
+                logger.warning(f"OCR failed: {str(e)}")
+                return []
+
+            detections = []
+            img_width, img_height = image.size
+
+            for box, text, conf in results:
+                # Ensure conf is float
+                conf_float = float(conf)
+                if conf_float < confidence_threshold:
+                    continue
+
+                # Convert box format to [x1, y1, x2, y2]
+                # Ensure box points are properly typed as float
+                x1 = min(float(point[0]) for point in box) / img_width
+                y1 = min(float(point[1]) for point in box) / img_height
+                x2 = max(float(point[0]) for point in box) / img_width
+                y2 = max(float(point[1]) for point in box) / img_height
+
+                detections.append(
+                    {
+                        "type": "text",
+                        "bbox": [x1, y1, x2, y2],
+                        "content": text,
+                        "confidence": conf,
+                        "interactivity": False,  # Text is typically non-interactive
+                    }
+                )
+
+            return detections
+        except Exception as e:
+            logger.error(f"Unexpected error in OCR processing: {str(e)}")
+            return []
@@ -0,0 +1,210 @@
+import logging
+import signal
+import time
+from contextlib import contextmanager
+from typing import Any, List, Optional, Sequence, Tuple, Union, cast
+
+import cv2
+import easyocr
+import matplotlib.pyplot as plt
+import numpy as np
+from PIL import Image
+
+logger = logging.getLogger(__name__)
+
+
+class TimeoutException(Exception):
+    pass
+
+
+@contextmanager
+def timeout(seconds):
+    def timeout_handler(signum, frame):
+        logger.warning(f"OCR process timed out after {seconds} seconds")
+        raise TimeoutException("OCR processing timed out")
+
+    # Register the signal handler
+    original_handler = signal.signal(signal.SIGALRM, timeout_handler)
+    signal.alarm(seconds)
+
+    try:
+        yield
+    finally:
+        signal.alarm(0)
+        signal.signal(signal.SIGALRM, original_handler)
+
+
+# Initialize EasyOCR with optimized settings
+logger.info("Initializing EasyOCR with optimized settings...")
+reader = easyocr.Reader(
+    ["en"],
+    gpu=True,  # Use GPU if available
+    model_storage_directory=None,  # Use default directory
+    download_enabled=True,
+    detector=True,  # Enable text detection
+    recognizer=True,  # Enable text recognition
+    verbose=False,  # Disable verbose output
+    quantize=True,  # Enable quantization for faster inference
+    cudnn_benchmark=True,  # Enable cuDNN benchmarking
+)
+logger.info("EasyOCR initialization complete")
+
+
+def check_ocr_box(
+    image_source: Union[str, Image.Image],
+    display_img=True,
+    output_bb_format="xywh",
+    goal_filtering=None,
+    easyocr_args=None,
+    use_paddleocr=False,
+) -> Tuple[Tuple[List[str], List[Tuple[float, float, float, float]]], Optional[Any]]:
+    """Check OCR box using EasyOCR with optimized settings.
+
+    Args:
+        image_source: Either a file path or PIL Image
+        display_img: Whether to display the annotated image
+        output_bb_format: Format for bounding boxes ('xywh' or 'xyxy')
+        goal_filtering: Optional filtering of results
+        easyocr_args: Arguments for EasyOCR
+        use_paddleocr: Ignored (kept for backward compatibility)
+
+    Returns:
+        Tuple containing:
+        - Tuple of (text_list, bounding_boxes)
+        - goal_filtering value
+    """
+    logger.info("Starting OCR processing...")
+    start_time = time.time()
+
+    if isinstance(image_source, str):
+        logger.info(f"Loading image from path: {image_source}")
+        image_source = Image.open(image_source)
+    if image_source.mode == "RGBA":
+        logger.info("Converting RGBA image to RGB")
+        image_source = image_source.convert("RGB")
+    image_np = np.array(image_source)
+    w, h = image_source.size
+    logger.info(f"Image size: {w}x{h}")
+
+    # Default EasyOCR arguments optimized for speed
+    default_args = {
+        "paragraph": False,  # Disable paragraph detection
+        "text_threshold": 0.5,  # Confidence threshold
+        "link_threshold": 0.4,  # Text link threshold
+        "canvas_size": 2560,  # Max image size
+        "mag_ratio": 1.0,  # Magnification ratio
+        "slope_ths": 0.1,  # Slope threshold
+        "ycenter_ths": 0.5,  # Y-center threshold
+        "height_ths": 0.5,  # Height threshold
+        "width_ths": 0.5,  # Width threshold
+        "add_margin": 0.1,  # Margin around text
+        "min_size": 20,  # Minimum text size
+    }
+
+    # Update with user-provided arguments
+    if easyocr_args:
+        logger.info(f"Using custom EasyOCR arguments: {easyocr_args}")
+        default_args.update(easyocr_args)
+
+    try:
+        # Use EasyOCR with timeout
+        logger.info("Starting EasyOCR detection with 5 second timeout...")
+        with timeout(5):  # 5 second timeout
+            # EasyOCR's readtext returns a list of tuples, where each tuple is (bbox, text, confidence)
+            raw_result = reader.readtext(image_np, **default_args)
+            result = cast(Sequence[Tuple[List[Tuple[float, float]], str, float]], raw_result)
+            coord = [item[0] for item in result]  # item[0] is the bbox coordinates
+            text = [item[1] for item in result]  # item[1] is the text content
+            logger.info(f"OCR completed successfully. Found {len(text)} text regions")
+            logger.info(f"Detected text: {text}")
+
+    except TimeoutException:
+        logger.error("OCR processing timed out after 5 seconds")
+        coord = []
+        text = []
+    except Exception as e:
+        logger.error(f"OCR processing failed with error: {str(e)}")
+        coord = []
+        text = []
+
+    processing_time = time.time() - start_time
+    logger.info(f"Total OCR processing time: {processing_time:.2f} seconds")
+
+    if display_img:
+        logger.info("Creating visualization of OCR results...")
+        opencv_img = cv2.cvtColor(image_np, cv2.COLOR_RGB2BGR)
+        bb = []
+        for item in coord:
+            x, y, a, b = get_xywh(item)
+            bb.append((x, y, a, b))
+            # Convert float coordinates to integers for cv2.rectangle
+            x_val = cast(float, x)
+            y_val = cast(float, y)
+            a_val = cast(float, a)
+            b_val = cast(float, b)
+            x_int, y_int = int(x_val), int(y_val)
+            a_int, b_int = int(a_val), int(b_val)
+            cv2.rectangle(
+                opencv_img, (x_int, y_int), (x_int + a_int, y_int + b_int), (0, 255, 0), 2
+            )
+        plt.imshow(cv2.cvtColor(opencv_img, cv2.COLOR_BGR2RGB))
+    else:
+        if output_bb_format == "xywh":
+            bb = [get_xywh(item) for item in coord]
+        elif output_bb_format == "xyxy":
+            bb = [get_xyxy(item) for item in coord]
+
+    # Cast the bounding boxes to the expected type
+    bb = cast(List[Tuple[float, float, float, float]], bb)
+
+    logger.info("OCR processing complete")
+    return (text, bb), goal_filtering
+
+
+def get_xywh(box):
+    """
+    Convert a bounding box to xywh format (x, y, width, height).
+
+    Args:
+        box: Bounding box coordinates (various formats supported)
+
+    Returns:
+        Tuple of (x, y, width, height)
+    """
+    # Handle different input formats
+    if len(box) == 4:
+        # If already in xywh format or xyxy format
+        if isinstance(box[0], (int, float)) and isinstance(box[2], (int, float)):
+            if box[2] < box[0] or box[3] < box[1]:
+                # Already xyxy format, convert to xywh
+                x1, y1, x2, y2 = box
+                return x1, y1, x2 - x1, y2 - y1
+            else:
+                # Already in xywh format
+                return box
+    elif len(box) == 2:
+        # Format like [[x1,y1],[x2,y2]] from some OCR engines
+        (x1, y1), (x2, y2) = box
+        return x1, y1, x2 - x1, y2 - y1
+
+    # Default case - try to convert assuming it's a list of points
+    x_coords = [p[0] for p in box]
+    y_coords = [p[1] for p in box]
+    x1, y1 = min(x_coords), min(y_coords)
+    width, height = max(x_coords) - x1, max(y_coords) - y1
+    return x1, y1, width, height
+
+
+def get_xyxy(box):
+    """
+    Convert a bounding box to xyxy format (x1, y1, x2, y2).
+
+    Args:
+        box: Bounding box coordinates (various formats supported)
+
+    Returns:
+        Tuple of (x1, y1, x2, y2)
+    """
+    # Get xywh first, then convert to xyxy
+    x, y, w, h = get_xywh(box)
+    return x, y, x + w, y + h
@@ -0,0 +1,294 @@
+import logging
+import os
+import platform
+from typing import Any, Dict, List, Tuple
+
+import numpy as np
+import supervision as sv
+from PIL import Image, ImageDraw, ImageFont
+
+logger = logging.getLogger(__name__)
+
+
+class BoxAnnotator:
+    """Class for drawing bounding boxes and labels on images."""
+
+    def __init__(self):
+        """Initialize the box annotator with a color palette."""
+        # WCAG 2.1 compliant color palette optimized for accessibility
+        self.colors = [
+            "#2E7D32",  # Green
+            "#C62828",  # Red
+            "#1565C0",  # Blue
+            "#6A1B9A",  # Purple
+            "#EF6C00",  # Orange
+            "#283593",  # Indigo
+            "#4527A0",  # Deep Purple
+            "#00695C",  # Teal
+            "#D84315",  # Deep Orange
+            "#1B5E20",  # Dark Green
+            "#B71C1C",  # Dark Red
+            "#0D47A1",  # Dark Blue
+            "#4A148C",  # Dark Purple
+            "#E65100",  # Dark Orange
+            "#1A237E",  # Dark Indigo
+            "#311B92",  # Darker Purple
+            "#004D40",  # Dark Teal
+            "#BF360C",  # Darker Orange
+            "#33691E",  # Darker Green
+            "#880E4F",  # Pink
+        ]
+        self.color_index = 0
+        self.default_font = None
+        self._initialize_font()
+
+    def _initialize_font(self) -> None:
+        """Initialize the default font."""
+        # Try to load a system font first
+        system = platform.system()
+        font_paths = []
+
+        if system == "Darwin":  # macOS
+            font_paths = [
+                "/System/Library/Fonts/Helvetica.ttc",
+                "/System/Library/Fonts/Arial.ttf",
+                "/Library/Fonts/Arial.ttf",
+            ]
+        elif system == "Linux":
+            font_paths = [
+                "/usr/share/fonts/truetype/dejavu/DejaVuSans.ttf",
+                "/usr/share/fonts/TTF/DejaVuSans.ttf",
+                "/usr/share/fonts/truetype/liberation/LiberationSans-Regular.ttf",
+            ]
+        else:  # Windows
+            font_paths = ["C:\\Windows\\Fonts\\arial.ttf"]
+
+        # Try each font path
+        for font_path in font_paths:
+            if os.path.exists(font_path):
+                try:
+                    # Test the font with a small size
+                    test_font = ImageFont.truetype(font_path, 12)
+                    # Test if the font can render text
+                    test_font.getbbox("1")
+                    self.default_font = font_path
+                    return
+                except Exception:
+                    continue
+
+    def _get_next_color(self) -> str:
+        """Get the next color from the palette."""
+        color = self.colors[self.color_index]
+        self.color_index = (self.color_index + 1) % len(self.colors)
+        return color
+
+    def _hex_to_rgb(self, hex_color: str) -> Tuple[int, int, int]:
+        """Convert hex color to RGB tuple."""
+        hex_color = hex_color.lstrip("#")
+        # Create explicit tuple of 3 integers to match the return type
+        r = int(hex_color[0:2], 16)
+        g = int(hex_color[2:4], 16)
+        b = int(hex_color[4:6], 16)
+        return (r, g, b)
+
+    def draw_boxes(
+        self, image: Image.Image, detections: List[Dict[str, Any]], draw_config: Dict[str, Any]
+    ) -> Image.Image:
+        """Draw bounding boxes and labels on the image."""
+        draw = ImageDraw.Draw(image)
+
+        # Create smaller font while keeping contrast
+        try:
+            if self.default_font:
+                font = ImageFont.truetype(self.default_font, size=12)  # Reduced from 16 to 12
+            else:
+                # If no TrueType font available, use default
+                font = ImageFont.load_default()
+        except Exception:
+            font = ImageFont.load_default()
+
+        padding = 2  # Reduced padding for smaller overall box
+        spacing = 1  # Reduced spacing between elements
+
+        # Keep track of used label areas to check for collisions
+        used_areas = []
+
+        # Store label information for third pass
+        labels_to_draw = []
+
+        # First pass: Initialize used_areas with all bounding boxes
+        for detection in detections:
+            box = detection["bbox"]
+            x1, y1, x2, y2 = [
+                int(coord * dim) for coord, dim in zip(box, [image.width, image.height] * 2)
+            ]
+            used_areas.append((x1, y1, x2, y2))
+
+        # Second pass: Draw all bounding boxes
+        for idx, detection in enumerate(detections, 1):
+            # Get box coordinates
+            box = detection["bbox"]
+            x1, y1, x2, y2 = [
+                int(coord * dim) for coord, dim in zip(box, [image.width, image.height] * 2)
+            ]
+
+            # Get color for this detection
+            color = self._get_next_color()
+            rgb_color = self._hex_to_rgb(color)
+
+            # Draw bounding box with original width
+            draw.rectangle(((x1, y1), (x2, y2)), outline=rgb_color, width=2)
+
+            # Use detection number as label
+            label = str(idx)
+
+            # Get text dimensions using getbbox
+            bbox = font.getbbox(label)
+            text_width = bbox[2] - bbox[0]
+            text_height = bbox[3] - bbox[1]
+
+            # Create box dimensions with padding
+            box_width = text_width + (padding * 2)  # Removed multiplier for tighter box
+            box_height = text_height + (padding * 2)  # Removed multiplier for tighter box
+
+            def is_inside_bbox(x, y):
+                """Check if a label box would be inside the bounding box."""
+                return x >= x1 and x + box_width <= x2 and y >= y1 and y + box_height <= y2
+
+            # Try different positions until we find one without collision
+            positions = [
+                # Top center (above bbox)
+                lambda: (x1 + ((x2 - x1) - box_width) // 2, y1 - box_height - spacing),
+                # Bottom center (below bbox)
+                lambda: (x1 + ((x2 - x1) - box_width) // 2, y2 + spacing),
+                # Right center (right of bbox)
+                lambda: (x2 + spacing, y1 + ((y2 - y1) - box_height) // 2),
+                # Left center (left of bbox)
+                lambda: (x1 - box_width - spacing, y1 + ((y2 - y1) - box_height) // 2),
+                # Top right (outside corner)
+                lambda: (x2 + spacing, y1 - box_height - spacing),
+                # Top left (outside corner)
+                lambda: (x1 - box_width - spacing, y1 - box_height - spacing),
+                # Bottom right (outside corner)
+                lambda: (x2 + spacing, y2 + spacing),
+                # Bottom left (outside corner)
+                lambda: (x1 - box_width - spacing, y2 + spacing),
+            ]
+
+            def check_occlusion(x, y):
+                """Check if a label box occludes any existing ones or is inside bbox."""
+                # First check if it's inside the bounding box
+                if is_inside_bbox(x, y):
+                    return True
+
+                # Then check collision with other labels
+                new_box = (x, y, x + box_width, y + box_height)
+                label_width = new_box[2] - new_box[0]
+                label_height = new_box[3] - new_box[1]
+
+                for used_box in used_areas:
+                    if not (
+                        new_box[2] < used_box[0]  # new box is left of used box
+                        or new_box[0] > used_box[2]  # new box is right of used box
+                        or new_box[3] < used_box[1]  # new box is above used box
+                        or new_box[1] > used_box[3]  # new box is below used box
+                    ):
+                        # Calculate dimensions of the used box
+                        used_box_width = used_box[2] - used_box[0]
+                        used_box_height = used_box[3] - used_box[1]
+
+                        # Only consider as collision if used box is NOT more than 5x bigger in both dimensions
+                        if not (
+                            used_box_width > 5 * label_width and used_box_height > 5 * label_height
+                        ):
+                            return True
+                return False
+
+            # Try each position until we find one without collision
+            label_x = None
+            label_y = None
+
+            for get_pos in positions:
+                x, y = get_pos()
+                # Ensure position is within image bounds
+                if x < 0 or y < 0 or x + box_width > image.width or y + box_height > image.height:
+                    continue
+                if not check_occlusion(x, y):
+                    label_x = x
+                    label_y = y
+                    break
+
+            # If all positions collide or are out of bounds, find the best possible position
+            if label_x is None:
+                # Try to place it in the nearest valid position outside the bbox
+                best_pos = positions[0]()  # Default to top center
+                label_x = max(0, min(image.width - box_width, best_pos[0]))
+                label_y = max(0, min(image.height - box_height, best_pos[1]))
+
+                # Ensure it's not inside the bounding box
+                if is_inside_bbox(label_x, label_y):
+                    # Force it above the bounding box
+                    label_y = max(0, y1 - box_height - spacing)
+
+            # Add this label area to used areas
+            if (
+                label_x is not None
+                and label_y is not None
+                and box_width is not None
+                and box_height is not None
+            ):
+                used_areas.append((label_x, label_y, label_x + box_width, label_y + box_height))
+
+            # Store label information for second pass
+            labels_to_draw.append(
+                {
+                    "label": label,
+                    "x": label_x,
+                    "y": label_y,
+                    "width": box_width,
+                    "height": box_height,
+                    "text_width": text_width,
+                    "text_height": text_height,
+                    "color": rgb_color,
+                }
+            )
+
+        # Third pass: Draw all labels on top
+        for label_info in labels_to_draw:
+            # Draw background box with white outline
+            draw.rectangle(
+                (
+                    (label_info["x"] - 1, label_info["y"] - 1),
+                    (
+                        label_info["x"] + label_info["width"] + 1,
+                        label_info["y"] + label_info["height"] + 1,
+                    ),
+                ),
+                outline="white",
+                width=2,
+            )
+            draw.rectangle(
+                (
+                    (label_info["x"], label_info["y"]),
+                    (label_info["x"] + label_info["width"], label_info["y"] + label_info["height"]),
+                ),
+                fill=label_info["color"],
+            )
+
+            # Center text in box
+            text_x = label_info["x"] + (label_info["width"] - label_info["text_width"]) // 2
+            text_y = label_info["y"] + (label_info["height"] - label_info["text_height"]) // 2
+
+            # Draw text with black outline for better visibility
+            outline_width = 1
+            for dx in [-outline_width, outline_width]:
+                for dy in [-outline_width, outline_width]:
+                    draw.text(
+                        (text_x + dx, text_y + dy), label_info["label"], fill="black", font=font
+                    )
+
+            # Draw the main white text
+            draw.text((text_x, text_y), label_info["label"], fill=(255, 255, 255), font=font)
+
+        logger.info("Finished drawing all boxes")
+        return image
@@ -0,0 +1,24 @@
+"""Pytest configuration for som tests.
+
+This module provides test fixtures for the som (Set-of-Mark) package.
+The som package depends on heavy ML models and will skip tests if not available.
+"""
+
+from unittest.mock import Mock, patch
+
+import pytest
+
+
+@pytest.fixture
+def mock_torch():
+    with patch("torch.load") as mock_load:
+        mock_load.return_value = Mock()
+        yield mock_load
+
+
+@pytest.fixture
+def mock_icon_detector():
+    with patch("omniparser.IconDetector") as mock_detector:
+        instance = Mock()
+        mock_detector.return_value = instance
+        yield instance
@@ -0,0 +1,73 @@
+"""Unit tests for som package (Set-of-Mark).
+
+This file tests ONLY basic som functionality.
+Following SRP: This file tests som module imports and basic operations.
+All external dependencies (ML models, OCR) are mocked.
+"""
+
+import pytest
+
+
+class TestSomImports:
+    """Test som module imports (SRP: Only tests imports)."""
+
+    def test_som_module_exists(self):
+        """Test that som module can be imported."""
+        try:
+            import som
+
+            assert som is not None
+        except ImportError:
+            pytest.skip("som module not installed")
+
+    def test_omniparser_import(self):
+        """Test that OmniParser can be imported."""
+        try:
+            from som import OmniParser
+
+            assert OmniParser is not None
+        except ImportError:
+            pytest.skip("som module not available")
+        except Exception as e:
+            pytest.skip(f"som initialization requires ML models: {e}")
+
+    def test_models_import(self):
+        """Test that model classes can be imported."""
+        try:
+            from som import BoundingBox, ParseResult, UIElement
+
+            assert BoundingBox is not None
+            assert UIElement is not None
+            assert ParseResult is not None
+        except ImportError:
+            pytest.skip("som models not available")
+        except Exception as e:
+            pytest.skip(f"som models require dependencies: {e}")
+
+
+class TestSomModels:
+    """Test som data models (SRP: Only tests model structure)."""
+
+    def test_bounding_box_structure(self):
+        """Test BoundingBox class structure."""
+        try:
+            from som import BoundingBox
+
+            # Check the class exists and has expected structure
+            assert hasattr(BoundingBox, "__init__")
+        except ImportError:
+            pytest.skip("som models not available")
+        except Exception as e:
+            pytest.skip(f"som models require dependencies: {e}")
+
+    def test_ui_element_structure(self):
+        """Test UIElement class structure."""
+        try:
+            from som import UIElement
+
+            # Check the class exists and has expected structure
+            assert hasattr(UIElement, "__init__")
+        except ImportError:
+            pytest.skip("som models not available")
+        except Exception as e:
+            pytest.skip(f"som models require dependencies: {e}")