Add Rust extension module (myfsio_core) for SigV4, hashing, and validation hot paths

- Fix duplicate _legacy_version_dir check in storage.py
      - Fix max_size_bytes -> max_bytes param in quota handler
      - Move base64 import to module level in s3_api.py
      - Add retry logic and atomic file ops to multipart upload
      - Add shutdown() method to ReplicationManager

      Performance:
      - Add LRU eviction with OrderedDict to object cache
      - Add cache version tracking for stale read detection
      - Add streaming uploads for large files (>10 MiB) in replication
      - Create _find_element() XML parsing helpers

      Security:
      - Gate SigV4 debug logging behind DEBUG_SIGV4 config

Dockerfile

@@ -1,25 +1,33 @@
-# syntax=docker/dockerfile:1.7
-FROM python:3.11-slim
+FROM python:3.14.3-slim
 
 ENV PYTHONDONTWRITEBYTECODE=1 \
     PYTHONUNBUFFERED=1
 
 WORKDIR /app
 
-# Install build deps for any wheels that need compilation, then clean up
-RUN apt-get update \ 
-    && apt-get install -y --no-install-recommends build-essential \ 
+RUN apt-get update \
+    && apt-get install -y --no-install-recommends build-essential curl \
+    && curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --profile minimal \
     && rm -rf /var/lib/apt/lists/*
 
+ENV PATH="/root/.cargo/bin:${PATH}"
+
 COPY requirements.txt ./
 RUN pip install --no-cache-dir -r requirements.txt
 
 COPY . .
 
-# Make entrypoint executable
+RUN pip install --no-cache-dir maturin \
+    && cd myfsio_core \
+    && maturin build --release \
+    && pip install target/wheels/*.whl \
+    && cd .. \
+    && rm -rf myfsio_core/target \
+    && pip uninstall -y maturin \
+    && rustup self uninstall -y
+
 RUN chmod +x docker-entrypoint.sh
 
-# Create data directory and set permissions
 RUN mkdir -p /app/data \
     && useradd -m -u 1000 myfsio \ 
     && chown -R myfsio:myfsio /app
@@ -32,6 +40,6 @@ ENV APP_HOST=0.0.0.0 \
     FLASK_DEBUG=0
 
 HEALTHCHECK --interval=30s --timeout=3s --start-period=5s --retries=3 \
-    CMD python -c "import requests; requests.get('http://localhost:5000/healthz', timeout=2)"
+    CMD python -c "import requests; requests.get('http://localhost:5000/myfsio/health', timeout=2)"
 
 CMD ["./docker-entrypoint.sh"]

LICENSE

@@ -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/>.

README.md

@@ -1,117 +1,250 @@
-# MyFSIO (Flask S3 + IAM)
+# MyFSIO
 
-MyFSIO is a batteries-included, Flask-based recreation of Amazon S3 and IAM workflows built for local development. The design mirrors the [AWS S3 documentation](https://docs.aws.amazon.com/s3/) wherever practical: bucket naming, Signature Version 4 presigning, Version 2012-10-17 bucket policies, IAM-style users, and familiar REST endpoints.
+A lightweight, S3-compatible object storage system built with Flask. MyFSIO implements core AWS S3 REST API operations with filesystem-backed storage, making it ideal for local development, testing, and self-hosted storage scenarios.
 
-## Why MyFSIO?
+## Features
 
-- **Dual servers:** Run both the API (port 5000) and UI (port 5100) with a single command: `python run.py`.
-- **IAM + access keys:** Users, access keys, key rotation, and bucket-scoped actions (`list/read/write/delete/policy`) now live in `data/.myfsio.sys/config/iam.json` and are editable from the IAM dashboard.
-- **Bucket policies + hot reload:** `data/.myfsio.sys/config/bucket_policies.json` uses AWS' policy grammar (Version `2012-10-17`) with a built-in watcher, so editing the JSON file applies immediately. The UI also ships Public/Private/Custom presets for faster edits.
-- **Presigned URLs everywhere:** Signature Version 4 presigned URLs respect IAM + bucket policies and replace the now-removed "share link" feature for public access scenarios.
-- **Modern UI:** Responsive tables, quick filters, preview sidebar, object-level delete buttons, a presign modal, and an inline JSON policy editor that respects dark mode keep bucket management friendly. The object browser supports folder navigation, infinite scroll pagination, bulk operations, and automatic retry on load failures.
-- **Tests & health:** `/healthz` for smoke checks and `pytest` coverage for IAM, CRUD, presign, and policy flows.
+**Core Storage**
+- S3-compatible REST API with AWS Signature Version 4 authentication
+- Bucket and object CRUD operations
+- Object versioning with version history
+- Multipart uploads for large files
+- Presigned URLs (1 second to 7 days validity)
 
-## Architecture at a Glance
+**Security & Access Control**
+- IAM users with access key management and rotation
+- Bucket policies (AWS Policy Version 2012-10-17)
+- Server-side encryption (SSE-S3 and SSE-KMS)
+- Built-in Key Management Service (KMS)
+- Rate limiting per endpoint
+
+**Advanced Features**
+- Cross-bucket replication to remote S3-compatible endpoints
+- Hot-reload for bucket policies (no restart required)
+- CORS configuration per bucket
+
+**Management UI**
+- Web console for bucket and object management
+- IAM dashboard for user administration
+- Inline JSON policy editor with presets
+- Object browser with folder navigation and bulk operations
+- Dark mode support
+
+## Architecture
 
 ```
-+-----------------+        +----------------+
-| API Server      |<----->| Object storage |
-| (port 5000)     |        | (filesystem)   |
-|  - S3 routes    |        +----------------+
-|  - Presigned URLs |
-|  - Bucket policy  |
-+-----------------+
-        ^
-        |
-+-----------------+
-| UI Server       |
-| (port 5100)     |
-|  - Auth console |
-|  - IAM dashboard|
-|  - Bucket editor|
-+-----------------+
++------------------+         +------------------+
+|   API Server     |         |   UI Server      |
+|   (port 5000)    |         |   (port 5100)    |
+|                  |         |                  |
+|  - S3 REST API   |<------->|  - Web Console   |
+|  - SigV4 Auth    |         |  - IAM Dashboard |
+|  - Presign URLs  |         |  - Bucket Editor |
++--------+---------+         +------------------+
+         |
+         v
++------------------+         +------------------+
+| Object Storage   |         | System Metadata  |
+| (filesystem)     |         | (.myfsio.sys/)   |
+|                  |         |                  |
+| data/<bucket>/   |         | - IAM config     |
+|   <objects>      |         | - Bucket policies|
+|                  |         | - Encryption keys|
++------------------+         +------------------+
 ```
 
-Both apps load the same configuration via `AppConfig` so IAM data and bucket policies stay consistent no matter which process you run.
-Bucket policies are automatically reloaded whenever `bucket_policies.json` changes—no restarts required.
-
-## Getting Started
+## Quick Start
 
 ```bash
+# Clone and setup
+git clone https://gitea.jzwsite.com/kqjy/MyFSIO
+cd s3
 python -m venv .venv
-. .venv/Scripts/activate  # PowerShell: .\.venv\Scripts\Activate.ps1
+
+# Activate virtual environment
+# Windows PowerShell:
+.\.venv\Scripts\Activate.ps1
+# Windows CMD:
+.venv\Scripts\activate.bat
+# Linux/macOS:
+source .venv/bin/activate
+
+# Install dependencies
 pip install -r requirements.txt
 
-# Run both API and UI (default)
+# Start both servers
 python run.py
 
-# Or run individually:
-# python run.py --mode api
-# python run.py --mode ui
+# Or start individually
+python run.py --mode api   # API only (port 5000)
+python run.py --mode ui    # UI only (port 5100)
 ```
 
-Visit `http://127.0.0.1:5100/ui` for the console and `http://127.0.0.1:5000/` for the raw API. Override ports/hosts with the environment variables listed below.
+**Default Credentials:** `localadmin` / `localadmin`
 
-## IAM, Access Keys, and Bucket Policies
-
-- First run creates `data/.myfsio.sys/config/iam.json` with `localadmin / localadmin` (full control). Sign in via the UI, then use the **IAM** tab to create users, rotate secrets, or edit inline policies without touching JSON by hand.
-- Bucket policies live in `data/.myfsio.sys/config/bucket_policies.json` and follow the AWS `arn:aws:s3:::bucket/key` resource syntax with Version `2012-10-17`. Attach/replace/remove policies from the bucket detail page or edit the JSON by hand—changes hot reload automatically.
-- IAM actions include extended verbs (`iam:list_users`, `iam:create_user`, `iam:update_policy`, etc.) so you can control who is allowed to manage other users and policies.
-
-### Bucket Policy Presets & Hot Reload
-
-- **Presets:** Every bucket detail view includes Public (read-only), Private (detach policy), and Custom presets. Public auto-populates a policy that grants anonymous `s3:ListBucket` + `s3:GetObject` access to the entire bucket.
-- **Custom drafts:** Switching back to Custom restores your last manual edit so you can toggle between presets without losing work.
-- **Hot reload:** The server watches `bucket_policies.json` and reloads statements on-the-fly—ideal for editing policies in your favorite editor while testing Via curl or the UI.
-
-## Presigned URLs
-
-Presigned URLs follow the AWS CLI playbook:
-
-- Call `POST /presign/<bucket>/<key>` (or use the "Presign" button in the UI) to request a Signature Version 4 URL valid for 1 second to 7 days.
-- The generated URL honors IAM permissions and bucket-policy decisions at generation-time and again when somebody fetches it.
-- Because presigned URLs cover both authenticated and public sharing scenarios, the legacy "share link" feature has been removed.
+- **Web Console:** http://127.0.0.1:5100/ui
+- **API Endpoint:** http://127.0.0.1:5000
 
 ## Configuration
 
 | Variable | Default | Description |
-| --- | --- | --- |
-| `STORAGE_ROOT` | `<project>/data` | Filesystem root for bucket directories |
-| `MAX_UPLOAD_SIZE` | `1073741824` | Maximum upload size (bytes) |
-| `UI_PAGE_SIZE` | `100` | `MaxKeys` hint for listings |
-| `SECRET_KEY` | `dev-secret-key` | Flask session secret for the UI |
-| `IAM_CONFIG` | `<project>/data/.myfsio.sys/config/iam.json` | IAM user + policy store |
-| `BUCKET_POLICY_PATH` | `<project>/data/.myfsio.sys/config/bucket_policies.json` | Bucket policy store |
-| `API_BASE_URL` | `http://127.0.0.1:5000` | Used by the UI when calling API endpoints (presign, bucket policy) |
-| `AWS_REGION` | `us-east-1` | Region used in Signature V4 scope |
-| `AWS_SERVICE` | `s3` | Service used in Signature V4 scope |
+|----------|---------|-------------|
+| `STORAGE_ROOT` | `./data` | Filesystem root for bucket storage |
+| `IAM_CONFIG` | `.myfsio.sys/config/iam.json` | IAM user and policy store |
+| `BUCKET_POLICY_PATH` | `.myfsio.sys/config/bucket_policies.json` | Bucket policy store |
+| `API_BASE_URL` | `http://127.0.0.1:5000` | API endpoint for UI calls |
+| `MAX_UPLOAD_SIZE` | `1073741824` | Maximum upload size in bytes (1 GB) |
+| `MULTIPART_MIN_PART_SIZE` | `5242880` | Minimum multipart part size (5 MB) |
+| `UI_PAGE_SIZE` | `100` | Default page size for listings |
+| `SECRET_KEY` | `dev-secret-key` | Flask session secret |
+| `AWS_REGION` | `us-east-1` | Region for SigV4 signing |
+| `AWS_SERVICE` | `s3` | Service name for SigV4 signing |
+| `ENCRYPTION_ENABLED` | `false` | Enable server-side encryption |
+| `KMS_ENABLED` | `false` | Enable Key Management Service |
+| `LOG_LEVEL` | `INFO` | Logging verbosity |
+| `SIGV4_TIMESTAMP_TOLERANCE_SECONDS` | `900` | Max time skew for SigV4 requests |
+| `PRESIGNED_URL_MAX_EXPIRY_SECONDS` | `604800` | Max presigned URL expiry (7 days) |
+| `REPLICATION_CONNECT_TIMEOUT_SECONDS` | `5` | Replication connection timeout |
+| `SITE_SYNC_ENABLED` | `false` | Enable bi-directional site sync |
+| `OBJECT_TAG_LIMIT` | `50` | Maximum tags per object |
 
-> Buckets now live directly under `data/` while system metadata (versions, IAM, bucket policies, multipart uploads, etc.) lives in `data/.myfsio.sys`.
-
-## API Cheatsheet (IAM headers required)
+## Data Layout
 
 ```
-GET    /                               -> List buckets (XML)
-PUT    /<bucket>                       -> Create bucket
-DELETE /<bucket>                       -> Delete bucket (must be empty)
-GET    /<bucket>                       -> List objects (XML)
-PUT    /<bucket>/<key>                 -> Upload object (binary stream)
-GET    /<bucket>/<key>                 -> Download object
-DELETE /<bucket>/<key>                 -> Delete object
-POST   /presign/<bucket>/<key>         -> Generate AWS SigV4 presigned URL (JSON)
-GET    /bucket-policy/<bucket>         -> Fetch bucket policy (JSON)
-PUT    /bucket-policy/<bucket>         -> Attach/replace bucket policy (JSON)
-DELETE /bucket-policy/<bucket>         -> Remove bucket policy
+data/
+├── <bucket>/                    # User buckets with objects
+└── .myfsio.sys/                 # System metadata
+    ├── config/
+    │   ├── iam.json             # IAM users and policies
+    │   ├── bucket_policies.json # Bucket policies
+    │   ├── replication_rules.json
+    │   └── connections.json     # Remote S3 connections
+    ├── buckets/<bucket>/
+    │   ├── meta/                # Object metadata (.meta.json)
+    │   ├── versions/            # Archived object versions
+    │   └── .bucket.json         # Bucket config (versioning, CORS)
+    ├── multipart/               # Active multipart uploads
+    └── keys/                    # Encryption keys (SSE-S3/KMS)
+```
+
+## API Reference
+
+All endpoints require AWS Signature Version 4 authentication unless using presigned URLs or public bucket policies.
+
+### Bucket Operations
+
+| Method | Endpoint | Description |
+|--------|----------|-------------|
+| `GET` | `/` | List all buckets |
+| `PUT` | `/<bucket>` | Create bucket |
+| `DELETE` | `/<bucket>` | Delete bucket (must be empty) |
+| `HEAD` | `/<bucket>` | Check bucket exists |
+
+### Object Operations
+
+| Method | Endpoint | Description |
+|--------|----------|-------------|
+| `GET` | `/<bucket>` | List objects (supports `list-type=2`) |
+| `PUT` | `/<bucket>/<key>` | Upload object |
+| `GET` | `/<bucket>/<key>` | Download object |
+| `DELETE` | `/<bucket>/<key>` | Delete object |
+| `HEAD` | `/<bucket>/<key>` | Get object metadata |
+| `POST` | `/<bucket>/<key>?uploads` | Initiate multipart upload |
+| `PUT` | `/<bucket>/<key>?partNumber=N&uploadId=X` | Upload part |
+| `POST` | `/<bucket>/<key>?uploadId=X` | Complete multipart upload |
+| `DELETE` | `/<bucket>/<key>?uploadId=X` | Abort multipart upload |
+
+### Bucket Policies (S3-compatible)
+
+| Method | Endpoint | Description |
+|--------|----------|-------------|
+| `GET` | `/<bucket>?policy` | Get bucket policy |
+| `PUT` | `/<bucket>?policy` | Set bucket policy |
+| `DELETE` | `/<bucket>?policy` | Delete bucket policy |
+
+### Versioning
+
+| Method | Endpoint | Description |
+|--------|----------|-------------|
+| `GET` | `/<bucket>/<key>?versionId=X` | Get specific version |
+| `DELETE` | `/<bucket>/<key>?versionId=X` | Delete specific version |
+| `GET` | `/<bucket>?versions` | List object versions |
+
+### Health Check
+
+| Method | Endpoint | Description |
+|--------|----------|-------------|
+| `GET` | `/myfsio/health` | Health check endpoint |
+
+## IAM & Access Control
+
+### Users and Access Keys
+
+On first run, MyFSIO creates a default admin user (`localadmin`/`localadmin`). Use the IAM dashboard to:
+
+- Create and delete users
+- Generate and rotate access keys
+- Attach inline policies to users
+- Control IAM management permissions
+
+### Bucket Policies
+
+Bucket policies follow AWS policy grammar (Version `2012-10-17`) with support for:
+
+- Principal-based access (`*` for anonymous, specific users)
+- Action-based permissions (`s3:GetObject`, `s3:PutObject`, etc.)
+- Resource patterns (`arn:aws:s3:::bucket/*`)
+- Condition keys
+
+**Policy Presets:**
+- **Public:** Grants anonymous read access (`s3:GetObject`, `s3:ListBucket`)
+- **Private:** Removes bucket policy (IAM-only access)
+- **Custom:** Manual policy editing with draft preservation
+
+Policies hot-reload when the JSON file changes.
+
+## Server-Side Encryption
+
+MyFSIO supports two encryption modes:
+
+- **SSE-S3:** Server-managed keys with automatic key rotation
+- **SSE-KMS:** Customer-managed keys via built-in KMS
+
+Enable encryption with:
+```bash
+ENCRYPTION_ENABLED=true python run.py
+```
+
+## Cross-Bucket Replication
+
+Replicate objects to remote S3-compatible endpoints:
+
+1. Configure remote connections in the UI
+2. Create replication rules specifying source/destination
+3. Objects are automatically replicated on upload
+
+## Docker
+
+```bash
+docker build -t myfsio .
+docker run -p 5000:5000 -p 5100:5100 -v ./data:/app/data myfsio
 ```
 
 ## Testing
 
 ```bash
-pytest -q
+# Run all tests
+pytest tests/ -v
+
+# Run specific test file
+pytest tests/test_api.py -v
+
+# Run with coverage
+pytest tests/ --cov=app --cov-report=html
 ```
 
 ## References
 
-- [Amazon Simple Storage Service Documentation](https://docs.aws.amazon.com/s3/)
-- [Signature Version 4 Signing Process](https://docs.aws.amazon.com/general/latest/gr/signature-version-4.html)
-- [Amazon S3 Bucket Policy Examples](https://docs.aws.amazon.com/AmazonS3/latest/userguide/example-bucket-policies.html)
+- [Amazon S3 Documentation](https://docs.aws.amazon.com/s3/)
+- [AWS Signature Version 4](https://docs.aws.amazon.com/general/latest/gr/signature-version-4.html)
+- [S3 Bucket Policy Examples](https://docs.aws.amazon.com/AmazonS3/latest/userguide/example-bucket-policies.html)

app/__init__.py

@@ -1,7 +1,8 @@
-"""Application factory for the mini S3-compatible object store."""
 from __future__ import annotations
 
+import html as html_module
 import logging
+import mimetypes
 import shutil
 import sys
 import time
@@ -11,11 +12,15 @@ from pathlib import Path
 from datetime import timedelta
 from typing import Any, Dict, List, Optional
 
-from flask import Flask, g, has_request_context, redirect, render_template, request, url_for
+from flask import Flask, Response, g, has_request_context, redirect, render_template, request, url_for
 from flask_cors import CORS
 from flask_wtf.csrf import CSRFError
 from werkzeug.middleware.proxy_fix import ProxyFix
 
+from .access_logging import AccessLoggingService
+from .operation_metrics import OperationMetricsCollector, classify_endpoint
+from .compression import GzipMiddleware
+from .acl import AclService
 from .bucket_policies import BucketPolicyStore
 from .config import AppConfig
 from .connections import ConnectionStore
@@ -23,10 +28,15 @@ from .encryption import EncryptionManager
 from .extensions import limiter, csrf
 from .iam import IamService
 from .kms import KMSManager
+from .lifecycle import LifecycleManager
+from .notifications import NotificationService
+from .object_lock import ObjectLockService
 from .replication import ReplicationManager
 from .secret_store import EphemeralSecretStore
-from .storage import ObjectStorage
+from .site_registry import SiteRegistry, SiteInfo
+from .storage import ObjectStorage, StorageError
 from .version import get_version
+from .website_domains import WebsiteDomainStore
 
 
 def _migrate_config_file(active_path: Path, legacy_paths: List[Path]) -> Path:
@@ -45,7 +55,6 @@ def _migrate_config_file(active_path: Path, legacy_paths: List[Path]) -> Path:
             try:
                 shutil.move(str(legacy_path), str(active_path))
             except OSError:
-                # Fall back to copy + delete if move fails (e.g., cross-device)
                 shutil.copy2(legacy_path, active_path)
                 try:
                     legacy_path.unlink(missing_ok=True)
@@ -86,13 +95,27 @@ def create_app(
     # Trust X-Forwarded-* headers from proxies
     app.wsgi_app = ProxyFix(app.wsgi_app, x_for=1, x_proto=1, x_host=1, x_prefix=1)
 
+    # Enable gzip compression for responses (10-20x smaller JSON payloads)
+    if app.config.get("ENABLE_GZIP", True):
+        app.wsgi_app = GzipMiddleware(app.wsgi_app, compression_level=6)
+
     _configure_cors(app)
     _configure_logging(app)
 
     limiter.init_app(app)
     csrf.init_app(app)
 
-    storage = ObjectStorage(Path(app.config["STORAGE_ROOT"]))
+    storage = ObjectStorage(
+        Path(app.config["STORAGE_ROOT"]),
+        cache_ttl=app.config.get("OBJECT_CACHE_TTL", 5),
+        object_cache_max_size=app.config.get("OBJECT_CACHE_MAX_SIZE", 100),
+        bucket_config_cache_ttl=app.config.get("BUCKET_CONFIG_CACHE_TTL_SECONDS", 30.0),
+        object_key_max_length_bytes=app.config.get("OBJECT_KEY_MAX_LENGTH_BYTES", 1024),
+    )
+
+    if app.config.get("WARM_CACHE_ON_STARTUP", True) and not app.config.get("TESTING"):
+        storage.warm_cache_async()
+
     iam = IamService(
         Path(app.config["IAM_CONFIG"]),
         auth_max_attempts=app.config.get("AUTH_MAX_ATTEMPTS", 5),
@@ -101,36 +124,53 @@ def create_app(
     bucket_policies = BucketPolicyStore(Path(app.config["BUCKET_POLICY_PATH"]))
     secret_store = EphemeralSecretStore(default_ttl=app.config.get("SECRET_TTL_SECONDS", 300))
     
-    # Initialize Replication components
-    # Store config files in the system config directory for consistency
     storage_root = Path(app.config["STORAGE_ROOT"])
     config_dir = storage_root / ".myfsio.sys" / "config"
     config_dir.mkdir(parents=True, exist_ok=True)
     
-    # Define paths with migration from legacy locations
     connections_path = _migrate_config_file(
         active_path=config_dir / "connections.json",
         legacy_paths=[
-            storage_root / ".myfsio.sys" / "connections.json",  # Previous location
-            storage_root / ".connections.json",  # Original legacy location
+            storage_root / ".myfsio.sys" / "connections.json",
+            storage_root / ".connections.json",
         ],
     )
     replication_rules_path = _migrate_config_file(
         active_path=config_dir / "replication_rules.json",
         legacy_paths=[
-            storage_root / ".myfsio.sys" / "replication_rules.json",  # Previous location
-            storage_root / ".replication_rules.json",  # Original legacy location
+            storage_root / ".myfsio.sys" / "replication_rules.json",
+            storage_root / ".replication_rules.json",
         ],
     )
     
     connections = ConnectionStore(connections_path)
-    replication = ReplicationManager(storage, connections, replication_rules_path)
-    
-    # Initialize encryption and KMS
+    replication = ReplicationManager(
+        storage,
+        connections,
+        replication_rules_path,
+        storage_root,
+        connect_timeout=app.config.get("REPLICATION_CONNECT_TIMEOUT_SECONDS", 5),
+        read_timeout=app.config.get("REPLICATION_READ_TIMEOUT_SECONDS", 30),
+        max_retries=app.config.get("REPLICATION_MAX_RETRIES", 2),
+        streaming_threshold_bytes=app.config.get("REPLICATION_STREAMING_THRESHOLD_BYTES", 10 * 1024 * 1024),
+        max_failures_per_bucket=app.config.get("REPLICATION_MAX_FAILURES_PER_BUCKET", 50),
+    )
+
+    site_registry_path = config_dir / "site_registry.json"
+    site_registry = SiteRegistry(site_registry_path)
+    if app.config.get("SITE_ID") and not site_registry.get_local_site():
+        site_registry.set_local_site(SiteInfo(
+            site_id=app.config["SITE_ID"],
+            endpoint=app.config.get("SITE_ENDPOINT") or "",
+            region=app.config.get("SITE_REGION", "us-east-1"),
+            priority=app.config.get("SITE_PRIORITY", 100),
+        ))
+
     encryption_config = {
         "encryption_enabled": app.config.get("ENCRYPTION_ENABLED", False),
         "encryption_master_key_path": app.config.get("ENCRYPTION_MASTER_KEY_PATH"),
         "default_encryption_algorithm": app.config.get("DEFAULT_ENCRYPTION_ALGORITHM", "AES256"),
+        "encryption_chunk_size_bytes": app.config.get("ENCRYPTION_CHUNK_SIZE_BYTES", 64 * 1024),
     }
     encryption_manager = EncryptionManager(encryption_config)
     
@@ -138,14 +178,38 @@ def create_app(
     if app.config.get("KMS_ENABLED", False):
         kms_keys_path = Path(app.config.get("KMS_KEYS_PATH", ""))
         kms_master_key_path = Path(app.config.get("ENCRYPTION_MASTER_KEY_PATH", ""))
-        kms_manager = KMSManager(kms_keys_path, kms_master_key_path)
+        kms_manager = KMSManager(
+            kms_keys_path,
+            kms_master_key_path,
+            generate_data_key_min_bytes=app.config.get("KMS_GENERATE_DATA_KEY_MIN_BYTES", 1),
+            generate_data_key_max_bytes=app.config.get("KMS_GENERATE_DATA_KEY_MAX_BYTES", 1024),
+        )
         encryption_manager.set_kms_provider(kms_manager)
 
-    # Wrap storage with encryption layer if encryption is enabled
     if app.config.get("ENCRYPTION_ENABLED", False):
         from .encrypted_storage import EncryptedObjectStorage
         storage = EncryptedObjectStorage(storage, encryption_manager)
 
+    acl_service = AclService(storage_root)
+    object_lock_service = ObjectLockService(storage_root)
+    notification_service = NotificationService(
+        storage_root,
+        allow_internal_endpoints=app.config.get("ALLOW_INTERNAL_ENDPOINTS", False),
+    )
+    access_logging_service = AccessLoggingService(storage_root)
+    access_logging_service.set_storage(storage)
+
+    lifecycle_manager = None
+    if app.config.get("LIFECYCLE_ENABLED", False):
+        base_storage = storage.storage if hasattr(storage, 'storage') else storage
+        lifecycle_manager = LifecycleManager(
+            base_storage,
+            interval_seconds=app.config.get("LIFECYCLE_INTERVAL_SECONDS", 3600),
+            storage_root=storage_root,
+            max_history_per_bucket=app.config.get("LIFECYCLE_MAX_HISTORY_PER_BUCKET", 50),
+        )
+        lifecycle_manager.start()
+
     app.extensions["object_storage"] = storage
     app.extensions["iam"] = iam
     app.extensions["bucket_policies"] = bucket_policies
@@ -155,14 +219,97 @@ def create_app(
     app.extensions["replication"] = replication
     app.extensions["encryption"] = encryption_manager
     app.extensions["kms"] = kms_manager
+    app.extensions["acl"] = acl_service
+    app.extensions["lifecycle"] = lifecycle_manager
+    app.extensions["object_lock"] = object_lock_service
+    app.extensions["notifications"] = notification_service
+    app.extensions["access_logging"] = access_logging_service
+    app.extensions["site_registry"] = site_registry
+
+    website_domains_store = None
+    if app.config.get("WEBSITE_HOSTING_ENABLED", False):
+        website_domains_path = config_dir / "website_domains.json"
+        website_domains_store = WebsiteDomainStore(website_domains_path)
+    app.extensions["website_domains"] = website_domains_store
+
+    from .s3_client import S3ProxyClient
+    api_base = app.config.get("API_BASE_URL") or "http://127.0.0.1:5000"
+    app.extensions["s3_proxy"] = S3ProxyClient(
+        api_base_url=api_base,
+        region=app.config.get("AWS_REGION", "us-east-1"),
+    )
+
+    operation_metrics_collector = None
+    if app.config.get("OPERATION_METRICS_ENABLED", False):
+        operation_metrics_collector = OperationMetricsCollector(
+            storage_root,
+            interval_minutes=app.config.get("OPERATION_METRICS_INTERVAL_MINUTES", 5),
+            retention_hours=app.config.get("OPERATION_METRICS_RETENTION_HOURS", 24),
+        )
+    app.extensions["operation_metrics"] = operation_metrics_collector
+
+    system_metrics_collector = None
+    if app.config.get("METRICS_HISTORY_ENABLED", False):
+        from .system_metrics import SystemMetricsCollector
+        system_metrics_collector = SystemMetricsCollector(
+            storage_root,
+            interval_minutes=app.config.get("METRICS_HISTORY_INTERVAL_MINUTES", 5),
+            retention_hours=app.config.get("METRICS_HISTORY_RETENTION_HOURS", 24),
+        )
+        system_metrics_collector.set_storage(storage)
+    app.extensions["system_metrics"] = system_metrics_collector
+
+    site_sync_worker = None
+    if app.config.get("SITE_SYNC_ENABLED", False):
+        from .site_sync import SiteSyncWorker
+        site_sync_worker = SiteSyncWorker(
+            storage=storage,
+            connections=connections,
+            replication_manager=replication,
+            storage_root=storage_root,
+            interval_seconds=app.config.get("SITE_SYNC_INTERVAL_SECONDS", 60),
+            batch_size=app.config.get("SITE_SYNC_BATCH_SIZE", 100),
+            connect_timeout=app.config.get("SITE_SYNC_CONNECT_TIMEOUT_SECONDS", 10),
+            read_timeout=app.config.get("SITE_SYNC_READ_TIMEOUT_SECONDS", 120),
+            max_retries=app.config.get("SITE_SYNC_MAX_RETRIES", 2),
+            clock_skew_tolerance_seconds=app.config.get("SITE_SYNC_CLOCK_SKEW_TOLERANCE_SECONDS", 1.0),
+        )
+        site_sync_worker.start()
+    app.extensions["site_sync"] = site_sync_worker
 
     @app.errorhandler(500)
     def internal_error(error):
-        return render_template('500.html'), 500
+        wants_html = request.accept_mimetypes.accept_html
+        path = request.path or ""
+        if include_ui and wants_html and (path.startswith("/ui") or path == "/"):
+            return render_template('500.html'), 500
+        error_xml = (
+            '<?xml version="1.0" encoding="UTF-8"?>'
+            '<Error>'
+            '<Code>InternalError</Code>'
+            '<Message>An internal server error occurred</Message>'
+            f'<Resource>{path}</Resource>'
+            f'<RequestId>{getattr(g, "request_id", "-")}</RequestId>'
+            '</Error>'
+        )
+        return error_xml, 500, {'Content-Type': 'application/xml'}
 
     @app.errorhandler(CSRFError)
     def handle_csrf_error(e):
-        return render_template('csrf_error.html', reason=e.description), 400
+        wants_html = request.accept_mimetypes.accept_html
+        path = request.path or ""
+        if include_ui and wants_html and (path.startswith("/ui") or path == "/"):
+            return render_template('csrf_error.html', reason=e.description), 400
+        error_xml = (
+            '<?xml version="1.0" encoding="UTF-8"?>'
+            '<Error>'
+            '<Code>CSRFError</Code>'
+            f'<Message>{e.description}</Message>'
+            f'<Resource>{path}</Resource>'
+            f'<RequestId>{getattr(g, "request_id", "-")}</RequestId>'
+            '</Error>'
+        )
+        return error_xml, 400, {'Content-Type': 'application/xml'}
 
     @app.template_filter("filesizeformat")
     def filesizeformat(value: int) -> str:
@@ -177,24 +324,60 @@ def create_app(
 
     @app.template_filter("timestamp_to_datetime")
     def timestamp_to_datetime(value: float) -> str:
-        """Format Unix timestamp as human-readable datetime."""
-        from datetime import datetime
+        """Format Unix timestamp as human-readable datetime in configured timezone."""
+        from datetime import datetime, timezone as dt_timezone
+        from zoneinfo import ZoneInfo
         if not value:
             return "Never"
         try:
-            dt = datetime.fromtimestamp(value)
-            return dt.strftime("%Y-%m-%d %H:%M:%S")
+            dt_utc = datetime.fromtimestamp(value, dt_timezone.utc)
+            display_tz = app.config.get("DISPLAY_TIMEZONE", "UTC")
+            if display_tz and display_tz != "UTC":
+                try:
+                    tz = ZoneInfo(display_tz)
+                    dt_local = dt_utc.astimezone(tz)
+                    return dt_local.strftime("%Y-%m-%d %H:%M:%S")
+                except (KeyError, ValueError):
+                    pass 
+            return dt_utc.strftime("%Y-%m-%d %H:%M:%S UTC")
         except (ValueError, OSError):
             return "Unknown"
 
+    @app.template_filter("format_datetime")
+    def format_datetime_filter(dt, include_tz: bool = True) -> str:
+        """Format datetime object as human-readable string in configured timezone."""
+        from datetime import datetime, timezone as dt_timezone
+        from zoneinfo import ZoneInfo
+        if not dt:
+            return ""
+        try:
+            display_tz = app.config.get("DISPLAY_TIMEZONE", "UTC")
+            if display_tz and display_tz != "UTC":
+                try:
+                    tz = ZoneInfo(display_tz)
+                    if dt.tzinfo is None:
+                        dt = dt.replace(tzinfo=dt_timezone.utc)
+                    dt = dt.astimezone(tz)
+                except (KeyError, ValueError):
+                    pass
+            tz_abbr = dt.strftime("%Z") or "UTC"
+            if include_tz:
+                return f"{dt.strftime('%b %d, %Y %H:%M')} ({tz_abbr})"
+            return dt.strftime("%b %d, %Y %H:%M")
+        except (ValueError, AttributeError):
+            return str(dt)
+
     if include_api:
         from .s3_api import s3_api_bp
         from .kms_api import kms_api_bp
+        from .admin_api import admin_api_bp
 
         app.register_blueprint(s3_api_bp)
         app.register_blueprint(kms_api_bp)
+        app.register_blueprint(admin_api_bp)
         csrf.exempt(s3_api_bp)
         csrf.exempt(kms_api_bp)
+        csrf.exempt(admin_api_bp)
 
     if include_ui:
         from .ui import ui_bp
@@ -214,9 +397,9 @@ def create_app(
                 return render_template("404.html"), 404
         return error
 
-    @app.get("/healthz")
+    @app.get("/myfsio/health")
     def healthcheck() -> Dict[str, str]:
-        return {"status": "ok", "version": app.config.get("APP_VERSION", "unknown")}
+        return {"status": "ok"}
 
     return app
 
@@ -244,7 +427,7 @@ def _configure_cors(app: Flask) -> None:
 class _RequestContextFilter(logging.Filter):
     """Inject request-specific attributes into log records."""
 
-    def filter(self, record: logging.LogRecord) -> bool:  # pragma: no cover - simple boilerplate
+    def filter(self, record: logging.LogRecord) -> bool:  
         if has_request_context():
             record.request_id = getattr(g, "request_id", "-")
             record.path = request.path
@@ -262,17 +445,17 @@ def _configure_logging(app: Flask) -> None:
     formatter = logging.Formatter(
         "%(asctime)s | %(levelname)s | %(request_id)s | %(method)s %(path)s | %(message)s"
     )
-    
-    # Stream Handler (stdout) - Primary for Docker
+
     stream_handler = logging.StreamHandler(sys.stdout)
     stream_handler.setFormatter(formatter)
     stream_handler.addFilter(_RequestContextFilter())
 
     logger = app.logger
+    for handler in logger.handlers[:]:
+        handler.close()
     logger.handlers.clear()
     logger.addHandler(stream_handler)
 
-    # File Handler (optional, if configured)
     if app.config.get("LOG_TO_FILE"):
         log_file = Path(app.config["LOG_FILE"])
         log_file.parent.mkdir(parents=True, exist_ok=True)
@@ -292,11 +475,134 @@ def _configure_logging(app: Flask) -> None:
     def _log_request_start() -> None:
         g.request_id = uuid.uuid4().hex
         g.request_started_at = time.perf_counter()
+        g.request_bytes_in = request.content_length or 0
         app.logger.info(
             "Request started",
             extra={"path": request.path, "method": request.method, "remote_addr": request.remote_addr},
         )
 
+    @app.before_request
+    def _maybe_serve_website():
+        if not app.config.get("WEBSITE_HOSTING_ENABLED"):
+            return None
+        if request.method not in {"GET", "HEAD"}:
+            return None
+        host = request.host
+        if ":" in host:
+            host = host.rsplit(":", 1)[0]
+        host = host.lower()
+        store = app.extensions.get("website_domains")
+        if not store:
+            return None
+        bucket = store.get_bucket(host)
+        if not bucket:
+            return None
+        storage = app.extensions["object_storage"]
+        if not storage.bucket_exists(bucket):
+            return _website_error_response(404, "Not Found")
+        website_config = storage.get_bucket_website(bucket)
+        if not website_config:
+            return _website_error_response(404, "Not Found")
+        index_doc = website_config.get("index_document", "index.html")
+        error_doc = website_config.get("error_document")
+        req_path = request.path.lstrip("/")
+        if not req_path or req_path.endswith("/"):
+            object_key = req_path + index_doc
+        else:
+            object_key = req_path
+        try:
+            obj_path = storage.get_object_path(bucket, object_key)
+        except (StorageError, OSError):
+            if object_key == req_path:
+                try:
+                    obj_path = storage.get_object_path(bucket, req_path + "/" + index_doc)
+                    object_key = req_path + "/" + index_doc
+                except (StorageError, OSError):
+                    return _serve_website_error(storage, bucket, error_doc, 404)
+            else:
+                return _serve_website_error(storage, bucket, error_doc, 404)
+        content_type = mimetypes.guess_type(object_key)[0] or "application/octet-stream"
+        is_encrypted = False
+        try:
+            metadata = storage.get_object_metadata(bucket, object_key)
+            is_encrypted = "x-amz-server-side-encryption" in metadata
+        except (StorageError, OSError):
+            pass
+        if request.method == "HEAD":
+            response = Response(status=200)
+            if is_encrypted and hasattr(storage, "get_object_data"):
+                try:
+                    data, _ = storage.get_object_data(bucket, object_key)
+                    response.headers["Content-Length"] = len(data)
+                except (StorageError, OSError):
+                    return _website_error_response(500, "Internal Server Error")
+            else:
+                try:
+                    stat = obj_path.stat()
+                    response.headers["Content-Length"] = stat.st_size
+                except OSError:
+                    return _website_error_response(500, "Internal Server Error")
+            response.headers["Content-Type"] = content_type
+            return response
+        if is_encrypted and hasattr(storage, "get_object_data"):
+            try:
+                data, _ = storage.get_object_data(bucket, object_key)
+                response = Response(data, mimetype=content_type)
+                response.headers["Content-Length"] = len(data)
+                return response
+            except (StorageError, OSError):
+                return _website_error_response(500, "Internal Server Error")
+        def _stream(file_path):
+            with file_path.open("rb") as f:
+                while True:
+                    chunk = f.read(65536)
+                    if not chunk:
+                        break
+                    yield chunk
+        try:
+            stat = obj_path.stat()
+            response = Response(_stream(obj_path), mimetype=content_type, direct_passthrough=True)
+            response.headers["Content-Length"] = stat.st_size
+            return response
+        except OSError:
+            return _website_error_response(500, "Internal Server Error")
+
+    def _serve_website_error(storage, bucket, error_doc_key, status_code):
+        if not error_doc_key:
+            return _website_error_response(status_code, "Not Found" if status_code == 404 else "Error")
+        try:
+            obj_path = storage.get_object_path(bucket, error_doc_key)
+        except (StorageError, OSError):
+            return _website_error_response(status_code, "Not Found")
+        content_type = mimetypes.guess_type(error_doc_key)[0] or "text/html"
+        is_encrypted = False
+        try:
+            metadata = storage.get_object_metadata(bucket, error_doc_key)
+            is_encrypted = "x-amz-server-side-encryption" in metadata
+        except (StorageError, OSError):
+            pass
+        if is_encrypted and hasattr(storage, "get_object_data"):
+            try:
+                data, _ = storage.get_object_data(bucket, error_doc_key)
+                response = Response(data, status=status_code, mimetype=content_type)
+                response.headers["Content-Length"] = len(data)
+                return response
+            except (StorageError, OSError):
+                return _website_error_response(status_code, "Not Found")
+        try:
+            data = obj_path.read_bytes()
+            response = Response(data, status=status_code, mimetype=content_type)
+            response.headers["Content-Length"] = len(data)
+            return response
+        except OSError:
+            return _website_error_response(status_code, "Not Found")
+
+    def _website_error_response(status_code, message):
+        safe_msg = html_module.escape(str(message))
+        safe_code = html_module.escape(str(status_code))
+        body = f"<html><head><title>{safe_code} {safe_msg}</title></head><body><h1>{safe_code} {safe_msg}</h1></body></html>"
+        return Response(body, status=status_code, mimetype="text/html")
+
     @app.after_request
     def _log_request_end(response):
         duration_ms = 0.0
@@ -313,4 +619,21 @@ def _configure_logging(app: Flask) -> None:
             },
         )
         response.headers["X-Request-Duration-ms"] = f"{duration_ms:.2f}"
+
+        operation_metrics = app.extensions.get("operation_metrics")
+        if operation_metrics:
+            bytes_in = getattr(g, "request_bytes_in", 0)
+            bytes_out = response.content_length or 0
+            error_code = getattr(g, "s3_error_code", None)
+            endpoint_type = classify_endpoint(request.path)
+            operation_metrics.record_request(
+                method=request.method,
+                endpoint_type=endpoint_type,
+                status_code=response.status_code,
+                latency_ms=duration_ms,
+                bytes_in=bytes_in,
+                bytes_out=bytes_out,
+                error_code=error_code,
+            )
+
         return response

app/access_logging.py

@@ -0,0 +1,265 @@
+from __future__ import annotations
+
+import io
+import json
+import logging
+import queue
+import threading
+import time
+import uuid
+from dataclasses import dataclass, field
+from datetime import datetime, timezone
+from pathlib import Path
+from typing import Any, Dict, List, Optional
+
+logger = logging.getLogger(__name__)
+
+
+@dataclass
+class AccessLogEntry:
+    bucket_owner: str = "-"
+    bucket: str = "-"
+    timestamp: datetime = field(default_factory=lambda: datetime.now(timezone.utc))
+    remote_ip: str = "-"
+    requester: str = "-"
+    request_id: str = field(default_factory=lambda: uuid.uuid4().hex[:16].upper())
+    operation: str = "-"
+    key: str = "-"
+    request_uri: str = "-"
+    http_status: int = 200
+    error_code: str = "-"
+    bytes_sent: int = 0
+    object_size: int = 0
+    total_time_ms: int = 0
+    turn_around_time_ms: int = 0
+    referrer: str = "-"
+    user_agent: str = "-"
+    version_id: str = "-"
+    host_id: str = "-"
+    signature_version: str = "SigV4"
+    cipher_suite: str = "-"
+    authentication_type: str = "AuthHeader"
+    host_header: str = "-"
+    tls_version: str = "-"
+
+    def to_log_line(self) -> str:
+        time_str = self.timestamp.strftime("[%d/%b/%Y:%H:%M:%S %z]")
+        return (
+            f'{self.bucket_owner} {self.bucket} {time_str} {self.remote_ip} '
+            f'{self.requester} {self.request_id} {self.operation} {self.key} '
+            f'"{self.request_uri}" {self.http_status} {self.error_code or "-"} '
+            f'{self.bytes_sent or "-"} {self.object_size or "-"} {self.total_time_ms or "-"} '
+            f'{self.turn_around_time_ms or "-"} "{self.referrer}" "{self.user_agent}" {self.version_id}'
+        )
+
+    def to_dict(self) -> Dict[str, Any]:
+        return {
+            "bucket_owner": self.bucket_owner,
+            "bucket": self.bucket,
+            "timestamp": self.timestamp.isoformat(),
+            "remote_ip": self.remote_ip,
+            "requester": self.requester,
+            "request_id": self.request_id,
+            "operation": self.operation,
+            "key": self.key,
+            "request_uri": self.request_uri,
+            "http_status": self.http_status,
+            "error_code": self.error_code,
+            "bytes_sent": self.bytes_sent,
+            "object_size": self.object_size,
+            "total_time_ms": self.total_time_ms,
+            "referrer": self.referrer,
+            "user_agent": self.user_agent,
+            "version_id": self.version_id,
+        }
+
+
+@dataclass
+class LoggingConfiguration:
+    target_bucket: str
+    target_prefix: str = ""
+    enabled: bool = True
+
+    def to_dict(self) -> Dict[str, Any]:
+        return {
+            "LoggingEnabled": {
+                "TargetBucket": self.target_bucket,
+                "TargetPrefix": self.target_prefix,
+            }
+        }
+
+    @classmethod
+    def from_dict(cls, data: Dict[str, Any]) -> Optional["LoggingConfiguration"]:
+        logging_enabled = data.get("LoggingEnabled")
+        if not logging_enabled:
+            return None
+        return cls(
+            target_bucket=logging_enabled.get("TargetBucket", ""),
+            target_prefix=logging_enabled.get("TargetPrefix", ""),
+            enabled=True,
+        )
+
+
+class AccessLoggingService:
+    def __init__(self, storage_root: Path, flush_interval: int = 60, max_buffer_size: int = 1000):
+        self.storage_root = storage_root
+        self.flush_interval = flush_interval
+        self.max_buffer_size = max_buffer_size
+        self._configs: Dict[str, LoggingConfiguration] = {}
+        self._buffer: Dict[str, List[AccessLogEntry]] = {}
+        self._buffer_lock = threading.Lock()
+        self._shutdown = threading.Event()
+        self._storage = None
+
+        self._flush_thread = threading.Thread(target=self._flush_loop, name="access-log-flush", daemon=True)
+        self._flush_thread.start()
+
+    def set_storage(self, storage: Any) -> None:
+        self._storage = storage
+
+    def _config_path(self, bucket_name: str) -> Path:
+        return self.storage_root / ".myfsio.sys" / "buckets" / bucket_name / "logging.json"
+
+    def get_bucket_logging(self, bucket_name: str) -> Optional[LoggingConfiguration]:
+        if bucket_name in self._configs:
+            return self._configs[bucket_name]
+
+        config_path = self._config_path(bucket_name)
+        if not config_path.exists():
+            return None
+
+        try:
+            data = json.loads(config_path.read_text(encoding="utf-8"))
+            config = LoggingConfiguration.from_dict(data)
+            if config:
+                self._configs[bucket_name] = config
+            return config
+        except (json.JSONDecodeError, OSError) as e:
+            logger.warning(f"Failed to load logging config for {bucket_name}: {e}")
+            return None
+
+    def set_bucket_logging(self, bucket_name: str, config: LoggingConfiguration) -> None:
+        config_path = self._config_path(bucket_name)
+        config_path.parent.mkdir(parents=True, exist_ok=True)
+        config_path.write_text(json.dumps(config.to_dict(), indent=2), encoding="utf-8")
+        self._configs[bucket_name] = config
+
+    def delete_bucket_logging(self, bucket_name: str) -> None:
+        config_path = self._config_path(bucket_name)
+        try:
+            if config_path.exists():
+                config_path.unlink()
+        except OSError:
+            pass
+        self._configs.pop(bucket_name, None)
+
+    def log_request(
+        self,
+        bucket_name: str,
+        *,
+        operation: str,
+        key: str = "-",
+        remote_ip: str = "-",
+        requester: str = "-",
+        request_uri: str = "-",
+        http_status: int = 200,
+        error_code: str = "",
+        bytes_sent: int = 0,
+        object_size: int = 0,
+        total_time_ms: int = 0,
+        referrer: str = "-",
+        user_agent: str = "-",
+        version_id: str = "-",
+        request_id: str = "",
+    ) -> None:
+        config = self.get_bucket_logging(bucket_name)
+        if not config or not config.enabled:
+            return
+
+        entry = AccessLogEntry(
+            bucket_owner="local-owner",
+            bucket=bucket_name,
+            remote_ip=remote_ip,
+            requester=requester,
+            request_id=request_id or uuid.uuid4().hex[:16].upper(),
+            operation=operation,
+            key=key,
+            request_uri=request_uri,
+            http_status=http_status,
+            error_code=error_code,
+            bytes_sent=bytes_sent,
+            object_size=object_size,
+            total_time_ms=total_time_ms,
+            referrer=referrer,
+            user_agent=user_agent,
+            version_id=version_id,
+        )
+
+        target_key = f"{config.target_bucket}:{config.target_prefix}"
+        should_flush = False
+        with self._buffer_lock:
+            if target_key not in self._buffer:
+                self._buffer[target_key] = []
+            self._buffer[target_key].append(entry)
+            should_flush = len(self._buffer[target_key]) >= self.max_buffer_size
+
+        if should_flush:
+            self._flush_buffer(target_key)
+
+    def _flush_loop(self) -> None:
+        while not self._shutdown.is_set():
+            self._shutdown.wait(timeout=self.flush_interval)
+            if not self._shutdown.is_set():
+                self._flush_all()
+
+    def _flush_all(self) -> None:
+        with self._buffer_lock:
+            targets = list(self._buffer.keys())
+
+        for target_key in targets:
+            self._flush_buffer(target_key)
+
+    def _flush_buffer(self, target_key: str) -> None:
+        with self._buffer_lock:
+            entries = self._buffer.pop(target_key, [])
+
+        if not entries or not self._storage:
+            return
+
+        try:
+            bucket_name, prefix = target_key.split(":", 1)
+        except ValueError:
+            logger.error(f"Invalid target key: {target_key}")
+            return
+
+        now = datetime.now(timezone.utc)
+        log_key = f"{prefix}{now.strftime('%Y-%m-%d-%H-%M-%S')}-{uuid.uuid4().hex[:8]}"
+
+        log_content = "\n".join(entry.to_log_line() for entry in entries) + "\n"
+
+        try:
+            stream = io.BytesIO(log_content.encode("utf-8"))
+            self._storage.put_object(bucket_name, log_key, stream, enforce_quota=False)
+            logger.info(f"Flushed {len(entries)} access log entries to {bucket_name}/{log_key}")
+        except Exception as e:
+            logger.error(f"Failed to write access log to {bucket_name}/{log_key}: {e}")
+            with self._buffer_lock:
+                if target_key not in self._buffer:
+                    self._buffer[target_key] = []
+                self._buffer[target_key] = entries + self._buffer[target_key]
+
+    def flush(self) -> None:
+        self._flush_all()
+
+    def shutdown(self) -> None:
+        self._shutdown.set()
+        self._flush_all()
+        self._flush_thread.join(timeout=5.0)
+
+    def get_stats(self) -> Dict[str, Any]:
+        with self._buffer_lock:
+            buffered = sum(len(entries) for entries in self._buffer.values())
+        return {
+            "buffered_entries": buffered,
+            "target_buckets": len(self._buffer),
+        }

app/acl.py

@@ -0,0 +1,204 @@
+from __future__ import annotations
+
+import json
+from dataclasses import dataclass, field
+from pathlib import Path
+from typing import Any, Dict, List, Optional, Set
+
+
+ACL_PERMISSION_FULL_CONTROL = "FULL_CONTROL"
+ACL_PERMISSION_WRITE = "WRITE"
+ACL_PERMISSION_WRITE_ACP = "WRITE_ACP"
+ACL_PERMISSION_READ = "READ"
+ACL_PERMISSION_READ_ACP = "READ_ACP"
+
+ALL_PERMISSIONS = {
+    ACL_PERMISSION_FULL_CONTROL,
+    ACL_PERMISSION_WRITE,
+    ACL_PERMISSION_WRITE_ACP,
+    ACL_PERMISSION_READ,
+    ACL_PERMISSION_READ_ACP,
+}
+
+PERMISSION_TO_ACTIONS = {
+    ACL_PERMISSION_FULL_CONTROL: {"read", "write", "delete", "list", "share"},
+    ACL_PERMISSION_WRITE: {"write", "delete"},
+    ACL_PERMISSION_WRITE_ACP: {"share"},
+    ACL_PERMISSION_READ: {"read", "list"},
+    ACL_PERMISSION_READ_ACP: {"share"},
+}
+
+GRANTEE_ALL_USERS = "*"
+GRANTEE_AUTHENTICATED_USERS = "authenticated"
+
+
+@dataclass
+class AclGrant:
+    grantee: str
+    permission: str
+
+    def to_dict(self) -> Dict[str, str]:
+        return {"grantee": self.grantee, "permission": self.permission}
+
+    @classmethod
+    def from_dict(cls, data: Dict[str, str]) -> "AclGrant":
+        return cls(grantee=data["grantee"], permission=data["permission"])
+
+
+@dataclass
+class Acl:
+    owner: str
+    grants: List[AclGrant] = field(default_factory=list)
+
+    def to_dict(self) -> Dict[str, Any]:
+        return {
+            "owner": self.owner,
+            "grants": [g.to_dict() for g in self.grants],
+        }
+
+    @classmethod
+    def from_dict(cls, data: Dict[str, Any]) -> "Acl":
+        return cls(
+            owner=data.get("owner", ""),
+            grants=[AclGrant.from_dict(g) for g in data.get("grants", [])],
+        )
+
+    def get_allowed_actions(self, principal_id: Optional[str], is_authenticated: bool = True) -> Set[str]:
+        actions: Set[str] = set()
+        if principal_id and principal_id == self.owner:
+            actions.update(PERMISSION_TO_ACTIONS[ACL_PERMISSION_FULL_CONTROL])
+        for grant in self.grants:
+            if grant.grantee == GRANTEE_ALL_USERS:
+                actions.update(PERMISSION_TO_ACTIONS.get(grant.permission, set()))
+            elif grant.grantee == GRANTEE_AUTHENTICATED_USERS and is_authenticated:
+                actions.update(PERMISSION_TO_ACTIONS.get(grant.permission, set()))
+            elif principal_id and grant.grantee == principal_id:
+                actions.update(PERMISSION_TO_ACTIONS.get(grant.permission, set()))
+        return actions
+
+
+CANNED_ACLS = {
+    "private": lambda owner: Acl(
+        owner=owner,
+        grants=[AclGrant(grantee=owner, permission=ACL_PERMISSION_FULL_CONTROL)],
+    ),
+    "public-read": lambda owner: Acl(
+        owner=owner,
+        grants=[
+            AclGrant(grantee=owner, permission=ACL_PERMISSION_FULL_CONTROL),
+            AclGrant(grantee=GRANTEE_ALL_USERS, permission=ACL_PERMISSION_READ),
+        ],
+    ),
+    "public-read-write": lambda owner: Acl(
+        owner=owner,
+        grants=[
+            AclGrant(grantee=owner, permission=ACL_PERMISSION_FULL_CONTROL),
+            AclGrant(grantee=GRANTEE_ALL_USERS, permission=ACL_PERMISSION_READ),
+            AclGrant(grantee=GRANTEE_ALL_USERS, permission=ACL_PERMISSION_WRITE),
+        ],
+    ),
+    "authenticated-read": lambda owner: Acl(
+        owner=owner,
+        grants=[
+            AclGrant(grantee=owner, permission=ACL_PERMISSION_FULL_CONTROL),
+            AclGrant(grantee=GRANTEE_AUTHENTICATED_USERS, permission=ACL_PERMISSION_READ),
+        ],
+    ),
+    "bucket-owner-read": lambda owner: Acl(
+        owner=owner,
+        grants=[
+            AclGrant(grantee=owner, permission=ACL_PERMISSION_FULL_CONTROL),
+        ],
+    ),
+    "bucket-owner-full-control": lambda owner: Acl(
+        owner=owner,
+        grants=[
+            AclGrant(grantee=owner, permission=ACL_PERMISSION_FULL_CONTROL),
+        ],
+    ),
+}
+
+
+def create_canned_acl(canned_acl: str, owner: str) -> Acl:
+    factory = CANNED_ACLS.get(canned_acl)
+    if not factory:
+        return CANNED_ACLS["private"](owner)
+    return factory(owner)
+
+
+class AclService:
+    def __init__(self, storage_root: Path):
+        self.storage_root = storage_root
+        self._bucket_acl_cache: Dict[str, Acl] = {}
+
+    def _bucket_acl_path(self, bucket_name: str) -> Path:
+        return self.storage_root / ".myfsio.sys" / "buckets" / bucket_name / ".acl.json"
+
+    def get_bucket_acl(self, bucket_name: str) -> Optional[Acl]:
+        if bucket_name in self._bucket_acl_cache:
+            return self._bucket_acl_cache[bucket_name]
+        acl_path = self._bucket_acl_path(bucket_name)
+        if not acl_path.exists():
+            return None
+        try:
+            data = json.loads(acl_path.read_text(encoding="utf-8"))
+            acl = Acl.from_dict(data)
+            self._bucket_acl_cache[bucket_name] = acl
+            return acl
+        except (OSError, json.JSONDecodeError):
+            return None
+
+    def set_bucket_acl(self, bucket_name: str, acl: Acl) -> None:
+        acl_path = self._bucket_acl_path(bucket_name)
+        acl_path.parent.mkdir(parents=True, exist_ok=True)
+        acl_path.write_text(json.dumps(acl.to_dict(), indent=2), encoding="utf-8")
+        self._bucket_acl_cache[bucket_name] = acl
+
+    def set_bucket_canned_acl(self, bucket_name: str, canned_acl: str, owner: str) -> Acl:
+        acl = create_canned_acl(canned_acl, owner)
+        self.set_bucket_acl(bucket_name, acl)
+        return acl
+
+    def delete_bucket_acl(self, bucket_name: str) -> None:
+        acl_path = self._bucket_acl_path(bucket_name)
+        if acl_path.exists():
+            acl_path.unlink()
+        self._bucket_acl_cache.pop(bucket_name, None)
+
+    def evaluate_bucket_acl(
+        self,
+        bucket_name: str,
+        principal_id: Optional[str],
+        action: str,
+        is_authenticated: bool = True,
+    ) -> bool:
+        acl = self.get_bucket_acl(bucket_name)
+        if not acl:
+            return False
+        allowed_actions = acl.get_allowed_actions(principal_id, is_authenticated)
+        return action in allowed_actions
+
+    def get_object_acl(self, bucket_name: str, object_key: str, object_metadata: Dict[str, Any]) -> Optional[Acl]:
+        acl_data = object_metadata.get("__acl__")
+        if not acl_data:
+            return None
+        try:
+            return Acl.from_dict(acl_data)
+        except (TypeError, KeyError):
+            return None
+
+    def create_object_acl_metadata(self, acl: Acl) -> Dict[str, Any]:
+        return {"__acl__": acl.to_dict()}
+
+    def evaluate_object_acl(
+        self,
+        object_metadata: Dict[str, Any],
+        principal_id: Optional[str],
+        action: str,
+        is_authenticated: bool = True,
+    ) -> bool:
+        acl = self.get_object_acl("", "", object_metadata)
+        if not acl:
+            return False
+        allowed_actions = acl.get_allowed_actions(principal_id, is_authenticated)
+        return action in allowed_actions

app/admin_api.py

@@ -0,0 +1,778 @@
+from __future__ import annotations
+
+import ipaddress
+import json
+import logging
+import re
+import socket
+import time
+from typing import Any, Dict, Optional, Tuple
+from urllib.parse import urlparse
+
+import requests
+from flask import Blueprint, Response, current_app, jsonify, request
+
+from .connections import ConnectionStore
+from .extensions import limiter
+from .iam import IamError, Principal
+from .replication import ReplicationManager
+from .site_registry import PeerSite, SiteInfo, SiteRegistry
+from .website_domains import WebsiteDomainStore, normalize_domain, is_valid_domain
+
+
+def _is_safe_url(url: str, allow_internal: bool = False) -> bool:
+    """Check if a URL is safe to make requests to (not internal/private).
+
+    Args:
+        url: The URL to check.
+        allow_internal: If True, allows internal/private IP addresses.
+                       Use for self-hosted deployments on internal networks.
+    """
+    try:
+        parsed = urlparse(url)
+        hostname = parsed.hostname
+        if not hostname:
+            return False
+        cloud_metadata_hosts = {
+            "metadata.google.internal",
+            "169.254.169.254",
+        }
+        if hostname.lower() in cloud_metadata_hosts:
+            return False
+        if allow_internal:
+            return True
+        blocked_hosts = {
+            "localhost",
+            "127.0.0.1",
+            "0.0.0.0",
+            "::1",
+            "[::1]",
+        }
+        if hostname.lower() in blocked_hosts:
+            return False
+        try:
+            resolved_ip = socket.gethostbyname(hostname)
+            ip = ipaddress.ip_address(resolved_ip)
+            if ip.is_private or ip.is_loopback or ip.is_link_local or ip.is_reserved:
+                return False
+        except (socket.gaierror, ValueError):
+            return False
+        return True
+    except Exception:
+        return False
+
+
+def _validate_endpoint(endpoint: str) -> Optional[str]:
+    """Validate endpoint URL format. Returns error message or None."""
+    try:
+        parsed = urlparse(endpoint)
+        if not parsed.scheme or parsed.scheme not in ("http", "https"):
+            return "Endpoint must be http or https URL"
+        if not parsed.netloc:
+            return "Endpoint must have a host"
+        return None
+    except Exception:
+        return "Invalid endpoint URL"
+
+
+def _validate_priority(priority: Any) -> Optional[str]:
+    """Validate priority value. Returns error message or None."""
+    try:
+        p = int(priority)
+        if p < 0 or p > 1000:
+            return "Priority must be between 0 and 1000"
+        return None
+    except (TypeError, ValueError):
+        return "Priority must be an integer"
+
+
+def _validate_region(region: str) -> Optional[str]:
+    """Validate region format. Returns error message or None."""
+    if not re.match(r"^[a-z]{2,}-[a-z]+-\d+$", region):
+        return "Region must match format like us-east-1"
+    return None
+
+
+def _validate_site_id(site_id: str) -> Optional[str]:
+    """Validate site_id format. Returns error message or None."""
+    if not site_id or len(site_id) > 63:
+        return "site_id must be 1-63 characters"
+    if not re.match(r'^[a-zA-Z0-9][a-zA-Z0-9_-]*$', site_id):
+        return "site_id must start with alphanumeric and contain only alphanumeric, hyphens, underscores"
+    return None
+
+
+logger = logging.getLogger(__name__)
+
+admin_api_bp = Blueprint("admin_api", __name__, url_prefix="/admin")
+
+
+def _require_principal() -> Tuple[Optional[Principal], Optional[Tuple[Dict[str, Any], int]]]:
+    from .s3_api import _require_principal as s3_require_principal
+    return s3_require_principal()
+
+
+def _require_admin() -> Tuple[Optional[Principal], Optional[Tuple[Dict[str, Any], int]]]:
+    principal, error = _require_principal()
+    if error:
+        return None, error
+
+    try:
+        _iam().authorize(principal, None, "iam:*")
+        return principal, None
+    except IamError:
+        return None, _json_error("AccessDenied", "Admin access required", 403)
+
+
+def _site_registry() -> SiteRegistry:
+    return current_app.extensions["site_registry"]
+
+
+def _connections() -> ConnectionStore:
+    return current_app.extensions["connections"]
+
+
+def _replication() -> ReplicationManager:
+    return current_app.extensions["replication"]
+
+
+def _iam():
+    return current_app.extensions["iam"]
+
+
+def _json_error(code: str, message: str, status: int) -> Tuple[Dict[str, Any], int]:
+    return {"error": {"code": code, "message": message}}, status
+
+
+def _get_admin_rate_limit() -> str:
+    return current_app.config.get("RATE_LIMIT_ADMIN", "60 per minute")
+
+
+@admin_api_bp.route("/site", methods=["GET"])
+@limiter.limit(lambda: _get_admin_rate_limit())
+def get_local_site():
+    principal, error = _require_admin()
+    if error:
+        return error
+
+    registry = _site_registry()
+    local_site = registry.get_local_site()
+
+    if local_site:
+        return jsonify(local_site.to_dict())
+
+    config_site_id = current_app.config.get("SITE_ID")
+    config_endpoint = current_app.config.get("SITE_ENDPOINT")
+
+    if config_site_id:
+        return jsonify({
+            "site_id": config_site_id,
+            "endpoint": config_endpoint or "",
+            "region": current_app.config.get("SITE_REGION", "us-east-1"),
+            "priority": current_app.config.get("SITE_PRIORITY", 100),
+            "display_name": config_site_id,
+            "source": "environment",
+        })
+
+    return _json_error("NotFound", "Local site not configured", 404)
+
+
+@admin_api_bp.route("/site", methods=["PUT"])
+@limiter.limit(lambda: _get_admin_rate_limit())
+def update_local_site():
+    principal, error = _require_admin()
+    if error:
+        return error
+
+    payload = request.get_json(silent=True) or {}
+
+    site_id = payload.get("site_id")
+    endpoint = payload.get("endpoint")
+
+    if not site_id:
+        return _json_error("ValidationError", "site_id is required", 400)
+
+    site_id_error = _validate_site_id(site_id)
+    if site_id_error:
+        return _json_error("ValidationError", site_id_error, 400)
+
+    if endpoint:
+        endpoint_error = _validate_endpoint(endpoint)
+        if endpoint_error:
+            return _json_error("ValidationError", endpoint_error, 400)
+
+    if "priority" in payload:
+        priority_error = _validate_priority(payload["priority"])
+        if priority_error:
+            return _json_error("ValidationError", priority_error, 400)
+
+    if "region" in payload:
+        region_error = _validate_region(payload["region"])
+        if region_error:
+            return _json_error("ValidationError", region_error, 400)
+
+    registry = _site_registry()
+    existing = registry.get_local_site()
+
+    site = SiteInfo(
+        site_id=site_id,
+        endpoint=endpoint or "",
+        region=payload.get("region", "us-east-1"),
+        priority=payload.get("priority", 100),
+        display_name=payload.get("display_name", site_id),
+        created_at=existing.created_at if existing else None,
+    )
+
+    registry.set_local_site(site)
+
+    logger.info("Local site updated", extra={"site_id": site_id, "principal": principal.access_key})
+    return jsonify(site.to_dict())
+
+
+@admin_api_bp.route("/sites", methods=["GET"])
+@limiter.limit(lambda: _get_admin_rate_limit())
+def list_all_sites():
+    principal, error = _require_admin()
+    if error:
+        return error
+
+    registry = _site_registry()
+    local = registry.get_local_site()
+    peers = registry.list_peers()
+
+    result = {
+        "local": local.to_dict() if local else None,
+        "peers": [peer.to_dict() for peer in peers],
+        "total_peers": len(peers),
+    }
+
+    return jsonify(result)
+
+
+@admin_api_bp.route("/sites", methods=["POST"])
+@limiter.limit(lambda: _get_admin_rate_limit())
+def register_peer_site():
+    principal, error = _require_admin()
+    if error:
+        return error
+
+    payload = request.get_json(silent=True) or {}
+
+    site_id = payload.get("site_id")
+    endpoint = payload.get("endpoint")
+
+    if not site_id:
+        return _json_error("ValidationError", "site_id is required", 400)
+
+    site_id_error = _validate_site_id(site_id)
+    if site_id_error:
+        return _json_error("ValidationError", site_id_error, 400)
+
+    if not endpoint:
+        return _json_error("ValidationError", "endpoint is required", 400)
+
+    endpoint_error = _validate_endpoint(endpoint)
+    if endpoint_error:
+        return _json_error("ValidationError", endpoint_error, 400)
+
+    region = payload.get("region", "us-east-1")
+    region_error = _validate_region(region)
+    if region_error:
+        return _json_error("ValidationError", region_error, 400)
+
+    priority = payload.get("priority", 100)
+    priority_error = _validate_priority(priority)
+    if priority_error:
+        return _json_error("ValidationError", priority_error, 400)
+
+    registry = _site_registry()
+
+    if registry.get_peer(site_id):
+        return _json_error("AlreadyExists", f"Peer site '{site_id}' already exists", 409)
+
+    connection_id = payload.get("connection_id")
+    if connection_id:
+        if not _connections().get(connection_id):
+            return _json_error("ValidationError", f"Connection '{connection_id}' not found", 400)
+
+    peer = PeerSite(
+        site_id=site_id,
+        endpoint=endpoint,
+        region=region,
+        priority=int(priority),
+        display_name=payload.get("display_name", site_id),
+        connection_id=connection_id,
+    )
+
+    registry.add_peer(peer)
+
+    logger.info("Peer site registered", extra={"site_id": site_id, "principal": principal.access_key})
+    return jsonify(peer.to_dict()), 201
+
+
+@admin_api_bp.route("/sites/<site_id>", methods=["GET"])
+@limiter.limit(lambda: _get_admin_rate_limit())
+def get_peer_site(site_id: str):
+    principal, error = _require_admin()
+    if error:
+        return error
+
+    registry = _site_registry()
+    peer = registry.get_peer(site_id)
+
+    if not peer:
+        return _json_error("NotFound", f"Peer site '{site_id}' not found", 404)
+
+    return jsonify(peer.to_dict())
+
+
+@admin_api_bp.route("/sites/<site_id>", methods=["PUT"])
+@limiter.limit(lambda: _get_admin_rate_limit())
+def update_peer_site(site_id: str):
+    principal, error = _require_admin()
+    if error:
+        return error
+
+    registry = _site_registry()
+    existing = registry.get_peer(site_id)
+
+    if not existing:
+        return _json_error("NotFound", f"Peer site '{site_id}' not found", 404)
+
+    payload = request.get_json(silent=True) or {}
+
+    if "endpoint" in payload:
+        endpoint_error = _validate_endpoint(payload["endpoint"])
+        if endpoint_error:
+            return _json_error("ValidationError", endpoint_error, 400)
+
+    if "priority" in payload:
+        priority_error = _validate_priority(payload["priority"])
+        if priority_error:
+            return _json_error("ValidationError", priority_error, 400)
+
+    if "region" in payload:
+        region_error = _validate_region(payload["region"])
+        if region_error:
+            return _json_error("ValidationError", region_error, 400)
+
+    if "connection_id" in payload:
+        if payload["connection_id"] and not _connections().get(payload["connection_id"]):
+            return _json_error("ValidationError", f"Connection '{payload['connection_id']}' not found", 400)
+
+    peer = PeerSite(
+        site_id=site_id,
+        endpoint=payload.get("endpoint", existing.endpoint),
+        region=payload.get("region", existing.region),
+        priority=payload.get("priority", existing.priority),
+        display_name=payload.get("display_name", existing.display_name),
+        connection_id=payload.get("connection_id", existing.connection_id),
+        created_at=existing.created_at,
+        is_healthy=existing.is_healthy,
+        last_health_check=existing.last_health_check,
+    )
+
+    registry.update_peer(peer)
+
+    logger.info("Peer site updated", extra={"site_id": site_id, "principal": principal.access_key})
+    return jsonify(peer.to_dict())
+
+
+@admin_api_bp.route("/sites/<site_id>", methods=["DELETE"])
+@limiter.limit(lambda: _get_admin_rate_limit())
+def delete_peer_site(site_id: str):
+    principal, error = _require_admin()
+    if error:
+        return error
+
+    registry = _site_registry()
+
+    if not registry.delete_peer(site_id):
+        return _json_error("NotFound", f"Peer site '{site_id}' not found", 404)
+
+    logger.info("Peer site deleted", extra={"site_id": site_id, "principal": principal.access_key})
+    return Response(status=204)
+
+
+@admin_api_bp.route("/sites/<site_id>/health", methods=["GET"])
+@limiter.limit(lambda: _get_admin_rate_limit())
+def check_peer_health(site_id: str):
+    principal, error = _require_admin()
+    if error:
+        return error
+
+    registry = _site_registry()
+    peer = registry.get_peer(site_id)
+
+    if not peer:
+        return _json_error("NotFound", f"Peer site '{site_id}' not found", 404)
+
+    is_healthy = False
+    error_message = None
+
+    if peer.connection_id:
+        connection = _connections().get(peer.connection_id)
+        if connection:
+            is_healthy = _replication().check_endpoint_health(connection)
+        else:
+            error_message = f"Connection '{peer.connection_id}' not found"
+    else:
+        error_message = "No connection configured for this peer"
+
+    registry.update_health(site_id, is_healthy)
+
+    result = {
+        "site_id": site_id,
+        "is_healthy": is_healthy,
+        "checked_at": time.time(),
+    }
+    if error_message:
+        result["error"] = error_message
+
+    return jsonify(result)
+
+
+@admin_api_bp.route("/topology", methods=["GET"])
+@limiter.limit(lambda: _get_admin_rate_limit())
+def get_topology():
+    principal, error = _require_admin()
+    if error:
+        return error
+
+    registry = _site_registry()
+    local = registry.get_local_site()
+    peers = registry.list_peers()
+
+    sites = []
+
+    if local:
+        sites.append({
+            **local.to_dict(),
+            "is_local": True,
+            "is_healthy": True,
+        })
+
+    for peer in peers:
+        sites.append({
+            **peer.to_dict(),
+            "is_local": False,
+        })
+
+    sites.sort(key=lambda s: s.get("priority", 100))
+
+    return jsonify({
+        "sites": sites,
+        "total": len(sites),
+        "healthy_count": sum(1 for s in sites if s.get("is_healthy")),
+    })
+
+
+@admin_api_bp.route("/sites/<site_id>/bidirectional-status", methods=["GET"])
+@limiter.limit(lambda: _get_admin_rate_limit())
+def check_bidirectional_status(site_id: str):
+    principal, error = _require_admin()
+    if error:
+        return error
+
+    registry = _site_registry()
+    peer = registry.get_peer(site_id)
+
+    if not peer:
+        return _json_error("NotFound", f"Peer site '{site_id}' not found", 404)
+
+    local_site = registry.get_local_site()
+    replication = _replication()
+    local_rules = replication.list_rules()
+
+    local_bidir_rules = []
+    for rule in local_rules:
+        if rule.target_connection_id == peer.connection_id and rule.mode == "bidirectional":
+            local_bidir_rules.append({
+                "bucket_name": rule.bucket_name,
+                "target_bucket": rule.target_bucket,
+                "enabled": rule.enabled,
+            })
+
+    result = {
+        "site_id": site_id,
+        "local_site_id": local_site.site_id if local_site else None,
+        "local_endpoint": local_site.endpoint if local_site else None,
+        "local_bidirectional_rules": local_bidir_rules,
+        "local_site_sync_enabled": current_app.config.get("SITE_SYNC_ENABLED", False),
+        "remote_status": None,
+        "issues": [],
+        "is_fully_configured": False,
+    }
+
+    if not local_site or not local_site.site_id:
+        result["issues"].append({
+            "code": "NO_LOCAL_SITE_ID",
+            "message": "Local site identity not configured",
+            "severity": "error",
+        })
+
+    if not local_site or not local_site.endpoint:
+        result["issues"].append({
+            "code": "NO_LOCAL_ENDPOINT",
+            "message": "Local site endpoint not configured (remote site cannot reach back)",
+            "severity": "error",
+        })
+
+    if not peer.connection_id:
+        result["issues"].append({
+            "code": "NO_CONNECTION",
+            "message": "No connection configured for this peer",
+            "severity": "error",
+        })
+        return jsonify(result)
+
+    connection = _connections().get(peer.connection_id)
+    if not connection:
+        result["issues"].append({
+            "code": "CONNECTION_NOT_FOUND",
+            "message": f"Connection '{peer.connection_id}' not found",
+            "severity": "error",
+        })
+        return jsonify(result)
+
+    if not local_bidir_rules:
+        result["issues"].append({
+            "code": "NO_LOCAL_BIDIRECTIONAL_RULES",
+            "message": "No bidirectional replication rules configured on this site",
+            "severity": "warning",
+        })
+
+    if not result["local_site_sync_enabled"]:
+        result["issues"].append({
+            "code": "SITE_SYNC_DISABLED",
+            "message": "Site sync worker is disabled (SITE_SYNC_ENABLED=false). Pull operations will not work.",
+            "severity": "warning",
+        })
+
+    if not replication.check_endpoint_health(connection):
+        result["issues"].append({
+            "code": "REMOTE_UNREACHABLE",
+            "message": "Remote endpoint is not reachable",
+            "severity": "error",
+        })
+        return jsonify(result)
+
+    allow_internal = current_app.config.get("ALLOW_INTERNAL_ENDPOINTS", False)
+    if not _is_safe_url(peer.endpoint, allow_internal=allow_internal):
+        result["issues"].append({
+            "code": "ENDPOINT_NOT_ALLOWED",
+            "message": "Peer endpoint points to cloud metadata service (SSRF protection)",
+            "severity": "error",
+        })
+        return jsonify(result)
+
+    try:
+        admin_url = peer.endpoint.rstrip("/") + "/admin/sites"
+        resp = requests.get(
+            admin_url,
+            timeout=10,
+            headers={
+                "Accept": "application/json",
+                "X-Access-Key": connection.access_key,
+                "X-Secret-Key": connection.secret_key,
+            },
+        )
+
+        if resp.status_code == 200:
+            try:
+                remote_data = resp.json()
+                if not isinstance(remote_data, dict):
+                    raise ValueError("Expected JSON object")
+                remote_local = remote_data.get("local")
+                if remote_local is not None and not isinstance(remote_local, dict):
+                    raise ValueError("Expected 'local' to be an object")
+                remote_peers = remote_data.get("peers", [])
+                if not isinstance(remote_peers, list):
+                    raise ValueError("Expected 'peers' to be a list")
+            except (ValueError, json.JSONDecodeError) as e:
+                logger.warning("Invalid JSON from remote admin API: %s", e)
+                result["remote_status"] = {"reachable": True, "invalid_response": True}
+                result["issues"].append({
+                    "code": "REMOTE_INVALID_RESPONSE",
+                    "message": "Remote admin API returned invalid JSON",
+                    "severity": "warning",
+                })
+                return jsonify(result)
+
+            result["remote_status"] = {
+                "reachable": True,
+                "local_site": remote_local,
+                "site_sync_enabled": None,
+                "has_peer_for_us": False,
+                "peer_connection_configured": False,
+                "has_bidirectional_rules_for_us": False,
+            }
+
+            for rp in remote_peers:
+                if not isinstance(rp, dict):
+                    continue
+                if local_site and (
+                    rp.get("site_id") == local_site.site_id or
+                    rp.get("endpoint") == local_site.endpoint
+                ):
+                    result["remote_status"]["has_peer_for_us"] = True
+                    result["remote_status"]["peer_connection_configured"] = bool(rp.get("connection_id"))
+                    break
+
+            if not result["remote_status"]["has_peer_for_us"]:
+                result["issues"].append({
+                    "code": "REMOTE_NO_PEER_FOR_US",
+                    "message": "Remote site does not have this site registered as a peer",
+                    "severity": "error",
+                })
+            elif not result["remote_status"]["peer_connection_configured"]:
+                result["issues"].append({
+                    "code": "REMOTE_NO_CONNECTION_FOR_US",
+                    "message": "Remote site has us as peer but no connection configured (cannot push back)",
+                    "severity": "error",
+                })
+        elif resp.status_code == 401 or resp.status_code == 403:
+            result["remote_status"] = {
+                "reachable": True,
+                "admin_access_denied": True,
+            }
+            result["issues"].append({
+                "code": "REMOTE_ADMIN_ACCESS_DENIED",
+                "message": "Cannot verify remote configuration (admin access denied)",
+                "severity": "warning",
+            })
+        else:
+            result["remote_status"] = {
+                "reachable": True,
+                "admin_api_error": resp.status_code,
+            }
+            result["issues"].append({
+                "code": "REMOTE_ADMIN_API_ERROR",
+                "message": f"Remote admin API returned status {resp.status_code}",
+                "severity": "warning",
+            })
+    except requests.RequestException as e:
+        logger.warning("Remote admin API unreachable: %s", e)
+        result["remote_status"] = {
+            "reachable": False,
+            "error": "Connection failed",
+        }
+        result["issues"].append({
+            "code": "REMOTE_ADMIN_UNREACHABLE",
+            "message": "Could not reach remote admin API",
+            "severity": "warning",
+        })
+    except Exception as e:
+        logger.warning("Error checking remote bidirectional status: %s", e, exc_info=True)
+        result["issues"].append({
+            "code": "VERIFICATION_ERROR",
+            "message": "Internal error during verification",
+            "severity": "warning",
+        })
+
+    error_issues = [i for i in result["issues"] if i["severity"] == "error"]
+    result["is_fully_configured"] = len(error_issues) == 0 and len(local_bidir_rules) > 0
+
+    return jsonify(result)
+
+
+def _website_domains() -> WebsiteDomainStore:
+    return current_app.extensions["website_domains"]
+
+
+def _storage():
+    return current_app.extensions["object_storage"]
+
+
+@admin_api_bp.route("/website-domains", methods=["GET"])
+@limiter.limit(lambda: _get_admin_rate_limit())
+def list_website_domains():
+    principal, error = _require_admin()
+    if error:
+        return error
+    if not current_app.config.get("WEBSITE_HOSTING_ENABLED", False):
+        return _json_error("InvalidRequest", "Website hosting is not enabled", 400)
+    return jsonify(_website_domains().list_all())
+
+
+@admin_api_bp.route("/website-domains", methods=["POST"])
+@limiter.limit(lambda: _get_admin_rate_limit())
+def create_website_domain():
+    principal, error = _require_admin()
+    if error:
+        return error
+    if not current_app.config.get("WEBSITE_HOSTING_ENABLED", False):
+        return _json_error("InvalidRequest", "Website hosting is not enabled", 400)
+    payload = request.get_json(silent=True) or {}
+    domain = normalize_domain(payload.get("domain") or "")
+    bucket = (payload.get("bucket") or "").strip()
+    if not domain:
+        return _json_error("ValidationError", "domain is required", 400)
+    if not is_valid_domain(domain):
+        return _json_error("ValidationError", f"Invalid domain: '{domain}'", 400)
+    if not bucket:
+        return _json_error("ValidationError", "bucket is required", 400)
+    storage = _storage()
+    if not storage.bucket_exists(bucket):
+        return _json_error("NoSuchBucket", f"Bucket '{bucket}' does not exist", 404)
+    store = _website_domains()
+    existing = store.get_bucket(domain)
+    if existing:
+        return _json_error("Conflict", f"Domain '{domain}' is already mapped to bucket '{existing}'", 409)
+    store.set_mapping(domain, bucket)
+    logger.info("Website domain mapping created: %s -> %s", domain, bucket)
+    return jsonify({"domain": domain, "bucket": bucket}), 201
+
+
+@admin_api_bp.route("/website-domains/<domain>", methods=["GET"])
+@limiter.limit(lambda: _get_admin_rate_limit())
+def get_website_domain(domain: str):
+    principal, error = _require_admin()
+    if error:
+        return error
+    if not current_app.config.get("WEBSITE_HOSTING_ENABLED", False):
+        return _json_error("InvalidRequest", "Website hosting is not enabled", 400)
+    domain = normalize_domain(domain)
+    bucket = _website_domains().get_bucket(domain)
+    if not bucket:
+        return _json_error("NotFound", f"No mapping found for domain '{domain}'", 404)
+    return jsonify({"domain": domain, "bucket": bucket})
+
+
+@admin_api_bp.route("/website-domains/<domain>", methods=["PUT"])
+@limiter.limit(lambda: _get_admin_rate_limit())
+def update_website_domain(domain: str):
+    principal, error = _require_admin()
+    if error:
+        return error
+    if not current_app.config.get("WEBSITE_HOSTING_ENABLED", False):
+        return _json_error("InvalidRequest", "Website hosting is not enabled", 400)
+    domain = normalize_domain(domain)
+    payload = request.get_json(silent=True) or {}
+    bucket = (payload.get("bucket") or "").strip()
+    if not bucket:
+        return _json_error("ValidationError", "bucket is required", 400)
+    storage = _storage()
+    if not storage.bucket_exists(bucket):
+        return _json_error("NoSuchBucket", f"Bucket '{bucket}' does not exist", 404)
+    store = _website_domains()
+    if not store.get_bucket(domain):
+        return _json_error("NotFound", f"No mapping found for domain '{domain}'", 404)
+    store.set_mapping(domain, bucket)
+    logger.info("Website domain mapping updated: %s -> %s", domain, bucket)
+    return jsonify({"domain": domain, "bucket": bucket})
+
+
+@admin_api_bp.route("/website-domains/<domain>", methods=["DELETE"])
+@limiter.limit(lambda: _get_admin_rate_limit())
+def delete_website_domain(domain: str):
+    principal, error = _require_admin()
+    if error:
+        return error
+    if not current_app.config.get("WEBSITE_HOSTING_ENABLED", False):
+        return _json_error("InvalidRequest", "Website hosting is not enabled", 400)
+    domain = normalize_domain(domain)
+    if not _website_domains().delete_mapping(domain):
+        return _json_error("NotFound", f"No mapping found for domain '{domain}'", 404)
+    logger.info("Website domain mapping deleted: %s", domain)
+    return Response(status=204)

app/bucket_policies.py

@@ -1,23 +1,88 @@
-"""Bucket policy loader/enforcer with a subset of AWS semantics."""
 from __future__ import annotations
 
+import ipaddress
 import json
-from dataclasses import dataclass
-from fnmatch import fnmatch
+import re
+import time
+from dataclasses import dataclass, field
+from fnmatch import fnmatch, translate
+from functools import lru_cache
 from pathlib import Path
-from typing import Any, Dict, Iterable, List, Optional, Sequence
+from typing import Any, Dict, Iterable, List, Optional, Pattern, Sequence, Tuple
 
 
 RESOURCE_PREFIX = "arn:aws:s3:::"
 
+
+@lru_cache(maxsize=256)
+def _compile_pattern(pattern: str) -> Pattern[str]:
+    return re.compile(translate(pattern), re.IGNORECASE)
+
+
+def _match_string_like(value: str, pattern: str) -> bool:
+    compiled = _compile_pattern(pattern)
+    return bool(compiled.match(value))
+
+
+def _ip_in_cidr(ip_str: str, cidr: str) -> bool:
+    try:
+        ip = ipaddress.ip_address(ip_str)
+        network = ipaddress.ip_network(cidr, strict=False)
+        return ip in network
+    except ValueError:
+        return False
+
+
+def _evaluate_condition_operator(
+    operator: str,
+    condition_key: str,
+    condition_values: List[str],
+    context: Dict[str, Any],
+) -> bool:
+    context_value = context.get(condition_key)
+    op_lower = operator.lower()
+    if_exists = op_lower.endswith("ifexists")
+    if if_exists:
+        op_lower = op_lower[:-8]
+
+    if context_value is None:
+        return if_exists
+
+    context_value_str = str(context_value)
+    context_value_lower = context_value_str.lower()
+
+    if op_lower == "stringequals":
+        return context_value_str in condition_values
+    elif op_lower == "stringnotequals":
+        return context_value_str not in condition_values
+    elif op_lower == "stringequalsignorecase":
+        return context_value_lower in [v.lower() for v in condition_values]
+    elif op_lower == "stringnotequalsignorecase":
+        return context_value_lower not in [v.lower() for v in condition_values]
+    elif op_lower == "stringlike":
+        return any(_match_string_like(context_value_str, p) for p in condition_values)
+    elif op_lower == "stringnotlike":
+        return not any(_match_string_like(context_value_str, p) for p in condition_values)
+    elif op_lower == "ipaddress":
+        return any(_ip_in_cidr(context_value_str, cidr) for cidr in condition_values)
+    elif op_lower == "notipaddress":
+        return not any(_ip_in_cidr(context_value_str, cidr) for cidr in condition_values)
+    elif op_lower == "bool":
+        bool_val = context_value_lower in ("true", "1", "yes")
+        return str(bool_val).lower() in [v.lower() for v in condition_values]
+    elif op_lower == "null":
+        is_null = context_value is None or context_value == ""
+        expected_null = condition_values[0].lower() in ("true", "1", "yes") if condition_values else True
+        return is_null == expected_null
+
+    return True
+
 ACTION_ALIASES = {
-    # List actions
     "s3:listbucket": "list",
     "s3:listallmybuckets": "list",
     "s3:listbucketversions": "list",
     "s3:listmultipartuploads": "list",
     "s3:listparts": "list",
-    # Read actions
     "s3:getobject": "read",
     "s3:getobjectversion": "read",
     "s3:getobjecttagging": "read",
@@ -26,7 +91,6 @@ ACTION_ALIASES = {
     "s3:getbucketversioning": "read",
     "s3:headobject": "read",
     "s3:headbucket": "read",
-    # Write actions
     "s3:putobject": "write",
     "s3:createbucket": "write",
     "s3:putobjecttagging": "write",
@@ -36,26 +100,30 @@ ACTION_ALIASES = {
     "s3:completemultipartupload": "write",
     "s3:abortmultipartupload": "write",
     "s3:copyobject": "write",
-    # Delete actions
     "s3:deleteobject": "delete",
     "s3:deleteobjectversion": "delete",
     "s3:deletebucket": "delete",
     "s3:deleteobjecttagging": "delete",
-    # Share actions (ACL)
     "s3:putobjectacl": "share",
     "s3:putbucketacl": "share",
     "s3:getbucketacl": "share",
-    # Policy actions
     "s3:putbucketpolicy": "policy",
     "s3:getbucketpolicy": "policy",
     "s3:deletebucketpolicy": "policy",
-    # Replication actions
     "s3:getreplicationconfiguration": "replication",
     "s3:putreplicationconfiguration": "replication",
     "s3:deletereplicationconfiguration": "replication",
     "s3:replicateobject": "replication",
     "s3:replicatetags": "replication",
     "s3:replicatedelete": "replication",
+    "s3:getlifecycleconfiguration": "lifecycle",
+    "s3:putlifecycleconfiguration": "lifecycle",
+    "s3:deletelifecycleconfiguration": "lifecycle",
+    "s3:getbucketlifecycle": "lifecycle",
+    "s3:putbucketlifecycle": "lifecycle",
+    "s3:getbucketcors": "cors",
+    "s3:putbucketcors": "cors",
+    "s3:deletebucketcors": "cors",
 }
 
 
@@ -133,7 +201,20 @@ class BucketPolicyStatement:
     effect: str
     principals: List[str] | str
     actions: List[str]
-    resources: List[tuple[str | None, str | None]]
+    resources: List[Tuple[str | None, str | None]]
+    conditions: Dict[str, Dict[str, List[str]]] = field(default_factory=dict)
+    _compiled_patterns: List[Tuple[str | None, Optional[Pattern[str]]]] | None = None
+
+    def _get_compiled_patterns(self) -> List[Tuple[str | None, Optional[Pattern[str]]]]:
+        if self._compiled_patterns is None:
+            self._compiled_patterns = []
+            for resource_bucket, key_pattern in self.resources:
+                if key_pattern is None:
+                    self._compiled_patterns.append((resource_bucket, None))
+                else:
+                    regex_pattern = translate(key_pattern)
+                    self._compiled_patterns.append((resource_bucket, re.compile(regex_pattern)))
+        return self._compiled_patterns
 
     def matches_principal(self, access_key: Optional[str]) -> bool:
         if self.principals == "*":
@@ -149,18 +230,29 @@ class BucketPolicyStatement:
     def matches_resource(self, bucket: Optional[str], object_key: Optional[str]) -> bool:
         bucket = (bucket or "*").lower()
         key = object_key or ""
-        for resource_bucket, key_pattern in self.resources:
+        for resource_bucket, compiled_pattern in self._get_compiled_patterns():
             resource_bucket = (resource_bucket or "*").lower()
             if resource_bucket not in {"*", bucket}:
                 continue
-            if key_pattern is None:
+            if compiled_pattern is None:
                 if not key:
                     return True
                 continue
-            if fnmatch(key, key_pattern):
+            if compiled_pattern.match(key):
                 return True
         return False
 
+    def matches_condition(self, context: Optional[Dict[str, Any]]) -> bool:
+        if not self.conditions:
+            return True
+        if context is None:
+            context = {}
+        for operator, key_values in self.conditions.items():
+            for condition_key, condition_values in key_values.items():
+                if not _evaluate_condition_operator(operator, condition_key, condition_values, context):
+                    return False
+        return True
+
 
 class BucketPolicyStore:
     """Loads bucket policies from disk and evaluates statements."""
@@ -174,8 +266,16 @@ class BucketPolicyStore:
         self._policies: Dict[str, List[BucketPolicyStatement]] = {}
         self._load()
         self._last_mtime = self._current_mtime()
+        # Performance: Avoid stat() on every request
+        self._last_stat_check = 0.0
+        self._stat_check_interval = 1.0  # Only check mtime every 1 second
 
     def maybe_reload(self) -> None:
+        # Performance: Skip stat check if we checked recently
+        now = time.time()
+        if now - self._last_stat_check < self._stat_check_interval:
+            return
+        self._last_stat_check = now
         current = self._current_mtime()
         if current is None or current == self._last_mtime:
             return
@@ -188,13 +288,13 @@ class BucketPolicyStore:
         except FileNotFoundError:
             return None
 
-    # ------------------------------------------------------------------
     def evaluate(
         self,
         access_key: Optional[str],
         bucket: Optional[str],
         object_key: Optional[str],
         action: str,
+        context: Optional[Dict[str, Any]] = None,
     ) -> str | None:
         bucket = (bucket or "").lower()
         statements = self._policies.get(bucket) or []
@@ -206,6 +306,8 @@ class BucketPolicyStore:
                 continue
             if not statement.matches_resource(bucket, object_key):
                 continue
+            if not statement.matches_condition(context):
+                continue
             if statement.effect == "deny":
                 return "deny"
             decision = "allow"
@@ -229,7 +331,6 @@ class BucketPolicyStore:
         self._policies.pop(bucket, None)
         self._persist()
 
-    # ------------------------------------------------------------------
     def _load(self) -> None:
         try:
             content = self.policy_path.read_text(encoding='utf-8')
@@ -271,6 +372,7 @@ class BucketPolicyStore:
             if not resources:
                 continue
             effect = statement.get("Effect", "Allow").lower()
+            conditions = self._normalize_conditions(statement.get("Condition", {}))
             statements.append(
                 BucketPolicyStatement(
                     sid=statement.get("Sid"),
@@ -278,6 +380,24 @@ class BucketPolicyStore:
                     principals=principals,
                     actions=actions or ["*"],
                     resources=resources,
+                    conditions=conditions,
                 )
             )
-        return statements
+        return statements
+
+    def _normalize_conditions(self, condition_block: Dict[str, Any]) -> Dict[str, Dict[str, List[str]]]:
+        if not condition_block or not isinstance(condition_block, dict):
+            return {}
+        normalized: Dict[str, Dict[str, List[str]]] = {}
+        for operator, key_values in condition_block.items():
+            if not isinstance(key_values, dict):
+                continue
+            normalized[operator] = {}
+            for cond_key, cond_values in key_values.items():
+                if isinstance(cond_values, str):
+                    normalized[operator][cond_key] = [cond_values]
+                elif isinstance(cond_values, list):
+                    normalized[operator][cond_key] = [str(v) for v in cond_values]
+                else:
+                    normalized[operator][cond_key] = [str(cond_values)]
+        return normalized

app/compression.py

@@ -0,0 +1,109 @@
+from __future__ import annotations
+
+import gzip
+import io
+from typing import Callable, Iterable, List, Tuple
+
+COMPRESSIBLE_MIMES = frozenset([
+    'application/json',
+    'application/javascript',
+    'application/xml',
+    'text/html',
+    'text/css',
+    'text/plain',
+    'text/xml',
+    'text/javascript',
+    'application/x-ndjson',
+])
+
+MIN_SIZE_FOR_COMPRESSION = 500
+
+
+class GzipMiddleware:
+    def __init__(self, app: Callable, compression_level: int = 6, min_size: int = MIN_SIZE_FOR_COMPRESSION):
+        self.app = app
+        self.compression_level = compression_level
+        self.min_size = min_size
+
+    def __call__(self, environ: dict, start_response: Callable) -> Iterable[bytes]:
+        accept_encoding = environ.get('HTTP_ACCEPT_ENCODING', '')
+        if 'gzip' not in accept_encoding.lower():
+            return self.app(environ, start_response)
+
+        response_started = False
+        status_code = None
+        response_headers: List[Tuple[str, str]] = []
+        content_type = None
+        content_length = None
+        should_compress = False
+        passthrough = False
+        exc_info_holder = [None]
+
+        def custom_start_response(status: str, headers: List[Tuple[str, str]], exc_info=None):
+            nonlocal response_started, status_code, response_headers, content_type, content_length, should_compress, passthrough
+            response_started = True
+            status_code = int(status.split(' ', 1)[0])
+            response_headers = list(headers)
+            exc_info_holder[0] = exc_info
+
+            for name, value in headers:
+                name_lower = name.lower()
+                if name_lower == 'content-type':
+                    content_type = value.split(';')[0].strip().lower()
+                elif name_lower == 'content-length':
+                    try:
+                        content_length = int(value)
+                    except (ValueError, TypeError):
+                        pass
+                elif name_lower == 'content-encoding':
+                    passthrough = True
+                    return start_response(status, headers, exc_info)
+                elif name_lower == 'x-stream-response':
+                    passthrough = True
+                    return start_response(status, headers, exc_info)
+
+            if content_type and content_type in COMPRESSIBLE_MIMES:
+                if content_length is None or content_length >= self.min_size:
+                    should_compress = True
+            else:
+                passthrough = True
+                return start_response(status, headers, exc_info)
+
+            return None
+
+        app_iter = self.app(environ, custom_start_response)
+
+        if passthrough:
+            return app_iter
+
+        response_body = b''.join(app_iter)
+
+        if not response_started:
+            return [response_body]
+
+        if should_compress and len(response_body) >= self.min_size:
+            buf = io.BytesIO()
+            with gzip.GzipFile(fileobj=buf, mode='wb', compresslevel=self.compression_level) as gz:
+                gz.write(response_body)
+            compressed = buf.getvalue()
+
+            if len(compressed) < len(response_body):
+                response_body = compressed
+                new_headers = []
+                for name, value in response_headers:
+                    if name.lower() not in ('content-length', 'content-encoding'):
+                        new_headers.append((name, value))
+                new_headers.append(('Content-Encoding', 'gzip'))
+                new_headers.append(('Content-Length', str(len(response_body))))
+                new_headers.append(('Vary', 'Accept-Encoding'))
+                response_headers = new_headers
+
+        status_str = f"{status_code} " + {
+            200: "OK", 201: "Created", 204: "No Content", 206: "Partial Content",
+            301: "Moved Permanently", 302: "Found", 304: "Not Modified",
+            400: "Bad Request", 401: "Unauthorized", 403: "Forbidden", 404: "Not Found",
+            405: "Method Not Allowed", 409: "Conflict", 500: "Internal Server Error",
+        }.get(status_code, "Unknown")
+
+        start_response(status_str, response_headers, exc_info_holder[0])
+        return [response_body]

app/config.py

@@ -1,7 +1,7 @@
-"""Configuration helpers for the S3 clone application."""
 from __future__ import annotations
 
 import os
+import re
 import secrets
 import shutil
 import sys
@@ -10,6 +10,30 @@ from dataclasses import dataclass
 from pathlib import Path
 from typing import Any, Dict, Optional
 
+import psutil
+
+
+def _calculate_auto_threads() -> int:
+    cpu_count = psutil.cpu_count(logical=True) or 4
+    return max(1, min(cpu_count * 2, 64))
+
+
+def _calculate_auto_connection_limit() -> int:
+    available_mb = psutil.virtual_memory().available / (1024 * 1024)
+    calculated = int(available_mb / 5)
+    return max(20, min(calculated, 1000))
+
+
+def _calculate_auto_backlog(connection_limit: int) -> int:
+    return max(64, min(connection_limit * 2, 4096))
+
+
+def _validate_rate_limit(value: str) -> str:
+    pattern = r"^\d+\s+per\s+(second|minute|hour|day)$"
+    if not re.match(pattern, value):
+        raise ValueError(f"Invalid rate limit format: {value}. Expected format: '200 per minute'")
+    return value
+
 if getattr(sys, "frozen", False):
     # Running in a PyInstaller bundle
     PROJECT_ROOT = Path(sys._MEIPASS)
@@ -56,6 +80,10 @@ class AppConfig:
     log_backup_count: int
     ratelimit_default: str
     ratelimit_storage_uri: str
+    ratelimit_list_buckets: str
+    ratelimit_bucket_ops: str
+    ratelimit_object_ops: str
+    ratelimit_head_ops: str
     cors_origins: list[str]
     cors_methods: list[str]
     cors_allow_headers: list[str]
@@ -68,11 +96,60 @@ class AppConfig:
     stream_chunk_size: int
     multipart_min_part_size: int
     bucket_stats_cache_ttl: int
+    object_cache_ttl: int
     encryption_enabled: bool
     encryption_master_key_path: Path
     kms_enabled: bool
     kms_keys_path: Path
     default_encryption_algorithm: str
+    display_timezone: str
+    lifecycle_enabled: bool
+    lifecycle_interval_seconds: int
+    metrics_history_enabled: bool
+    metrics_history_retention_hours: int
+    metrics_history_interval_minutes: int
+    operation_metrics_enabled: bool
+    operation_metrics_interval_minutes: int
+    operation_metrics_retention_hours: int
+    server_threads: int
+    server_connection_limit: int
+    server_backlog: int
+    server_channel_timeout: int
+    server_threads_auto: bool
+    server_connection_limit_auto: bool
+    server_backlog_auto: bool
+    site_sync_enabled: bool
+    site_sync_interval_seconds: int
+    site_sync_batch_size: int
+    sigv4_timestamp_tolerance_seconds: int
+    presigned_url_min_expiry_seconds: int
+    presigned_url_max_expiry_seconds: int
+    replication_connect_timeout_seconds: int
+    replication_read_timeout_seconds: int
+    replication_max_retries: int
+    replication_streaming_threshold_bytes: int
+    replication_max_failures_per_bucket: int
+    site_sync_connect_timeout_seconds: int
+    site_sync_read_timeout_seconds: int
+    site_sync_max_retries: int
+    site_sync_clock_skew_tolerance_seconds: float
+    object_key_max_length_bytes: int
+    object_cache_max_size: int
+    bucket_config_cache_ttl_seconds: float
+    object_tag_limit: int
+    encryption_chunk_size_bytes: int
+    kms_generate_data_key_min_bytes: int
+    kms_generate_data_key_max_bytes: int
+    lifecycle_max_history_per_bucket: int
+    site_id: Optional[str]
+    site_endpoint: Optional[str]
+    site_region: str
+    site_priority: int
+    ratelimit_admin: str
+    num_trusted_proxies: int
+    allowed_redirect_hosts: list[str]
+    allow_internal_endpoints: bool
+    website_hosting_enabled: bool
 
     @classmethod
     def from_env(cls, overrides: Optional[Dict[str, Any]] = None) -> "AppConfig":
@@ -82,7 +159,7 @@ class AppConfig:
             return overrides.get(name, os.getenv(name, default))
 
         storage_root = Path(_get("STORAGE_ROOT", PROJECT_ROOT / "data")).resolve()
-        max_upload_size = int(_get("MAX_UPLOAD_SIZE", 1024 * 1024 * 1024))  # 1 GiB default
+        max_upload_size = int(_get("MAX_UPLOAD_SIZE", 1024 * 1024 * 1024)) 
         ui_page_size = int(_get("UI_PAGE_SIZE", 100))
         auth_max_attempts = int(_get("AUTH_MAX_ATTEMPTS", 5))
         auth_lockout_minutes = int(_get("AUTH_LOCKOUT_MINUTES", 15))
@@ -90,6 +167,8 @@ class AppConfig:
         secret_ttl_seconds = int(_get("SECRET_TTL_SECONDS", 300))
         stream_chunk_size = int(_get("STREAM_CHUNK_SIZE", 64 * 1024))
         multipart_min_part_size = int(_get("MULTIPART_MIN_PART_SIZE", 5 * 1024 * 1024))
+        lifecycle_enabled = _get("LIFECYCLE_ENABLED", "false").lower() in ("true", "1", "yes")
+        lifecycle_interval_seconds = int(_get("LIFECYCLE_INTERVAL_SECONDS", 3600))
         default_secret = "dev-secret-key"
         secret_key = str(_get("SECRET_KEY", default_secret))
         
@@ -104,6 +183,10 @@ class AppConfig:
                 try:
                     secret_file.parent.mkdir(parents=True, exist_ok=True)
                     secret_file.write_text(generated)
+                    try:
+                        os.chmod(secret_file, 0o600)
+                    except OSError:
+                        pass
                     secret_key = generated
                 except OSError:
                     secret_key = generated
@@ -139,8 +222,12 @@ class AppConfig:
         log_path = log_dir / str(_get("LOG_FILE", "app.log"))
         log_max_bytes = int(_get("LOG_MAX_BYTES", 5 * 1024 * 1024))
         log_backup_count = int(_get("LOG_BACKUP_COUNT", 3))
-        ratelimit_default = str(_get("RATE_LIMIT_DEFAULT", "200 per minute"))
+        ratelimit_default = _validate_rate_limit(str(_get("RATE_LIMIT_DEFAULT", "200 per minute")))
         ratelimit_storage_uri = str(_get("RATE_LIMIT_STORAGE_URI", "memory://"))
+        ratelimit_list_buckets = _validate_rate_limit(str(_get("RATE_LIMIT_LIST_BUCKETS", "60 per minute")))
+        ratelimit_bucket_ops = _validate_rate_limit(str(_get("RATE_LIMIT_BUCKET_OPS", "120 per minute")))
+        ratelimit_object_ops = _validate_rate_limit(str(_get("RATE_LIMIT_OBJECT_OPS", "240 per minute")))
+        ratelimit_head_ops = _validate_rate_limit(str(_get("RATE_LIMIT_HEAD_OPS", "100 per minute")))
 
         def _csv(value: str, default: list[str]) -> list[str]:
             if not value:
@@ -153,15 +240,85 @@ class AppConfig:
         cors_allow_headers = _csv(str(_get("CORS_ALLOW_HEADERS", "*")), ["*"])
         cors_expose_headers = _csv(str(_get("CORS_EXPOSE_HEADERS", "*")), ["*"])
         session_lifetime_days = int(_get("SESSION_LIFETIME_DAYS", 30))
-        bucket_stats_cache_ttl = int(_get("BUCKET_STATS_CACHE_TTL", 60))  # Default 60 seconds
-        
-        # Encryption settings
+        bucket_stats_cache_ttl = int(_get("BUCKET_STATS_CACHE_TTL", 60))
+        object_cache_ttl = int(_get("OBJECT_CACHE_TTL", 5))
+
         encryption_enabled = str(_get("ENCRYPTION_ENABLED", "0")).lower() in {"1", "true", "yes", "on"}
         encryption_keys_dir = storage_root / ".myfsio.sys" / "keys"
         encryption_master_key_path = Path(_get("ENCRYPTION_MASTER_KEY_PATH", encryption_keys_dir / "master.key")).resolve()
         kms_enabled = str(_get("KMS_ENABLED", "0")).lower() in {"1", "true", "yes", "on"}
         kms_keys_path = Path(_get("KMS_KEYS_PATH", encryption_keys_dir / "kms_keys.json")).resolve()
         default_encryption_algorithm = str(_get("DEFAULT_ENCRYPTION_ALGORITHM", "AES256"))
+        display_timezone = str(_get("DISPLAY_TIMEZONE", "UTC"))
+        metrics_history_enabled = str(_get("METRICS_HISTORY_ENABLED", "0")).lower() in {"1", "true", "yes", "on"}
+        metrics_history_retention_hours = int(_get("METRICS_HISTORY_RETENTION_HOURS", 24))
+        metrics_history_interval_minutes = int(_get("METRICS_HISTORY_INTERVAL_MINUTES", 5))
+        operation_metrics_enabled = str(_get("OPERATION_METRICS_ENABLED", "0")).lower() in {"1", "true", "yes", "on"}
+        operation_metrics_interval_minutes = int(_get("OPERATION_METRICS_INTERVAL_MINUTES", 5))
+        operation_metrics_retention_hours = int(_get("OPERATION_METRICS_RETENTION_HOURS", 24))
+
+        _raw_threads = int(_get("SERVER_THREADS", 0))
+        if _raw_threads == 0:
+            server_threads = _calculate_auto_threads()
+            server_threads_auto = True
+        else:
+            server_threads = _raw_threads
+            server_threads_auto = False
+
+        _raw_conn_limit = int(_get("SERVER_CONNECTION_LIMIT", 0))
+        if _raw_conn_limit == 0:
+            server_connection_limit = _calculate_auto_connection_limit()
+            server_connection_limit_auto = True
+        else:
+            server_connection_limit = _raw_conn_limit
+            server_connection_limit_auto = False
+
+        _raw_backlog = int(_get("SERVER_BACKLOG", 0))
+        if _raw_backlog == 0:
+            server_backlog = _calculate_auto_backlog(server_connection_limit)
+            server_backlog_auto = True
+        else:
+            server_backlog = _raw_backlog
+            server_backlog_auto = False
+
+        server_channel_timeout = int(_get("SERVER_CHANNEL_TIMEOUT", 120))
+        site_sync_enabled = str(_get("SITE_SYNC_ENABLED", "0")).lower() in {"1", "true", "yes", "on"}
+        site_sync_interval_seconds = int(_get("SITE_SYNC_INTERVAL_SECONDS", 60))
+        site_sync_batch_size = int(_get("SITE_SYNC_BATCH_SIZE", 100))
+
+        sigv4_timestamp_tolerance_seconds = int(_get("SIGV4_TIMESTAMP_TOLERANCE_SECONDS", 900))
+        presigned_url_min_expiry_seconds = int(_get("PRESIGNED_URL_MIN_EXPIRY_SECONDS", 1))
+        presigned_url_max_expiry_seconds = int(_get("PRESIGNED_URL_MAX_EXPIRY_SECONDS", 604800))
+        replication_connect_timeout_seconds = int(_get("REPLICATION_CONNECT_TIMEOUT_SECONDS", 5))
+        replication_read_timeout_seconds = int(_get("REPLICATION_READ_TIMEOUT_SECONDS", 30))
+        replication_max_retries = int(_get("REPLICATION_MAX_RETRIES", 2))
+        replication_streaming_threshold_bytes = int(_get("REPLICATION_STREAMING_THRESHOLD_BYTES", 10 * 1024 * 1024))
+        replication_max_failures_per_bucket = int(_get("REPLICATION_MAX_FAILURES_PER_BUCKET", 50))
+        site_sync_connect_timeout_seconds = int(_get("SITE_SYNC_CONNECT_TIMEOUT_SECONDS", 10))
+        site_sync_read_timeout_seconds = int(_get("SITE_SYNC_READ_TIMEOUT_SECONDS", 120))
+        site_sync_max_retries = int(_get("SITE_SYNC_MAX_RETRIES", 2))
+        site_sync_clock_skew_tolerance_seconds = float(_get("SITE_SYNC_CLOCK_SKEW_TOLERANCE_SECONDS", 1.0))
+        object_key_max_length_bytes = int(_get("OBJECT_KEY_MAX_LENGTH_BYTES", 1024))
+        object_cache_max_size = int(_get("OBJECT_CACHE_MAX_SIZE", 100))
+        bucket_config_cache_ttl_seconds = float(_get("BUCKET_CONFIG_CACHE_TTL_SECONDS", 30.0))
+        object_tag_limit = int(_get("OBJECT_TAG_LIMIT", 50))
+        encryption_chunk_size_bytes = int(_get("ENCRYPTION_CHUNK_SIZE_BYTES", 64 * 1024))
+        kms_generate_data_key_min_bytes = int(_get("KMS_GENERATE_DATA_KEY_MIN_BYTES", 1))
+        kms_generate_data_key_max_bytes = int(_get("KMS_GENERATE_DATA_KEY_MAX_BYTES", 1024))
+        lifecycle_max_history_per_bucket = int(_get("LIFECYCLE_MAX_HISTORY_PER_BUCKET", 50))
+
+        site_id_raw = _get("SITE_ID", None)
+        site_id = str(site_id_raw).strip() if site_id_raw else None
+        site_endpoint_raw = _get("SITE_ENDPOINT", None)
+        site_endpoint = str(site_endpoint_raw).strip() if site_endpoint_raw else None
+        site_region = str(_get("SITE_REGION", "us-east-1"))
+        site_priority = int(_get("SITE_PRIORITY", 100))
+        ratelimit_admin = _validate_rate_limit(str(_get("RATE_LIMIT_ADMIN", "60 per minute")))
+        num_trusted_proxies = int(_get("NUM_TRUSTED_PROXIES", 0))
+        allowed_redirect_hosts_raw = _get("ALLOWED_REDIRECT_HOSTS", "")
+        allowed_redirect_hosts = [h.strip() for h in str(allowed_redirect_hosts_raw).split(",") if h.strip()]
+        allow_internal_endpoints = str(_get("ALLOW_INTERNAL_ENDPOINTS", "0")).lower() in {"1", "true", "yes", "on"}
+        website_hosting_enabled = str(_get("WEBSITE_HOSTING_ENABLED", "0")).lower() in {"1", "true", "yes", "on"}
 
         return cls(storage_root=storage_root,
                    max_upload_size=max_upload_size,
@@ -180,6 +337,10 @@ class AppConfig:
                    log_backup_count=log_backup_count,
                    ratelimit_default=ratelimit_default,
                    ratelimit_storage_uri=ratelimit_storage_uri,
+                   ratelimit_list_buckets=ratelimit_list_buckets,
+                   ratelimit_bucket_ops=ratelimit_bucket_ops,
+                   ratelimit_object_ops=ratelimit_object_ops,
+                   ratelimit_head_ops=ratelimit_head_ops,
                    cors_origins=cors_origins,
                    cors_methods=cors_methods,
                    cors_allow_headers=cors_allow_headers,
@@ -192,11 +353,60 @@ class AppConfig:
                    stream_chunk_size=stream_chunk_size,
                    multipart_min_part_size=multipart_min_part_size,
                    bucket_stats_cache_ttl=bucket_stats_cache_ttl,
+                   object_cache_ttl=object_cache_ttl,
                    encryption_enabled=encryption_enabled,
                    encryption_master_key_path=encryption_master_key_path,
                    kms_enabled=kms_enabled,
                    kms_keys_path=kms_keys_path,
-                   default_encryption_algorithm=default_encryption_algorithm)
+                   default_encryption_algorithm=default_encryption_algorithm,
+                   display_timezone=display_timezone,
+                   lifecycle_enabled=lifecycle_enabled,
+                   lifecycle_interval_seconds=lifecycle_interval_seconds,
+                   metrics_history_enabled=metrics_history_enabled,
+                   metrics_history_retention_hours=metrics_history_retention_hours,
+                   metrics_history_interval_minutes=metrics_history_interval_minutes,
+                   operation_metrics_enabled=operation_metrics_enabled,
+                   operation_metrics_interval_minutes=operation_metrics_interval_minutes,
+                   operation_metrics_retention_hours=operation_metrics_retention_hours,
+                   server_threads=server_threads,
+                   server_connection_limit=server_connection_limit,
+                   server_backlog=server_backlog,
+                   server_channel_timeout=server_channel_timeout,
+                   server_threads_auto=server_threads_auto,
+                   server_connection_limit_auto=server_connection_limit_auto,
+                   server_backlog_auto=server_backlog_auto,
+                   site_sync_enabled=site_sync_enabled,
+                   site_sync_interval_seconds=site_sync_interval_seconds,
+                   site_sync_batch_size=site_sync_batch_size,
+                   sigv4_timestamp_tolerance_seconds=sigv4_timestamp_tolerance_seconds,
+                   presigned_url_min_expiry_seconds=presigned_url_min_expiry_seconds,
+                   presigned_url_max_expiry_seconds=presigned_url_max_expiry_seconds,
+                   replication_connect_timeout_seconds=replication_connect_timeout_seconds,
+                   replication_read_timeout_seconds=replication_read_timeout_seconds,
+                   replication_max_retries=replication_max_retries,
+                   replication_streaming_threshold_bytes=replication_streaming_threshold_bytes,
+                   replication_max_failures_per_bucket=replication_max_failures_per_bucket,
+                   site_sync_connect_timeout_seconds=site_sync_connect_timeout_seconds,
+                   site_sync_read_timeout_seconds=site_sync_read_timeout_seconds,
+                   site_sync_max_retries=site_sync_max_retries,
+                   site_sync_clock_skew_tolerance_seconds=site_sync_clock_skew_tolerance_seconds,
+                   object_key_max_length_bytes=object_key_max_length_bytes,
+                   object_cache_max_size=object_cache_max_size,
+                   bucket_config_cache_ttl_seconds=bucket_config_cache_ttl_seconds,
+                   object_tag_limit=object_tag_limit,
+                   encryption_chunk_size_bytes=encryption_chunk_size_bytes,
+                   kms_generate_data_key_min_bytes=kms_generate_data_key_min_bytes,
+                   kms_generate_data_key_max_bytes=kms_generate_data_key_max_bytes,
+                   lifecycle_max_history_per_bucket=lifecycle_max_history_per_bucket,
+                   site_id=site_id,
+                   site_endpoint=site_endpoint,
+                   site_region=site_region,
+                   site_priority=site_priority,
+                   ratelimit_admin=ratelimit_admin,
+                   num_trusted_proxies=num_trusted_proxies,
+                   allowed_redirect_hosts=allowed_redirect_hosts,
+                   allow_internal_endpoints=allow_internal_endpoints,
+                   website_hosting_enabled=website_hosting_enabled)
 
     def validate_and_report(self) -> list[str]:
         """Validate configuration and return a list of warnings/issues.
@@ -206,7 +416,6 @@ class AppConfig:
         """
         issues = []
         
-        # Check if storage_root is writable
         try:
             test_file = self.storage_root / ".write_test"
             test_file.touch()
@@ -214,24 +423,20 @@ class AppConfig:
         except (OSError, PermissionError) as e:
             issues.append(f"CRITICAL: STORAGE_ROOT '{self.storage_root}' is not writable: {e}")
         
-        # Check if storage_root looks like a temp directory
         storage_str = str(self.storage_root).lower()
         if "/tmp" in storage_str or "\\temp" in storage_str or "appdata\\local\\temp" in storage_str:
             issues.append(f"WARNING: STORAGE_ROOT '{self.storage_root}' appears to be a temporary directory. Data may be lost on reboot!")
         
-        # Check if IAM config path is under storage_root
         try:
             self.iam_config_path.relative_to(self.storage_root)
         except ValueError:
             issues.append(f"WARNING: IAM_CONFIG '{self.iam_config_path}' is outside STORAGE_ROOT '{self.storage_root}'. Consider setting IAM_CONFIG explicitly or ensuring paths are aligned.")
         
-        # Check if bucket policy path is under storage_root
         try:
             self.bucket_policy_path.relative_to(self.storage_root)
         except ValueError:
             issues.append(f"WARNING: BUCKET_POLICY_PATH '{self.bucket_policy_path}' is outside STORAGE_ROOT '{self.storage_root}'. Consider setting BUCKET_POLICY_PATH explicitly.")
         
-        # Check if log path is writable
         try:
             self.log_path.parent.mkdir(parents=True, exist_ok=True)
             test_log = self.log_path.parent / ".write_test"
@@ -240,32 +445,56 @@ class AppConfig:
         except (OSError, PermissionError) as e:
             issues.append(f"WARNING: Log directory '{self.log_path.parent}' is not writable: {e}")
         
-        # Check log path location
         log_str = str(self.log_path).lower()
         if "/tmp" in log_str or "\\temp" in log_str or "appdata\\local\\temp" in log_str:
             issues.append(f"WARNING: LOG_DIR '{self.log_path.parent}' appears to be a temporary directory. Logs may be lost on reboot!")
         
-        # Check if encryption keys path is under storage_root (when encryption is enabled)
         if self.encryption_enabled:
             try:
                 self.encryption_master_key_path.relative_to(self.storage_root)
             except ValueError:
                 issues.append(f"WARNING: ENCRYPTION_MASTER_KEY_PATH '{self.encryption_master_key_path}' is outside STORAGE_ROOT. Ensure proper backup procedures.")
         
-        # Check if KMS keys path is under storage_root (when KMS is enabled)
         if self.kms_enabled:
             try:
                 self.kms_keys_path.relative_to(self.storage_root)
             except ValueError:
                 issues.append(f"WARNING: KMS_KEYS_PATH '{self.kms_keys_path}' is outside STORAGE_ROOT. Ensure proper backup procedures.")
         
-        # Warn about production settings
         if self.secret_key == "dev-secret-key":
             issues.append("WARNING: Using default SECRET_KEY. Set SECRET_KEY environment variable for production.")
         
         if "*" in self.cors_origins:
             issues.append("INFO: CORS_ORIGINS is set to '*'. Consider restricting to specific domains in production.")
-        
+
+        if not (1 <= self.server_threads <= 64):
+            issues.append(f"CRITICAL: SERVER_THREADS={self.server_threads} is outside valid range (1-64). Server cannot start.")
+        if not (10 <= self.server_connection_limit <= 1000):
+            issues.append(f"CRITICAL: SERVER_CONNECTION_LIMIT={self.server_connection_limit} is outside valid range (10-1000). Server cannot start.")
+        if not (64 <= self.server_backlog <= 4096):
+            issues.append(f"CRITICAL: SERVER_BACKLOG={self.server_backlog} is outside valid range (64-4096). Server cannot start.")
+        if not (10 <= self.server_channel_timeout <= 300):
+            issues.append(f"CRITICAL: SERVER_CHANNEL_TIMEOUT={self.server_channel_timeout} is outside valid range (10-300). Server cannot start.")
+
+        if sys.platform != "win32":
+            try:
+                import resource
+                soft_limit, _ = resource.getrlimit(resource.RLIMIT_NOFILE)
+                threshold = int(soft_limit * 0.8)
+                if self.server_connection_limit > threshold:
+                    issues.append(f"WARNING: SERVER_CONNECTION_LIMIT={self.server_connection_limit} exceeds 80% of system file descriptor limit (soft={soft_limit}). Consider running 'ulimit -n {self.server_connection_limit + 100}'.")
+            except (ImportError, OSError):
+                pass
+
+        try:
+            import psutil
+            available_mb = psutil.virtual_memory().available / (1024 * 1024)
+            estimated_mb = self.server_threads * 50
+            if estimated_mb > available_mb * 0.5:
+                issues.append(f"WARNING: SERVER_THREADS={self.server_threads} may require ~{estimated_mb}MB memory, exceeding 50% of available RAM ({int(available_mb)}MB).")
+        except ImportError:
+            pass
+
         return issues
 
     def print_startup_summary(self) -> None:
@@ -283,6 +512,14 @@ class AppConfig:
             print(f"  ENCRYPTION:       Enabled (Master key: {self.encryption_master_key_path})")
         if self.kms_enabled:
             print(f"  KMS:              Enabled (Keys: {self.kms_keys_path})")
+        if self.website_hosting_enabled:
+            print(f"  WEBSITE_HOSTING:  Enabled")
+        def _auto(flag: bool) -> str:
+            return " (auto)" if flag else ""
+        print(f"  SERVER_THREADS:   {self.server_threads}{_auto(self.server_threads_auto)}")
+        print(f"  CONNECTION_LIMIT: {self.server_connection_limit}{_auto(self.server_connection_limit_auto)}")
+        print(f"  BACKLOG:          {self.server_backlog}{_auto(self.server_backlog_auto)}")
+        print(f"  CHANNEL_TIMEOUT:  {self.server_channel_timeout}s")
         print("=" * 60)
         
         issues = self.validate_and_report()
@@ -313,6 +550,7 @@ class AppConfig:
             "STREAM_CHUNK_SIZE": self.stream_chunk_size,
             "MULTIPART_MIN_PART_SIZE": self.multipart_min_part_size,
             "BUCKET_STATS_CACHE_TTL": self.bucket_stats_cache_ttl,
+            "OBJECT_CACHE_TTL": self.object_cache_ttl,
             "LOG_LEVEL": self.log_level,
             "LOG_TO_FILE": self.log_to_file,
             "LOG_FILE": str(self.log_path),
@@ -320,6 +558,10 @@ class AppConfig:
             "LOG_BACKUP_COUNT": self.log_backup_count,
             "RATELIMIT_DEFAULT": self.ratelimit_default,
             "RATELIMIT_STORAGE_URI": self.ratelimit_storage_uri,
+            "RATELIMIT_LIST_BUCKETS": self.ratelimit_list_buckets,
+            "RATELIMIT_BUCKET_OPS": self.ratelimit_bucket_ops,
+            "RATELIMIT_OBJECT_OPS": self.ratelimit_object_ops,
+            "RATELIMIT_HEAD_OPS": self.ratelimit_head_ops,
             "CORS_ORIGINS": self.cors_origins,
             "CORS_METHODS": self.cors_methods,
             "CORS_ALLOW_HEADERS": self.cors_allow_headers,
@@ -330,4 +572,49 @@ class AppConfig:
             "KMS_ENABLED": self.kms_enabled,
             "KMS_KEYS_PATH": str(self.kms_keys_path),
             "DEFAULT_ENCRYPTION_ALGORITHM": self.default_encryption_algorithm,
+            "DISPLAY_TIMEZONE": self.display_timezone,
+            "LIFECYCLE_ENABLED": self.lifecycle_enabled,
+            "LIFECYCLE_INTERVAL_SECONDS": self.lifecycle_interval_seconds,
+            "METRICS_HISTORY_ENABLED": self.metrics_history_enabled,
+            "METRICS_HISTORY_RETENTION_HOURS": self.metrics_history_retention_hours,
+            "METRICS_HISTORY_INTERVAL_MINUTES": self.metrics_history_interval_minutes,
+            "OPERATION_METRICS_ENABLED": self.operation_metrics_enabled,
+            "OPERATION_METRICS_INTERVAL_MINUTES": self.operation_metrics_interval_minutes,
+            "OPERATION_METRICS_RETENTION_HOURS": self.operation_metrics_retention_hours,
+            "SERVER_THREADS": self.server_threads,
+            "SERVER_CONNECTION_LIMIT": self.server_connection_limit,
+            "SERVER_BACKLOG": self.server_backlog,
+            "SERVER_CHANNEL_TIMEOUT": self.server_channel_timeout,
+            "SITE_SYNC_ENABLED": self.site_sync_enabled,
+            "SITE_SYNC_INTERVAL_SECONDS": self.site_sync_interval_seconds,
+            "SITE_SYNC_BATCH_SIZE": self.site_sync_batch_size,
+            "SIGV4_TIMESTAMP_TOLERANCE_SECONDS": self.sigv4_timestamp_tolerance_seconds,
+            "PRESIGNED_URL_MIN_EXPIRY_SECONDS": self.presigned_url_min_expiry_seconds,
+            "PRESIGNED_URL_MAX_EXPIRY_SECONDS": self.presigned_url_max_expiry_seconds,
+            "REPLICATION_CONNECT_TIMEOUT_SECONDS": self.replication_connect_timeout_seconds,
+            "REPLICATION_READ_TIMEOUT_SECONDS": self.replication_read_timeout_seconds,
+            "REPLICATION_MAX_RETRIES": self.replication_max_retries,
+            "REPLICATION_STREAMING_THRESHOLD_BYTES": self.replication_streaming_threshold_bytes,
+            "REPLICATION_MAX_FAILURES_PER_BUCKET": self.replication_max_failures_per_bucket,
+            "SITE_SYNC_CONNECT_TIMEOUT_SECONDS": self.site_sync_connect_timeout_seconds,
+            "SITE_SYNC_READ_TIMEOUT_SECONDS": self.site_sync_read_timeout_seconds,
+            "SITE_SYNC_MAX_RETRIES": self.site_sync_max_retries,
+            "SITE_SYNC_CLOCK_SKEW_TOLERANCE_SECONDS": self.site_sync_clock_skew_tolerance_seconds,
+            "OBJECT_KEY_MAX_LENGTH_BYTES": self.object_key_max_length_bytes,
+            "OBJECT_CACHE_MAX_SIZE": self.object_cache_max_size,
+            "BUCKET_CONFIG_CACHE_TTL_SECONDS": self.bucket_config_cache_ttl_seconds,
+            "OBJECT_TAG_LIMIT": self.object_tag_limit,
+            "ENCRYPTION_CHUNK_SIZE_BYTES": self.encryption_chunk_size_bytes,
+            "KMS_GENERATE_DATA_KEY_MIN_BYTES": self.kms_generate_data_key_min_bytes,
+            "KMS_GENERATE_DATA_KEY_MAX_BYTES": self.kms_generate_data_key_max_bytes,
+            "LIFECYCLE_MAX_HISTORY_PER_BUCKET": self.lifecycle_max_history_per_bucket,
+            "SITE_ID": self.site_id,
+            "SITE_ENDPOINT": self.site_endpoint,
+            "SITE_REGION": self.site_region,
+            "SITE_PRIORITY": self.site_priority,
+            "RATE_LIMIT_ADMIN": self.ratelimit_admin,
+            "NUM_TRUSTED_PROXIES": self.num_trusted_proxies,
+            "ALLOWED_REDIRECT_HOSTS": self.allowed_redirect_hosts,
+            "ALLOW_INTERNAL_ENDPOINTS": self.allow_internal_endpoints,
+            "WEBSITE_HOSTING_ENABLED": self.website_hosting_enabled,
         }

app/connections.py

@@ -1,4 +1,3 @@
-"""Manage remote S3 connections."""
 from __future__ import annotations
 
 import json

app/encrypted_storage.py

@@ -1,4 +1,3 @@
-"""Encrypted storage layer that wraps ObjectStorage with encryption support."""
 from __future__ import annotations
 
 import io
@@ -79,7 +78,7 @@ class EncryptedObjectStorage:
         kms_key_id: Optional[str] = None,
     ) -> ObjectMeta:
         """Store an object, optionally with encryption.
-        
+
         Args:
             bucket_name: Name of the bucket
             object_key: Key for the object
@@ -87,42 +86,41 @@ class EncryptedObjectStorage:
             metadata: Optional user metadata
             server_side_encryption: Encryption algorithm ("AES256" or "aws:kms")
             kms_key_id: KMS key ID (for aws:kms encryption)
-        
+
         Returns:
             ObjectMeta with object information
+
+        Performance: Uses streaming encryption for large files to reduce memory usage.
         """
         should_encrypt, algorithm, detected_kms_key = self._should_encrypt(
             bucket_name, server_side_encryption
         )
-        
+
         if kms_key_id is None:
             kms_key_id = detected_kms_key
-        
+
         if should_encrypt:
-            data = stream.read()
-            
             try:
-                ciphertext, enc_metadata = self.encryption.encrypt_object(
-                    data, 
+                # Performance: Use streaming encryption to avoid loading entire file into memory
+                encrypted_stream, enc_metadata = self.encryption.encrypt_stream(
+                    stream,
                     algorithm=algorithm,
-                    kms_key_id=kms_key_id,
                     context={"bucket": bucket_name, "key": object_key},
                 )
-                
+
                 combined_metadata = metadata.copy() if metadata else {}
                 combined_metadata.update(enc_metadata.to_dict())
-                
-                encrypted_stream = io.BytesIO(ciphertext)
+
                 result = self.storage.put_object(
                     bucket_name,
                     object_key,
                     encrypted_stream,
                     metadata=combined_metadata,
                 )
-                
+
                 result.metadata = combined_metadata
                 return result
-                
+
             except EncryptionError as exc:
                 raise StorageError(f"Encryption failed: {exc}") from exc
         else:
@@ -135,33 +133,34 @@ class EncryptedObjectStorage:
     
     def get_object_data(self, bucket_name: str, object_key: str) -> tuple[bytes, Dict[str, str]]:
         """Get object data, decrypting if necessary.
-        
+
         Returns:
             Tuple of (data, metadata)
+
+        Performance: Uses streaming decryption to reduce memory usage.
         """
         path = self.storage.get_object_path(bucket_name, object_key)
         metadata = self.storage.get_object_metadata(bucket_name, object_key)
-        
-        with path.open("rb") as f:
-            data = f.read()
-        
+
         enc_metadata = EncryptionMetadata.from_dict(metadata)
         if enc_metadata:
             try:
-                data = self.encryption.decrypt_object(
-                    data,
-                    enc_metadata,
-                    context={"bucket": bucket_name, "key": object_key},
-                )
+                # Performance: Use streaming decryption to avoid loading entire file into memory
+                with path.open("rb") as f:
+                    decrypted_stream = self.encryption.decrypt_stream(f, enc_metadata)
+                    data = decrypted_stream.read()
             except EncryptionError as exc:
                 raise StorageError(f"Decryption failed: {exc}") from exc
-        
+        else:
+            with path.open("rb") as f:
+                data = f.read()
+
         clean_metadata = {
             k: v for k, v in metadata.items()
-            if not k.startswith("x-amz-encryption") 
+            if not k.startswith("x-amz-encryption")
             and k != "x-amz-encrypted-data-key"
         }
-        
+
         return data, clean_metadata
     
     def get_object_stream(self, bucket_name: str, object_key: str) -> tuple[BinaryIO, Dict[str, str], int]:
@@ -271,9 +270,15 @@ class EncryptedObjectStorage:
     
     def get_bucket_quota(self, bucket_name: str):
         return self.storage.get_bucket_quota(bucket_name)
-    
+
     def set_bucket_quota(self, bucket_name: str, *, max_bytes=None, max_objects=None):
         return self.storage.set_bucket_quota(bucket_name, max_bytes=max_bytes, max_objects=max_objects)
+
+    def get_bucket_website(self, bucket_name: str):
+        return self.storage.get_bucket_website(bucket_name)
+
+    def set_bucket_website(self, bucket_name: str, website_config):
+        return self.storage.set_bucket_website(bucket_name, website_config)
     
     def _compute_etag(self, path: Path) -> str:
         return self.storage._compute_etag(path)

app/encryption.py

@@ -1,15 +1,44 @@
-"""Encryption providers for server-side and client-side encryption."""
 from __future__ import annotations
 
 import base64
 import io
 import json
+import logging
+import os
 import secrets
+import subprocess
+import sys
 from dataclasses import dataclass
 from pathlib import Path
 from typing import Any, BinaryIO, Dict, Generator, Optional
 
 from cryptography.hazmat.primitives.ciphers.aead import AESGCM
+from cryptography.hazmat.primitives.kdf.hkdf import HKDF
+from cryptography.hazmat.primitives import hashes
+
+if sys.platform != "win32":
+    import fcntl
+
+logger = logging.getLogger(__name__)
+
+
+def _set_secure_file_permissions(file_path: Path) -> None:
+    """Set restrictive file permissions (owner read/write only)."""
+    if sys.platform == "win32":
+        try:
+            username = os.environ.get("USERNAME", "")
+            if username:
+                subprocess.run(
+                    ["icacls", str(file_path), "/inheritance:r",
+                     "/grant:r", f"{username}:F"],
+                    check=True, capture_output=True
+                )
+            else:
+                logger.warning("Could not set secure permissions on %s: USERNAME not set", file_path)
+        except (subprocess.SubprocessError, OSError) as exc:
+            logger.warning("Failed to set secure permissions on %s: %s", file_path, exc)
+    else:
+        os.chmod(file_path, 0o600)
 
 
 class EncryptionError(Exception):
@@ -59,22 +88,34 @@ class EncryptionMetadata:
 
 class EncryptionProvider:
     """Base class for encryption providers."""
-    
+
     def encrypt(self, plaintext: bytes, context: Dict[str, str] | None = None) -> EncryptionResult:
         raise NotImplementedError
-    
+
     def decrypt(self, ciphertext: bytes, nonce: bytes, encrypted_data_key: bytes,
                 key_id: str, context: Dict[str, str] | None = None) -> bytes:
         raise NotImplementedError
-    
+
     def generate_data_key(self) -> tuple[bytes, bytes]:
         """Generate a data key and its encrypted form.
-        
+
         Returns:
             Tuple of (plaintext_key, encrypted_key)
         """
         raise NotImplementedError
 
+    def decrypt_data_key(self, encrypted_data_key: bytes, key_id: str | None = None) -> bytes:
+        """Decrypt an encrypted data key.
+
+        Args:
+            encrypted_data_key: The encrypted data key bytes
+            key_id: Optional key identifier (used by KMS providers)
+
+        Returns:
+            The decrypted data key
+        """
+        raise NotImplementedError
+
 
 class LocalKeyEncryption(EncryptionProvider):
     """SSE-S3 style encryption using a local master key.
@@ -99,28 +140,48 @@ class LocalKeyEncryption(EncryptionProvider):
         return self._master_key
     
     def _load_or_create_master_key(self) -> bytes:
-        """Load master key from file or generate a new one."""
-        if self.master_key_path.exists():
-            try:
-                return base64.b64decode(self.master_key_path.read_text().strip())
-            except Exception as exc:
-                raise EncryptionError(f"Failed to load master key: {exc}") from exc
-        
-        key = secrets.token_bytes(32)
+        """Load master key from file or generate a new one (with file locking)."""
+        lock_path = self.master_key_path.with_suffix(".lock")
+        lock_path.parent.mkdir(parents=True, exist_ok=True)
+
         try:
-            self.master_key_path.parent.mkdir(parents=True, exist_ok=True)
-            self.master_key_path.write_text(base64.b64encode(key).decode())
+            with open(lock_path, "w") as lock_file:
+                if sys.platform == "win32":
+                    import msvcrt
+                    msvcrt.locking(lock_file.fileno(), msvcrt.LK_LOCK, 1)
+                else:
+                    fcntl.flock(lock_file.fileno(), fcntl.LOCK_EX)
+                try:
+                    if self.master_key_path.exists():
+                        try:
+                            return base64.b64decode(self.master_key_path.read_text().strip())
+                        except Exception as exc:
+                            raise EncryptionError(f"Failed to load master key: {exc}") from exc
+                    key = secrets.token_bytes(32)
+                    try:
+                        self.master_key_path.write_text(base64.b64encode(key).decode())
+                        _set_secure_file_permissions(self.master_key_path)
+                    except OSError as exc:
+                        raise EncryptionError(f"Failed to save master key: {exc}") from exc
+                    return key
+                finally:
+                    if sys.platform == "win32":
+                        import msvcrt
+                        msvcrt.locking(lock_file.fileno(), msvcrt.LK_UNLCK, 1)
+                    else:
+                        fcntl.flock(lock_file.fileno(), fcntl.LOCK_UN)
         except OSError as exc:
-            raise EncryptionError(f"Failed to save master key: {exc}") from exc
-        return key
+            raise EncryptionError(f"Failed to acquire lock for master key: {exc}") from exc
     
+    DATA_KEY_AAD = b'{"purpose":"data_key","version":1}'
+
     def _encrypt_data_key(self, data_key: bytes) -> bytes:
         """Encrypt the data key with the master key."""
         aesgcm = AESGCM(self.master_key)
         nonce = secrets.token_bytes(12)
-        encrypted = aesgcm.encrypt(nonce, data_key, None)
+        encrypted = aesgcm.encrypt(nonce, data_key, self.DATA_KEY_AAD)
         return nonce + encrypted
-    
+
     def _decrypt_data_key(self, encrypted_data_key: bytes) -> bytes:
         """Decrypt the data key using the master key."""
         if len(encrypted_data_key) < 12 + 32 + 16:  # nonce + key + tag
@@ -129,10 +190,17 @@ class LocalKeyEncryption(EncryptionProvider):
         nonce = encrypted_data_key[:12]
         ciphertext = encrypted_data_key[12:]
         try:
-            return aesgcm.decrypt(nonce, ciphertext, None)
-        except Exception as exc:
-            raise EncryptionError(f"Failed to decrypt data key: {exc}") from exc
-    
+            return aesgcm.decrypt(nonce, ciphertext, self.DATA_KEY_AAD)
+        except Exception:
+            try:
+                return aesgcm.decrypt(nonce, ciphertext, None)
+            except Exception as exc:
+                raise EncryptionError(f"Failed to decrypt data key: {exc}") from exc
+
+    def decrypt_data_key(self, encrypted_data_key: bytes, key_id: str | None = None) -> bytes:
+        """Decrypt an encrypted data key (key_id ignored for local encryption)."""
+        return self._decrypt_data_key(encrypted_data_key)
+
     def generate_data_key(self) -> tuple[bytes, bytes]:
         """Generate a data key and its encrypted form."""
         plaintext_key = secrets.token_bytes(32)
@@ -142,11 +210,12 @@ class LocalKeyEncryption(EncryptionProvider):
     def encrypt(self, plaintext: bytes, context: Dict[str, str] | None = None) -> EncryptionResult:
         """Encrypt data using envelope encryption."""
         data_key, encrypted_data_key = self.generate_data_key()
-        
+
         aesgcm = AESGCM(data_key)
         nonce = secrets.token_bytes(12)
-        ciphertext = aesgcm.encrypt(nonce, plaintext, None)
-        
+        aad = json.dumps(context, sort_keys=True).encode() if context else None
+        ciphertext = aesgcm.encrypt(nonce, plaintext, aad)
+
         return EncryptionResult(
             ciphertext=ciphertext,
             nonce=nonce,
@@ -157,15 +226,13 @@ class LocalKeyEncryption(EncryptionProvider):
     def decrypt(self, ciphertext: bytes, nonce: bytes, encrypted_data_key: bytes,
                 key_id: str, context: Dict[str, str] | None = None) -> bytes:
         """Decrypt data using envelope encryption."""
-        # Decrypt the data key
         data_key = self._decrypt_data_key(encrypted_data_key)
-        
-        # Decrypt the data
         aesgcm = AESGCM(data_key)
+        aad = json.dumps(context, sort_keys=True).encode() if context else None
         try:
-            return aesgcm.decrypt(nonce, ciphertext, None)
+            return aesgcm.decrypt(nonce, ciphertext, aad)
         except Exception as exc:
-            raise EncryptionError(f"Failed to decrypt data: {exc}") from exc
+            raise EncryptionError("Failed to decrypt data") from exc
 
 
 class StreamingEncryptor:
@@ -183,81 +250,93 @@ class StreamingEncryptor:
         self.chunk_size = chunk_size
     
     def _derive_chunk_nonce(self, base_nonce: bytes, chunk_index: int) -> bytes:
-        """Derive a unique nonce for each chunk."""
-        # XOR the base nonce with the chunk index
-        nonce_int = int.from_bytes(base_nonce, "big")
-        derived = nonce_int ^ chunk_index
-        return derived.to_bytes(12, "big")
-    
-    def encrypt_stream(self, stream: BinaryIO, 
-                       context: Dict[str, str] | None = None) -> tuple[BinaryIO, EncryptionMetadata]:
-        """Encrypt a stream and return encrypted stream + metadata."""
+        """Derive a unique nonce for each chunk using HKDF."""
+        hkdf = HKDF(
+            algorithm=hashes.SHA256(),
+            length=12,
+            salt=base_nonce,
+            info=chunk_index.to_bytes(4, "big"),
+        )
+        return hkdf.derive(b"chunk_nonce")
 
+    def encrypt_stream(self, stream: BinaryIO,
+                       context: Dict[str, str] | None = None) -> tuple[BinaryIO, EncryptionMetadata]:
+        """Encrypt a stream and return encrypted stream + metadata.
+
+        Performance: Writes chunks directly to output buffer instead of accumulating in list.
+        """
         data_key, encrypted_data_key = self.provider.generate_data_key()
         base_nonce = secrets.token_bytes(12)
-        
+
         aesgcm = AESGCM(data_key)
-        encrypted_chunks = []
+        # Performance: Write directly to BytesIO instead of accumulating chunks
+        output = io.BytesIO()
+        output.write(b"\x00\x00\x00\x00")  # Placeholder for chunk count
         chunk_index = 0
-        
+
         while True:
             chunk = stream.read(self.chunk_size)
             if not chunk:
                 break
-            
+
             chunk_nonce = self._derive_chunk_nonce(base_nonce, chunk_index)
             encrypted_chunk = aesgcm.encrypt(chunk_nonce, chunk, None)
-            
-            size_prefix = len(encrypted_chunk).to_bytes(self.HEADER_SIZE, "big")
-            encrypted_chunks.append(size_prefix + encrypted_chunk)
+
+            # Write size prefix + encrypted chunk directly
+            output.write(len(encrypted_chunk).to_bytes(self.HEADER_SIZE, "big"))
+            output.write(encrypted_chunk)
             chunk_index += 1
-        
-        header = chunk_index.to_bytes(4, "big")
-        encrypted_data = header + b"".join(encrypted_chunks)
-        
+
+        # Write actual chunk count to header
+        output.seek(0)
+        output.write(chunk_index.to_bytes(4, "big"))
+        output.seek(0)
+
         metadata = EncryptionMetadata(
             algorithm="AES256",
             key_id=self.provider.KEY_ID if hasattr(self.provider, "KEY_ID") else "local",
             nonce=base_nonce,
             encrypted_data_key=encrypted_data_key,
         )
-        
-        return io.BytesIO(encrypted_data), metadata
-    
+
+        return output, metadata
+
     def decrypt_stream(self, stream: BinaryIO, metadata: EncryptionMetadata) -> BinaryIO:
-        """Decrypt a stream using the provided metadata."""
-        if isinstance(self.provider, LocalKeyEncryption):
-            data_key = self.provider._decrypt_data_key(metadata.encrypted_data_key)
-        else:
-            raise EncryptionError("Unsupported provider for streaming decryption")
-        
+        """Decrypt a stream using the provided metadata.
+
+        Performance: Writes chunks directly to output buffer instead of accumulating in list.
+        """
+        data_key = self.provider.decrypt_data_key(metadata.encrypted_data_key, metadata.key_id)
+
         aesgcm = AESGCM(data_key)
         base_nonce = metadata.nonce
-        
+
         chunk_count_bytes = stream.read(4)
         if len(chunk_count_bytes) < 4:
             raise EncryptionError("Invalid encrypted stream: missing header")
         chunk_count = int.from_bytes(chunk_count_bytes, "big")
-        
-        decrypted_chunks = []
+
+        # Performance: Write directly to BytesIO instead of accumulating chunks
+        output = io.BytesIO()
         for chunk_index in range(chunk_count):
             size_bytes = stream.read(self.HEADER_SIZE)
             if len(size_bytes) < self.HEADER_SIZE:
                 raise EncryptionError(f"Invalid encrypted stream: truncated at chunk {chunk_index}")
             chunk_size = int.from_bytes(size_bytes, "big")
-            
+
             encrypted_chunk = stream.read(chunk_size)
             if len(encrypted_chunk) < chunk_size:
                 raise EncryptionError(f"Invalid encrypted stream: incomplete chunk {chunk_index}")
-            
+
             chunk_nonce = self._derive_chunk_nonce(base_nonce, chunk_index)
             try:
                 decrypted_chunk = aesgcm.decrypt(chunk_nonce, encrypted_chunk, None)
-                decrypted_chunks.append(decrypted_chunk)
+                output.write(decrypted_chunk)  # Write directly instead of appending to list
             except Exception as exc:
                 raise EncryptionError(f"Failed to decrypt chunk {chunk_index}: {exc}") from exc
-        
-        return io.BytesIO(b"".join(decrypted_chunks))
+
+        output.seek(0)
+        return output
 
 
 class EncryptionManager:
@@ -300,7 +379,8 @@ class EncryptionManager:
     
     def get_streaming_encryptor(self) -> StreamingEncryptor:
         if self._streaming_encryptor is None:
-            self._streaming_encryptor = StreamingEncryptor(self.get_local_provider())
+            chunk_size = self.config.get("encryption_chunk_size_bytes", 64 * 1024)
+            self._streaming_encryptor = StreamingEncryptor(self.get_local_provider(), chunk_size=chunk_size)
         return self._streaming_encryptor
     
     def encrypt_object(self, data: bytes, algorithm: str = "AES256",
@@ -343,13 +423,115 @@ class EncryptionManager:
         return encryptor.decrypt_stream(stream, metadata)
 
 
+class SSECEncryption(EncryptionProvider):
+    """SSE-C: Server-Side Encryption with Customer-Provided Keys.
+
+    The client provides the encryption key with each request.
+    Server encrypts/decrypts but never stores the key.
+
+    Required headers for PUT:
+    - x-amz-server-side-encryption-customer-algorithm: AES256
+    - x-amz-server-side-encryption-customer-key: Base64-encoded 256-bit key
+    - x-amz-server-side-encryption-customer-key-MD5: Base64-encoded MD5 of key
+    """
+
+    KEY_ID = "customer-provided"
+
+    def __init__(self, customer_key: bytes):
+        if len(customer_key) != 32:
+            raise EncryptionError("Customer key must be exactly 256 bits (32 bytes)")
+        self.customer_key = customer_key
+
+    @classmethod
+    def from_headers(cls, headers: Dict[str, str]) -> "SSECEncryption":
+        algorithm = headers.get("x-amz-server-side-encryption-customer-algorithm", "")
+        if algorithm.upper() != "AES256":
+            raise EncryptionError(f"Unsupported SSE-C algorithm: {algorithm}. Only AES256 is supported.")
+
+        key_b64 = headers.get("x-amz-server-side-encryption-customer-key", "")
+        if not key_b64:
+            raise EncryptionError("Missing x-amz-server-side-encryption-customer-key header")
+
+        key_md5_b64 = headers.get("x-amz-server-side-encryption-customer-key-md5", "")
+
+        try:
+            customer_key = base64.b64decode(key_b64)
+        except Exception as e:
+            raise EncryptionError(f"Invalid base64 in customer key: {e}") from e
+
+        if len(customer_key) != 32:
+            raise EncryptionError(f"Customer key must be 256 bits, got {len(customer_key) * 8} bits")
+
+        if key_md5_b64:
+            import hashlib
+            expected_md5 = base64.b64encode(hashlib.md5(customer_key).digest()).decode()
+            if key_md5_b64 != expected_md5:
+                raise EncryptionError("Customer key MD5 mismatch")
+
+        return cls(customer_key)
+
+    def encrypt(self, plaintext: bytes, context: Dict[str, str] | None = None) -> EncryptionResult:
+        aesgcm = AESGCM(self.customer_key)
+        nonce = secrets.token_bytes(12)
+        aad = json.dumps(context, sort_keys=True).encode() if context else None
+        ciphertext = aesgcm.encrypt(nonce, plaintext, aad)
+
+        return EncryptionResult(
+            ciphertext=ciphertext,
+            nonce=nonce,
+            key_id=self.KEY_ID,
+            encrypted_data_key=b"",
+        )
+
+    def decrypt(self, ciphertext: bytes, nonce: bytes, encrypted_data_key: bytes,
+                key_id: str, context: Dict[str, str] | None = None) -> bytes:
+        aesgcm = AESGCM(self.customer_key)
+        aad = json.dumps(context, sort_keys=True).encode() if context else None
+        try:
+            return aesgcm.decrypt(nonce, ciphertext, aad)
+        except Exception as exc:
+            raise EncryptionError("SSE-C decryption failed") from exc
+
+    def generate_data_key(self) -> tuple[bytes, bytes]:
+        return self.customer_key, b""
+
+
+@dataclass
+class SSECMetadata:
+    algorithm: str = "AES256"
+    nonce: bytes = b""
+    key_md5: str = ""
+
+    def to_dict(self) -> Dict[str, str]:
+        return {
+            "x-amz-server-side-encryption-customer-algorithm": self.algorithm,
+            "x-amz-encryption-nonce": base64.b64encode(self.nonce).decode(),
+            "x-amz-server-side-encryption-customer-key-MD5": self.key_md5,
+        }
+
+    @classmethod
+    def from_dict(cls, data: Dict[str, str]) -> Optional["SSECMetadata"]:
+        algorithm = data.get("x-amz-server-side-encryption-customer-algorithm")
+        if not algorithm:
+            return None
+        try:
+            nonce = base64.b64decode(data.get("x-amz-encryption-nonce", ""))
+            return cls(
+                algorithm=algorithm,
+                nonce=nonce,
+                key_md5=data.get("x-amz-server-side-encryption-customer-key-MD5", ""),
+            )
+        except Exception:
+            return None
+
+
 class ClientEncryptionHelper:
     """Helpers for client-side encryption.
-    
+
     Client-side encryption is performed by the client, but this helper
     provides key generation and materials for clients that need them.
     """
-    
+
     @staticmethod
     def generate_client_key() -> Dict[str, str]:
         """Generate a new client encryption key."""
@@ -362,34 +544,36 @@ class ClientEncryptionHelper:
         }
     
     @staticmethod
-    def encrypt_with_key(plaintext: bytes, key_b64: str) -> Dict[str, str]:
+    def encrypt_with_key(plaintext: bytes, key_b64: str, context: Dict[str, str] | None = None) -> Dict[str, str]:
         """Encrypt data with a client-provided key."""
         key = base64.b64decode(key_b64)
         if len(key) != 32:
             raise EncryptionError("Key must be 256 bits (32 bytes)")
-        
+
         aesgcm = AESGCM(key)
         nonce = secrets.token_bytes(12)
-        ciphertext = aesgcm.encrypt(nonce, plaintext, None)
-        
+        aad = json.dumps(context, sort_keys=True).encode() if context else None
+        ciphertext = aesgcm.encrypt(nonce, plaintext, aad)
+
         return {
             "ciphertext": base64.b64encode(ciphertext).decode(),
             "nonce": base64.b64encode(nonce).decode(),
             "algorithm": "AES-256-GCM",
         }
-    
+
     @staticmethod
-    def decrypt_with_key(ciphertext_b64: str, nonce_b64: str, key_b64: str) -> bytes:
+    def decrypt_with_key(ciphertext_b64: str, nonce_b64: str, key_b64: str, context: Dict[str, str] | None = None) -> bytes:
         """Decrypt data with a client-provided key."""
         key = base64.b64decode(key_b64)
         nonce = base64.b64decode(nonce_b64)
         ciphertext = base64.b64decode(ciphertext_b64)
-        
+
         if len(key) != 32:
             raise EncryptionError("Key must be 256 bits (32 bytes)")
-        
+
         aesgcm = AESGCM(key)
+        aad = json.dumps(context, sort_keys=True).encode() if context else None
         try:
-            return aesgcm.decrypt(nonce, ciphertext, None)
+            return aesgcm.decrypt(nonce, ciphertext, aad)
         except Exception as exc:
-            raise EncryptionError(f"Decryption failed: {exc}") from exc
+            raise EncryptionError("Decryption failed") from exc

app/errors.py

@@ -1,4 +1,3 @@
-"""Standardized error handling for API and UI responses."""
 from __future__ import annotations
 
 import logging
@@ -7,6 +6,7 @@ from typing import Optional, Dict, Any
 from xml.etree.ElementTree import Element, SubElement, tostring
 
 from flask import Response, jsonify, request, flash, redirect, url_for, g
+from flask_limiter import RateLimitExceeded
 
 logger = logging.getLogger(__name__)
 
@@ -173,10 +173,22 @@ def handle_app_error(error: AppError) -> Response:
         return error.to_xml_response()
 
 
+def handle_rate_limit_exceeded(e: RateLimitExceeded) -> Response:
+    g.s3_error_code = "SlowDown"
+    error = Element("Error")
+    SubElement(error, "Code").text = "SlowDown"
+    SubElement(error, "Message").text = "Please reduce your request rate."
+    SubElement(error, "Resource").text = request.path
+    SubElement(error, "RequestId").text = getattr(g, "request_id", "")
+    xml_bytes = tostring(error, encoding="utf-8")
+    return Response(xml_bytes, status=429, mimetype="application/xml")
+
+
 def register_error_handlers(app):
     """Register error handlers with a Flask app."""
     app.register_error_handler(AppError, handle_app_error)
-    
+    app.register_error_handler(RateLimitExceeded, handle_rate_limit_exceeded)
+
     for error_class in [
         BucketNotFoundError, BucketAlreadyExistsError, BucketNotEmptyError,
         ObjectNotFoundError, InvalidObjectKeyError,

app/extensions.py

@@ -1,4 +1,3 @@
-"""Application-wide extension instances."""
 from flask import g
 from flask_limiter import Limiter
 from flask_limiter.util import get_remote_address

app/iam.py

@@ -1,21 +1,25 @@
-"""Lightweight IAM-style user and policy management."""
 from __future__ import annotations
 
+import hashlib
+import hmac
 import json
 import math
+import os
 import secrets
+import threading
+import time
 from collections import deque
 from dataclasses import dataclass
-from datetime import datetime, timedelta
+from datetime import datetime, timedelta, timezone
 from pathlib import Path
-from typing import Any, Deque, Dict, Iterable, List, Optional, Sequence, Set
+from typing import Any, Deque, Dict, Iterable, List, Optional, Sequence, Set, Tuple
 
 
 class IamError(RuntimeError):
     """Raised when authentication or authorization fails."""
 
 
-S3_ACTIONS = {"list", "read", "write", "delete", "share", "policy", "replication"}
+S3_ACTIONS = {"list", "read", "write", "delete", "share", "policy", "replication", "lifecycle", "cors"}
 IAM_ACTIONS = {
     "iam:list_users",
     "iam:create_user",
@@ -26,14 +30,12 @@ IAM_ACTIONS = {
 ALLOWED_ACTIONS = (S3_ACTIONS | IAM_ACTIONS) | {"iam:*"}
 
 ACTION_ALIASES = {
-    # List actions
     "list": "list",
     "s3:listbucket": "list",
     "s3:listallmybuckets": "list",
     "s3:listbucketversions": "list",
     "s3:listmultipartuploads": "list",
     "s3:listparts": "list",
-    # Read actions
     "read": "read",
     "s3:getobject": "read",
     "s3:getobjectversion": "read",
@@ -43,7 +45,6 @@ ACTION_ALIASES = {
     "s3:getbucketversioning": "read",
     "s3:headobject": "read",
     "s3:headbucket": "read",
-    # Write actions
     "write": "write",
     "s3:putobject": "write",
     "s3:createbucket": "write",
@@ -54,23 +55,19 @@ ACTION_ALIASES = {
     "s3:completemultipartupload": "write",
     "s3:abortmultipartupload": "write",
     "s3:copyobject": "write",
-    # Delete actions
     "delete": "delete",
     "s3:deleteobject": "delete",
     "s3:deleteobjectversion": "delete",
     "s3:deletebucket": "delete",
     "s3:deleteobjecttagging": "delete",
-    # Share actions (ACL)
     "share": "share",
     "s3:putobjectacl": "share",
     "s3:putbucketacl": "share",
     "s3:getbucketacl": "share",
-    # Policy actions
     "policy": "policy",
     "s3:putbucketpolicy": "policy",
     "s3:getbucketpolicy": "policy",
     "s3:deletebucketpolicy": "policy",
-    # Replication actions
     "replication": "replication",
     "s3:getreplicationconfiguration": "replication",
     "s3:putreplicationconfiguration": "replication",
@@ -78,7 +75,16 @@ ACTION_ALIASES = {
     "s3:replicateobject": "replication",
     "s3:replicatetags": "replication",
     "s3:replicatedelete": "replication",
-    # IAM actions
+    "lifecycle": "lifecycle",
+    "s3:getlifecycleconfiguration": "lifecycle",
+    "s3:putlifecycleconfiguration": "lifecycle",
+    "s3:deletelifecycleconfiguration": "lifecycle",
+    "s3:getbucketlifecycle": "lifecycle",
+    "s3:putbucketlifecycle": "lifecycle",
+    "cors": "cors",
+    "s3:getbucketcors": "cors",
+    "s3:putbucketcors": "cors",
+    "s3:deletebucketcors": "cors",
     "iam:listusers": "iam:list_users",
     "iam:createuser": "iam:create_user",
     "iam:deleteuser": "iam:delete_user",
@@ -115,17 +121,30 @@ class IamService:
         self._raw_config: Dict[str, Any] = {}
         self._failed_attempts: Dict[str, Deque[datetime]] = {}
         self._last_load_time = 0.0
+        self._principal_cache: Dict[str, Tuple[Principal, float]] = {}
+        self._secret_key_cache: Dict[str, Tuple[str, float]] = {}
+        self._cache_ttl = float(os.environ.get("IAM_CACHE_TTL_SECONDS", "5.0"))
+        self._last_stat_check = 0.0
+        self._stat_check_interval = 1.0
+        self._sessions: Dict[str, Dict[str, Any]] = {}
+        self._session_lock = threading.Lock()
         self._load()
+        self._load_lockout_state()
 
     def _maybe_reload(self) -> None:
         """Reload configuration if the file has changed on disk."""
+        now = time.time()
+        if now - self._last_stat_check < self._stat_check_interval:
+            return
+        self._last_stat_check = now
         try:
             if self.config_path.stat().st_mtime > self._last_load_time:
                 self._load()
+                self._principal_cache.clear()
+                self._secret_key_cache.clear()
         except OSError:
             pass
 
-    # ---------------------- authz helpers ----------------------
     def authenticate(self, access_key: str, secret_key: str) -> Principal:
         self._maybe_reload()
         access_key = (access_key or "").strip()
@@ -138,7 +157,8 @@ class IamService:
                 f"Access temporarily locked. Try again in {seconds} seconds."
             )
         record = self._users.get(access_key)
-        if not record or record["secret_key"] != secret_key:
+        stored_secret = record["secret_key"] if record else secrets.token_urlsafe(24)
+        if not record or not hmac.compare_digest(stored_secret, secret_key):
             self._record_failed_attempt(access_key)
             raise IamError("Invalid credentials")
         self._clear_failed_attempts(access_key)
@@ -149,15 +169,50 @@ class IamService:
             return
         attempts = self._failed_attempts.setdefault(access_key, deque())
         self._prune_attempts(attempts)
-        attempts.append(datetime.now())
+        attempts.append(datetime.now(timezone.utc))
+        self._save_lockout_state()
 
     def _clear_failed_attempts(self, access_key: str) -> None:
         if not access_key:
             return
-        self._failed_attempts.pop(access_key, None)
+        if self._failed_attempts.pop(access_key, None) is not None:
+            self._save_lockout_state()
+
+    def _lockout_file(self) -> Path:
+        return self.config_path.parent / "lockout_state.json"
+
+    def _load_lockout_state(self) -> None:
+        """Load lockout state from disk."""
+        try:
+            if self._lockout_file().exists():
+                data = json.loads(self._lockout_file().read_text(encoding="utf-8"))
+                cutoff = datetime.now(timezone.utc) - self.auth_lockout_window
+                for key, timestamps in data.get("failed_attempts", {}).items():
+                    valid = []
+                    for ts in timestamps:
+                        try:
+                            dt = datetime.fromisoformat(ts)
+                            if dt > cutoff:
+                                valid.append(dt)
+                        except (ValueError, TypeError):
+                            continue
+                    if valid:
+                        self._failed_attempts[key] = deque(valid)
+        except (OSError, json.JSONDecodeError):
+            pass
+
+    def _save_lockout_state(self) -> None:
+        """Persist lockout state to disk."""
+        data: Dict[str, Any] = {"failed_attempts": {}}
+        for key, attempts in self._failed_attempts.items():
+            data["failed_attempts"][key] = [ts.isoformat() for ts in attempts]
+        try:
+            self._lockout_file().write_text(json.dumps(data), encoding="utf-8")
+        except OSError:
+            pass
 
     def _prune_attempts(self, attempts: Deque[datetime]) -> None:
-        cutoff = datetime.now() - self.auth_lockout_window
+        cutoff = datetime.now(timezone.utc) - self.auth_lockout_window
         while attempts and attempts[0] < cutoff:
             attempts.popleft()
 
@@ -178,15 +233,65 @@ class IamService:
         if len(attempts) < self.auth_max_attempts:
             return 0
         oldest = attempts[0]
-        elapsed = (datetime.now() - oldest).total_seconds()
+        elapsed = (datetime.now(timezone.utc) - oldest).total_seconds()
         return int(max(0, self.auth_lockout_window.total_seconds() - elapsed))
 
-    def principal_for_key(self, access_key: str) -> Principal:
+    def create_session_token(self, access_key: str, duration_seconds: int = 3600) -> str:
+        """Create a temporary session token for an access key."""
         self._maybe_reload()
         record = self._users.get(access_key)
         if not record:
             raise IamError("Unknown access key")
-        return self._build_principal(access_key, record)
+        self._cleanup_expired_sessions()
+        token = secrets.token_urlsafe(32)
+        expires_at = time.time() + duration_seconds
+        self._sessions[token] = {
+            "access_key": access_key,
+            "expires_at": expires_at,
+        }
+        return token
+
+    def validate_session_token(self, access_key: str, session_token: str) -> bool:
+        """Validate a session token for an access key (thread-safe, constant-time)."""
+        dummy_key = secrets.token_urlsafe(16)
+        dummy_token = secrets.token_urlsafe(32)
+        with self._session_lock:
+            session = self._sessions.get(session_token)
+            if not session:
+                hmac.compare_digest(access_key, dummy_key)
+                hmac.compare_digest(session_token, dummy_token)
+                return False
+            key_match = hmac.compare_digest(session["access_key"], access_key)
+            if not key_match:
+                hmac.compare_digest(session_token, dummy_token)
+                return False
+            if time.time() > session["expires_at"]:
+                self._sessions.pop(session_token, None)
+                return False
+            return True
+
+    def _cleanup_expired_sessions(self) -> None:
+        """Remove expired session tokens."""
+        now = time.time()
+        expired = [token for token, data in self._sessions.items() if now > data["expires_at"]]
+        for token in expired:
+            del self._sessions[token]
+
+    def principal_for_key(self, access_key: str) -> Principal:
+        now = time.time()
+        cached = self._principal_cache.get(access_key)
+        if cached:
+            principal, cached_time = cached
+            if now - cached_time < self._cache_ttl:
+                return principal
+
+        self._maybe_reload()
+        record = self._users.get(access_key)
+        if not record:
+            raise IamError("Unknown access key")
+        principal = self._build_principal(access_key, record)
+        self._principal_cache[access_key] = (principal, now)
+        return principal
 
     def secret_for_key(self, access_key: str) -> str:
         self._maybe_reload()
@@ -204,6 +309,18 @@ class IamService:
         if not self._is_allowed(principal, normalized, action):
             raise IamError(f"Access denied for action '{action}' on bucket '{bucket_name}'")
 
+    def check_permissions(self, principal: Principal, bucket_name: str | None, actions: Iterable[str]) -> Dict[str, bool]:
+        self._maybe_reload()
+        bucket_name = (bucket_name or "*").lower() if bucket_name != "*" else (bucket_name or "*")
+        normalized_actions = {a: self._normalize_action(a) for a in actions}
+        results: Dict[str, bool] = {}
+        for original, canonical in normalized_actions.items():
+            if canonical not in ALLOWED_ACTIONS:
+                results[original] = False
+            else:
+                results[original] = self._is_allowed(principal, bucket_name, canonical)
+        return results
+
     def buckets_for_principal(self, principal: Principal, buckets: Iterable[str]) -> List[str]:
         return [bucket for bucket in buckets if self._is_allowed(principal, bucket, "list")]
 
@@ -218,7 +335,6 @@ class IamService:
                 return True
         return False
 
-    # ---------------------- management helpers ----------------------
     def list_users(self) -> List[Dict[str, Any]]:
         listing: List[Dict[str, Any]] = []
         for access_key, record in self._users.items():
@@ -265,6 +381,10 @@ class IamService:
         new_secret = self._generate_secret_key()
         user["secret_key"] = new_secret
         self._save()
+        self._principal_cache.pop(access_key, None)
+        self._secret_key_cache.pop(access_key, None)
+        from .s3_api import clear_signing_key_cache
+        clear_signing_key_cache()
         self._load()
         return new_secret
 
@@ -283,6 +403,10 @@ class IamService:
             raise IamError("User not found")
         self._raw_config["users"] = remaining
         self._save()
+        self._principal_cache.pop(access_key, None)
+        self._secret_key_cache.pop(access_key, None)
+        from .s3_api import clear_signing_key_cache
+        clear_signing_key_cache()
         self._load()
 
     def update_user_policies(self, access_key: str, policies: Sequence[Dict[str, Any]]) -> None:
@@ -291,7 +415,6 @@ class IamService:
         self._save()
         self._load()
 
-    # ---------------------- config helpers ----------------------
     def _load(self) -> None:
         try:
             self._last_load_time = self.config_path.stat().st_mtime
@@ -337,7 +460,6 @@ class IamService:
         except (OSError, PermissionError) as e:
             raise IamError(f"Cannot save IAM config: {e}")
 
-    # ---------------------- insight helpers ----------------------
     def config_summary(self) -> Dict[str, Any]:
         return {
             "path": str(self.config_path),
@@ -419,11 +541,13 @@ class IamService:
         return candidate if candidate in ALLOWED_ACTIONS else ""
 
     def _write_default(self) -> None:
+        access_key = secrets.token_hex(12)
+        secret_key = secrets.token_urlsafe(32)
         default = {
             "users": [
                 {
-                    "access_key": "localadmin",
-                    "secret_key": "localadmin",
+                    "access_key": access_key,
+                    "secret_key": secret_key,
                     "display_name": "Local Admin",
                     "policies": [
                         {"bucket": "*", "actions": list(ALLOWED_ACTIONS)}
@@ -432,6 +556,14 @@ class IamService:
             ]
         }
         self.config_path.write_text(json.dumps(default, indent=2))
+        print(f"\n{'='*60}")
+        print("MYFSIO FIRST RUN - ADMIN CREDENTIALS GENERATED")
+        print(f"{'='*60}")
+        print(f"Access Key: {access_key}")
+        print(f"Secret Key: {secret_key}")
+        print(f"{'='*60}")
+        print(f"Missed this? Check: {self.config_path}")
+        print(f"{'='*60}\n")
 
     def _generate_access_key(self) -> str:
         return secrets.token_hex(8)
@@ -446,11 +578,33 @@ class IamService:
         raise IamError("User not found")
 
     def get_secret_key(self, access_key: str) -> str | None:
+        now = time.time()
+        cached = self._secret_key_cache.get(access_key)
+        if cached:
+            secret_key, cached_time = cached
+            if now - cached_time < self._cache_ttl:
+                return secret_key
+
         self._maybe_reload()
         record = self._users.get(access_key)
-        return record["secret_key"] if record else None
+        if record:
+            secret_key = record["secret_key"]
+            self._secret_key_cache[access_key] = (secret_key, now)
+            return secret_key
+        return None
 
     def get_principal(self, access_key: str) -> Principal | None:
+        now = time.time()
+        cached = self._principal_cache.get(access_key)
+        if cached:
+            principal, cached_time = cached
+            if now - cached_time < self._cache_ttl:
+                return principal
+
         self._maybe_reload()
         record = self._users.get(access_key)
-        return self._build_principal(access_key, record) if record else None
+        if record:
+            principal = self._build_principal(access_key, record)
+            self._principal_cache[access_key] = (principal, now)
+            return principal
+        return None

app/kms.py

@@ -1,9 +1,12 @@
-"""Key Management Service (KMS) for encryption key management."""
 from __future__ import annotations
 
 import base64
 import json
+import logging
+import os
 import secrets
+import subprocess
+import sys
 import uuid
 from dataclasses import dataclass, field
 from datetime import datetime, timezone
@@ -14,6 +17,30 @@ from cryptography.hazmat.primitives.ciphers.aead import AESGCM
 
 from .encryption import EncryptionError, EncryptionProvider, EncryptionResult
 
+if sys.platform != "win32":
+    import fcntl
+
+logger = logging.getLogger(__name__)
+
+
+def _set_secure_file_permissions(file_path: Path) -> None:
+    """Set restrictive file permissions (owner read/write only)."""
+    if sys.platform == "win32":
+        try:
+            username = os.environ.get("USERNAME", "")
+            if username:
+                subprocess.run(
+                    ["icacls", str(file_path), "/inheritance:r",
+                     "/grant:r", f"{username}:F"],
+                    check=True, capture_output=True
+                )
+            else:
+                logger.warning("Could not set secure permissions on %s: USERNAME not set", file_path)
+        except (subprocess.SubprocessError, OSError) as exc:
+            logger.warning("Failed to set secure permissions on %s: %s", file_path, exc)
+    else:
+        os.chmod(file_path, 0o600)
+
 
 @dataclass
 class KMSKey:
@@ -75,11 +102,11 @@ class KMSEncryptionProvider(EncryptionProvider):
     def encrypt(self, plaintext: bytes, context: Dict[str, str] | None = None) -> EncryptionResult:
         """Encrypt data using envelope encryption with KMS."""
         data_key, encrypted_data_key = self.generate_data_key()
-        
+
         aesgcm = AESGCM(data_key)
         nonce = secrets.token_bytes(12)
-        ciphertext = aesgcm.encrypt(nonce, plaintext, 
-                                     json.dumps(context).encode() if context else None)
+        ciphertext = aesgcm.encrypt(nonce, plaintext,
+                                     json.dumps(context, sort_keys=True).encode() if context else None)
         
         return EncryptionResult(
             ciphertext=ciphertext,
@@ -91,15 +118,26 @@ class KMSEncryptionProvider(EncryptionProvider):
     def decrypt(self, ciphertext: bytes, nonce: bytes, encrypted_data_key: bytes,
                 key_id: str, context: Dict[str, str] | None = None) -> bytes:
         """Decrypt data using envelope encryption with KMS."""
-        # Note: Data key is encrypted without context (AAD), so we decrypt without context
         data_key = self.kms.decrypt_data_key(key_id, encrypted_data_key, context=None)
-        
+        if len(data_key) != 32:
+            raise EncryptionError("Invalid data key size")
+
         aesgcm = AESGCM(data_key)
         try:
             return aesgcm.decrypt(nonce, ciphertext,
-                                  json.dumps(context).encode() if context else None)
+                                  json.dumps(context, sort_keys=True).encode() if context else None)
         except Exception as exc:
-            raise EncryptionError(f"Failed to decrypt data: {exc}") from exc
+            logger.debug("KMS decryption failed: %s", exc)
+            raise EncryptionError("Failed to decrypt data") from exc
+
+    def decrypt_data_key(self, encrypted_data_key: bytes, key_id: str | None = None) -> bytes:
+        """Decrypt an encrypted data key using KMS."""
+        if key_id is None:
+            key_id = self.key_id
+        data_key = self.kms.decrypt_data_key(key_id, encrypted_data_key, context=None)
+        if len(data_key) != 32:
+            raise EncryptionError("Invalid data key size")
+        return data_key
 
 
 class KMSManager:
@@ -109,27 +147,52 @@ class KMSManager:
     Keys are stored encrypted on disk.
     """
     
-    def __init__(self, keys_path: Path, master_key_path: Path):
+    def __init__(
+        self,
+        keys_path: Path,
+        master_key_path: Path,
+        generate_data_key_min_bytes: int = 1,
+        generate_data_key_max_bytes: int = 1024,
+    ):
         self.keys_path = keys_path
         self.master_key_path = master_key_path
+        self.generate_data_key_min_bytes = generate_data_key_min_bytes
+        self.generate_data_key_max_bytes = generate_data_key_max_bytes
         self._keys: Dict[str, KMSKey] = {}
         self._master_key: bytes | None = None
+        self._master_aesgcm: AESGCM | None = None
         self._loaded = False
     
     @property
     def master_key(self) -> bytes:
-        """Load or create the master key for encrypting KMS keys."""
+        """Load or create the master key for encrypting KMS keys (with file locking)."""
         if self._master_key is None:
-            if self.master_key_path.exists():
-                self._master_key = base64.b64decode(
-                    self.master_key_path.read_text().strip()
-                )
-            else:
-                self._master_key = secrets.token_bytes(32)
-                self.master_key_path.parent.mkdir(parents=True, exist_ok=True)
-                self.master_key_path.write_text(
-                    base64.b64encode(self._master_key).decode()
-                )
+            lock_path = self.master_key_path.with_suffix(".lock")
+            lock_path.parent.mkdir(parents=True, exist_ok=True)
+            with open(lock_path, "w") as lock_file:
+                if sys.platform == "win32":
+                    import msvcrt
+                    msvcrt.locking(lock_file.fileno(), msvcrt.LK_LOCK, 1)
+                else:
+                    fcntl.flock(lock_file.fileno(), fcntl.LOCK_EX)
+                try:
+                    if self.master_key_path.exists():
+                        self._master_key = base64.b64decode(
+                            self.master_key_path.read_text().strip()
+                        )
+                    else:
+                        self._master_key = secrets.token_bytes(32)
+                        self.master_key_path.write_text(
+                            base64.b64encode(self._master_key).decode()
+                        )
+                        _set_secure_file_permissions(self.master_key_path)
+                finally:
+                    if sys.platform == "win32":
+                        import msvcrt
+                        msvcrt.locking(lock_file.fileno(), msvcrt.LK_UNLCK, 1)
+                    else:
+                        fcntl.flock(lock_file.fileno(), fcntl.LOCK_UN)
+            self._master_aesgcm = AESGCM(self._master_key)
         return self._master_key
     
     def _load_keys(self) -> None:
@@ -146,8 +209,10 @@ class KMSManager:
                         encrypted = base64.b64decode(key_data["EncryptedKeyMaterial"])
                         key.key_material = self._decrypt_key_material(encrypted)
                     self._keys[key.key_id] = key
-            except Exception:
-                pass
+            except json.JSONDecodeError as exc:
+                logger.error("Failed to parse KMS keys file: %s", exc)
+            except (ValueError, KeyError) as exc:
+                logger.error("Invalid KMS key data: %s", exc)
         
         self._loaded = True
     
@@ -159,26 +224,25 @@ class KMSManager:
             encrypted = self._encrypt_key_material(key.key_material)
             data["EncryptedKeyMaterial"] = base64.b64encode(encrypted).decode()
             keys_data.append(data)
-        
+
         self.keys_path.parent.mkdir(parents=True, exist_ok=True)
         self.keys_path.write_text(
             json.dumps({"keys": keys_data}, indent=2),
             encoding="utf-8"
         )
+        _set_secure_file_permissions(self.keys_path)
     
     def _encrypt_key_material(self, key_material: bytes) -> bytes:
-        """Encrypt key material with the master key."""
-        aesgcm = AESGCM(self.master_key)
+        _ = self.master_key
         nonce = secrets.token_bytes(12)
-        ciphertext = aesgcm.encrypt(nonce, key_material, None)
+        ciphertext = self._master_aesgcm.encrypt(nonce, key_material, None)
         return nonce + ciphertext
-    
+
     def _decrypt_key_material(self, encrypted: bytes) -> bytes:
-        """Decrypt key material with the master key."""
-        aesgcm = AESGCM(self.master_key)
+        _ = self.master_key
         nonce = encrypted[:12]
         ciphertext = encrypted[12:]
-        return aesgcm.decrypt(nonce, ciphertext, None)
+        return self._master_aesgcm.decrypt(nonce, ciphertext, None)
     
     def create_key(self, description: str = "", key_id: str | None = None) -> KMSKey:
         """Create a new KMS key."""
@@ -211,7 +275,27 @@ class KMSManager:
         """List all keys."""
         self._load_keys()
         return list(self._keys.values())
-    
+
+    def get_default_key_id(self) -> str:
+        """Get the default KMS key ID, creating one if none exist."""
+        self._load_keys()
+        for key in self._keys.values():
+            if key.enabled:
+                return key.key_id
+        default_key = self.create_key(description="Default KMS Key")
+        return default_key.key_id
+
+    def get_provider(self, key_id: str | None = None) -> "KMSEncryptionProvider":
+        """Get a KMS encryption provider for the specified key."""
+        if key_id is None:
+            key_id = self.get_default_key_id()
+        key = self.get_key(key_id)
+        if not key:
+            raise EncryptionError(f"Key not found: {key_id}")
+        if not key.enabled:
+            raise EncryptionError(f"Key is disabled: {key_id}")
+        return KMSEncryptionProvider(self, key_id)
+
     def enable_key(self, key_id: str) -> None:
         """Enable a key."""
         self._load_keys()
@@ -250,7 +334,7 @@ class KMSManager:
         
         aesgcm = AESGCM(key.key_material)
         nonce = secrets.token_bytes(12)
-        aad = json.dumps(context).encode() if context else None
+        aad = json.dumps(context, sort_keys=True).encode() if context else None
         ciphertext = aesgcm.encrypt(nonce, plaintext, aad)
         
         key_id_bytes = key_id.encode("utf-8")
@@ -279,17 +363,24 @@ class KMSManager:
         encrypted = rest[12:]
         
         aesgcm = AESGCM(key.key_material)
-        aad = json.dumps(context).encode() if context else None
+        aad = json.dumps(context, sort_keys=True).encode() if context else None
         try:
             plaintext = aesgcm.decrypt(nonce, encrypted, aad)
             return plaintext, key_id
         except Exception as exc:
-            raise EncryptionError(f"Decryption failed: {exc}") from exc
+            logger.debug("KMS decrypt operation failed: %s", exc)
+            raise EncryptionError("Decryption failed") from exc
     
     def generate_data_key(self, key_id: str,
-                          context: Dict[str, str] | None = None) -> tuple[bytes, bytes]:
+                          context: Dict[str, str] | None = None,
+                          key_spec: str = "AES_256") -> tuple[bytes, bytes]:
         """Generate a data key and return both plaintext and encrypted versions.
-        
+
+        Args:
+            key_id: The KMS key ID to use for encryption
+            context: Optional encryption context
+            key_spec: Key specification - AES_128 or AES_256 (default)
+
         Returns:
             Tuple of (plaintext_key, encrypted_key)
         """
@@ -299,11 +390,12 @@ class KMSManager:
             raise EncryptionError(f"Key not found: {key_id}")
         if not key.enabled:
             raise EncryptionError(f"Key is disabled: {key_id}")
-        
-        plaintext_key = secrets.token_bytes(32)
+
+        key_bytes = 32 if key_spec == "AES_256" else 16
+        plaintext_key = secrets.token_bytes(key_bytes)
 
         encrypted_key = self.encrypt(key_id, plaintext_key, context)
-        
+
         return plaintext_key, encrypted_key
     
     def decrypt_data_key(self, key_id: str, encrypted_key: bytes,
@@ -312,22 +404,6 @@ class KMSManager:
         plaintext, _ = self.decrypt(encrypted_key, context)
         return plaintext
     
-    def get_provider(self, key_id: str | None = None) -> KMSEncryptionProvider:
-        """Get an encryption provider for a specific key."""
-        self._load_keys()
-        
-        if key_id is None:
-            if not self._keys:
-                key = self.create_key("Default KMS Key")
-                key_id = key.key_id
-            else:
-                key_id = next(iter(self._keys.keys()))
-        
-        if key_id not in self._keys:
-            raise EncryptionError(f"Key not found: {key_id}")
-        
-        return KMSEncryptionProvider(self, key_id)
-    
     def re_encrypt(self, ciphertext: bytes, destination_key_id: str,
                    source_context: Dict[str, str] | None = None,
                    destination_context: Dict[str, str] | None = None) -> bytes:
@@ -339,6 +415,8 @@ class KMSManager:
     
     def generate_random(self, num_bytes: int = 32) -> bytes:
         """Generate cryptographically secure random bytes."""
-        if num_bytes < 1 or num_bytes > 1024:
-            raise EncryptionError("Number of bytes must be between 1 and 1024")
+        if num_bytes < self.generate_data_key_min_bytes or num_bytes > self.generate_data_key_max_bytes:
+            raise EncryptionError(
+                f"Number of bytes must be between {self.generate_data_key_min_bytes} and {self.generate_data_key_max_bytes}"
+            )
         return secrets.token_bytes(num_bytes)

app/kms_api.py

@@ -1,4 +1,3 @@
-"""KMS and encryption API endpoints."""
 from __future__ import annotations
 
 import base64
@@ -33,9 +32,6 @@ def _encryption():
 def _error_response(code: str, message: str, status: int) -> tuple[Dict[str, Any], int]:
     return {"__type": code, "message": message}, status
 
-
-# ---------------------- Key Management ----------------------
-
 @kms_api_bp.route("/keys", methods=["GET", "POST"])
 @limiter.limit("30 per minute")
 def list_or_create_keys():
@@ -65,7 +61,6 @@ def list_or_create_keys():
         except EncryptionError as exc:
             return _error_response("KMSInternalException", str(exc), 400)
     
-    # GET - List keys
     keys = kms.list_keys()
     return jsonify({
         "Keys": [{"KeyId": k.key_id, "KeyArn": k.arn} for k in keys],
@@ -96,7 +91,6 @@ def get_or_delete_key(key_id: str):
         except EncryptionError as exc:
             return _error_response("NotFoundException", str(exc), 404)
     
-    # GET
     key = kms.get_key(key_id)
     if not key:
         return _error_response("NotFoundException", f"Key not found: {key_id}", 404)
@@ -149,9 +143,6 @@ def disable_key(key_id: str):
     except EncryptionError as exc:
         return _error_response("NotFoundException", str(exc), 404)
 
-
-# ---------------------- Encryption Operations ----------------------
-
 @kms_api_bp.route("/encrypt", methods=["POST"])
 @limiter.limit("60 per minute")
 def encrypt_data():
@@ -251,7 +242,6 @@ def generate_data_key():
     try:
         plaintext_key, encrypted_key = kms.generate_data_key(key_id, context)
         
-        # Trim key if AES_128 requested
         if key_spec == "AES_128":
             plaintext_key = plaintext_key[:16]
         
@@ -322,10 +312,7 @@ def re_encrypt():
         return _error_response("ValidationException", "CiphertextBlob must be base64 encoded", 400)
     
     try:
-        # First decrypt, get source key id
         plaintext, source_key_id = kms.decrypt(ciphertext, source_context)
-        
-        # Re-encrypt with destination key
         new_ciphertext = kms.encrypt(destination_key_id, plaintext, destination_context)
         
         return jsonify({
@@ -365,9 +352,6 @@ def generate_random():
     except EncryptionError as exc:
         return _error_response("ValidationException", str(exc), 400)
 
-
-# ---------------------- Client-Side Encryption Helpers ----------------------
-
 @kms_api_bp.route("/client/generate-key", methods=["POST"])
 @limiter.limit("30 per minute")
 def generate_client_key():
@@ -427,9 +411,6 @@ def client_decrypt():
     except Exception as exc:
         return _error_response("DecryptionError", str(exc), 400)
 
-
-# ---------------------- Encryption Materials for S3 Client-Side Encryption ----------------------
-
 @kms_api_bp.route("/materials/<key_id>", methods=["POST"])
 @limiter.limit("60 per minute")
 def get_encryption_materials(key_id: str):

app/lifecycle.py

@@ -0,0 +1,340 @@
+from __future__ import annotations
+
+import json
+import logging
+import threading
+import time
+from dataclasses import dataclass, field
+from datetime import datetime, timedelta, timezone
+from pathlib import Path
+from typing import Any, Dict, List, Optional
+
+from .storage import ObjectStorage, StorageError
+
+logger = logging.getLogger(__name__)
+
+
+@dataclass
+class LifecycleResult:
+    bucket_name: str
+    objects_deleted: int = 0
+    versions_deleted: int = 0
+    uploads_aborted: int = 0
+    errors: List[str] = field(default_factory=list)
+    execution_time_seconds: float = 0.0
+
+
+@dataclass
+class LifecycleExecutionRecord:
+    timestamp: float
+    bucket_name: str
+    objects_deleted: int
+    versions_deleted: int
+    uploads_aborted: int
+    errors: List[str]
+    execution_time_seconds: float
+
+    def to_dict(self) -> dict:
+        return {
+            "timestamp": self.timestamp,
+            "bucket_name": self.bucket_name,
+            "objects_deleted": self.objects_deleted,
+            "versions_deleted": self.versions_deleted,
+            "uploads_aborted": self.uploads_aborted,
+            "errors": self.errors,
+            "execution_time_seconds": self.execution_time_seconds,
+        }
+
+    @classmethod
+    def from_dict(cls, data: dict) -> "LifecycleExecutionRecord":
+        return cls(
+            timestamp=data["timestamp"],
+            bucket_name=data["bucket_name"],
+            objects_deleted=data["objects_deleted"],
+            versions_deleted=data["versions_deleted"],
+            uploads_aborted=data["uploads_aborted"],
+            errors=data.get("errors", []),
+            execution_time_seconds=data["execution_time_seconds"],
+        )
+
+    @classmethod
+    def from_result(cls, result: LifecycleResult) -> "LifecycleExecutionRecord":
+        return cls(
+            timestamp=time.time(),
+            bucket_name=result.bucket_name,
+            objects_deleted=result.objects_deleted,
+            versions_deleted=result.versions_deleted,
+            uploads_aborted=result.uploads_aborted,
+            errors=result.errors.copy(),
+            execution_time_seconds=result.execution_time_seconds,
+        )
+
+
+class LifecycleHistoryStore:
+    def __init__(self, storage_root: Path, max_history_per_bucket: int = 50) -> None:
+        self.storage_root = storage_root
+        self.max_history_per_bucket = max_history_per_bucket
+        self._lock = threading.Lock()
+
+    def _get_history_path(self, bucket_name: str) -> Path:
+        return self.storage_root / ".myfsio.sys" / "buckets" / bucket_name / "lifecycle_history.json"
+
+    def load_history(self, bucket_name: str) -> List[LifecycleExecutionRecord]:
+        path = self._get_history_path(bucket_name)
+        if not path.exists():
+            return []
+        try:
+            with open(path, "r") as f:
+                data = json.load(f)
+                return [LifecycleExecutionRecord.from_dict(d) for d in data.get("executions", [])]
+        except (OSError, ValueError, KeyError) as e:
+            logger.error(f"Failed to load lifecycle history for {bucket_name}: {e}")
+            return []
+
+    def save_history(self, bucket_name: str, records: List[LifecycleExecutionRecord]) -> None:
+        path = self._get_history_path(bucket_name)
+        path.parent.mkdir(parents=True, exist_ok=True)
+        data = {"executions": [r.to_dict() for r in records[:self.max_history_per_bucket]]}
+        try:
+            with open(path, "w") as f:
+                json.dump(data, f, indent=2)
+        except OSError as e:
+            logger.error(f"Failed to save lifecycle history for {bucket_name}: {e}")
+
+    def add_record(self, bucket_name: str, record: LifecycleExecutionRecord) -> None:
+        with self._lock:
+            records = self.load_history(bucket_name)
+            records.insert(0, record)
+            self.save_history(bucket_name, records)
+
+    def get_history(self, bucket_name: str, limit: int = 50, offset: int = 0) -> List[LifecycleExecutionRecord]:
+        records = self.load_history(bucket_name)
+        return records[offset:offset + limit]
+
+
+class LifecycleManager:
+    def __init__(
+        self,
+        storage: ObjectStorage,
+        interval_seconds: int = 3600,
+        storage_root: Optional[Path] = None,
+        max_history_per_bucket: int = 50,
+    ):
+        self.storage = storage
+        self.interval_seconds = interval_seconds
+        self.storage_root = storage_root
+        self._timer: Optional[threading.Timer] = None
+        self._shutdown = False
+        self._lock = threading.Lock()
+        self.history_store = LifecycleHistoryStore(storage_root, max_history_per_bucket) if storage_root else None
+
+    def start(self) -> None:
+        if self._timer is not None:
+            return
+        self._shutdown = False
+        self._schedule_next()
+        logger.info(f"Lifecycle manager started with interval {self.interval_seconds}s")
+
+    def stop(self) -> None:
+        self._shutdown = True
+        if self._timer:
+            self._timer.cancel()
+            self._timer = None
+        logger.info("Lifecycle manager stopped")
+
+    def _schedule_next(self) -> None:
+        if self._shutdown:
+            return
+        self._timer = threading.Timer(self.interval_seconds, self._run_enforcement)
+        self._timer.daemon = True
+        self._timer.start()
+
+    def _run_enforcement(self) -> None:
+        if self._shutdown:
+            return
+        try:
+            self.enforce_all_buckets()
+        except Exception as e:
+            logger.error(f"Lifecycle enforcement failed: {e}")
+        finally:
+            self._schedule_next()
+
+    def enforce_all_buckets(self) -> Dict[str, LifecycleResult]:
+        results = {}
+        try:
+            buckets = self.storage.list_buckets()
+            for bucket in buckets:
+                result = self.enforce_rules(bucket.name)
+                if result.objects_deleted > 0 or result.versions_deleted > 0 or result.uploads_aborted > 0:
+                    results[bucket.name] = result
+        except StorageError as e:
+            logger.error(f"Failed to list buckets for lifecycle: {e}")
+        return results
+
+    def enforce_rules(self, bucket_name: str) -> LifecycleResult:
+        start_time = time.time()
+        result = LifecycleResult(bucket_name=bucket_name)
+
+        try:
+            lifecycle = self.storage.get_bucket_lifecycle(bucket_name)
+            if not lifecycle:
+                return result
+
+            for rule in lifecycle:
+                if rule.get("Status") != "Enabled":
+                    continue
+                rule_id = rule.get("ID", "unknown")
+                prefix = rule.get("Prefix", rule.get("Filter", {}).get("Prefix", ""))
+
+                self._enforce_expiration(bucket_name, rule, prefix, result)
+                self._enforce_noncurrent_expiration(bucket_name, rule, prefix, result)
+                self._enforce_abort_multipart(bucket_name, rule, result)
+
+        except StorageError as e:
+            result.errors.append(str(e))
+            logger.error(f"Lifecycle enforcement error for {bucket_name}: {e}")
+
+        result.execution_time_seconds = time.time() - start_time
+        if result.objects_deleted > 0 or result.versions_deleted > 0 or result.uploads_aborted > 0 or result.errors:
+            logger.info(
+                f"Lifecycle enforcement for {bucket_name}: "
+                f"deleted={result.objects_deleted}, versions={result.versions_deleted}, "
+                f"aborted={result.uploads_aborted}, time={result.execution_time_seconds:.2f}s"
+            )
+            if self.history_store:
+                record = LifecycleExecutionRecord.from_result(result)
+                self.history_store.add_record(bucket_name, record)
+        return result
+
+    def _enforce_expiration(
+        self, bucket_name: str, rule: Dict[str, Any], prefix: str, result: LifecycleResult
+    ) -> None:
+        expiration = rule.get("Expiration", {})
+        if not expiration:
+            return
+
+        days = expiration.get("Days")
+        date_str = expiration.get("Date")
+
+        if days:
+            cutoff = datetime.now(timezone.utc) - timedelta(days=days)
+        elif date_str:
+            try:
+                cutoff = datetime.fromisoformat(date_str.replace("Z", "+00:00"))
+            except ValueError:
+                return
+        else:
+            return
+
+        try:
+            objects = self.storage.list_objects_all(bucket_name)
+            for obj in objects:
+                if prefix and not obj.key.startswith(prefix):
+                    continue
+                if obj.last_modified < cutoff:
+                    try:
+                        self.storage.delete_object(bucket_name, obj.key)
+                        result.objects_deleted += 1
+                    except StorageError as e:
+                        result.errors.append(f"Failed to delete {obj.key}: {e}")
+        except StorageError as e:
+            result.errors.append(f"Failed to list objects: {e}")
+
+    def _enforce_noncurrent_expiration(
+        self, bucket_name: str, rule: Dict[str, Any], prefix: str, result: LifecycleResult
+    ) -> None:
+        noncurrent = rule.get("NoncurrentVersionExpiration", {})
+        noncurrent_days = noncurrent.get("NoncurrentDays")
+        if not noncurrent_days:
+            return
+
+        cutoff = datetime.now(timezone.utc) - timedelta(days=noncurrent_days)
+
+        try:
+            objects = self.storage.list_objects_all(bucket_name)
+            for obj in objects:
+                if prefix and not obj.key.startswith(prefix):
+                    continue
+                try:
+                    versions = self.storage.list_object_versions(bucket_name, obj.key)
+                    for version in versions:
+                        archived_at_str = version.get("archived_at", "")
+                        if not archived_at_str:
+                            continue
+                        try:
+                            archived_at = datetime.fromisoformat(archived_at_str.replace("Z", "+00:00"))
+                            if archived_at < cutoff:
+                                version_id = version.get("version_id")
+                                if version_id:
+                                    self.storage.delete_object_version(bucket_name, obj.key, version_id)
+                                    result.versions_deleted += 1
+                        except (ValueError, StorageError) as e:
+                            result.errors.append(f"Failed to process version: {e}")
+                except StorageError:
+                    pass
+        except StorageError as e:
+            result.errors.append(f"Failed to list objects: {e}")
+
+        try:
+            orphaned = self.storage.list_orphaned_objects(bucket_name)
+            for item in orphaned:
+                obj_key = item.get("key", "")
+                if prefix and not obj_key.startswith(prefix):
+                    continue
+                try:
+                    versions = self.storage.list_object_versions(bucket_name, obj_key)
+                    for version in versions:
+                        archived_at_str = version.get("archived_at", "")
+                        if not archived_at_str:
+                            continue
+                        try:
+                            archived_at = datetime.fromisoformat(archived_at_str.replace("Z", "+00:00"))
+                            if archived_at < cutoff:
+                                version_id = version.get("version_id")
+                                if version_id:
+                                    self.storage.delete_object_version(bucket_name, obj_key, version_id)
+                                    result.versions_deleted += 1
+                        except (ValueError, StorageError) as e:
+                            result.errors.append(f"Failed to process orphaned version: {e}")
+                except StorageError:
+                    pass
+        except StorageError as e:
+            result.errors.append(f"Failed to list orphaned objects: {e}")
+
+    def _enforce_abort_multipart(
+        self, bucket_name: str, rule: Dict[str, Any], result: LifecycleResult
+    ) -> None:
+        abort_config = rule.get("AbortIncompleteMultipartUpload", {})
+        days_after = abort_config.get("DaysAfterInitiation")
+        if not days_after:
+            return
+
+        cutoff = datetime.now(timezone.utc) - timedelta(days=days_after)
+
+        try:
+            uploads = self.storage.list_multipart_uploads(bucket_name)
+            for upload in uploads:
+                created_at_str = upload.get("created_at", "")
+                if not created_at_str:
+                    continue
+                try:
+                    created_at = datetime.fromisoformat(created_at_str.replace("Z", "+00:00"))
+                    if created_at < cutoff:
+                        upload_id = upload.get("upload_id")
+                        if upload_id:
+                            self.storage.abort_multipart_upload(bucket_name, upload_id)
+                            result.uploads_aborted += 1
+                except (ValueError, StorageError) as e:
+                    result.errors.append(f"Failed to abort upload: {e}")
+        except StorageError as e:
+            result.errors.append(f"Failed to list multipart uploads: {e}")
+
+    def run_now(self, bucket_name: Optional[str] = None) -> Dict[str, LifecycleResult]:
+        if bucket_name:
+            return {bucket_name: self.enforce_rules(bucket_name)}
+        return self.enforce_all_buckets()
+
+    def get_execution_history(self, bucket_name: str, limit: int = 50, offset: int = 0) -> List[LifecycleExecutionRecord]:
+        if not self.history_store:
+            return []
+        return self.history_store.get_history(bucket_name, limit, offset)

app/notifications.py

@@ -0,0 +1,381 @@
+from __future__ import annotations
+
+import ipaddress
+import json
+import logging
+import queue
+import socket
+import threading
+import time
+import uuid
+from dataclasses import dataclass, field
+from datetime import datetime, timezone
+from pathlib import Path
+from typing import Any, Dict, List, Optional
+from urllib.parse import urlparse
+
+import requests
+
+
+def _is_safe_url(url: str, allow_internal: bool = False) -> bool:
+    """Check if a URL is safe to make requests to (not internal/private).
+
+    Args:
+        url: The URL to check.
+        allow_internal: If True, allows internal/private IP addresses.
+                       Use for self-hosted deployments on internal networks.
+    """
+    try:
+        parsed = urlparse(url)
+        hostname = parsed.hostname
+        if not hostname:
+            return False
+        cloud_metadata_hosts = {
+            "metadata.google.internal",
+            "169.254.169.254",
+        }
+        if hostname.lower() in cloud_metadata_hosts:
+            return False
+        if allow_internal:
+            return True
+        blocked_hosts = {
+            "localhost",
+            "127.0.0.1",
+            "0.0.0.0",
+            "::1",
+            "[::1]",
+        }
+        if hostname.lower() in blocked_hosts:
+            return False
+        try:
+            resolved_ip = socket.gethostbyname(hostname)
+            ip = ipaddress.ip_address(resolved_ip)
+            if ip.is_private or ip.is_loopback or ip.is_link_local or ip.is_reserved:
+                return False
+        except (socket.gaierror, ValueError):
+            return False
+        return True
+    except Exception:
+        return False
+
+logger = logging.getLogger(__name__)
+
+
+@dataclass
+class NotificationEvent:
+    event_name: str
+    bucket_name: str
+    object_key: str
+    object_size: int = 0
+    etag: str = ""
+    version_id: Optional[str] = None
+    timestamp: datetime = field(default_factory=lambda: datetime.now(timezone.utc))
+    request_id: str = field(default_factory=lambda: uuid.uuid4().hex)
+    source_ip: str = ""
+    user_identity: str = ""
+
+    def to_s3_event(self) -> Dict[str, Any]:
+        return {
+            "Records": [
+                {
+                    "eventVersion": "2.1",
+                    "eventSource": "myfsio:s3",
+                    "awsRegion": "local",
+                    "eventTime": self.timestamp.strftime("%Y-%m-%dT%H:%M:%S.000Z"),
+                    "eventName": self.event_name,
+                    "userIdentity": {
+                        "principalId": self.user_identity or "ANONYMOUS",
+                    },
+                    "requestParameters": {
+                        "sourceIPAddress": self.source_ip or "127.0.0.1",
+                    },
+                    "responseElements": {
+                        "x-amz-request-id": self.request_id,
+                        "x-amz-id-2": self.request_id,
+                    },
+                    "s3": {
+                        "s3SchemaVersion": "1.0",
+                        "configurationId": "notification",
+                        "bucket": {
+                            "name": self.bucket_name,
+                            "ownerIdentity": {"principalId": "local"},
+                            "arn": f"arn:aws:s3:::{self.bucket_name}",
+                        },
+                        "object": {
+                            "key": self.object_key,
+                            "size": self.object_size,
+                            "eTag": self.etag,
+                            "versionId": self.version_id or "null",
+                            "sequencer": f"{int(time.time() * 1000):016X}",
+                        },
+                    },
+                }
+            ]
+        }
+
+
+@dataclass
+class WebhookDestination:
+    url: str
+    headers: Dict[str, str] = field(default_factory=dict)
+    timeout_seconds: int = 30
+    retry_count: int = 3
+    retry_delay_seconds: int = 1
+
+    def to_dict(self) -> Dict[str, Any]:
+        return {
+            "url": self.url,
+            "headers": self.headers,
+            "timeout_seconds": self.timeout_seconds,
+            "retry_count": self.retry_count,
+            "retry_delay_seconds": self.retry_delay_seconds,
+        }
+
+    @classmethod
+    def from_dict(cls, data: Dict[str, Any]) -> "WebhookDestination":
+        return cls(
+            url=data.get("url", ""),
+            headers=data.get("headers", {}),
+            timeout_seconds=data.get("timeout_seconds", 30),
+            retry_count=data.get("retry_count", 3),
+            retry_delay_seconds=data.get("retry_delay_seconds", 1),
+        )
+
+
+@dataclass
+class NotificationConfiguration:
+    id: str
+    events: List[str]
+    destination: WebhookDestination
+    prefix_filter: str = ""
+    suffix_filter: str = ""
+
+    def matches_event(self, event_name: str, object_key: str) -> bool:
+        event_match = False
+        for pattern in self.events:
+            if pattern.endswith("*"):
+                base = pattern[:-1]
+                if event_name.startswith(base):
+                    event_match = True
+                    break
+            elif pattern == event_name:
+                event_match = True
+                break
+
+        if not event_match:
+            return False
+
+        if self.prefix_filter and not object_key.startswith(self.prefix_filter):
+            return False
+        if self.suffix_filter and not object_key.endswith(self.suffix_filter):
+            return False
+
+        return True
+
+    def to_dict(self) -> Dict[str, Any]:
+        return {
+            "Id": self.id,
+            "Events": self.events,
+            "Destination": self.destination.to_dict(),
+            "Filter": {
+                "Key": {
+                    "FilterRules": [
+                        {"Name": "prefix", "Value": self.prefix_filter},
+                        {"Name": "suffix", "Value": self.suffix_filter},
+                    ]
+                }
+            },
+        }
+
+    @classmethod
+    def from_dict(cls, data: Dict[str, Any]) -> "NotificationConfiguration":
+        prefix = ""
+        suffix = ""
+        filter_data = data.get("Filter", {})
+        key_filter = filter_data.get("Key", {})
+        for rule in key_filter.get("FilterRules", []):
+            if rule.get("Name") == "prefix":
+                prefix = rule.get("Value", "")
+            elif rule.get("Name") == "suffix":
+                suffix = rule.get("Value", "")
+
+        return cls(
+            id=data.get("Id", uuid.uuid4().hex),
+            events=data.get("Events", []),
+            destination=WebhookDestination.from_dict(data.get("Destination", {})),
+            prefix_filter=prefix,
+            suffix_filter=suffix,
+        )
+
+
+class NotificationService:
+    def __init__(self, storage_root: Path, worker_count: int = 2, allow_internal_endpoints: bool = False):
+        self.storage_root = storage_root
+        self._allow_internal_endpoints = allow_internal_endpoints
+        self._configs: Dict[str, List[NotificationConfiguration]] = {}
+        self._queue: queue.Queue[tuple[NotificationEvent, WebhookDestination]] = queue.Queue()
+        self._workers: List[threading.Thread] = []
+        self._shutdown = threading.Event()
+        self._stats = {
+            "events_queued": 0,
+            "events_sent": 0,
+            "events_failed": 0,
+        }
+
+        for i in range(worker_count):
+            worker = threading.Thread(target=self._worker_loop, name=f"notification-worker-{i}", daemon=True)
+            worker.start()
+            self._workers.append(worker)
+
+    def _config_path(self, bucket_name: str) -> Path:
+        return self.storage_root / ".myfsio.sys" / "buckets" / bucket_name / "notifications.json"
+
+    def get_bucket_notifications(self, bucket_name: str) -> List[NotificationConfiguration]:
+        if bucket_name in self._configs:
+            return self._configs[bucket_name]
+
+        config_path = self._config_path(bucket_name)
+        if not config_path.exists():
+            return []
+
+        try:
+            data = json.loads(config_path.read_text(encoding="utf-8"))
+            configs = [NotificationConfiguration.from_dict(c) for c in data.get("configurations", [])]
+            self._configs[bucket_name] = configs
+            return configs
+        except (json.JSONDecodeError, OSError) as e:
+            logger.warning(f"Failed to load notification config for {bucket_name}: {e}")
+            return []
+
+    def set_bucket_notifications(
+        self, bucket_name: str, configurations: List[NotificationConfiguration]
+    ) -> None:
+        config_path = self._config_path(bucket_name)
+        config_path.parent.mkdir(parents=True, exist_ok=True)
+
+        data = {"configurations": [c.to_dict() for c in configurations]}
+        config_path.write_text(json.dumps(data, indent=2), encoding="utf-8")
+        self._configs[bucket_name] = configurations
+
+    def delete_bucket_notifications(self, bucket_name: str) -> None:
+        config_path = self._config_path(bucket_name)
+        try:
+            if config_path.exists():
+                config_path.unlink()
+        except OSError:
+            pass
+        self._configs.pop(bucket_name, None)
+
+    def emit_event(self, event: NotificationEvent) -> None:
+        configurations = self.get_bucket_notifications(event.bucket_name)
+        if not configurations:
+            return
+
+        for config in configurations:
+            if config.matches_event(event.event_name, event.object_key):
+                self._queue.put((event, config.destination))
+                self._stats["events_queued"] += 1
+                logger.debug(
+                    f"Queued notification for {event.event_name} on {event.bucket_name}/{event.object_key}"
+                )
+
+    def emit_object_created(
+        self,
+        bucket_name: str,
+        object_key: str,
+        *,
+        size: int = 0,
+        etag: str = "",
+        version_id: Optional[str] = None,
+        request_id: str = "",
+        source_ip: str = "",
+        user_identity: str = "",
+        operation: str = "Put",
+    ) -> None:
+        event = NotificationEvent(
+            event_name=f"s3:ObjectCreated:{operation}",
+            bucket_name=bucket_name,
+            object_key=object_key,
+            object_size=size,
+            etag=etag,
+            version_id=version_id,
+            request_id=request_id or uuid.uuid4().hex,
+            source_ip=source_ip,
+            user_identity=user_identity,
+        )
+        self.emit_event(event)
+
+    def emit_object_removed(
+        self,
+        bucket_name: str,
+        object_key: str,
+        *,
+        version_id: Optional[str] = None,
+        request_id: str = "",
+        source_ip: str = "",
+        user_identity: str = "",
+        operation: str = "Delete",
+    ) -> None:
+        event = NotificationEvent(
+            event_name=f"s3:ObjectRemoved:{operation}",
+            bucket_name=bucket_name,
+            object_key=object_key,
+            version_id=version_id,
+            request_id=request_id or uuid.uuid4().hex,
+            source_ip=source_ip,
+            user_identity=user_identity,
+        )
+        self.emit_event(event)
+
+    def _worker_loop(self) -> None:
+        while not self._shutdown.is_set():
+            try:
+                event, destination = self._queue.get(timeout=1.0)
+            except queue.Empty:
+                continue
+
+            try:
+                self._send_notification(event, destination)
+                self._stats["events_sent"] += 1
+            except Exception as e:
+                self._stats["events_failed"] += 1
+                logger.error(f"Failed to send notification: {e}")
+            finally:
+                self._queue.task_done()
+
+    def _send_notification(self, event: NotificationEvent, destination: WebhookDestination) -> None:
+        if not _is_safe_url(destination.url, allow_internal=self._allow_internal_endpoints):
+            raise RuntimeError(f"Blocked request to cloud metadata service (SSRF protection): {destination.url}")
+        payload = event.to_s3_event()
+        headers = {"Content-Type": "application/json", **destination.headers}
+
+        last_error = None
+        for attempt in range(destination.retry_count):
+            try:
+                response = requests.post(
+                    destination.url,
+                    json=payload,
+                    headers=headers,
+                    timeout=destination.timeout_seconds,
+                )
+                if response.status_code < 400:
+                    logger.info(
+                        f"Notification sent: {event.event_name} -> {destination.url} (status={response.status_code})"
+                    )
+                    return
+                last_error = f"HTTP {response.status_code}: {response.text[:200]}"
+            except requests.RequestException as e:
+                last_error = str(e)
+
+            if attempt < destination.retry_count - 1:
+                time.sleep(destination.retry_delay_seconds * (attempt + 1))
+
+        raise RuntimeError(f"Failed after {destination.retry_count} attempts: {last_error}")
+
+    def get_stats(self) -> Dict[str, int]:
+        return dict(self._stats)
+
+    def shutdown(self) -> None:
+        self._shutdown.set()
+        for worker in self._workers:
+            worker.join(timeout=5.0)

app/object_lock.py

@@ -0,0 +1,234 @@
+from __future__ import annotations
+
+import json
+from dataclasses import dataclass
+from datetime import datetime, timezone
+from enum import Enum
+from pathlib import Path
+from typing import Any, Dict, Optional
+
+
+class RetentionMode(Enum):
+    GOVERNANCE = "GOVERNANCE"
+    COMPLIANCE = "COMPLIANCE"
+
+
+class ObjectLockError(Exception):
+    pass
+
+
+@dataclass
+class ObjectLockRetention:
+    mode: RetentionMode
+    retain_until_date: datetime
+
+    def to_dict(self) -> Dict[str, str]:
+        return {
+            "Mode": self.mode.value,
+            "RetainUntilDate": self.retain_until_date.isoformat(),
+        }
+
+    @classmethod
+    def from_dict(cls, data: Dict[str, Any]) -> Optional["ObjectLockRetention"]:
+        if not data:
+            return None
+        mode_str = data.get("Mode")
+        date_str = data.get("RetainUntilDate")
+        if not mode_str or not date_str:
+            return None
+        try:
+            mode = RetentionMode(mode_str)
+            retain_until = datetime.fromisoformat(date_str.replace("Z", "+00:00"))
+            return cls(mode=mode, retain_until_date=retain_until)
+        except (ValueError, KeyError):
+            return None
+
+    def is_expired(self) -> bool:
+        return datetime.now(timezone.utc) > self.retain_until_date
+
+
+@dataclass
+class ObjectLockConfig:
+    enabled: bool = False
+    default_retention: Optional[ObjectLockRetention] = None
+
+    def to_dict(self) -> Dict[str, Any]:
+        result: Dict[str, Any] = {"ObjectLockEnabled": "Enabled" if self.enabled else "Disabled"}
+        if self.default_retention:
+            result["Rule"] = {
+                "DefaultRetention": {
+                    "Mode": self.default_retention.mode.value,
+                    "Days": None,
+                    "Years": None,
+                }
+            }
+        return result
+
+    @classmethod
+    def from_dict(cls, data: Dict[str, Any]) -> "ObjectLockConfig":
+        enabled = data.get("ObjectLockEnabled") == "Enabled"
+        default_retention = None
+        rule = data.get("Rule")
+        if rule and "DefaultRetention" in rule:
+            dr = rule["DefaultRetention"]
+            mode_str = dr.get("Mode", "GOVERNANCE")
+            days = dr.get("Days")
+            years = dr.get("Years")
+            if days or years:
+                from datetime import timedelta
+                now = datetime.now(timezone.utc)
+                if years:
+                    delta = timedelta(days=int(years) * 365)
+                else:
+                    delta = timedelta(days=int(days))
+                default_retention = ObjectLockRetention(
+                    mode=RetentionMode(mode_str),
+                    retain_until_date=now + delta,
+                )
+        return cls(enabled=enabled, default_retention=default_retention)
+
+
+class ObjectLockService:
+    def __init__(self, storage_root: Path):
+        self.storage_root = storage_root
+        self._config_cache: Dict[str, ObjectLockConfig] = {}
+
+    def _bucket_lock_config_path(self, bucket_name: str) -> Path:
+        return self.storage_root / ".myfsio.sys" / "buckets" / bucket_name / "object_lock.json"
+
+    def _object_lock_meta_path(self, bucket_name: str, object_key: str) -> Path:
+        safe_key = object_key.replace("/", "_").replace("\\", "_")
+        return (
+            self.storage_root / ".myfsio.sys" / "buckets" / bucket_name /
+            "locks" / f"{safe_key}.lock.json"
+        )
+
+    def get_bucket_lock_config(self, bucket_name: str) -> ObjectLockConfig:
+        if bucket_name in self._config_cache:
+            return self._config_cache[bucket_name]
+
+        config_path = self._bucket_lock_config_path(bucket_name)
+        if not config_path.exists():
+            return ObjectLockConfig(enabled=False)
+
+        try:
+            data = json.loads(config_path.read_text(encoding="utf-8"))
+            config = ObjectLockConfig.from_dict(data)
+            self._config_cache[bucket_name] = config
+            return config
+        except (json.JSONDecodeError, OSError):
+            return ObjectLockConfig(enabled=False)
+
+    def set_bucket_lock_config(self, bucket_name: str, config: ObjectLockConfig) -> None:
+        config_path = self._bucket_lock_config_path(bucket_name)
+        config_path.parent.mkdir(parents=True, exist_ok=True)
+        config_path.write_text(json.dumps(config.to_dict()), encoding="utf-8")
+        self._config_cache[bucket_name] = config
+
+    def enable_bucket_lock(self, bucket_name: str) -> None:
+        config = self.get_bucket_lock_config(bucket_name)
+        config.enabled = True
+        self.set_bucket_lock_config(bucket_name, config)
+
+    def is_bucket_lock_enabled(self, bucket_name: str) -> bool:
+        return self.get_bucket_lock_config(bucket_name).enabled
+
+    def get_object_retention(self, bucket_name: str, object_key: str) -> Optional[ObjectLockRetention]:
+        meta_path = self._object_lock_meta_path(bucket_name, object_key)
+        if not meta_path.exists():
+            return None
+        try:
+            data = json.loads(meta_path.read_text(encoding="utf-8"))
+            return ObjectLockRetention.from_dict(data.get("retention", {}))
+        except (json.JSONDecodeError, OSError):
+            return None
+
+    def set_object_retention(
+        self,
+        bucket_name: str,
+        object_key: str,
+        retention: ObjectLockRetention,
+        bypass_governance: bool = False,
+    ) -> None:
+        existing = self.get_object_retention(bucket_name, object_key)
+        if existing and not existing.is_expired():
+            if existing.mode == RetentionMode.COMPLIANCE:
+                raise ObjectLockError(
+                    "Cannot modify retention on object with COMPLIANCE mode until retention expires"
+                )
+            if existing.mode == RetentionMode.GOVERNANCE and not bypass_governance:
+                raise ObjectLockError(
+                    "Cannot modify GOVERNANCE retention without bypass-governance permission"
+                )
+
+        meta_path = self._object_lock_meta_path(bucket_name, object_key)
+        meta_path.parent.mkdir(parents=True, exist_ok=True)
+
+        existing_data: Dict[str, Any] = {}
+        if meta_path.exists():
+            try:
+                existing_data = json.loads(meta_path.read_text(encoding="utf-8"))
+            except (json.JSONDecodeError, OSError):
+                pass
+
+        existing_data["retention"] = retention.to_dict()
+        meta_path.write_text(json.dumps(existing_data), encoding="utf-8")
+
+    def get_legal_hold(self, bucket_name: str, object_key: str) -> bool:
+        meta_path = self._object_lock_meta_path(bucket_name, object_key)
+        if not meta_path.exists():
+            return False
+        try:
+            data = json.loads(meta_path.read_text(encoding="utf-8"))
+            return data.get("legal_hold", False)
+        except (json.JSONDecodeError, OSError):
+            return False
+
+    def set_legal_hold(self, bucket_name: str, object_key: str, enabled: bool) -> None:
+        meta_path = self._object_lock_meta_path(bucket_name, object_key)
+        meta_path.parent.mkdir(parents=True, exist_ok=True)
+
+        existing_data: Dict[str, Any] = {}
+        if meta_path.exists():
+            try:
+                existing_data = json.loads(meta_path.read_text(encoding="utf-8"))
+            except (json.JSONDecodeError, OSError):
+                pass
+
+        existing_data["legal_hold"] = enabled
+        meta_path.write_text(json.dumps(existing_data), encoding="utf-8")
+
+    def can_delete_object(
+        self,
+        bucket_name: str,
+        object_key: str,
+        bypass_governance: bool = False,
+    ) -> tuple[bool, str]:
+        if self.get_legal_hold(bucket_name, object_key):
+            return False, "Object is under legal hold"
+
+        retention = self.get_object_retention(bucket_name, object_key)
+        if retention and not retention.is_expired():
+            if retention.mode == RetentionMode.COMPLIANCE:
+                return False, f"Object is locked in COMPLIANCE mode until {retention.retain_until_date.isoformat()}"
+            if retention.mode == RetentionMode.GOVERNANCE:
+                if not bypass_governance:
+                    return False, f"Object is locked in GOVERNANCE mode until {retention.retain_until_date.isoformat()}"
+
+        return True, ""
+
+    def can_overwrite_object(
+        self,
+        bucket_name: str,
+        object_key: str,
+        bypass_governance: bool = False,
+    ) -> tuple[bool, str]:
+        return self.can_delete_object(bucket_name, object_key, bypass_governance)
+
+    def delete_object_lock_metadata(self, bucket_name: str, object_key: str) -> None:
+        meta_path = self._object_lock_meta_path(bucket_name, object_key)
+        try:
+            if meta_path.exists():
+                meta_path.unlink()
+        except OSError:
+            pass

app/operation_metrics.py

@@ -0,0 +1,300 @@
+from __future__ import annotations
+
+import json
+import logging
+import random
+import threading
+import time
+from dataclasses import dataclass, field
+from datetime import datetime, timezone
+from pathlib import Path
+from typing import Any, Dict, List, Optional
+
+MAX_LATENCY_SAMPLES = 5000
+
+logger = logging.getLogger(__name__)
+
+
+@dataclass
+class OperationStats:
+    count: int = 0
+    success_count: int = 0
+    error_count: int = 0
+    latency_sum_ms: float = 0.0
+    latency_min_ms: float = float("inf")
+    latency_max_ms: float = 0.0
+    bytes_in: int = 0
+    bytes_out: int = 0
+    latency_samples: List[float] = field(default_factory=list)
+
+    @staticmethod
+    def _compute_percentile(sorted_data: List[float], p: float) -> float:
+        if not sorted_data:
+            return 0.0
+        k = (len(sorted_data) - 1) * (p / 100.0)
+        f = int(k)
+        c = min(f + 1, len(sorted_data) - 1)
+        d = k - f
+        return sorted_data[f] + d * (sorted_data[c] - sorted_data[f])
+
+    def record(self, latency_ms: float, success: bool, bytes_in: int = 0, bytes_out: int = 0) -> None:
+        self.count += 1
+        if success:
+            self.success_count += 1
+        else:
+            self.error_count += 1
+        self.latency_sum_ms += latency_ms
+        if latency_ms < self.latency_min_ms:
+            self.latency_min_ms = latency_ms
+        if latency_ms > self.latency_max_ms:
+            self.latency_max_ms = latency_ms
+        self.bytes_in += bytes_in
+        self.bytes_out += bytes_out
+        if len(self.latency_samples) < MAX_LATENCY_SAMPLES:
+            self.latency_samples.append(latency_ms)
+        else:
+            j = random.randint(0, self.count - 1)
+            if j < MAX_LATENCY_SAMPLES:
+                self.latency_samples[j] = latency_ms
+
+    def to_dict(self) -> Dict[str, Any]:
+        avg_latency = self.latency_sum_ms / self.count if self.count > 0 else 0.0
+        min_latency = self.latency_min_ms if self.latency_min_ms != float("inf") else 0.0
+        sorted_latencies = sorted(self.latency_samples)
+        return {
+            "count": self.count,
+            "success_count": self.success_count,
+            "error_count": self.error_count,
+            "latency_avg_ms": round(avg_latency, 2),
+            "latency_min_ms": round(min_latency, 2),
+            "latency_max_ms": round(self.latency_max_ms, 2),
+            "latency_p50_ms": round(self._compute_percentile(sorted_latencies, 50), 2),
+            "latency_p95_ms": round(self._compute_percentile(sorted_latencies, 95), 2),
+            "latency_p99_ms": round(self._compute_percentile(sorted_latencies, 99), 2),
+            "bytes_in": self.bytes_in,
+            "bytes_out": self.bytes_out,
+        }
+
+    def merge(self, other: "OperationStats") -> None:
+        self.count += other.count
+        self.success_count += other.success_count
+        self.error_count += other.error_count
+        self.latency_sum_ms += other.latency_sum_ms
+        if other.latency_min_ms < self.latency_min_ms:
+            self.latency_min_ms = other.latency_min_ms
+        if other.latency_max_ms > self.latency_max_ms:
+            self.latency_max_ms = other.latency_max_ms
+        self.bytes_in += other.bytes_in
+        self.bytes_out += other.bytes_out
+        combined = self.latency_samples + other.latency_samples
+        if len(combined) > MAX_LATENCY_SAMPLES:
+            random.shuffle(combined)
+            combined = combined[:MAX_LATENCY_SAMPLES]
+        self.latency_samples = combined
+
+
+@dataclass
+class MetricsSnapshot:
+    timestamp: datetime
+    window_seconds: int
+    by_method: Dict[str, Dict[str, Any]]
+    by_endpoint: Dict[str, Dict[str, Any]]
+    by_status_class: Dict[str, int]
+    error_codes: Dict[str, int]
+    totals: Dict[str, Any]
+
+    def to_dict(self) -> Dict[str, Any]:
+        return {
+            "timestamp": self.timestamp.isoformat(),
+            "window_seconds": self.window_seconds,
+            "by_method": self.by_method,
+            "by_endpoint": self.by_endpoint,
+            "by_status_class": self.by_status_class,
+            "error_codes": self.error_codes,
+            "totals": self.totals,
+        }
+
+    @classmethod
+    def from_dict(cls, data: Dict[str, Any]) -> "MetricsSnapshot":
+        return cls(
+            timestamp=datetime.fromisoformat(data["timestamp"]),
+            window_seconds=data.get("window_seconds", 300),
+            by_method=data.get("by_method", {}),
+            by_endpoint=data.get("by_endpoint", {}),
+            by_status_class=data.get("by_status_class", {}),
+            error_codes=data.get("error_codes", {}),
+            totals=data.get("totals", {}),
+        )
+
+
+class OperationMetricsCollector:
+    def __init__(
+        self,
+        storage_root: Path,
+        interval_minutes: int = 5,
+        retention_hours: int = 24,
+    ):
+        self.storage_root = storage_root
+        self.interval_seconds = interval_minutes * 60
+        self.retention_hours = retention_hours
+        self._lock = threading.Lock()
+        self._by_method: Dict[str, OperationStats] = {}
+        self._by_endpoint: Dict[str, OperationStats] = {}
+        self._by_status_class: Dict[str, int] = {}
+        self._error_codes: Dict[str, int] = {}
+        self._totals = OperationStats()
+        self._window_start = time.time()
+        self._shutdown = threading.Event()
+        self._snapshots: List[MetricsSnapshot] = []
+
+        self._load_history()
+
+        self._snapshot_thread = threading.Thread(
+            target=self._snapshot_loop, name="operation-metrics-snapshot", daemon=True
+        )
+        self._snapshot_thread.start()
+
+    def _config_path(self) -> Path:
+        return self.storage_root / ".myfsio.sys" / "config" / "operation_metrics.json"
+
+    def _load_history(self) -> None:
+        config_path = self._config_path()
+        if not config_path.exists():
+            return
+        try:
+            data = json.loads(config_path.read_text(encoding="utf-8"))
+            snapshots_data = data.get("snapshots", [])
+            self._snapshots = [MetricsSnapshot.from_dict(s) for s in snapshots_data]
+            self._prune_old_snapshots()
+        except (json.JSONDecodeError, OSError, KeyError) as e:
+            logger.warning(f"Failed to load operation metrics history: {e}")
+
+    def _save_history(self) -> None:
+        config_path = self._config_path()
+        config_path.parent.mkdir(parents=True, exist_ok=True)
+        try:
+            data = {"snapshots": [s.to_dict() for s in self._snapshots]}
+            config_path.write_text(json.dumps(data, indent=2), encoding="utf-8")
+        except OSError as e:
+            logger.warning(f"Failed to save operation metrics history: {e}")
+
+    def _prune_old_snapshots(self) -> None:
+        if not self._snapshots:
+            return
+        cutoff = datetime.now(timezone.utc).timestamp() - (self.retention_hours * 3600)
+        self._snapshots = [
+            s for s in self._snapshots if s.timestamp.timestamp() > cutoff
+        ]
+
+    def _snapshot_loop(self) -> None:
+        while not self._shutdown.is_set():
+            self._shutdown.wait(timeout=self.interval_seconds)
+            if not self._shutdown.is_set():
+                self._take_snapshot()
+
+    def _take_snapshot(self) -> None:
+        with self._lock:
+            now = datetime.now(timezone.utc)
+            window_seconds = int(time.time() - self._window_start)
+
+            snapshot = MetricsSnapshot(
+                timestamp=now,
+                window_seconds=window_seconds,
+                by_method={k: v.to_dict() for k, v in self._by_method.items()},
+                by_endpoint={k: v.to_dict() for k, v in self._by_endpoint.items()},
+                by_status_class=dict(self._by_status_class),
+                error_codes=dict(self._error_codes),
+                totals=self._totals.to_dict(),
+            )
+
+            self._snapshots.append(snapshot)
+            self._prune_old_snapshots()
+            self._save_history()
+
+            self._by_method.clear()
+            self._by_endpoint.clear()
+            self._by_status_class.clear()
+            self._error_codes.clear()
+            self._totals = OperationStats()
+            self._window_start = time.time()
+
+    def record_request(
+        self,
+        method: str,
+        endpoint_type: str,
+        status_code: int,
+        latency_ms: float,
+        bytes_in: int = 0,
+        bytes_out: int = 0,
+        error_code: Optional[str] = None,
+    ) -> None:
+        success = 200 <= status_code < 400
+        status_class = f"{status_code // 100}xx"
+
+        with self._lock:
+            if method not in self._by_method:
+                self._by_method[method] = OperationStats()
+            self._by_method[method].record(latency_ms, success, bytes_in, bytes_out)
+
+            if endpoint_type not in self._by_endpoint:
+                self._by_endpoint[endpoint_type] = OperationStats()
+            self._by_endpoint[endpoint_type].record(latency_ms, success, bytes_in, bytes_out)
+
+            self._by_status_class[status_class] = self._by_status_class.get(status_class, 0) + 1
+
+            if error_code:
+                self._error_codes[error_code] = self._error_codes.get(error_code, 0) + 1
+
+            self._totals.record(latency_ms, success, bytes_in, bytes_out)
+
+    def get_current_stats(self) -> Dict[str, Any]:
+        with self._lock:
+            window_seconds = int(time.time() - self._window_start)
+            return {
+                "timestamp": datetime.now(timezone.utc).isoformat(),
+                "window_seconds": window_seconds,
+                "by_method": {k: v.to_dict() for k, v in self._by_method.items()},
+                "by_endpoint": {k: v.to_dict() for k, v in self._by_endpoint.items()},
+                "by_status_class": dict(self._by_status_class),
+                "error_codes": dict(self._error_codes),
+                "totals": self._totals.to_dict(),
+            }
+
+    def get_history(self, hours: Optional[int] = None) -> List[Dict[str, Any]]:
+        with self._lock:
+            snapshots = list(self._snapshots)
+
+        if hours:
+            cutoff = datetime.now(timezone.utc).timestamp() - (hours * 3600)
+            snapshots = [s for s in snapshots if s.timestamp.timestamp() > cutoff]
+
+        return [s.to_dict() for s in snapshots]
+
+    def shutdown(self) -> None:
+        self._shutdown.set()
+        self._take_snapshot()
+        self._snapshot_thread.join(timeout=5.0)
+
+
+def classify_endpoint(path: str) -> str:
+    if not path or path == "/":
+        return "service"
+
+    path = path.rstrip("/")
+
+    if path.startswith("/ui"):
+        return "ui"
+
+    if path.startswith("/kms"):
+        return "kms"
+
+    if path.startswith("/myfsio"):
+        return "service"
+
+    parts = path.lstrip("/").split("/")
+    if len(parts) == 0:
+        return "service"
+    elif len(parts) == 1:
+        return "bucket"
+    else:
+        return "object"

app/replication.py

@@ -1,4 +1,3 @@
-"""Background replication worker."""
 from __future__ import annotations
 
 import json
@@ -9,7 +8,7 @@ import time
 from concurrent.futures import ThreadPoolExecutor
 from dataclasses import dataclass, field
 from pathlib import Path
-from typing import Dict, Optional
+from typing import Any, Dict, List, Optional
 
 import boto3
 from botocore.config import Config
@@ -25,15 +24,49 @@ REPLICATION_USER_AGENT = "S3ReplicationAgent/1.0"
 
 REPLICATION_MODE_NEW_ONLY = "new_only"
 REPLICATION_MODE_ALL = "all"
+REPLICATION_MODE_BIDIRECTIONAL = "bidirectional"
+
+
+def _create_s3_client(
+    connection: RemoteConnection,
+    *,
+    health_check: bool = False,
+    connect_timeout: int = 5,
+    read_timeout: int = 30,
+    max_retries: int = 2,
+) -> Any:
+    """Create a boto3 S3 client for the given connection.
+    Args:
+        connection: Remote S3 connection configuration
+        health_check: If True, use minimal retries for quick health checks
+    """
+    config = Config(
+        user_agent_extra=REPLICATION_USER_AGENT,
+        connect_timeout=connect_timeout,
+        read_timeout=read_timeout,
+        retries={'max_attempts': 1 if health_check else max_retries},
+        signature_version='s3v4',
+        s3={'addressing_style': 'path'},
+        request_checksum_calculation='when_required',
+        response_checksum_validation='when_required',
+    )
+    return boto3.client(
+        "s3",
+        endpoint_url=connection.endpoint_url,
+        aws_access_key_id=connection.access_key,
+        aws_secret_access_key=connection.secret_key,
+        region_name=connection.region or 'us-east-1',
+        config=config,
+    )
 
 
 @dataclass
 class ReplicationStats:
     """Statistics for replication operations - computed dynamically."""
-    objects_synced: int = 0          # Objects that exist in both source and destination
-    objects_pending: int = 0         # Objects in source but not in destination
-    objects_orphaned: int = 0        # Objects in destination but not in source (will be deleted)
-    bytes_synced: int = 0            # Total bytes synced to destination
+    objects_synced: int = 0
+    objects_pending: int = 0
+    objects_orphaned: int = 0
+    bytes_synced: int = 0      
     last_sync_at: Optional[float] = None
     last_sync_key: Optional[str] = None
     
@@ -59,16 +92,53 @@ class ReplicationStats:
         )
 
 
+@dataclass
+class ReplicationFailure:
+    object_key: str
+    error_message: str
+    timestamp: float
+    failure_count: int
+    bucket_name: str
+    action: str
+    last_error_code: Optional[str] = None
+
+    def to_dict(self) -> dict:
+        return {
+            "object_key": self.object_key,
+            "error_message": self.error_message,
+            "timestamp": self.timestamp,
+            "failure_count": self.failure_count,
+            "bucket_name": self.bucket_name,
+            "action": self.action,
+            "last_error_code": self.last_error_code,
+        }
+
+    @classmethod
+    def from_dict(cls, data: dict) -> "ReplicationFailure":
+        return cls(
+            object_key=data["object_key"],
+            error_message=data["error_message"],
+            timestamp=data["timestamp"],
+            failure_count=data["failure_count"],
+            bucket_name=data["bucket_name"],
+            action=data["action"],
+            last_error_code=data.get("last_error_code"),
+        )
+
+
 @dataclass
 class ReplicationRule:
     bucket_name: str
     target_connection_id: str
     target_bucket: str
     enabled: bool = True
-    mode: str = REPLICATION_MODE_NEW_ONLY 
+    mode: str = REPLICATION_MODE_NEW_ONLY
     created_at: Optional[float] = None
     stats: ReplicationStats = field(default_factory=ReplicationStats)
-    
+    sync_deletions: bool = True
+    last_pull_at: Optional[float] = None
+    filter_prefix: Optional[str] = None
+
     def to_dict(self) -> dict:
         return {
             "bucket_name": self.bucket_name,
@@ -78,31 +148,159 @@ class ReplicationRule:
             "mode": self.mode,
             "created_at": self.created_at,
             "stats": self.stats.to_dict(),
+            "sync_deletions": self.sync_deletions,
+            "last_pull_at": self.last_pull_at,
+            "filter_prefix": self.filter_prefix,
         }
-    
+
     @classmethod
     def from_dict(cls, data: dict) -> "ReplicationRule":
         stats_data = data.pop("stats", {})
-        # Handle old rules without mode/created_at
         if "mode" not in data:
             data["mode"] = REPLICATION_MODE_NEW_ONLY
         if "created_at" not in data:
             data["created_at"] = None
+        if "sync_deletions" not in data:
+            data["sync_deletions"] = True
+        if "last_pull_at" not in data:
+            data["last_pull_at"] = None
+        if "filter_prefix" not in data:
+            data["filter_prefix"] = None
         rule = cls(**data)
         rule.stats = ReplicationStats.from_dict(stats_data) if stats_data else ReplicationStats()
         return rule
 
 
+class ReplicationFailureStore:
+    def __init__(self, storage_root: Path, max_failures_per_bucket: int = 50) -> None:
+        self.storage_root = storage_root
+        self.max_failures_per_bucket = max_failures_per_bucket
+        self._lock = threading.Lock()
+        self._cache: Dict[str, List[ReplicationFailure]] = {}
+
+    def _get_failures_path(self, bucket_name: str) -> Path:
+        return self.storage_root / ".myfsio.sys" / "buckets" / bucket_name / "replication_failures.json"
+
+    def _load_from_disk(self, bucket_name: str) -> List[ReplicationFailure]:
+        path = self._get_failures_path(bucket_name)
+        if not path.exists():
+            return []
+        try:
+            with open(path, "r") as f:
+                data = json.load(f)
+                return [ReplicationFailure.from_dict(d) for d in data.get("failures", [])]
+        except (OSError, ValueError, KeyError) as e:
+            logger.error(f"Failed to load replication failures for {bucket_name}: {e}")
+            return []
+
+    def _save_to_disk(self, bucket_name: str, failures: List[ReplicationFailure]) -> None:
+        path = self._get_failures_path(bucket_name)
+        path.parent.mkdir(parents=True, exist_ok=True)
+        data = {"failures": [f.to_dict() for f in failures[:self.max_failures_per_bucket]]}
+        try:
+            with open(path, "w") as f:
+                json.dump(data, f, indent=2)
+        except OSError as e:
+            logger.error(f"Failed to save replication failures for {bucket_name}: {e}")
+
+    def load_failures(self, bucket_name: str) -> List[ReplicationFailure]:
+        if bucket_name in self._cache:
+            return list(self._cache[bucket_name])
+        failures = self._load_from_disk(bucket_name)
+        self._cache[bucket_name] = failures
+        return list(failures)
+
+    def save_failures(self, bucket_name: str, failures: List[ReplicationFailure]) -> None:
+        trimmed = failures[:self.max_failures_per_bucket]
+        self._cache[bucket_name] = trimmed
+        self._save_to_disk(bucket_name, trimmed)
+
+    def add_failure(self, bucket_name: str, failure: ReplicationFailure) -> None:
+        with self._lock:
+            failures = self.load_failures(bucket_name)
+            existing = next((f for f in failures if f.object_key == failure.object_key), None)
+            if existing:
+                existing.failure_count += 1
+                existing.timestamp = failure.timestamp
+                existing.error_message = failure.error_message
+                existing.last_error_code = failure.last_error_code
+            else:
+                failures.insert(0, failure)
+            self.save_failures(bucket_name, failures)
+
+    def remove_failure(self, bucket_name: str, object_key: str) -> bool:
+        with self._lock:
+            failures = self.load_failures(bucket_name)
+            original_len = len(failures)
+            failures = [f for f in failures if f.object_key != object_key]
+            if len(failures) < original_len:
+                self.save_failures(bucket_name, failures)
+                return True
+            return False
+
+    def clear_failures(self, bucket_name: str) -> None:
+        with self._lock:
+            self._cache.pop(bucket_name, None)
+            path = self._get_failures_path(bucket_name)
+            if path.exists():
+                path.unlink()
+
+    def get_failure(self, bucket_name: str, object_key: str) -> Optional[ReplicationFailure]:
+        failures = self.load_failures(bucket_name)
+        return next((f for f in failures if f.object_key == object_key), None)
+
+    def get_failure_count(self, bucket_name: str) -> int:
+        return len(self.load_failures(bucket_name))
+
+
 class ReplicationManager:
-    def __init__(self, storage: ObjectStorage, connections: ConnectionStore, rules_path: Path) -> None:
+    def __init__(
+        self,
+        storage: ObjectStorage,
+        connections: ConnectionStore,
+        rules_path: Path,
+        storage_root: Path,
+        connect_timeout: int = 5,
+        read_timeout: int = 30,
+        max_retries: int = 2,
+        streaming_threshold_bytes: int = 10 * 1024 * 1024,
+        max_failures_per_bucket: int = 50,
+    ) -> None:
         self.storage = storage
         self.connections = connections
         self.rules_path = rules_path
+        self.storage_root = storage_root
+        self.connect_timeout = connect_timeout
+        self.read_timeout = read_timeout
+        self.max_retries = max_retries
+        self.streaming_threshold_bytes = streaming_threshold_bytes
         self._rules: Dict[str, ReplicationRule] = {}
         self._stats_lock = threading.Lock()
         self._executor = ThreadPoolExecutor(max_workers=4, thread_name_prefix="ReplicationWorker")
+        self._shutdown = False
+        self.failure_store = ReplicationFailureStore(storage_root, max_failures_per_bucket)
         self.reload_rules()
 
+    def _create_client(self, connection: RemoteConnection, *, health_check: bool = False) -> Any:
+        """Create an S3 client with the manager's configured timeouts."""
+        return _create_s3_client(
+            connection,
+            health_check=health_check,
+            connect_timeout=self.connect_timeout,
+            read_timeout=self.read_timeout,
+            max_retries=self.max_retries,
+        )
+
+    def shutdown(self, wait: bool = True) -> None:
+        """Shutdown the replication executor gracefully.
+
+        Args:
+            wait: If True, wait for pending tasks to complete
+        """
+        self._shutdown = True
+        self._executor.shutdown(wait=wait)
+        logger.info("Replication manager shut down")
+
     def reload_rules(self) -> None:
         if not self.rules_path.exists():
             self._rules = {}
@@ -121,13 +319,36 @@ class ReplicationManager:
         with open(self.rules_path, "w") as f:
             json.dump(data, f, indent=2)
 
+    def check_endpoint_health(self, connection: RemoteConnection) -> bool:
+        """Check if a remote endpoint is reachable and responsive.
+
+        Returns True if endpoint is healthy, False otherwise.
+        Uses short timeouts to prevent blocking.
+        """
+        try:
+            s3 = self._create_client(connection, health_check=True)
+            s3.list_buckets()
+            return True
+        except Exception as e:
+            logger.warning(f"Endpoint health check failed for {connection.name} ({connection.endpoint_url}): {e}")
+            return False
+
     def get_rule(self, bucket_name: str) -> Optional[ReplicationRule]:
         return self._rules.get(bucket_name)
 
+    def list_rules(self) -> List[ReplicationRule]:
+        return list(self._rules.values())
+
     def set_rule(self, rule: ReplicationRule) -> None:
+        old_rule = self._rules.get(rule.bucket_name)
+        was_all_mode = old_rule and old_rule.mode == REPLICATION_MODE_ALL if old_rule else False
         self._rules[rule.bucket_name] = rule
         self.save_rules()
 
+        if rule.mode == REPLICATION_MODE_ALL and rule.enabled and not was_all_mode:
+            logger.info(f"Replication mode ALL enabled for {rule.bucket_name}, triggering sync of existing objects")
+            self._executor.submit(self.replicate_existing_objects, rule.bucket_name)
+
     def delete_rule(self, bucket_name: str) -> None:
         if bucket_name in self._rules:
             del self._rules[bucket_name]
@@ -151,22 +372,14 @@ class ReplicationManager:
         
         connection = self.connections.get(rule.target_connection_id)
         if not connection:
-            return rule.stats  # Return cached stats if connection unavailable
+            return rule.stats
         
         try:
-            # Get source objects
             source_objects = self.storage.list_objects_all(bucket_name)
             source_keys = {obj.key: obj.size for obj in source_objects}
-            
-            # Get destination objects
-            s3 = boto3.client(
-                "s3",
-                endpoint_url=connection.endpoint_url,
-                aws_access_key_id=connection.access_key,
-                aws_secret_access_key=connection.secret_key,
-                region_name=connection.region,
-            )
-            
+
+            s3 = self._create_client(connection)
+
             dest_keys = set()
             bytes_synced = 0
             paginator = s3.get_paginator('list_objects_v2')
@@ -178,24 +391,18 @@ class ReplicationManager:
                             bytes_synced += obj.get('Size', 0)
             except ClientError as e:
                 if e.response['Error']['Code'] == 'NoSuchBucket':
-                    # Destination bucket doesn't exist yet
                     dest_keys = set()
                 else:
                     raise
             
-            # Compute stats
-            synced = source_keys.keys() & dest_keys  # Objects in both
-            orphaned = dest_keys - source_keys.keys()  # In dest but not source
+            synced = source_keys.keys() & dest_keys  
+            orphaned = dest_keys - source_keys.keys() 
             
-            # For "new_only" mode, we can't determine pending since we don't know
-            # which objects existed before replication was enabled. Only "all" mode
-            # should show pending (objects that should be replicated but aren't yet).
             if rule.mode == REPLICATION_MODE_ALL:
-                pending = source_keys.keys() - dest_keys  # In source but not dest
+                pending = source_keys.keys() - dest_keys 
             else:
-                pending = set()  # New-only mode: don't show pre-existing as pending
+                pending = set()
             
-            # Update cached stats with computed values
             rule.stats.objects_synced = len(synced)
             rule.stats.objects_pending = len(pending)
             rule.stats.objects_orphaned = len(orphaned)
@@ -205,7 +412,7 @@ class ReplicationManager:
             
         except (ClientError, StorageError) as e:
             logger.error(f"Failed to compute sync status for {bucket_name}: {e}")
-            return rule.stats  # Return cached stats on error
+            return rule.stats
     
     def replicate_existing_objects(self, bucket_name: str) -> None:
         """Trigger replication for all existing objects in a bucket."""
@@ -218,6 +425,10 @@ class ReplicationManager:
             logger.warning(f"Cannot replicate existing objects: Connection {rule.target_connection_id} not found")
             return
         
+        if not self.check_endpoint_health(connection):
+            logger.warning(f"Cannot replicate existing objects: Endpoint {connection.name} ({connection.endpoint_url}) is not reachable")
+            return
+        
         try:
             objects = self.storage.list_objects_all(bucket_name)
             logger.info(f"Starting replication of {len(objects)} existing objects from {bucket_name}")
@@ -233,13 +444,7 @@ class ReplicationManager:
             raise ValueError(f"Connection {connection_id} not found")
 
         try:
-            s3 = boto3.client(
-                "s3",
-                endpoint_url=connection.endpoint_url,
-                aws_access_key_id=connection.access_key,
-                aws_secret_access_key=connection.secret_key,
-                region_name=connection.region,
-            )
+            s3 = self._create_client(connection)
             s3.create_bucket(Bucket=bucket_name)
         except ClientError as e:
             logger.error(f"Failed to create remote bucket {bucket_name}: {e}")
@@ -255,39 +460,53 @@ class ReplicationManager:
             logger.warning(f"Replication skipped for {bucket_name}/{object_key}: Connection {rule.target_connection_id} not found")
             return
 
+        if not self.check_endpoint_health(connection):
+            logger.warning(f"Replication skipped for {bucket_name}/{object_key}: Endpoint {connection.name} ({connection.endpoint_url}) is not reachable")
+            return
+
         self._executor.submit(self._replicate_task, bucket_name, object_key, rule, connection, action)
 
     def _replicate_task(self, bucket_name: str, object_key: str, rule: ReplicationRule, conn: RemoteConnection, action: str) -> None:
+        if self._shutdown:
+            return
+
+        current_rule = self.get_rule(bucket_name)
+        if not current_rule or not current_rule.enabled:
+            logger.debug(f"Replication skipped for {bucket_name}/{object_key}: rule disabled or removed")
+            return
+
         if ".." in object_key or object_key.startswith("/") or object_key.startswith("\\"):
             logger.error(f"Invalid object key in replication (path traversal attempt): {object_key}")
             return
-        
+
         try:
             from .storage import ObjectStorage
             ObjectStorage._sanitize_object_key(object_key)
         except StorageError as e:
             logger.error(f"Object key validation failed in replication: {e}")
             return
-        
-        file_size = 0
+
         try:
-            config = Config(user_agent_extra=REPLICATION_USER_AGENT)
-            s3 = boto3.client(
-                "s3",
-                endpoint_url=conn.endpoint_url,
-                aws_access_key_id=conn.access_key,
-                aws_secret_access_key=conn.secret_key,
-                region_name=conn.region,
-                config=config,
-            )
+            s3 = self._create_client(conn)
 
             if action == "delete":
                 try:
                     s3.delete_object(Bucket=rule.target_bucket, Key=object_key)
                     logger.info(f"Replicated DELETE {bucket_name}/{object_key} to {conn.name} ({rule.target_bucket})")
                     self._update_last_sync(bucket_name, object_key)
+                    self.failure_store.remove_failure(bucket_name, object_key)
                 except ClientError as e:
+                    error_code = e.response.get('Error', {}).get('Code')
                     logger.error(f"Replication DELETE failed for {bucket_name}/{object_key}: {e}")
+                    self.failure_store.add_failure(bucket_name, ReplicationFailure(
+                        object_key=object_key,
+                        error_message=str(e),
+                        timestamp=time.time(),
+                        failure_count=1,
+                        bucket_name=bucket_name,
+                        action="delete",
+                        last_error_code=error_code,
+                    ))
                 return
 
             try:
@@ -296,61 +515,153 @@ class ReplicationManager:
                 logger.error(f"Source object not found: {bucket_name}/{object_key}")
                 return
 
-            metadata = self.storage.get_object_metadata(bucket_name, object_key)
-
-            extra_args = {}
-            if metadata:
-                extra_args["Metadata"] = metadata
-            
-            # Guess content type to prevent corruption/wrong handling
             content_type, _ = mimetypes.guess_type(path)
             file_size = path.stat().st_size
 
             logger.info(f"Replicating {bucket_name}/{object_key}: Size={file_size}, ContentType={content_type}")
 
-            try:
-                with path.open("rb") as f:
-                    s3.put_object(
-                        Bucket=rule.target_bucket,
-                        Key=object_key,
-                        Body=f,
-                        ContentLength=file_size,
-                        ContentType=content_type or "application/octet-stream",
-                        Metadata=metadata or {}
+            def do_upload() -> None:
+                """Upload object using appropriate method based on file size.
+
+                For small files (< 10 MiB): Read into memory for simpler handling
+                For large files: Use streaming upload to avoid memory issues
+                """
+                extra_args = {}
+                if content_type:
+                    extra_args["ContentType"] = content_type
+
+                if file_size >= self.streaming_threshold_bytes:
+                    s3.upload_file(
+                        str(path),
+                        rule.target_bucket,
+                        object_key,
+                        ExtraArgs=extra_args if extra_args else None,
                     )
+                else:
+                    file_content = path.read_bytes()
+                    put_kwargs = {
+                        "Bucket": rule.target_bucket,
+                        "Key": object_key,
+                        "Body": file_content,
+                        **extra_args,
+                    }
+                    s3.put_object(**put_kwargs)
+
+            try:
+                do_upload()
             except (ClientError, S3UploadFailedError) as e:
-                is_no_bucket = False
+                error_code = None
                 if isinstance(e, ClientError):
-                    if e.response['Error']['Code'] == 'NoSuchBucket':
-                        is_no_bucket = True
+                    error_code = e.response['Error']['Code']
                 elif isinstance(e, S3UploadFailedError):
                     if "NoSuchBucket" in str(e):
-                        is_no_bucket = True
+                        error_code = 'NoSuchBucket'
 
-                if is_no_bucket:
+                if error_code == 'NoSuchBucket':
                     logger.info(f"Target bucket {rule.target_bucket} not found. Attempting to create it.")
+                    bucket_ready = False
                     try:
                         s3.create_bucket(Bucket=rule.target_bucket)
-                        # Retry upload
-                        with path.open("rb") as f:
-                            s3.put_object(
-                                Bucket=rule.target_bucket,
-                                Key=object_key,
-                                Body=f,
-                                ContentLength=file_size,
-                                ContentType=content_type or "application/octet-stream",
-                                Metadata=metadata or {}
-                            )
-                    except Exception as create_err:
-                        logger.error(f"Failed to create target bucket {rule.target_bucket}: {create_err}")
-                        raise e # Raise original error
+                        bucket_ready = True
+                        logger.info(f"Created target bucket {rule.target_bucket}")
+                    except ClientError as bucket_err:
+                        if bucket_err.response['Error']['Code'] in ('BucketAlreadyExists', 'BucketAlreadyOwnedByYou'):
+                            logger.debug(f"Bucket {rule.target_bucket} already exists (created by another thread)")
+                            bucket_ready = True
+                        else:
+                            logger.error(f"Failed to create target bucket {rule.target_bucket}: {bucket_err}")
+                            raise e
+
+                    if bucket_ready:
+                        do_upload()
                 else:
                     raise e
-            
+
             logger.info(f"Replicated {bucket_name}/{object_key} to {conn.name} ({rule.target_bucket})")
             self._update_last_sync(bucket_name, object_key)
+            self.failure_store.remove_failure(bucket_name, object_key)
 
         except (ClientError, OSError, ValueError) as e:
+            error_code = None
+            if isinstance(e, ClientError):
+                error_code = e.response.get('Error', {}).get('Code')
             logger.error(f"Replication failed for {bucket_name}/{object_key}: {e}")
-        except Exception:
+            self.failure_store.add_failure(bucket_name, ReplicationFailure(
+                object_key=object_key,
+                error_message=str(e),
+                timestamp=time.time(),
+                failure_count=1,
+                bucket_name=bucket_name,
+                action=action,
+                last_error_code=error_code,
+            ))
+        except Exception as e:
             logger.exception(f"Unexpected error during replication for {bucket_name}/{object_key}")
+            self.failure_store.add_failure(bucket_name, ReplicationFailure(
+                object_key=object_key,
+                error_message=str(e),
+                timestamp=time.time(),
+                failure_count=1,
+                bucket_name=bucket_name,
+                action=action,
+                last_error_code=None,
+            ))
+
+    def get_failed_items(self, bucket_name: str, limit: int = 50, offset: int = 0) -> List[ReplicationFailure]:
+        failures = self.failure_store.load_failures(bucket_name)
+        return failures[offset:offset + limit]
+
+    def get_failure_count(self, bucket_name: str) -> int:
+        return self.failure_store.get_failure_count(bucket_name)
+
+    def retry_failed_item(self, bucket_name: str, object_key: str) -> bool:
+        failure = self.failure_store.get_failure(bucket_name, object_key)
+        if not failure:
+            return False
+
+        rule = self.get_rule(bucket_name)
+        if not rule or not rule.enabled:
+            return False
+
+        connection = self.connections.get(rule.target_connection_id)
+        if not connection:
+            logger.warning(f"Cannot retry: Connection {rule.target_connection_id} not found")
+            return False
+
+        if not self.check_endpoint_health(connection):
+            logger.warning(f"Cannot retry: Endpoint {connection.name} is not reachable")
+            return False
+
+        self._executor.submit(self._replicate_task, bucket_name, object_key, rule, connection, failure.action)
+        return True
+
+    def retry_all_failed(self, bucket_name: str) -> Dict[str, int]:
+        failures = self.failure_store.load_failures(bucket_name)
+        if not failures:
+            return {"submitted": 0, "skipped": 0}
+
+        rule = self.get_rule(bucket_name)
+        if not rule or not rule.enabled:
+            return {"submitted": 0, "skipped": len(failures)}
+
+        connection = self.connections.get(rule.target_connection_id)
+        if not connection:
+            logger.warning(f"Cannot retry: Connection {rule.target_connection_id} not found")
+            return {"submitted": 0, "skipped": len(failures)}
+
+        if not self.check_endpoint_health(connection):
+            logger.warning(f"Cannot retry: Endpoint {connection.name} is not reachable")
+            return {"submitted": 0, "skipped": len(failures)}
+
+        submitted = 0
+        for failure in failures:
+            self._executor.submit(self._replicate_task, bucket_name, failure.object_key, rule, connection, failure.action)
+            submitted += 1
+
+        return {"submitted": submitted, "skipped": 0}
+
+    def dismiss_failure(self, bucket_name: str, object_key: str) -> bool:
+        return self.failure_store.remove_failure(bucket_name, object_key)
+
+    def clear_failures(self, bucket_name: str) -> None:
+        self.failure_store.clear_failures(bucket_name)

app/s3_client.py

@@ -0,0 +1,284 @@
+from __future__ import annotations
+
+import json
+import logging
+import threading
+import time
+from typing import Any, Generator, Optional
+
+import boto3
+from botocore.config import Config
+from botocore.exceptions import ClientError, EndpointConnectionError, ConnectionClosedError
+from flask import current_app, session
+
+logger = logging.getLogger(__name__)
+
+UI_PROXY_USER_AGENT = "MyFSIO-UIProxy/1.0"
+
+_BOTO_ERROR_MAP = {
+    "NoSuchBucket": 404,
+    "NoSuchKey": 404,
+    "NoSuchUpload": 404,
+    "BucketAlreadyExists": 409,
+    "BucketAlreadyOwnedByYou": 409,
+    "BucketNotEmpty": 409,
+    "AccessDenied": 403,
+    "InvalidAccessKeyId": 403,
+    "SignatureDoesNotMatch": 403,
+    "InvalidBucketName": 400,
+    "InvalidArgument": 400,
+    "MalformedXML": 400,
+    "EntityTooLarge": 400,
+    "QuotaExceeded": 403,
+}
+
+_UPLOAD_REGISTRY_MAX_AGE = 86400
+_UPLOAD_REGISTRY_CLEANUP_INTERVAL = 3600
+
+
+class UploadRegistry:
+    def __init__(self) -> None:
+        self._entries: dict[str, tuple[str, str, float]] = {}
+        self._lock = threading.Lock()
+        self._last_cleanup = time.monotonic()
+
+    def register(self, upload_id: str, bucket_name: str, object_key: str) -> None:
+        with self._lock:
+            self._entries[upload_id] = (bucket_name, object_key, time.monotonic())
+            self._maybe_cleanup()
+
+    def get_key(self, upload_id: str, bucket_name: str) -> Optional[str]:
+        with self._lock:
+            entry = self._entries.get(upload_id)
+            if entry is None:
+                return None
+            stored_bucket, key, created_at = entry
+            if stored_bucket != bucket_name:
+                return None
+            if time.monotonic() - created_at > _UPLOAD_REGISTRY_MAX_AGE:
+                del self._entries[upload_id]
+                return None
+            return key
+
+    def remove(self, upload_id: str) -> None:
+        with self._lock:
+            self._entries.pop(upload_id, None)
+
+    def _maybe_cleanup(self) -> None:
+        now = time.monotonic()
+        if now - self._last_cleanup < _UPLOAD_REGISTRY_CLEANUP_INTERVAL:
+            return
+        self._last_cleanup = now
+        cutoff = now - _UPLOAD_REGISTRY_MAX_AGE
+        stale = [uid for uid, (_, _, ts) in self._entries.items() if ts < cutoff]
+        for uid in stale:
+            del self._entries[uid]
+
+
+class S3ProxyClient:
+    def __init__(self, api_base_url: str, region: str = "us-east-1") -> None:
+        if not api_base_url:
+            raise ValueError("api_base_url is required for S3ProxyClient")
+        self._api_base_url = api_base_url.rstrip("/")
+        self._region = region
+        self.upload_registry = UploadRegistry()
+
+    @property
+    def api_base_url(self) -> str:
+        return self._api_base_url
+
+    def get_client(self, access_key: str, secret_key: str) -> Any:
+        if not access_key or not secret_key:
+            raise ValueError("Both access_key and secret_key are required")
+        config = Config(
+            user_agent_extra=UI_PROXY_USER_AGENT,
+            connect_timeout=5,
+            read_timeout=30,
+            retries={"max_attempts": 0},
+            signature_version="s3v4",
+            s3={"addressing_style": "path"},
+            request_checksum_calculation="when_required",
+            response_checksum_validation="when_required",
+        )
+        return boto3.client(
+            "s3",
+            endpoint_url=self._api_base_url,
+            aws_access_key_id=access_key,
+            aws_secret_access_key=secret_key,
+            region_name=self._region,
+            config=config,
+        )
+
+
+def _get_proxy() -> S3ProxyClient:
+    proxy = current_app.extensions.get("s3_proxy")
+    if proxy is None:
+        raise RuntimeError(
+            "S3 proxy not configured. Set API_BASE_URL or run both API and UI servers."
+        )
+    return proxy
+
+
+def _get_session_creds() -> tuple[str, str]:
+    secret_store = current_app.extensions["secret_store"]
+    secret_store.purge_expired()
+    token = session.get("cred_token")
+    if not token:
+        raise PermissionError("Not authenticated")
+    creds = secret_store.peek(token)
+    if not creds:
+        raise PermissionError("Session expired")
+    access_key = creds.get("access_key", "")
+    secret_key = creds.get("secret_key", "")
+    if not access_key or not secret_key:
+        raise PermissionError("Invalid session credentials")
+    return access_key, secret_key
+
+
+def get_session_s3_client() -> Any:
+    proxy = _get_proxy()
+    access_key, secret_key = _get_session_creds()
+    return proxy.get_client(access_key, secret_key)
+
+
+def get_upload_registry() -> UploadRegistry:
+    return _get_proxy().upload_registry
+
+
+def handle_client_error(exc: ClientError) -> tuple[dict[str, str], int]:
+    error_info = exc.response.get("Error", {})
+    code = error_info.get("Code", "InternalError")
+    message = error_info.get("Message") or "S3 operation failed"
+    http_status = _BOTO_ERROR_MAP.get(code)
+    if http_status is None:
+        http_status = exc.response.get("ResponseMetadata", {}).get("HTTPStatusCode", 500)
+    return {"error": message}, http_status
+
+
+def handle_connection_error(exc: Exception) -> tuple[dict[str, str], int]:
+    logger.error("S3 API connection failed: %s", exc)
+    return {"error": "S3 API server is unreachable. Ensure the API server is running."}, 502
+
+
+def format_datetime_display(dt: Any, display_tz: str = "UTC") -> str:
+    from .ui import _format_datetime_display
+    return _format_datetime_display(dt, display_tz)
+
+
+def format_datetime_iso(dt: Any, display_tz: str = "UTC") -> str:
+    from .ui import _format_datetime_iso
+    return _format_datetime_iso(dt, display_tz)
+
+
+def build_url_templates(bucket_name: str) -> dict[str, str]:
+    from flask import url_for
+    preview_t = url_for("ui.object_preview", bucket_name=bucket_name, object_key="KEY_PLACEHOLDER")
+    delete_t = url_for("ui.delete_object", bucket_name=bucket_name, object_key="KEY_PLACEHOLDER")
+    presign_t = url_for("ui.object_presign", bucket_name=bucket_name, object_key="KEY_PLACEHOLDER")
+    versions_t = url_for("ui.object_versions", bucket_name=bucket_name, object_key="KEY_PLACEHOLDER")
+    restore_t = url_for(
+        "ui.restore_object_version",
+        bucket_name=bucket_name,
+        object_key="KEY_PLACEHOLDER",
+        version_id="VERSION_ID_PLACEHOLDER",
+    )
+    tags_t = url_for("ui.object_tags", bucket_name=bucket_name, object_key="KEY_PLACEHOLDER")
+    copy_t = url_for("ui.copy_object", bucket_name=bucket_name, object_key="KEY_PLACEHOLDER")
+    move_t = url_for("ui.move_object", bucket_name=bucket_name, object_key="KEY_PLACEHOLDER")
+    metadata_t = url_for("ui.object_metadata", bucket_name=bucket_name, object_key="KEY_PLACEHOLDER")
+    return {
+        "preview": preview_t,
+        "download": preview_t + "?download=1",
+        "presign": presign_t,
+        "delete": delete_t,
+        "versions": versions_t,
+        "restore": restore_t,
+        "tags": tags_t,
+        "copy": copy_t,
+        "move": move_t,
+        "metadata": metadata_t,
+    }
+
+
+def translate_list_objects(
+    boto3_response: dict[str, Any],
+    url_templates: dict[str, str],
+    display_tz: str = "UTC",
+    versioning_enabled: bool = False,
+) -> dict[str, Any]:
+    objects_data = []
+    for obj in boto3_response.get("Contents", []):
+        last_mod = obj["LastModified"]
+        objects_data.append({
+            "key": obj["Key"],
+            "size": obj["Size"],
+            "last_modified": last_mod.isoformat(),
+            "last_modified_display": format_datetime_display(last_mod, display_tz),
+            "last_modified_iso": format_datetime_iso(last_mod, display_tz),
+            "etag": obj.get("ETag", "").strip('"'),
+        })
+    return {
+        "objects": objects_data,
+        "is_truncated": boto3_response.get("IsTruncated", False),
+        "next_continuation_token": boto3_response.get("NextContinuationToken"),
+        "total_count": boto3_response.get("KeyCount", len(objects_data)),
+        "versioning_enabled": versioning_enabled,
+        "url_templates": url_templates,
+    }
+
+
+def get_versioning_via_s3(client: Any, bucket_name: str) -> bool:
+    try:
+        resp = client.get_bucket_versioning(Bucket=bucket_name)
+        return resp.get("Status") == "Enabled"
+    except ClientError as exc:
+        code = exc.response.get("Error", {}).get("Code", "")
+        if code != "NoSuchBucket":
+            logger.warning("Failed to check versioning for %s: %s", bucket_name, code)
+        return False
+
+
+def stream_objects_ndjson(
+    client: Any,
+    bucket_name: str,
+    prefix: Optional[str],
+    url_templates: dict[str, str],
+    display_tz: str = "UTC",
+    versioning_enabled: bool = False,
+) -> Generator[str, None, None]:
+    meta_line = json.dumps({
+        "type": "meta",
+        "versioning_enabled": versioning_enabled,
+        "url_templates": url_templates,
+    }) + "\n"
+    yield meta_line
+
+    yield json.dumps({"type": "count", "total_count": 0}) + "\n"
+
+    kwargs: dict[str, Any] = {"Bucket": bucket_name, "MaxKeys": 1000}
+    if prefix:
+        kwargs["Prefix"] = prefix
+
+    try:
+        paginator = client.get_paginator("list_objects_v2")
+        for page in paginator.paginate(**kwargs):
+            for obj in page.get("Contents", []):
+                last_mod = obj["LastModified"]
+                yield json.dumps({
+                    "type": "object",
+                    "key": obj["Key"],
+                    "size": obj["Size"],
+                    "last_modified": last_mod.isoformat(),
+                    "last_modified_display": format_datetime_display(last_mod, display_tz),
+                    "last_modified_iso": format_datetime_iso(last_mod, display_tz),
+                    "etag": obj.get("ETag", "").strip('"'),
+                }) + "\n"
+    except ClientError as exc:
+        error_msg = exc.response.get("Error", {}).get("Message", "S3 operation failed")
+        yield json.dumps({"type": "error", "error": error_msg}) + "\n"
+        return
+    except (EndpointConnectionError, ConnectionClosedError):
+        yield json.dumps({"type": "error", "error": "S3 API server is unreachable"}) + "\n"
+        return
+
+    yield json.dumps({"type": "done"}) + "\n"

app/secret_store.py

@@ -1,4 +1,3 @@
-"""Ephemeral store for one-time secrets communicated to the UI."""
 from __future__ import annotations
 
 import secrets
@@ -19,6 +18,18 @@ class EphemeralSecretStore:
         self._store[token] = (payload, expires_at)
         return token
 
+    def peek(self, token: str | None) -> Any | None:
+        if not token:
+            return None
+        entry = self._store.get(token)
+        if not entry:
+            return None
+        payload, expires_at = entry
+        if expires_at < time.time():
+            self._store.pop(token, None)
+            return None
+        return payload
+
     def pop(self, token: str | None) -> Any | None:
         if not token:
             return None

app/select_content.py

@@ -0,0 +1,171 @@
+"""S3 SelectObjectContent SQL query execution using DuckDB."""
+from __future__ import annotations
+
+import json
+from pathlib import Path
+from typing import Any, Dict, Generator, Optional
+
+try:
+    import duckdb
+    DUCKDB_AVAILABLE = True
+except ImportError:
+    DUCKDB_AVAILABLE = False
+
+
+class SelectError(Exception):
+    """Error during SELECT query execution."""
+    pass
+
+
+def execute_select_query(
+    file_path: Path,
+    expression: str,
+    input_format: str,
+    input_config: Dict[str, Any],
+    output_format: str,
+    output_config: Dict[str, Any],
+    chunk_size: int = 65536,
+) -> Generator[bytes, None, None]:
+    """Execute SQL query on object content."""
+    if not DUCKDB_AVAILABLE:
+        raise SelectError("DuckDB is not installed. Install with: pip install duckdb")
+
+    conn = duckdb.connect(":memory:")
+
+    try:
+        if input_format == "CSV":
+            _load_csv(conn, file_path, input_config)
+        elif input_format == "JSON":
+            _load_json(conn, file_path, input_config)
+        elif input_format == "Parquet":
+            _load_parquet(conn, file_path)
+        else:
+            raise SelectError(f"Unsupported input format: {input_format}")
+
+        normalized_expression = expression.replace("s3object", "data").replace("S3Object", "data")
+
+        try:
+            result = conn.execute(normalized_expression)
+        except duckdb.Error as exc:
+            raise SelectError(f"SQL execution error: {exc}")
+
+        if output_format == "CSV":
+            yield from _output_csv(result, output_config, chunk_size)
+        elif output_format == "JSON":
+            yield from _output_json(result, output_config, chunk_size)
+        else:
+            raise SelectError(f"Unsupported output format: {output_format}")
+
+    finally:
+        conn.close()
+
+
+def _load_csv(conn, file_path: Path, config: Dict[str, Any]) -> None:
+    """Load CSV file into DuckDB."""
+    file_header_info = config.get("file_header_info", "NONE")
+    delimiter = config.get("field_delimiter", ",")
+    quote = config.get("quote_character", '"')
+
+    header = file_header_info in ("USE", "IGNORE")
+    path_str = str(file_path).replace("\\", "/")
+
+    conn.execute(f"""
+        CREATE TABLE data AS
+        SELECT * FROM read_csv('{path_str}',
+            header={header},
+            delim='{delimiter}',
+            quote='{quote}'
+        )
+    """)
+
+
+def _load_json(conn, file_path: Path, config: Dict[str, Any]) -> None:
+    """Load JSON file into DuckDB."""
+    json_type = config.get("type", "DOCUMENT")
+    path_str = str(file_path).replace("\\", "/")
+
+    if json_type == "LINES":
+        conn.execute(f"""
+            CREATE TABLE data AS
+            SELECT * FROM read_json_auto('{path_str}', format='newline_delimited')
+        """)
+    else:
+        conn.execute(f"""
+            CREATE TABLE data AS
+            SELECT * FROM read_json_auto('{path_str}', format='array')
+        """)
+
+
+def _load_parquet(conn, file_path: Path) -> None:
+    """Load Parquet file into DuckDB."""
+    path_str = str(file_path).replace("\\", "/")
+    conn.execute(f"CREATE TABLE data AS SELECT * FROM read_parquet('{path_str}')")
+
+
+def _output_csv(
+    result,
+    config: Dict[str, Any],
+    chunk_size: int,
+) -> Generator[bytes, None, None]:
+    """Output query results as CSV."""
+    delimiter = config.get("field_delimiter", ",")
+    record_delimiter = config.get("record_delimiter", "\n")
+    quote = config.get("quote_character", '"')
+
+    buffer = ""
+
+    while True:
+        rows = result.fetchmany(1000)
+        if not rows:
+            break
+
+        for row in rows:
+            fields = []
+            for value in row:
+                if value is None:
+                    fields.append("")
+                elif isinstance(value, str):
+                    if delimiter in value or quote in value or record_delimiter in value:
+                        escaped = value.replace(quote, quote + quote)
+                        fields.append(f'{quote}{escaped}{quote}')
+                    else:
+                        fields.append(value)
+                else:
+                    fields.append(str(value))
+
+            buffer += delimiter.join(fields) + record_delimiter
+
+            while len(buffer) >= chunk_size:
+                yield buffer[:chunk_size].encode("utf-8")
+                buffer = buffer[chunk_size:]
+
+    if buffer:
+        yield buffer.encode("utf-8")
+
+
+def _output_json(
+    result,
+    config: Dict[str, Any],
+    chunk_size: int,
+) -> Generator[bytes, None, None]:
+    """Output query results as JSON Lines."""
+    record_delimiter = config.get("record_delimiter", "\n")
+    columns = [desc[0] for desc in result.description]
+
+    buffer = ""
+
+    while True:
+        rows = result.fetchmany(1000)
+        if not rows:
+            break
+
+        for row in rows:
+            record = dict(zip(columns, row))
+            buffer += json.dumps(record, default=str) + record_delimiter
+
+            while len(buffer) >= chunk_size:
+                yield buffer[:chunk_size].encode("utf-8")
+                buffer = buffer[chunk_size:]
+
+    if buffer:
+        yield buffer.encode("utf-8")

app/site_registry.py

@@ -0,0 +1,177 @@
+from __future__ import annotations
+
+import json
+import time
+from dataclasses import dataclass, field
+from pathlib import Path
+from typing import Any, Dict, List, Optional
+
+
+@dataclass
+class SiteInfo:
+    site_id: str
+    endpoint: str
+    region: str = "us-east-1"
+    priority: int = 100
+    display_name: str = ""
+    created_at: Optional[float] = None
+    updated_at: Optional[float] = None
+
+    def __post_init__(self) -> None:
+        if not self.display_name:
+            self.display_name = self.site_id
+        if self.created_at is None:
+            self.created_at = time.time()
+
+    def to_dict(self) -> Dict[str, Any]:
+        return {
+            "site_id": self.site_id,
+            "endpoint": self.endpoint,
+            "region": self.region,
+            "priority": self.priority,
+            "display_name": self.display_name,
+            "created_at": self.created_at,
+            "updated_at": self.updated_at,
+        }
+
+    @classmethod
+    def from_dict(cls, data: Dict[str, Any]) -> SiteInfo:
+        return cls(
+            site_id=data["site_id"],
+            endpoint=data.get("endpoint", ""),
+            region=data.get("region", "us-east-1"),
+            priority=data.get("priority", 100),
+            display_name=data.get("display_name", ""),
+            created_at=data.get("created_at"),
+            updated_at=data.get("updated_at"),
+        )
+
+
+@dataclass
+class PeerSite:
+    site_id: str
+    endpoint: str
+    region: str = "us-east-1"
+    priority: int = 100
+    display_name: str = ""
+    created_at: Optional[float] = None
+    updated_at: Optional[float] = None
+    connection_id: Optional[str] = None
+    is_healthy: Optional[bool] = None
+    last_health_check: Optional[float] = None
+
+    def __post_init__(self) -> None:
+        if not self.display_name:
+            self.display_name = self.site_id
+        if self.created_at is None:
+            self.created_at = time.time()
+
+    def to_dict(self) -> Dict[str, Any]:
+        return {
+            "site_id": self.site_id,
+            "endpoint": self.endpoint,
+            "region": self.region,
+            "priority": self.priority,
+            "display_name": self.display_name,
+            "created_at": self.created_at,
+            "updated_at": self.updated_at,
+            "connection_id": self.connection_id,
+            "is_healthy": self.is_healthy,
+            "last_health_check": self.last_health_check,
+        }
+
+    @classmethod
+    def from_dict(cls, data: Dict[str, Any]) -> PeerSite:
+        return cls(
+            site_id=data["site_id"],
+            endpoint=data.get("endpoint", ""),
+            region=data.get("region", "us-east-1"),
+            priority=data.get("priority", 100),
+            display_name=data.get("display_name", ""),
+            created_at=data.get("created_at"),
+            updated_at=data.get("updated_at"),
+            connection_id=data.get("connection_id"),
+            is_healthy=data.get("is_healthy"),
+            last_health_check=data.get("last_health_check"),
+        )
+
+
+class SiteRegistry:
+    def __init__(self, config_path: Path) -> None:
+        self.config_path = config_path
+        self._local_site: Optional[SiteInfo] = None
+        self._peers: Dict[str, PeerSite] = {}
+        self.reload()
+
+    def reload(self) -> None:
+        if not self.config_path.exists():
+            self._local_site = None
+            self._peers = {}
+            return
+
+        try:
+            with open(self.config_path, "r", encoding="utf-8") as f:
+                data = json.load(f)
+
+            if data.get("local"):
+                self._local_site = SiteInfo.from_dict(data["local"])
+            else:
+                self._local_site = None
+
+            self._peers = {}
+            for peer_data in data.get("peers", []):
+                peer = PeerSite.from_dict(peer_data)
+                self._peers[peer.site_id] = peer
+
+        except (OSError, json.JSONDecodeError, KeyError):
+            self._local_site = None
+            self._peers = {}
+
+    def save(self) -> None:
+        self.config_path.parent.mkdir(parents=True, exist_ok=True)
+        data = {
+            "local": self._local_site.to_dict() if self._local_site else None,
+            "peers": [peer.to_dict() for peer in self._peers.values()],
+        }
+        with open(self.config_path, "w", encoding="utf-8") as f:
+            json.dump(data, f, indent=2)
+
+    def get_local_site(self) -> Optional[SiteInfo]:
+        return self._local_site
+
+    def set_local_site(self, site: SiteInfo) -> None:
+        site.updated_at = time.time()
+        self._local_site = site
+        self.save()
+
+    def list_peers(self) -> List[PeerSite]:
+        return list(self._peers.values())
+
+    def get_peer(self, site_id: str) -> Optional[PeerSite]:
+        return self._peers.get(site_id)
+
+    def add_peer(self, peer: PeerSite) -> None:
+        peer.created_at = peer.created_at or time.time()
+        self._peers[peer.site_id] = peer
+        self.save()
+
+    def update_peer(self, peer: PeerSite) -> None:
+        if peer.site_id not in self._peers:
+            raise ValueError(f"Peer {peer.site_id} not found")
+        peer.updated_at = time.time()
+        self._peers[peer.site_id] = peer
+        self.save()
+
+    def delete_peer(self, site_id: str) -> bool:
+        if site_id in self._peers:
+            del self._peers[site_id]
+            self.save()
+            return True
+        return False
+
+    def update_health(self, site_id: str, is_healthy: bool) -> None:
+        peer = self._peers.get(site_id)
+        if peer:
+            peer.is_healthy = is_healthy
+            peer.last_health_check = time.time()
+            self.save()

app/site_sync.py

@@ -0,0 +1,416 @@
+from __future__ import annotations
+
+import json
+import logging
+import tempfile
+import threading
+import time
+from dataclasses import dataclass, field
+from datetime import datetime, timezone
+from pathlib import Path
+from typing import Any, Dict, List, Optional, TYPE_CHECKING
+
+import boto3
+from botocore.config import Config
+from botocore.exceptions import ClientError
+
+if TYPE_CHECKING:
+    from .connections import ConnectionStore, RemoteConnection
+    from .replication import ReplicationManager, ReplicationRule
+    from .storage import ObjectStorage
+
+logger = logging.getLogger(__name__)
+
+SITE_SYNC_USER_AGENT = "SiteSyncAgent/1.0"
+
+
+@dataclass
+class SyncedObjectInfo:
+    last_synced_at: float
+    remote_etag: str
+    source: str
+
+    def to_dict(self) -> Dict[str, Any]:
+        return {
+            "last_synced_at": self.last_synced_at,
+            "remote_etag": self.remote_etag,
+            "source": self.source,
+        }
+
+    @classmethod
+    def from_dict(cls, data: Dict[str, Any]) -> "SyncedObjectInfo":
+        return cls(
+            last_synced_at=data["last_synced_at"],
+            remote_etag=data["remote_etag"],
+            source=data["source"],
+        )
+
+
+@dataclass
+class SyncState:
+    synced_objects: Dict[str, SyncedObjectInfo] = field(default_factory=dict)
+    last_full_sync: Optional[float] = None
+
+    def to_dict(self) -> Dict[str, Any]:
+        return {
+            "synced_objects": {k: v.to_dict() for k, v in self.synced_objects.items()},
+            "last_full_sync": self.last_full_sync,
+        }
+
+    @classmethod
+    def from_dict(cls, data: Dict[str, Any]) -> "SyncState":
+        synced_objects = {}
+        for k, v in data.get("synced_objects", {}).items():
+            synced_objects[k] = SyncedObjectInfo.from_dict(v)
+        return cls(
+            synced_objects=synced_objects,
+            last_full_sync=data.get("last_full_sync"),
+        )
+
+
+@dataclass
+class SiteSyncStats:
+    last_sync_at: Optional[float] = None
+    objects_pulled: int = 0
+    objects_skipped: int = 0
+    conflicts_resolved: int = 0
+    deletions_applied: int = 0
+    errors: int = 0
+
+    def to_dict(self) -> Dict[str, Any]:
+        return {
+            "last_sync_at": self.last_sync_at,
+            "objects_pulled": self.objects_pulled,
+            "objects_skipped": self.objects_skipped,
+            "conflicts_resolved": self.conflicts_resolved,
+            "deletions_applied": self.deletions_applied,
+            "errors": self.errors,
+        }
+
+
+@dataclass
+class RemoteObjectMeta:
+    key: str
+    size: int
+    last_modified: datetime
+    etag: str
+
+    @classmethod
+    def from_s3_object(cls, obj: Dict[str, Any]) -> "RemoteObjectMeta":
+        return cls(
+            key=obj["Key"],
+            size=obj.get("Size", 0),
+            last_modified=obj["LastModified"],
+            etag=obj.get("ETag", "").strip('"'),
+        )
+
+
+def _create_sync_client(
+    connection: "RemoteConnection",
+    *,
+    connect_timeout: int = 10,
+    read_timeout: int = 120,
+    max_retries: int = 2,
+) -> Any:
+    config = Config(
+        user_agent_extra=SITE_SYNC_USER_AGENT,
+        connect_timeout=connect_timeout,
+        read_timeout=read_timeout,
+        retries={"max_attempts": max_retries},
+        signature_version="s3v4",
+        s3={"addressing_style": "path"},
+        request_checksum_calculation="when_required",
+        response_checksum_validation="when_required",
+    )
+    return boto3.client(
+        "s3",
+        endpoint_url=connection.endpoint_url,
+        aws_access_key_id=connection.access_key,
+        aws_secret_access_key=connection.secret_key,
+        region_name=connection.region or "us-east-1",
+        config=config,
+    )
+
+
+class SiteSyncWorker:
+    def __init__(
+        self,
+        storage: "ObjectStorage",
+        connections: "ConnectionStore",
+        replication_manager: "ReplicationManager",
+        storage_root: Path,
+        interval_seconds: int = 60,
+        batch_size: int = 100,
+        connect_timeout: int = 10,
+        read_timeout: int = 120,
+        max_retries: int = 2,
+        clock_skew_tolerance_seconds: float = 1.0,
+    ):
+        self.storage = storage
+        self.connections = connections
+        self.replication_manager = replication_manager
+        self.storage_root = storage_root
+        self.interval_seconds = interval_seconds
+        self.batch_size = batch_size
+        self.connect_timeout = connect_timeout
+        self.read_timeout = read_timeout
+        self.max_retries = max_retries
+        self.clock_skew_tolerance_seconds = clock_skew_tolerance_seconds
+        self._lock = threading.Lock()
+        self._shutdown = threading.Event()
+        self._sync_thread: Optional[threading.Thread] = None
+        self._bucket_stats: Dict[str, SiteSyncStats] = {}
+
+    def _create_client(self, connection: "RemoteConnection") -> Any:
+        """Create an S3 client with the worker's configured timeouts."""
+        return _create_sync_client(
+            connection,
+            connect_timeout=self.connect_timeout,
+            read_timeout=self.read_timeout,
+            max_retries=self.max_retries,
+        )
+
+    def start(self) -> None:
+        if self._sync_thread is not None and self._sync_thread.is_alive():
+            return
+        self._shutdown.clear()
+        self._sync_thread = threading.Thread(
+            target=self._sync_loop, name="site-sync-worker", daemon=True
+        )
+        self._sync_thread.start()
+        logger.info("Site sync worker started (interval=%ds)", self.interval_seconds)
+
+    def shutdown(self) -> None:
+        self._shutdown.set()
+        if self._sync_thread is not None:
+            self._sync_thread.join(timeout=10.0)
+        logger.info("Site sync worker shut down")
+
+    def trigger_sync(self, bucket_name: str) -> Optional[SiteSyncStats]:
+        from .replication import REPLICATION_MODE_BIDIRECTIONAL
+        rule = self.replication_manager.get_rule(bucket_name)
+        if not rule or rule.mode != REPLICATION_MODE_BIDIRECTIONAL or not rule.enabled:
+            return None
+        return self._sync_bucket(rule)
+
+    def get_stats(self, bucket_name: str) -> Optional[SiteSyncStats]:
+        with self._lock:
+            return self._bucket_stats.get(bucket_name)
+
+    def _sync_loop(self) -> None:
+        while not self._shutdown.is_set():
+            self._shutdown.wait(timeout=self.interval_seconds)
+            if self._shutdown.is_set():
+                break
+            self._run_sync_cycle()
+
+    def _run_sync_cycle(self) -> None:
+        from .replication import REPLICATION_MODE_BIDIRECTIONAL
+        for bucket_name, rule in list(self.replication_manager._rules.items()):
+            if self._shutdown.is_set():
+                break
+            if rule.mode != REPLICATION_MODE_BIDIRECTIONAL or not rule.enabled:
+                continue
+            try:
+                stats = self._sync_bucket(rule)
+                with self._lock:
+                    self._bucket_stats[bucket_name] = stats
+            except Exception as e:
+                logger.exception("Site sync failed for bucket %s: %s", bucket_name, e)
+
+    def _sync_bucket(self, rule: "ReplicationRule") -> SiteSyncStats:
+        stats = SiteSyncStats()
+        connection = self.connections.get(rule.target_connection_id)
+        if not connection:
+            logger.warning("Connection %s not found for bucket %s", rule.target_connection_id, rule.bucket_name)
+            stats.errors += 1
+            return stats
+
+        try:
+            local_objects = self._list_local_objects(rule.bucket_name)
+        except Exception as e:
+            logger.error("Failed to list local objects for %s: %s", rule.bucket_name, e)
+            stats.errors += 1
+            return stats
+
+        try:
+            remote_objects = self._list_remote_objects(rule, connection)
+        except Exception as e:
+            logger.error("Failed to list remote objects for %s: %s", rule.bucket_name, e)
+            stats.errors += 1
+            return stats
+
+        sync_state = self._load_sync_state(rule.bucket_name)
+        local_keys = set(local_objects.keys())
+        remote_keys = set(remote_objects.keys())
+
+        to_pull = []
+        for key in remote_keys:
+            remote_meta = remote_objects[key]
+            local_meta = local_objects.get(key)
+            if local_meta is None:
+                to_pull.append(key)
+            else:
+                resolution = self._resolve_conflict(local_meta, remote_meta)
+                if resolution == "pull":
+                    to_pull.append(key)
+                    stats.conflicts_resolved += 1
+                else:
+                    stats.objects_skipped += 1
+
+        pulled_count = 0
+        for key in to_pull:
+            if self._shutdown.is_set():
+                break
+            if pulled_count >= self.batch_size:
+                break
+            remote_meta = remote_objects[key]
+            success = self._pull_object(rule, key, connection, remote_meta)
+            if success:
+                stats.objects_pulled += 1
+                pulled_count += 1
+                sync_state.synced_objects[key] = SyncedObjectInfo(
+                    last_synced_at=time.time(),
+                    remote_etag=remote_meta.etag,
+                    source="remote",
+                )
+            else:
+                stats.errors += 1
+
+        if rule.sync_deletions:
+            for key in list(sync_state.synced_objects.keys()):
+                if key not in remote_keys and key in local_keys:
+                    tracked = sync_state.synced_objects[key]
+                    if tracked.source == "remote":
+                        local_meta = local_objects.get(key)
+                        if local_meta and local_meta.last_modified.timestamp() <= tracked.last_synced_at:
+                            success = self._apply_remote_deletion(rule.bucket_name, key)
+                            if success:
+                                stats.deletions_applied += 1
+                                del sync_state.synced_objects[key]
+
+        sync_state.last_full_sync = time.time()
+        self._save_sync_state(rule.bucket_name, sync_state)
+
+        with self.replication_manager._stats_lock:
+            rule.last_pull_at = time.time()
+            self.replication_manager.save_rules()
+
+        stats.last_sync_at = time.time()
+        logger.info(
+            "Site sync completed for %s: pulled=%d, skipped=%d, conflicts=%d, deletions=%d, errors=%d",
+            rule.bucket_name,
+            stats.objects_pulled,
+            stats.objects_skipped,
+            stats.conflicts_resolved,
+            stats.deletions_applied,
+            stats.errors,
+        )
+        return stats
+
+    def _list_local_objects(self, bucket_name: str) -> Dict[str, Any]:
+        from .storage import ObjectMeta
+        objects = self.storage.list_objects_all(bucket_name)
+        return {obj.key: obj for obj in objects}
+
+    def _list_remote_objects(self, rule: "ReplicationRule", connection: "RemoteConnection") -> Dict[str, RemoteObjectMeta]:
+        s3 = self._create_client(connection)
+        result: Dict[str, RemoteObjectMeta] = {}
+        paginator = s3.get_paginator("list_objects_v2")
+        try:
+            for page in paginator.paginate(Bucket=rule.target_bucket):
+                for obj in page.get("Contents", []):
+                    meta = RemoteObjectMeta.from_s3_object(obj)
+                    result[meta.key] = meta
+        except ClientError as e:
+            if e.response["Error"]["Code"] == "NoSuchBucket":
+                return {}
+            raise
+        return result
+
+    def _resolve_conflict(self, local_meta: Any, remote_meta: RemoteObjectMeta) -> str:
+        local_ts = local_meta.last_modified.timestamp()
+        remote_ts = remote_meta.last_modified.timestamp()
+
+        if abs(remote_ts - local_ts) < self.clock_skew_tolerance_seconds:
+            local_etag = local_meta.etag or ""
+            if remote_meta.etag == local_etag:
+                return "skip"
+            return "pull" if remote_meta.etag > local_etag else "keep"
+
+        return "pull" if remote_ts > local_ts else "keep"
+
+    def _pull_object(
+        self,
+        rule: "ReplicationRule",
+        object_key: str,
+        connection: "RemoteConnection",
+        remote_meta: RemoteObjectMeta,
+    ) -> bool:
+        s3 = self._create_client(connection)
+        tmp_path = None
+        try:
+            tmp_dir = self.storage_root / ".myfsio.sys" / "tmp"
+            tmp_dir.mkdir(parents=True, exist_ok=True)
+            with tempfile.NamedTemporaryFile(dir=tmp_dir, delete=False) as tmp_file:
+                tmp_path = Path(tmp_file.name)
+
+            s3.download_file(rule.target_bucket, object_key, str(tmp_path))
+
+            head_response = s3.head_object(Bucket=rule.target_bucket, Key=object_key)
+            user_metadata = head_response.get("Metadata", {})
+
+            with open(tmp_path, "rb") as f:
+                self.storage.put_object(
+                    rule.bucket_name,
+                    object_key,
+                    f,
+                    metadata=user_metadata if user_metadata else None,
+                )
+
+            logger.debug("Pulled object %s/%s from remote", rule.bucket_name, object_key)
+            return True
+
+        except ClientError as e:
+            logger.error("Failed to pull %s/%s: %s", rule.bucket_name, object_key, e)
+            return False
+        except Exception as e:
+            logger.error("Failed to store pulled object %s/%s: %s", rule.bucket_name, object_key, e)
+            return False
+        finally:
+            if tmp_path and tmp_path.exists():
+                try:
+                    tmp_path.unlink()
+                except OSError:
+                    pass
+
+    def _apply_remote_deletion(self, bucket_name: str, object_key: str) -> bool:
+        try:
+            self.storage.delete_object(bucket_name, object_key)
+            logger.debug("Applied remote deletion for %s/%s", bucket_name, object_key)
+            return True
+        except Exception as e:
+            logger.error("Failed to apply remote deletion for %s/%s: %s", bucket_name, object_key, e)
+            return False
+
+    def _sync_state_path(self, bucket_name: str) -> Path:
+        return self.storage_root / ".myfsio.sys" / "buckets" / bucket_name / "site_sync_state.json"
+
+    def _load_sync_state(self, bucket_name: str) -> SyncState:
+        path = self._sync_state_path(bucket_name)
+        if not path.exists():
+            return SyncState()
+        try:
+            data = json.loads(path.read_text(encoding="utf-8"))
+            return SyncState.from_dict(data)
+        except (json.JSONDecodeError, OSError, KeyError) as e:
+            logger.warning("Failed to load sync state for %s: %s", bucket_name, e)
+            return SyncState()
+
+    def _save_sync_state(self, bucket_name: str, state: SyncState) -> None:
+        path = self._sync_state_path(bucket_name)
+        path.parent.mkdir(parents=True, exist_ok=True)
+        try:
+            path.write_text(json.dumps(state.to_dict(), indent=2), encoding="utf-8")
+        except OSError as e:
+            logger.warning("Failed to save sync state for %s: %s", bucket_name, e)

app/system_metrics.py

@@ -0,0 +1,215 @@
+from __future__ import annotations
+
+import json
+import logging
+import threading
+import time
+from dataclasses import dataclass
+from datetime import datetime, timezone
+from pathlib import Path
+from typing import Any, Dict, List, Optional, TYPE_CHECKING
+
+import psutil
+
+if TYPE_CHECKING:
+    from .storage import ObjectStorage
+
+logger = logging.getLogger(__name__)
+
+
+@dataclass
+class SystemMetricsSnapshot:
+    timestamp: datetime
+    cpu_percent: float
+    memory_percent: float
+    disk_percent: float
+    storage_bytes: int
+
+    def to_dict(self) -> Dict[str, Any]:
+        return {
+            "timestamp": self.timestamp.strftime("%Y-%m-%dT%H:%M:%SZ"),
+            "cpu_percent": round(self.cpu_percent, 2),
+            "memory_percent": round(self.memory_percent, 2),
+            "disk_percent": round(self.disk_percent, 2),
+            "storage_bytes": self.storage_bytes,
+        }
+
+    @classmethod
+    def from_dict(cls, data: Dict[str, Any]) -> "SystemMetricsSnapshot":
+        timestamp_str = data["timestamp"]
+        if timestamp_str.endswith("Z"):
+            timestamp_str = timestamp_str[:-1] + "+00:00"
+        return cls(
+            timestamp=datetime.fromisoformat(timestamp_str),
+            cpu_percent=data.get("cpu_percent", 0.0),
+            memory_percent=data.get("memory_percent", 0.0),
+            disk_percent=data.get("disk_percent", 0.0),
+            storage_bytes=data.get("storage_bytes", 0),
+        )
+
+
+class SystemMetricsCollector:
+    def __init__(
+        self,
+        storage_root: Path,
+        interval_minutes: int = 5,
+        retention_hours: int = 24,
+    ):
+        self.storage_root = storage_root
+        self.interval_seconds = interval_minutes * 60
+        self.retention_hours = retention_hours
+        self._lock = threading.Lock()
+        self._shutdown = threading.Event()
+        self._snapshots: List[SystemMetricsSnapshot] = []
+        self._storage_ref: Optional["ObjectStorage"] = None
+
+        self._load_history()
+
+        self._snapshot_thread = threading.Thread(
+            target=self._snapshot_loop,
+            name="system-metrics-snapshot",
+            daemon=True,
+        )
+        self._snapshot_thread.start()
+
+    def set_storage(self, storage: "ObjectStorage") -> None:
+        with self._lock:
+            self._storage_ref = storage
+
+    def _config_path(self) -> Path:
+        return self.storage_root / ".myfsio.sys" / "config" / "metrics_history.json"
+
+    def _load_history(self) -> None:
+        config_path = self._config_path()
+        if not config_path.exists():
+            return
+        try:
+            data = json.loads(config_path.read_text(encoding="utf-8"))
+            history_data = data.get("history", [])
+            self._snapshots = [SystemMetricsSnapshot.from_dict(s) for s in history_data]
+            self._prune_old_snapshots()
+        except (json.JSONDecodeError, OSError, KeyError) as e:
+            logger.warning(f"Failed to load system metrics history: {e}")
+
+    def _save_history(self) -> None:
+        config_path = self._config_path()
+        config_path.parent.mkdir(parents=True, exist_ok=True)
+        try:
+            data = {"history": [s.to_dict() for s in self._snapshots]}
+            config_path.write_text(json.dumps(data, indent=2), encoding="utf-8")
+        except OSError as e:
+            logger.warning(f"Failed to save system metrics history: {e}")
+
+    def _prune_old_snapshots(self) -> None:
+        if not self._snapshots:
+            return
+        cutoff = datetime.now(timezone.utc).timestamp() - (self.retention_hours * 3600)
+        self._snapshots = [
+            s for s in self._snapshots if s.timestamp.timestamp() > cutoff
+        ]
+
+    def _snapshot_loop(self) -> None:
+        while not self._shutdown.is_set():
+            self._shutdown.wait(timeout=self.interval_seconds)
+            if not self._shutdown.is_set():
+                self._take_snapshot()
+
+    def _take_snapshot(self) -> None:
+        try:
+            cpu_percent = psutil.cpu_percent(interval=0.1)
+            memory = psutil.virtual_memory()
+            disk = psutil.disk_usage(str(self.storage_root))
+
+            storage_bytes = 0
+            with self._lock:
+                storage = self._storage_ref
+            if storage:
+                try:
+                    buckets = storage.list_buckets()
+                    for bucket in buckets:
+                        stats = storage.bucket_stats(bucket.name, cache_ttl=60)
+                        storage_bytes += stats.get("total_bytes", stats.get("bytes", 0))
+                except Exception as e:
+                    logger.warning(f"Failed to collect bucket stats: {e}")
+
+            snapshot = SystemMetricsSnapshot(
+                timestamp=datetime.now(timezone.utc),
+                cpu_percent=cpu_percent,
+                memory_percent=memory.percent,
+                disk_percent=disk.percent,
+                storage_bytes=storage_bytes,
+            )
+
+            with self._lock:
+                self._snapshots.append(snapshot)
+                self._prune_old_snapshots()
+                self._save_history()
+
+            logger.debug(f"System metrics snapshot taken: CPU={cpu_percent:.1f}%, Memory={memory.percent:.1f}%")
+        except Exception as e:
+            logger.warning(f"Failed to take system metrics snapshot: {e}")
+
+    def get_current(self) -> Dict[str, Any]:
+        cpu_percent = psutil.cpu_percent(interval=0.1)
+        memory = psutil.virtual_memory()
+        disk = psutil.disk_usage(str(self.storage_root))
+        boot_time = psutil.boot_time()
+        uptime_seconds = time.time() - boot_time
+        uptime_days = int(uptime_seconds / 86400)
+
+        total_buckets = 0
+        total_objects = 0
+        total_bytes_used = 0
+        total_versions = 0
+
+        with self._lock:
+            storage = self._storage_ref
+        if storage:
+            try:
+                buckets = storage.list_buckets()
+                total_buckets = len(buckets)
+                for bucket in buckets:
+                    stats = storage.bucket_stats(bucket.name, cache_ttl=60)
+                    total_objects += stats.get("total_objects", stats.get("objects", 0))
+                    total_bytes_used += stats.get("total_bytes", stats.get("bytes", 0))
+                    total_versions += stats.get("version_count", 0)
+            except Exception as e:
+                logger.warning(f"Failed to collect current bucket stats: {e}")
+
+        return {
+            "cpu_percent": round(cpu_percent, 2),
+            "memory": {
+                "total": memory.total,
+                "available": memory.available,
+                "used": memory.used,
+                "percent": round(memory.percent, 2),
+            },
+            "disk": {
+                "total": disk.total,
+                "free": disk.free,
+                "used": disk.used,
+                "percent": round(disk.percent, 2),
+            },
+            "app": {
+                "buckets": total_buckets,
+                "objects": total_objects,
+                "versions": total_versions,
+                "storage_bytes": total_bytes_used,
+                "uptime_days": uptime_days,
+            },
+        }
+
+    def get_history(self, hours: Optional[int] = None) -> List[Dict[str, Any]]:
+        with self._lock:
+            snapshots = list(self._snapshots)
+
+        if hours:
+            cutoff = datetime.now(timezone.utc).timestamp() - (hours * 3600)
+            snapshots = [s for s in snapshots if s.timestamp.timestamp() > cutoff]
+
+        return [s.to_dict() for s in snapshots]
+
+    def shutdown(self) -> None:
+        self._shutdown.set()
+        self._take_snapshot()
+        self._snapshot_thread.join(timeout=5.0)

app/version.py

@@ -1,7 +1,6 @@
-"""Central location for the application version string."""
 from __future__ import annotations
 
-APP_VERSION = "0.1.7"
+APP_VERSION = "0.3.0"
 
 
 def get_version() -> str:

app/website_domains.py

@@ -0,0 +1,79 @@
+from __future__ import annotations
+
+import json
+import re
+import threading
+from pathlib import Path
+from typing import Dict, List, Optional
+
+_DOMAIN_RE = re.compile(
+    r"^(?!-)[a-z0-9]([a-z0-9-]*[a-z0-9])?(\.[a-z0-9]([a-z0-9-]*[a-z0-9])?)*$"
+)
+
+
+def normalize_domain(raw: str) -> str:
+    raw = raw.strip().lower()
+    for prefix in ("https://", "http://"):
+        if raw.startswith(prefix):
+            raw = raw[len(prefix):]
+    raw = raw.split("/", 1)[0]
+    raw = raw.split("?", 1)[0]
+    raw = raw.split("#", 1)[0]
+    if ":" in raw:
+        raw = raw.rsplit(":", 1)[0]
+    return raw
+
+
+def is_valid_domain(domain: str) -> bool:
+    if not domain or len(domain) > 253:
+        return False
+    return bool(_DOMAIN_RE.match(domain))
+
+
+class WebsiteDomainStore:
+    def __init__(self, config_path: Path) -> None:
+        self.config_path = config_path
+        self._lock = threading.Lock()
+        self._domains: Dict[str, str] = {}
+        self.reload()
+
+    def reload(self) -> None:
+        if not self.config_path.exists():
+            self._domains = {}
+            return
+        try:
+            with open(self.config_path, "r", encoding="utf-8") as f:
+                data = json.load(f)
+                if isinstance(data, dict):
+                    self._domains = {k.lower(): v for k, v in data.items()}
+                else:
+                    self._domains = {}
+        except (OSError, json.JSONDecodeError):
+            self._domains = {}
+
+    def _save(self) -> None:
+        self.config_path.parent.mkdir(parents=True, exist_ok=True)
+        with open(self.config_path, "w", encoding="utf-8") as f:
+            json.dump(self._domains, f, indent=2)
+
+    def list_all(self) -> List[Dict[str, str]]:
+        with self._lock:
+            return [{"domain": d, "bucket": b} for d, b in self._domains.items()]
+
+    def get_bucket(self, domain: str) -> Optional[str]:
+        with self._lock:
+            return self._domains.get(domain.lower())
+
+    def set_mapping(self, domain: str, bucket: str) -> None:
+        with self._lock:
+            self._domains[domain.lower()] = bucket
+            self._save()
+
+    def delete_mapping(self, domain: str) -> bool:
+        with self._lock:
+            key = domain.lower()
+            if key not in self._domains:
+                return False
+            del self._domains[key]
+            self._save()
+            return True

myfsio_core/Cargo.lock

@@ -0,0 +1,421 @@
+# This file is automatically @generated by Cargo.
+# It is not intended for manual editing.
+version = 4
+
+[[package]]
+name = "aho-corasick"
+version = "1.1.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ddd31a130427c27518df266943a5308ed92d4b226cc639f5a8f1002816174301"
+dependencies = [
+ "memchr",
+]
+
+[[package]]
+name = "allocator-api2"
+version = "0.2.21"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "683d7910e743518b0e34f1186f92494becacb047c7b6bf616c96772180fef923"
+
+[[package]]
+name = "bitflags"
+version = "2.11.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "843867be96c8daad0d758b57df9392b6d8d271134fce549de6ce169ff98a92af"
+
+[[package]]
+name = "block-buffer"
+version = "0.10.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3078c7629b62d3f0439517fa394996acacc5cbc91c5a20d8c658e77abd503a71"
+dependencies = [
+ "generic-array",
+]
+
+[[package]]
+name = "cfg-if"
+version = "1.0.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9330f8b2ff13f34540b44e946ef35111825727b38d33286ef986142615121801"
+
+[[package]]
+name = "cpufeatures"
+version = "0.2.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "59ed5838eebb26a2bb2e58f6d5b5316989ae9d08bab10e0e6d103e656d1b0280"
+dependencies = [
+ "libc",
+]
+
+[[package]]
+name = "crypto-common"
+version = "0.1.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "78c8292055d1c1df0cce5d180393dc8cce0abec0a7102adb6c7b1eef6016d60a"
+dependencies = [
+ "generic-array",
+ "typenum",
+]
+
+[[package]]
+name = "digest"
+version = "0.10.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9ed9a281f7bc9b7576e61468ba615a66a5c8cfdff42420a70aa82701a3b1e292"
+dependencies = [
+ "block-buffer",
+ "crypto-common",
+ "subtle",
+]
+
+[[package]]
+name = "equivalent"
+version = "1.0.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "877a4ace8713b0bcf2a4e7eec82529c029f1d0619886d18145fea96c3ffe5c0f"
+
+[[package]]
+name = "foldhash"
+version = "0.1.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d9c4f5dac5e15c24eb999c26181a6ca40b39fe946cbe4c263c7209467bc83af2"
+
+[[package]]
+name = "generic-array"
+version = "0.14.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "85649ca51fd72272d7821adaf274ad91c288277713d9c18820d8499a7ff69e9a"
+dependencies = [
+ "typenum",
+ "version_check",
+]
+
+[[package]]
+name = "hashbrown"
+version = "0.15.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9229cfe53dfd69f0609a49f65461bd93001ea1ef889cd5529dd176593f5338a1"
+dependencies = [
+ "allocator-api2",
+ "equivalent",
+ "foldhash",
+]
+
+[[package]]
+name = "heck"
+version = "0.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea"
+
+[[package]]
+name = "hex"
+version = "0.4.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7f24254aa9a54b5c858eaee2f5bccdb46aaf0e486a595ed5fd8f86ba55232a70"
+
+[[package]]
+name = "hmac"
+version = "0.12.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6c49c37c09c17a53d937dfbb742eb3a961d65a994e6bcdcf37e7399d0cc8ab5e"
+dependencies = [
+ "digest",
+]
+
+[[package]]
+name = "libc"
+version = "0.2.182"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6800badb6cb2082ffd7b6a67e6125bb39f18782f793520caee8cb8846be06112"
+
+[[package]]
+name = "lock_api"
+version = "0.4.14"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "224399e74b87b5f3557511d98dff8b14089b3dadafcab6bb93eab67d3aace965"
+dependencies = [
+ "scopeguard",
+]
+
+[[package]]
+name = "lru"
+version = "0.14.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9f8cc7106155f10bdf99a6f379688f543ad6596a415375b36a59a054ceda1198"
+dependencies = [
+ "hashbrown",
+]
+
+[[package]]
+name = "md-5"
+version = "0.10.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d89e7ee0cfbedfc4da3340218492196241d89eefb6dab27de5df917a6d2e78cf"
+dependencies = [
+ "cfg-if",
+ "digest",
+]
+
+[[package]]
+name = "memchr"
+version = "2.8.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f8ca58f447f06ed17d5fc4043ce1b10dd205e060fb3ce5b979b8ed8e59ff3f79"
+
+[[package]]
+name = "myfsio_core"
+version = "0.1.0"
+dependencies = [
+ "hex",
+ "hmac",
+ "lru",
+ "md-5",
+ "parking_lot",
+ "pyo3",
+ "regex",
+ "sha2",
+ "unicode-normalization",
+]
+
+[[package]]
+name = "once_cell"
+version = "1.21.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "42f5e15c9953c5e4ccceeb2e7382a716482c34515315f7b03532b8b4e8393d2d"
+
+[[package]]
+name = "parking_lot"
+version = "0.12.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "93857453250e3077bd71ff98b6a65ea6621a19bb0f559a85248955ac12c45a1a"
+dependencies = [
+ "lock_api",
+ "parking_lot_core",
+]
+
+[[package]]
+name = "parking_lot_core"
+version = "0.9.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2621685985a2ebf1c516881c026032ac7deafcda1a2c9b7850dc81e3dfcb64c1"
+dependencies = [
+ "cfg-if",
+ "libc",
+ "redox_syscall",
+ "smallvec",
+ "windows-link",
+]
+
+[[package]]
+name = "portable-atomic"
+version = "1.13.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c33a9471896f1c69cecef8d20cbe2f7accd12527ce60845ff44c153bb2a21b49"
+
+[[package]]
+name = "proc-macro2"
+version = "1.0.106"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8fd00f0bb2e90d81d1044c2b32617f68fcb9fa3bb7640c23e9c748e53fb30934"
+dependencies = [
+ "unicode-ident",
+]
+
+[[package]]
+name = "pyo3"
+version = "0.28.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "14c738662e2181be11cb82487628404254902bb3225d8e9e99c31f3ef82a405c"
+dependencies = [
+ "libc",
+ "once_cell",
+ "portable-atomic",
+ "pyo3-build-config",
+ "pyo3-ffi",
+ "pyo3-macros",
+]
+
+[[package]]
+name = "pyo3-build-config"
+version = "0.28.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f9ca0864a7dd3c133a7f3f020cbff2e12e88420da854c35540fd20ce2d60e435"
+dependencies = [
+ "target-lexicon",
+]
+
+[[package]]
+name = "pyo3-ffi"
+version = "0.28.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9dfc1956b709823164763a34cc42bbfd26b8730afa77809a3df8b94a3ae3b059"
+dependencies = [
+ "libc",
+ "pyo3-build-config",
+]
+
+[[package]]
+name = "pyo3-macros"
+version = "0.28.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "29dc660ad948bae134d579661d08033fbb1918f4529c3bbe3257a68f2009ddf2"
+dependencies = [
+ "proc-macro2",
+ "pyo3-macros-backend",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "pyo3-macros-backend"
+version = "0.28.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e78cd6c6d718acfcedf26c3d21fe0f053624368b0d44298c55d7138fde9331f7"
+dependencies = [
+ "heck",
+ "proc-macro2",
+ "pyo3-build-config",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "quote"
+version = "1.0.44"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "21b2ebcf727b7760c461f091f9f0f539b77b8e87f2fd88131e7f1b433b3cece4"
+dependencies = [
+ "proc-macro2",
+]
+
+[[package]]
+name = "redox_syscall"
+version = "0.5.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ed2bf2547551a7053d6fdfafda3f938979645c44812fbfcda098faae3f1a362d"
+dependencies = [
+ "bitflags",
+]
+
+[[package]]
+name = "regex"
+version = "1.12.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e10754a14b9137dd7b1e3e5b0493cc9171fdd105e0ab477f51b72e7f3ac0e276"
+dependencies = [
+ "aho-corasick",
+ "memchr",
+ "regex-automata",
+ "regex-syntax",
+]
+
+[[package]]
+name = "regex-automata"
+version = "0.4.14"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6e1dd4122fc1595e8162618945476892eefca7b88c52820e74af6262213cae8f"
+dependencies = [
+ "aho-corasick",
+ "memchr",
+ "regex-syntax",
+]
+
+[[package]]
+name = "regex-syntax"
+version = "0.8.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a96887878f22d7bad8a3b6dc5b7440e0ada9a245242924394987b21cf2210a4c"
+
+[[package]]
+name = "scopeguard"
+version = "1.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "94143f37725109f92c262ed2cf5e59bce7498c01bcc1502d7b9afe439a4e9f49"
+
+[[package]]
+name = "sha2"
+version = "0.10.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a7507d819769d01a365ab707794a4084392c824f54a7a6a7862f8c3d0892b283"
+dependencies = [
+ "cfg-if",
+ "cpufeatures",
+ "digest",
+]
+
+[[package]]
+name = "smallvec"
+version = "1.15.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "67b1b7a3b5fe4f1376887184045fcf45c69e92af734b7aaddc05fb777b6fbd03"
+
+[[package]]
+name = "subtle"
+version = "2.6.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "13c2bddecc57b384dee18652358fb23172facb8a2c51ccc10d74c157bdea3292"
+
+[[package]]
+name = "syn"
+version = "2.0.116"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3df424c70518695237746f84cede799c9c58fcb37450d7b23716568cc8bc69cb"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-ident",
+]
+
+[[package]]
+name = "target-lexicon"
+version = "0.13.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "adb6935a6f5c20170eeceb1a3835a49e12e19d792f6dd344ccc76a985ca5a6ca"
+
+[[package]]
+name = "tinyvec"
+version = "1.10.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bfa5fdc3bce6191a1dbc8c02d5c8bffcf557bafa17c124c5264a458f1b0613fa"
+dependencies = [
+ "tinyvec_macros",
+]
+
+[[package]]
+name = "tinyvec_macros"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1f3ccbac311fea05f86f61904b462b55fb3df8837a366dfc601a0161d0532f20"
+
+[[package]]
+name = "typenum"
+version = "1.19.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "562d481066bde0658276a35467c4af00bdc6ee726305698a55b86e61d7ad82bb"
+
+[[package]]
+name = "unicode-ident"
+version = "1.0.24"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e6e4313cd5fcd3dad5cafa179702e2b244f760991f45397d14d4ebf38247da75"
+
+[[package]]
+name = "unicode-normalization"
+version = "0.1.25"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5fd4f6878c9cb28d874b009da9e8d183b5abc80117c40bbd187a1fde336be6e8"
+dependencies = [
+ "tinyvec",
+]
+
+[[package]]
+name = "version_check"
+version = "0.9.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0b928f33d975fc6ad9f86c8f283853ad26bdd5b10b7f1542aa2fa15e2289105a"
+
+[[package]]
+name = "windows-link"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f0805222e57f7521d6a62e36fa9163bc891acd422f971defe97d64e70d0a4fe5"

myfsio_core/Cargo.toml

@@ -0,0 +1,19 @@
+[package]
+name = "myfsio_core"
+version = "0.1.0"
+edition = "2021"
+
+[lib]
+name = "myfsio_core"
+crate-type = ["cdylib"]
+
+[dependencies]
+pyo3 = { version = "0.28", features = ["extension-module"] }
+hmac = "0.12"
+sha2 = "0.10"
+md-5 = "0.10"
+hex = "0.4"
+unicode-normalization = "0.1"
+regex = "1"
+lru = "0.14"
+parking_lot = "0.12"

myfsio_core/pyproject.toml

@@ -0,0 +1,11 @@
+[build-system]
+requires = ["maturin>=1.0,<2.0"]
+build-backend = "maturin"
+
+[project]
+name = "myfsio_core"
+version = "0.1.0"
+requires-python = ">=3.10"
+
+[tool.maturin]
+features = ["pyo3/extension-module"]

myfsio_core/src/hashing.rs

@@ -0,0 +1,90 @@
+use md5::{Digest, Md5};
+use pyo3::exceptions::PyIOError;
+use pyo3::prelude::*;
+use sha2::Sha256;
+use std::fs::File;
+use std::io::Read;
+
+const CHUNK_SIZE: usize = 65536;
+
+#[pyfunction]
+pub fn md5_file(py: Python<'_>, path: &str) -> PyResult<String> {
+    let path = path.to_owned();
+    py.detach(move || {
+        let mut file = File::open(&path)
+            .map_err(|e| PyIOError::new_err(format!("Failed to open file: {}", e)))?;
+        let mut hasher = Md5::new();
+        let mut buf = vec![0u8; CHUNK_SIZE];
+        loop {
+            let n = file
+                .read(&mut buf)
+                .map_err(|e| PyIOError::new_err(format!("Failed to read file: {}", e)))?;
+            if n == 0 {
+                break;
+            }
+            hasher.update(&buf[..n]);
+        }
+        Ok(format!("{:x}", hasher.finalize()))
+    })
+}
+
+#[pyfunction]
+pub fn md5_bytes(data: &[u8]) -> String {
+    let mut hasher = Md5::new();
+    hasher.update(data);
+    format!("{:x}", hasher.finalize())
+}
+
+#[pyfunction]
+pub fn sha256_file(py: Python<'_>, path: &str) -> PyResult<String> {
+    let path = path.to_owned();
+    py.detach(move || {
+        let mut file = File::open(&path)
+            .map_err(|e| PyIOError::new_err(format!("Failed to open file: {}", e)))?;
+        let mut hasher = Sha256::new();
+        let mut buf = vec![0u8; CHUNK_SIZE];
+        loop {
+            let n = file
+                .read(&mut buf)
+                .map_err(|e| PyIOError::new_err(format!("Failed to read file: {}", e)))?;
+            if n == 0 {
+                break;
+            }
+            hasher.update(&buf[..n]);
+        }
+        Ok(format!("{:x}", hasher.finalize()))
+    })
+}
+
+#[pyfunction]
+pub fn sha256_bytes(data: &[u8]) -> String {
+    let mut hasher = Sha256::new();
+    hasher.update(data);
+    format!("{:x}", hasher.finalize())
+}
+
+#[pyfunction]
+pub fn md5_sha256_file(py: Python<'_>, path: &str) -> PyResult<(String, String)> {
+    let path = path.to_owned();
+    py.detach(move || {
+        let mut file = File::open(&path)
+            .map_err(|e| PyIOError::new_err(format!("Failed to open file: {}", e)))?;
+        let mut md5_hasher = Md5::new();
+        let mut sha_hasher = Sha256::new();
+        let mut buf = vec![0u8; CHUNK_SIZE];
+        loop {
+            let n = file
+                .read(&mut buf)
+                .map_err(|e| PyIOError::new_err(format!("Failed to read file: {}", e)))?;
+            if n == 0 {
+                break;
+            }
+            md5_hasher.update(&buf[..n]);
+            sha_hasher.update(&buf[..n]);
+        }
+        Ok((
+            format!("{:x}", md5_hasher.finalize()),
+            format!("{:x}", sha_hasher.finalize()),
+        ))
+    })
+}

myfsio_core/src/lib.rs

@@ -0,0 +1,30 @@
+mod hashing;
+mod sigv4;
+mod validation;
+
+use pyo3::prelude::*;
+
+#[pymodule]
+mod myfsio_core {
+    use super::*;
+
+    #[pymodule_init]
+    fn init(m: &Bound<'_, PyModule>) -> PyResult<()> {
+        m.add_function(wrap_pyfunction!(sigv4::derive_signing_key, m)?)?;
+        m.add_function(wrap_pyfunction!(sigv4::compute_signature, m)?)?;
+        m.add_function(wrap_pyfunction!(sigv4::build_string_to_sign, m)?)?;
+        m.add_function(wrap_pyfunction!(sigv4::constant_time_compare, m)?)?;
+        m.add_function(wrap_pyfunction!(sigv4::clear_signing_key_cache, m)?)?;
+
+        m.add_function(wrap_pyfunction!(hashing::md5_file, m)?)?;
+        m.add_function(wrap_pyfunction!(hashing::md5_bytes, m)?)?;
+        m.add_function(wrap_pyfunction!(hashing::sha256_file, m)?)?;
+        m.add_function(wrap_pyfunction!(hashing::sha256_bytes, m)?)?;
+        m.add_function(wrap_pyfunction!(hashing::md5_sha256_file, m)?)?;
+
+        m.add_function(wrap_pyfunction!(validation::validate_object_key, m)?)?;
+        m.add_function(wrap_pyfunction!(validation::validate_bucket_name, m)?)?;
+
+        Ok(())
+    }
+}

myfsio_core/src/sigv4.rs

@@ -0,0 +1,108 @@
+use hmac::{Hmac, Mac};
+use lru::LruCache;
+use parking_lot::Mutex;
+use pyo3::prelude::*;
+use sha2::{Digest, Sha256};
+use std::num::NonZeroUsize;
+use std::sync::LazyLock;
+use std::time::Instant;
+
+type HmacSha256 = Hmac<Sha256>;
+
+struct CacheEntry {
+    key: Vec<u8>,
+    created: Instant,
+}
+
+static SIGNING_KEY_CACHE: LazyLock<Mutex<LruCache<(String, String, String, String), CacheEntry>>> =
+    LazyLock::new(|| Mutex::new(LruCache::new(NonZeroUsize::new(256).unwrap())));
+
+const CACHE_TTL_SECS: u64 = 60;
+
+fn hmac_sha256(key: &[u8], msg: &[u8]) -> Vec<u8> {
+    let mut mac = HmacSha256::new_from_slice(key).expect("HMAC key length is always valid");
+    mac.update(msg);
+    mac.finalize().into_bytes().to_vec()
+}
+
+#[pyfunction]
+pub fn derive_signing_key(
+    secret_key: &str,
+    date_stamp: &str,
+    region: &str,
+    service: &str,
+) -> Vec<u8> {
+    let cache_key = (
+        secret_key.to_owned(),
+        date_stamp.to_owned(),
+        region.to_owned(),
+        service.to_owned(),
+    );
+
+    {
+        let mut cache = SIGNING_KEY_CACHE.lock();
+        if let Some(entry) = cache.get(&cache_key) {
+            if entry.created.elapsed().as_secs() < CACHE_TTL_SECS {
+                return entry.key.clone();
+            }
+            cache.pop(&cache_key);
+        }
+    }
+
+    let k_date = hmac_sha256(format!("AWS4{}", secret_key).as_bytes(), date_stamp.as_bytes());
+    let k_region = hmac_sha256(&k_date, region.as_bytes());
+    let k_service = hmac_sha256(&k_region, service.as_bytes());
+    let k_signing = hmac_sha256(&k_service, b"aws4_request");
+
+    {
+        let mut cache = SIGNING_KEY_CACHE.lock();
+        cache.put(
+            cache_key,
+            CacheEntry {
+                key: k_signing.clone(),
+                created: Instant::now(),
+            },
+        );
+    }
+
+    k_signing
+}
+
+#[pyfunction]
+pub fn compute_signature(signing_key: &[u8], string_to_sign: &str) -> String {
+    let sig = hmac_sha256(signing_key, string_to_sign.as_bytes());
+    hex::encode(sig)
+}
+
+fn sha256_hex(data: &[u8]) -> String {
+    let mut hasher = Sha256::new();
+    hasher.update(data);
+    hex::encode(hasher.finalize())
+}
+
+#[pyfunction]
+pub fn build_string_to_sign(
+    amz_date: &str,
+    credential_scope: &str,
+    canonical_request: &str,
+) -> String {
+    let cr_hash = sha256_hex(canonical_request.as_bytes());
+    format!("AWS4-HMAC-SHA256\n{}\n{}\n{}", amz_date, credential_scope, cr_hash)
+}
+
+#[pyfunction]
+pub fn constant_time_compare(a: &str, b: &str) -> bool {
+    if a.len() != b.len() {
+        return false;
+    }
+    let mut result: u8 = 0;
+    for (x, y) in a.bytes().zip(b.bytes()) {
+        result |= x ^ y;
+    }
+    result == 0
+}
+
+#[pyfunction]
+pub fn clear_signing_key_cache() {
+    SIGNING_KEY_CACHE.lock().clear();
+}

myfsio_core/src/validation.rs

@@ -0,0 +1,149 @@
+use pyo3::prelude::*;
+use std::sync::LazyLock;
+use unicode_normalization::UnicodeNormalization;
+
+const WINDOWS_RESERVED: &[&str] = &[
+    "CON", "PRN", "AUX", "NUL", "COM0", "COM1", "COM2", "COM3", "COM4", "COM5", "COM6", "COM7",
+    "COM8", "COM9", "LPT0", "LPT1", "LPT2", "LPT3", "LPT4", "LPT5", "LPT6", "LPT7", "LPT8",
+    "LPT9",
+];
+
+const WINDOWS_ILLEGAL_CHARS: &[char] = &['<', '>', ':', '"', '/', '\\', '|', '?', '*'];
+
+const INTERNAL_FOLDERS: &[&str] = &[".meta", ".versions", ".multipart"];
+const SYSTEM_ROOT: &str = ".myfsio.sys";
+
+static IP_REGEX: LazyLock<regex::Regex> =
+    LazyLock::new(|| regex::Regex::new(r"^\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}$").unwrap());
+
+#[pyfunction]
+#[pyo3(signature = (object_key, max_length_bytes=1024, is_windows=false, reserved_prefixes=None))]
+pub fn validate_object_key(
+    object_key: &str,
+    max_length_bytes: usize,
+    is_windows: bool,
+    reserved_prefixes: Option<Vec<String>>,
+) -> PyResult<Option<String>> {
+    if object_key.is_empty() {
+        return Ok(Some("Object key required".to_string()));
+    }
+
+    if object_key.contains('\0') {
+        return Ok(Some("Object key contains null bytes".to_string()));
+    }
+
+    let normalized: String = object_key.nfc().collect();
+
+    if normalized.len() > max_length_bytes {
+        return Ok(Some(format!(
+            "Object key exceeds maximum length of {} bytes",
+            max_length_bytes
+        )));
+    }
+
+    if normalized.starts_with('/') || normalized.starts_with('\\') {
+        return Ok(Some("Object key cannot start with a slash".to_string()));
+    }
+
+    let parts: Vec<&str> = if cfg!(windows) || is_windows {
+        normalized.split(['/', '\\']).collect()
+    } else {
+        normalized.split('/').collect()
+    };
+
+    for part in &parts {
+        if part.is_empty() {
+            continue;
+        }
+
+        if *part == ".." {
+            return Ok(Some(
+                "Object key contains parent directory references".to_string(),
+            ));
+        }
+
+        if *part == "." {
+            return Ok(Some("Object key contains invalid segments".to_string()));
+        }
+
+        if part.chars().any(|c| (c as u32) < 32) {
+            return Ok(Some(
+                "Object key contains control characters".to_string(),
+            ));
+        }
+
+        if is_windows {
+            if part.chars().any(|c| WINDOWS_ILLEGAL_CHARS.contains(&c)) {
+                return Ok(Some(
+                    "Object key contains characters not supported on Windows filesystems"
+                        .to_string(),
+                ));
+            }
+            if part.ends_with(' ') || part.ends_with('.') {
+                return Ok(Some(
+                    "Object key segments cannot end with spaces or periods on Windows".to_string(),
+                ));
+            }
+            let trimmed = part.trim_end_matches(['.', ' ']).to_uppercase();
+            if WINDOWS_RESERVED.contains(&trimmed.as_str()) {
+                return Ok(Some(format!("Invalid filename segment: {}", part)));
+            }
+        }
+    }
+
+    let non_empty_parts: Vec<&str> = parts.iter().filter(|p| !p.is_empty()).copied().collect();
+    if let Some(top) = non_empty_parts.first() {
+        if INTERNAL_FOLDERS.contains(top) || *top == SYSTEM_ROOT {
+            return Ok(Some("Object key uses a reserved prefix".to_string()));
+        }
+
+        if let Some(ref prefixes) = reserved_prefixes {
+            for prefix in prefixes {
+                if *top == prefix.as_str() {
+                    return Ok(Some("Object key uses a reserved prefix".to_string()));
+                }
+            }
+        }
+    }
+
+    Ok(None)
+}
+
+#[pyfunction]
+pub fn validate_bucket_name(bucket_name: &str) -> Option<String> {
+    let len = bucket_name.len();
+    if len < 3 || len > 63 {
+        return Some("Bucket name must be between 3 and 63 characters".to_string());
+    }
+
+    let bytes = bucket_name.as_bytes();
+    if !bytes[0].is_ascii_lowercase() && !bytes[0].is_ascii_digit() {
+        return Some(
+            "Bucket name must start and end with a lowercase letter or digit".to_string(),
+        );
+    }
+    if !bytes[len - 1].is_ascii_lowercase() && !bytes[len - 1].is_ascii_digit() {
+        return Some(
+            "Bucket name must start and end with a lowercase letter or digit".to_string(),
+        );
+    }
+
+    for &b in bytes {
+        if !b.is_ascii_lowercase() && !b.is_ascii_digit() && b != b'.' && b != b'-' {
+            return Some(
+                "Bucket name can only contain lowercase letters, digits, dots, and hyphens"
+                    .to_string(),
+            );
+        }
+    }
+
+    if bucket_name.contains("..") {
+        return Some("Bucket name must not contain consecutive periods".to_string());
+    }
+
+    if IP_REGEX.is_match(bucket_name) {
+        return Some("Bucket name must not be formatted as an IP address".to_string());
+    }
+
+    None
+}

myfsio_core/target/.rustc_info.json

@@ -0,0 +1 @@
+{"rustc_fingerprint":13172970000770725120,"outputs":{"7971740275564407648":{"success":true,"status":"","code":0,"stdout":"___.exe\nlib___.rlib\n___.dll\n___.dll\n___.lib\n___.dll\nC:\\Users\\jun\\.rustup\\toolchains\\stable-x86_64-pc-windows-msvc\npacked\n___\ndebug_assertions\npanic=\"unwind\"\nproc_macro\ntarget_abi=\"\"\ntarget_arch=\"x86_64\"\ntarget_endian=\"little\"\ntarget_env=\"msvc\"\ntarget_family=\"windows\"\ntarget_feature=\"cmpxchg16b\"\ntarget_feature=\"fxsr\"\ntarget_feature=\"sse\"\ntarget_feature=\"sse2\"\ntarget_feature=\"sse3\"\ntarget_has_atomic=\"128\"\ntarget_has_atomic=\"16\"\ntarget_has_atomic=\"32\"\ntarget_has_atomic=\"64\"\ntarget_has_atomic=\"8\"\ntarget_has_atomic=\"ptr\"\ntarget_os=\"windows\"\ntarget_pointer_width=\"64\"\ntarget_vendor=\"pc\"\nwindows\n","stderr":""},"17747080675513052775":{"success":true,"status":"","code":0,"stdout":"rustc 1.93.1 (01f6ddf75 2026-02-11)\nbinary: rustc\ncommit-hash: 01f6ddf7588f42ae2d7eb0a2f21d44e8e96674cf\ncommit-date: 2026-02-11\nhost: x86_64-pc-windows-msvc\nrelease: 1.93.1\nLLVM version: 21.1.8\n","stderr":""}},"successes":{}}

myfsio_core/target/CACHEDIR.TAG

@@ -0,0 +1,3 @@
+Signature: 8a477f597d28d172789f06886806bc55
+# This file is a cache directory tag created by cargo.
+# For information about cache directory tags see https://bford.info/cachedir/

myfsio_core/target/release/.fingerprint/aho-corasick-45694771b543be75/invoked.timestamp

@@ -0,0 +1 @@
+This file has an mtime of when this was started.

myfsio_core/target/release/.fingerprint/aho-corasick-45694771b543be75/lib-aho_corasick

@@ -0,0 +1 @@
+801af22cf202da8e

myfsio_core/target/release/.fingerprint/aho-corasick-45694771b543be75/lib-aho_corasick.json

@@ -0,0 +1 @@
+{"rustc":8323788817864214825,"features":"[\"perf-literal\", \"std\"]","declared_features":"[\"default\", \"logging\", \"perf-literal\", \"std\"]","target":7534583537114156500,"profile":2040997289075261528,"path":6364296192483896971,"deps":[[1363051979936526615,"memchr",false,11090220145123168660]],"local":[{"CheckDepInfo":{"dep_info":"release\\.fingerprint\\aho-corasick-45694771b543be75\\dep-lib-aho_corasick","checksum":false}}],"rustflags":[],"config":2069994364910194474,"compile_kind":0}

myfsio_core/target/release/.fingerprint/allocator-api2-db7934dbe96de5b4/invoked.timestamp

@@ -0,0 +1 @@
+This file has an mtime of when this was started.

myfsio_core/target/release/.fingerprint/allocator-api2-db7934dbe96de5b4/lib-allocator_api2

@@ -0,0 +1 @@
+435555ec2fb592e3

myfsio_core/target/release/.fingerprint/allocator-api2-db7934dbe96de5b4/lib-allocator_api2.json

@@ -0,0 +1 @@
+{"rustc":8323788817864214825,"features":"[\"alloc\"]","declared_features":"[\"alloc\", \"default\", \"fresh-rust\", \"nightly\", \"serde\", \"std\"]","target":5388200169723499962,"profile":4067574213046180398,"path":10654049299693593327,"deps":[],"local":[{"CheckDepInfo":{"dep_info":"release\\.fingerprint\\allocator-api2-db7934dbe96de5b4\\dep-lib-allocator_api2","checksum":false}}],"rustflags":[],"config":2069994364910194474,"compile_kind":0}

myfsio_core/target/release/.fingerprint/autocfg-1c4fb7a37cc3df69/invoked.timestamp

@@ -0,0 +1 @@
+This file has an mtime of when this was started.

myfsio_core/target/release/.fingerprint/autocfg-1c4fb7a37cc3df69/lib-autocfg

@@ -0,0 +1 @@
+d28af275d001c358

myfsio_core/target/release/.fingerprint/autocfg-1c4fb7a37cc3df69/lib-autocfg.json

@@ -0,0 +1 @@
+{"rustc":8323788817864214825,"features":"[]","declared_features":"[]","target":6962977057026645649,"profile":1369601567987815722,"path":9853093265219907461,"deps":[],"local":[{"CheckDepInfo":{"dep_info":"release\\.fingerprint\\autocfg-1c4fb7a37cc3df69\\dep-lib-autocfg","checksum":false}}],"rustflags":[],"config":2069994364910194474,"compile_kind":0}

myfsio_core/target/release/.fingerprint/block-buffer-95b0ac364bec72f9/invoked.timestamp

@@ -0,0 +1 @@
+This file has an mtime of when this was started.

myfsio_core/target/release/.fingerprint/block-buffer-95b0ac364bec72f9/lib-block_buffer

@@ -0,0 +1 @@
+1fbf4ba9542edced

myfsio_core/target/release/.fingerprint/block-buffer-95b0ac364bec72f9/lib-block_buffer.json

@@ -0,0 +1 @@
+{"rustc":8323788817864214825,"features":"[]","declared_features":"[]","target":4098124618827574291,"profile":2040997289075261528,"path":3658007358608479489,"deps":[[10520923840501062997,"generic_array",false,11555283918993371487]],"local":[{"CheckDepInfo":{"dep_info":"release\\.fingerprint\\block-buffer-95b0ac364bec72f9\\dep-lib-block_buffer","checksum":false}}],"rustflags":[],"config":2069994364910194474,"compile_kind":0}

myfsio_core/target/release/.fingerprint/cfg-if-be2711f84a777e73/invoked.timestamp

@@ -0,0 +1 @@
+This file has an mtime of when this was started.

myfsio_core/target/release/.fingerprint/cfg-if-be2711f84a777e73/lib-cfg_if

@@ -0,0 +1 @@
+37923e6f5f9687ab

myfsio_core/target/release/.fingerprint/cfg-if-be2711f84a777e73/lib-cfg_if.json

@@ -0,0 +1 @@
+{"rustc":8323788817864214825,"features":"[]","declared_features":"[\"core\", \"rustc-dep-of-std\"]","target":13840298032947503755,"profile":2040997289075261528,"path":4093486168504982869,"deps":[],"local":[{"CheckDepInfo":{"dep_info":"release\\.fingerprint\\cfg-if-be2711f84a777e73\\dep-lib-cfg_if","checksum":false}}],"rustflags":[],"config":2069994364910194474,"compile_kind":0}

myfsio_core/target/release/.fingerprint/cpufeatures-980094f8735c42d1/invoked.timestamp

@@ -0,0 +1 @@
+This file has an mtime of when this was started.

myfsio_core/target/release/.fingerprint/cpufeatures-980094f8735c42d1/lib-cpufeatures

@@ -0,0 +1 @@
+603e28136cf5763c

myfsio_core/target/release/.fingerprint/cpufeatures-980094f8735c42d1/lib-cpufeatures.json

@@ -0,0 +1 @@
+{"rustc":8323788817864214825,"features":"[]","declared_features":"[]","target":2330704043955282025,"profile":2040997289075261528,"path":13200428550696548327,"deps":[],"local":[{"CheckDepInfo":{"dep_info":"release\\.fingerprint\\cpufeatures-980094f8735c42d1\\dep-lib-cpufeatures","checksum":false}}],"rustflags":[],"config":2069994364910194474,"compile_kind":0}

myfsio_core/target/release/.fingerprint/crypto-common-289a508abdda3048/invoked.timestamp

@@ -0,0 +1 @@
+This file has an mtime of when this was started.

myfsio_core/target/release/.fingerprint/crypto-common-289a508abdda3048/lib-crypto_common

@@ -0,0 +1 @@
+896672d759b5299c

myfsio_core/target/release/.fingerprint/crypto-common-289a508abdda3048/lib-crypto_common.json

@@ -0,0 +1 @@
+{"rustc":8323788817864214825,"features":"[\"std\"]","declared_features":"[\"getrandom\", \"rand_core\", \"std\"]","target":12082577455412410174,"profile":2040997289075261528,"path":14902376638882023040,"deps":[[857979250431893282,"typenum",false,7416411392359930020],[10520923840501062997,"generic_array",false,11555283918993371487]],"local":[{"CheckDepInfo":{"dep_info":"release\\.fingerprint\\crypto-common-289a508abdda3048\\dep-lib-crypto_common","checksum":false}}],"rustflags":[],"config":2069994364910194474,"compile_kind":0}

myfsio_core/target/release/.fingerprint/digest-a91458bfa5613332/invoked.timestamp

@@ -0,0 +1 @@
+This file has an mtime of when this was started.

myfsio_core/target/release/.fingerprint/digest-a91458bfa5613332/lib-digest

@@ -0,0 +1 @@
+914a617b9f05c9d8

myfsio_core/target/release/.fingerprint/digest-a91458bfa5613332/lib-digest.json

@@ -0,0 +1 @@
+{"rustc":8323788817864214825,"features":"[\"alloc\", \"block-buffer\", \"core-api\", \"default\", \"mac\", \"std\", \"subtle\"]","declared_features":"[\"alloc\", \"blobby\", \"block-buffer\", \"const-oid\", \"core-api\", \"default\", \"dev\", \"mac\", \"oid\", \"rand_core\", \"std\", \"subtle\"]","target":7510122432137863311,"profile":2040997289075261528,"path":11503432597517024930,"deps":[[6039282458970808711,"crypto_common",false,11252724541433210505],[10626340395483396037,"block_buffer",false,17139625223017709343],[17003143334332120809,"subtle",false,8597342066671925934]],"local":[{"CheckDepInfo":{"dep_info":"release\\.fingerprint\\digest-a91458bfa5613332\\dep-lib-digest","checksum":false}}],"rustflags":[],"config":2069994364910194474,"compile_kind":0}

myfsio_core/target/release/.fingerprint/equivalent-943ac856871c0988/invoked.timestamp

@@ -0,0 +1 @@
+This file has an mtime of when this was started.

myfsio_core/target/release/.fingerprint/equivalent-943ac856871c0988/lib-equivalent

@@ -0,0 +1 @@
+3b95cf48bbd7dc53

myfsio_core/target/release/.fingerprint/equivalent-943ac856871c0988/lib-equivalent.json

@@ -0,0 +1 @@
+{"rustc":8323788817864214825,"features":"[]","declared_features":"[]","target":1524667692659508025,"profile":2040997289075261528,"path":17534356223679657546,"deps":[],"local":[{"CheckDepInfo":{"dep_info":"release\\.fingerprint\\equivalent-943ac856871c0988\\dep-lib-equivalent","checksum":false}}],"rustflags":[],"config":2069994364910194474,"compile_kind":0}

myfsio_core/target/release/.fingerprint/foldhash-b8a92f8c10d550f7/invoked.timestamp

@@ -0,0 +1 @@
+This file has an mtime of when this was started.

myfsio_core/target/release/.fingerprint/foldhash-b8a92f8c10d550f7/lib-foldhash

@@ -0,0 +1 @@
+b7ba5182ce570398

myfsio_core/target/release/.fingerprint/foldhash-b8a92f8c10d550f7/lib-foldhash.json

@@ -0,0 +1 @@
+{"rustc":8323788817864214825,"features":"[]","declared_features":"[\"default\", \"std\"]","target":18077926938045032029,"profile":2040997289075261528,"path":9869209539952544870,"deps":[],"local":[{"CheckDepInfo":{"dep_info":"release\\.fingerprint\\foldhash-b8a92f8c10d550f7\\dep-lib-foldhash","checksum":false}}],"rustflags":[],"config":2069994364910194474,"compile_kind":0}

myfsio_core/target/release/.fingerprint/generic-array-2462daa120fe5936/build-script-build-script-build

@@ -0,0 +1 @@
+f0a5af4d8a8c7106

myfsio_core/target/release/.fingerprint/generic-array-2462daa120fe5936/build-script-build-script-build.json

@@ -0,0 +1 @@
+{"rustc":8323788817864214825,"features":"[\"more_lengths\"]","declared_features":"[\"more_lengths\", \"serde\", \"zeroize\"]","target":12318548087768197662,"profile":1369601567987815722,"path":13853454403963664247,"deps":[[5398981501050481332,"version_check",false,16419025953046340415]],"local":[{"CheckDepInfo":{"dep_info":"release\\.fingerprint\\generic-array-2462daa120fe5936\\dep-build-script-build-script-build","checksum":false}}],"rustflags":[],"config":2069994364910194474,"compile_kind":0}

myfsio_core/target/release/.fingerprint/generic-array-2462daa120fe5936/invoked.timestamp

@@ -0,0 +1 @@
+This file has an mtime of when this was started.

myfsio_core/target/release/.fingerprint/generic-array-62216349963f3a3c/invoked.timestamp

@@ -0,0 +1 @@
+This file has an mtime of when this was started.

myfsio_core/target/release/.fingerprint/generic-array-62216349963f3a3c/lib-generic_array

@@ -0,0 +1 @@
+5f316276809d5ca0

myfsio_core/target/release/.fingerprint/generic-array-62216349963f3a3c/lib-generic_array.json

@@ -0,0 +1 @@
+{"rustc":8323788817864214825,"features":"[\"more_lengths\"]","declared_features":"[\"more_lengths\", \"serde\", \"zeroize\"]","target":13084005262763373425,"profile":2040997289075261528,"path":12463275850883329568,"deps":[[857979250431893282,"typenum",false,7416411392359930020],[10520923840501062997,"build_script_build",false,16977603856295925732]],"local":[{"CheckDepInfo":{"dep_info":"release\\.fingerprint\\generic-array-62216349963f3a3c\\dep-lib-generic_array","checksum":false}}],"rustflags":[],"config":2069994364910194474,"compile_kind":0}

myfsio_core/target/release/.fingerprint/generic-array-a1f36f10f654fafd/run-build-script-build-script-build

@@ -0,0 +1 @@
+e417d28fc1909ceb

myfsio_core/target/release/.fingerprint/generic-array-a1f36f10f654fafd/run-build-script-build-script-build.json

@@ -0,0 +1 @@
+{"rustc":8323788817864214825,"features":"","declared_features":"","target":0,"profile":0,"path":0,"deps":[[10520923840501062997,"build_script_build",false,464306762232604144]],"local":[{"Precalculated":"0.14.7"}],"rustflags":[],"config":0,"compile_kind":0}

myfsio_core/target/release/.fingerprint/hashbrown-510d641b592c306b/invoked.timestamp

@@ -0,0 +1 @@
+This file has an mtime of when this was started.

myfsio_core/target/release/.fingerprint/hashbrown-510d641b592c306b/lib-hashbrown

@@ -0,0 +1 @@
+aec88a641c5288e3

myfsio_core/target/release/.fingerprint/hashbrown-510d641b592c306b/lib-hashbrown.json

@@ -0,0 +1 @@
+{"rustc":8323788817864214825,"features":"[\"allocator-api2\", \"default\", \"default-hasher\", \"equivalent\", \"inline-more\", \"raw-entry\"]","declared_features":"[\"alloc\", \"allocator-api2\", \"core\", \"default\", \"default-hasher\", \"equivalent\", \"inline-more\", \"nightly\", \"raw-entry\", \"rayon\", \"rustc-dep-of-std\", \"rustc-internal-api\", \"serde\"]","target":13796197676120832388,"profile":2040997289075261528,"path":12448322139402656924,"deps":[[5230392855116717286,"equivalent",false,6042941999404782907],[9150530836556604396,"allocator_api2",false,16398368410642502979],[10842263908529601448,"foldhash",false,10953695263156452023]],"local":[{"CheckDepInfo":{"dep_info":"release\\.fingerprint\\hashbrown-510d641b592c306b\\dep-lib-hashbrown","checksum":false}}],"rustflags":[],"config":2069994364910194474,"compile_kind":0}