nedb-engine 0.1.0__tar.gz

nedb_engine-0.1.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or Derivative
+          Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and do
+          not modify the License. You may add Your own attribution notices
+          within Derivative Works that You distribute, alongside or as an
+          addendum to the NOTICE text from the Work, provided that such
+          additional attribution notices cannot be construed as modifying
+          the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2026 Interchained
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

nedb_engine-0.1.0/PKG-INFO

@@ -0,0 +1,168 @@
+Metadata-Version: 2.4
+Name: nedb-engine
+Version: 0.1.0
+Summary: NEDB — a versioned, self-compressing, time-traveling embedded database (replay-protected, idempotent, relational, searchable).
+Author: Interchained
+License: Apache-2.0
+Project-URL: Homepage, https://github.com/interchained/nedb
+Project-URL: Repository, https://github.com/interchained/nedb
+Keywords: database,embedded,mvcc,time-travel,versioning,compression,dedup,graph,search,redis,git
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Rust
+Classifier: Topic :: Database :: Database Engines/Servers
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file
+
+<div align="center">
+
+# NEDB
+
+**A versioned, self-compressing, time-traveling embedded database.**
+
+Replay-protected · idempotent · relational · filterable · sortable · searchable · provable.
+One Rust core → ships to **PyPI** and **npm** from a single source.
+
+</div>
+
+---
+
+## Why NEDB
+
+Redis is fast because it's in-memory and simple — but relations are hand-rolled, history is gone the moment you overwrite, and every call pays a network hop. NEDB keeps the speed and adds the things real systems actually need:
+
+- **Faster-than-Redis latency where it's honest to claim it** — NEDB runs **embedded, in-process**, so point reads pay *no socket hop*. The networked server (`nedbd`, RESP-compatible) competes on the Rust core's merits.
+- **Replay protection + idempotency in the core, not the app.** Every write carries a strictly-monotonic per-client nonce and an optional idempotency key. Retries are no-ops; stale/out-of-order ops are rejected. This is built into one **hash-chained, append-only log**.
+- **Time-travel.** Read the database *exactly as it existed* at any past sequence — `AS OF seq`. Debugging, audit, MVCC snapshots, and deterministic replay all fall out of the same log.
+- **First-class relations.** Adjacency-list graph edges with O(1) traversal — *and the graph time-travels too*.
+- **Filter / sort / search.** Equality, ordered, and full-text inverted indexes, maintained incrementally.
+- **git-style files with maximum compression.** Content-defined chunking + content-addressed dedup + temperature tiers (fast warm codec, max-ratio cold archival). Every file version has a Merkle root you can **anchor on-chain**.
+
+> **The keystone:** one nonce-enforced append-only log is the substrate for idempotency, replay protection, crash recovery, MVCC, *and* time-travel — simultaneously.
+
+---
+
+## Quickstart (Python reference engine — runs today, zero build)
+
+```bash
+git clone https://github.com/interchained/nedb && cd nedb
+pip install -e .                 # pure-Python reference; no toolchain needed
+python3 examples/demo.py         # see every feature
+python3 tests/test_nedb.py       # 10/10 invariants
+```
+
+```python
+from nedb import NEDB
+
+db = NEDB()
+db.create_index("users", "status", "eq")
+db.create_index("users", "age", "ordered")
+db.create_index("users", "bio", "search")
+
+db.put("users", "alice", {"name": "Alice", "age": 31, "status": "active",
+                          "city": "Austin", "bio": "rust systems hacker"})
+
+# Idempotent, replay-protected write (safe to retry forever):
+db.put("orders", "o1", {"total": 42}, client="checkout", nonce=7, idem="charge-o1")
+
+# NQL — filter + sort
+db.query('FROM users WHERE age >= 25 AND status = "active" ORDER BY age DESC')
+
+# Full-text search
+db.query('FROM users SEARCH "rust"')
+
+# Relations + graph traversal
+db.link("users:alice", "follows", "users:bob")
+db.q("users").where("_id", "=", "alice").traverse("follows").run()
+
+# Time-travel
+s = db.seq
+db.put("users", "alice", {"name": "Alice", "city": "Lisbon", "age": 31, "status": "active"})
+db.get("users", "alice", as_of=s)["city"]      # -> "Austin"
+
+# git-style files with Cascade compression + provable history
+v1 = db.put_file("notes.txt", open("notes.txt","rb").read())
+db.file_root("notes.txt", v1)                  # Merkle root — anchorable on ITC
+```
+
+---
+
+## NQL — the NEDB Query Language
+
+One small grammar; the Rust parser is the single source of truth so Python and Node share identical semantics. A fluent builder compiles to the same plan.
+
+```
+FROM <collection>
+  [ AS OF <seq> ]
+  [ WHERE <field> <op> <value> (AND ...)* ]      op ∈ = != < <= > >=
+  [ SEARCH "<text>" ]
+  [ ORDER BY <field> [ASC|DESC] ]
+  [ TRAVERSE <relation> ]
+  [ LIMIT <n> ]
+```
+
+---
+
+## What's measured (reference engine, pure Python, 2 vCPU)
+
+| Operation | Result |
+|---|---|
+| GET (embedded, in-process) | **~1.2M ops/s** (~800 ns/op) |
+| SET (logged + indexed) | ~77K ops/s |
+| Indexed query latency | ~75 µs |
+| File compression — warm (zlib stand-in) | **39.9×** |
+| File compression — cold (LZMA archival) | **88.9×** |
+| Cross-version dedup | 20 of 22 chunks reused on edit |
+
+The reference engine proves the **architecture**. The Rust core (`rust/`) is the speed target — see `bench/bench_redis.py` for the embedded-vs-Redis harness.
+
+---
+
+## Architecture
+
+```
+            ┌──────────────────────────────────────────────┐
+  put/del → │  OpLog  (append-only · BLAKE3 hash chain ·    │ ← single source of truth
+  link      │          per-client nonce · idempotency keys) │
+            └───────────────┬──────────────────────────────┘
+            deterministic fold │ (state = pure function of the log)
+        ┌──────────────┬───────┴────────┬───────────────────┐
+        ▼              ▼                ▼                   ▼
+   MVCC store     Relations         Indexes            BlobStore (Cascade)
+   (time-travel)  (graph, AS OF)    eq/ordered/search  CDC+dedup+tiers, Merkle roots
+```
+
+One Rust core (`nedb-core`) → **PyO3** wheels (PyPI) and **napi-rs** binaries (npm), plus a future `nedbd` server (RESP-compatible) and a WASM build for browser/edge.
+
+Full design: [`docs/SPEC.md`](docs/SPEC.md).
+
+---
+
+## Repo layout
+
+```
+nedb/            pure-Python reference engine (this is what `pip install` ships today)
+rust/            production core — nedb-core + nedb-py (PyO3) + nedb-node (napi-rs)
+examples/demo.py end-to-end walkthrough
+tests/           invariant tests
+bench/           embedded micro-bench + Redis head-to-head harness
+docs/SPEC.md     architecture specification
+.github/         release CI → PyPI + npm on tag
+```
+
+## Roadmap
+
+- [x] Reference engine: log, MVCC, relations, indexes, NQL, Cascade, Merkle
+- [ ] Rust core parity + criterion benches + `cargo test`
+- [ ] PyO3 wheels + napi-rs binaries published on tag
+- [ ] `nedbd` server: RESP-compatible + native protocol
+- [ ] Similarity-picked deltas + schema-aware columnar transforms
+- [ ] On-chain (ITC) root anchoring; WASM build
+
+## License
+
+Apache-2.0. Part of the [Interchained](https://github.com/interchained) ecosystem.

nedb_engine-0.1.0/README.md

@@ -0,0 +1,148 @@
+<div align="center">
+
+# NEDB
+
+**A versioned, self-compressing, time-traveling embedded database.**
+
+Replay-protected · idempotent · relational · filterable · sortable · searchable · provable.
+One Rust core → ships to **PyPI** and **npm** from a single source.
+
+</div>
+
+---
+
+## Why NEDB
+
+Redis is fast because it's in-memory and simple — but relations are hand-rolled, history is gone the moment you overwrite, and every call pays a network hop. NEDB keeps the speed and adds the things real systems actually need:
+
+- **Faster-than-Redis latency where it's honest to claim it** — NEDB runs **embedded, in-process**, so point reads pay *no socket hop*. The networked server (`nedbd`, RESP-compatible) competes on the Rust core's merits.
+- **Replay protection + idempotency in the core, not the app.** Every write carries a strictly-monotonic per-client nonce and an optional idempotency key. Retries are no-ops; stale/out-of-order ops are rejected. This is built into one **hash-chained, append-only log**.
+- **Time-travel.** Read the database *exactly as it existed* at any past sequence — `AS OF seq`. Debugging, audit, MVCC snapshots, and deterministic replay all fall out of the same log.
+- **First-class relations.** Adjacency-list graph edges with O(1) traversal — *and the graph time-travels too*.
+- **Filter / sort / search.** Equality, ordered, and full-text inverted indexes, maintained incrementally.
+- **git-style files with maximum compression.** Content-defined chunking + content-addressed dedup + temperature tiers (fast warm codec, max-ratio cold archival). Every file version has a Merkle root you can **anchor on-chain**.
+
+> **The keystone:** one nonce-enforced append-only log is the substrate for idempotency, replay protection, crash recovery, MVCC, *and* time-travel — simultaneously.
+
+---
+
+## Quickstart (Python reference engine — runs today, zero build)
+
+```bash
+git clone https://github.com/interchained/nedb && cd nedb
+pip install -e .                 # pure-Python reference; no toolchain needed
+python3 examples/demo.py         # see every feature
+python3 tests/test_nedb.py       # 10/10 invariants
+```
+
+```python
+from nedb import NEDB
+
+db = NEDB()
+db.create_index("users", "status", "eq")
+db.create_index("users", "age", "ordered")
+db.create_index("users", "bio", "search")
+
+db.put("users", "alice", {"name": "Alice", "age": 31, "status": "active",
+                          "city": "Austin", "bio": "rust systems hacker"})
+
+# Idempotent, replay-protected write (safe to retry forever):
+db.put("orders", "o1", {"total": 42}, client="checkout", nonce=7, idem="charge-o1")
+
+# NQL — filter + sort
+db.query('FROM users WHERE age >= 25 AND status = "active" ORDER BY age DESC')
+
+# Full-text search
+db.query('FROM users SEARCH "rust"')
+
+# Relations + graph traversal
+db.link("users:alice", "follows", "users:bob")
+db.q("users").where("_id", "=", "alice").traverse("follows").run()
+
+# Time-travel
+s = db.seq
+db.put("users", "alice", {"name": "Alice", "city": "Lisbon", "age": 31, "status": "active"})
+db.get("users", "alice", as_of=s)["city"]      # -> "Austin"
+
+# git-style files with Cascade compression + provable history
+v1 = db.put_file("notes.txt", open("notes.txt","rb").read())
+db.file_root("notes.txt", v1)                  # Merkle root — anchorable on ITC
+```
+
+---
+
+## NQL — the NEDB Query Language
+
+One small grammar; the Rust parser is the single source of truth so Python and Node share identical semantics. A fluent builder compiles to the same plan.
+
+```
+FROM <collection>
+  [ AS OF <seq> ]
+  [ WHERE <field> <op> <value> (AND ...)* ]      op ∈ = != < <= > >=
+  [ SEARCH "<text>" ]
+  [ ORDER BY <field> [ASC|DESC] ]
+  [ TRAVERSE <relation> ]
+  [ LIMIT <n> ]
+```
+
+---
+
+## What's measured (reference engine, pure Python, 2 vCPU)
+
+| Operation | Result |
+|---|---|
+| GET (embedded, in-process) | **~1.2M ops/s** (~800 ns/op) |
+| SET (logged + indexed) | ~77K ops/s |
+| Indexed query latency | ~75 µs |
+| File compression — warm (zlib stand-in) | **39.9×** |
+| File compression — cold (LZMA archival) | **88.9×** |
+| Cross-version dedup | 20 of 22 chunks reused on edit |
+
+The reference engine proves the **architecture**. The Rust core (`rust/`) is the speed target — see `bench/bench_redis.py` for the embedded-vs-Redis harness.
+
+---
+
+## Architecture
+
+```
+            ┌──────────────────────────────────────────────┐
+  put/del → │  OpLog  (append-only · BLAKE3 hash chain ·    │ ← single source of truth
+  link      │          per-client nonce · idempotency keys) │
+            └───────────────┬──────────────────────────────┘
+            deterministic fold │ (state = pure function of the log)
+        ┌──────────────┬───────┴────────┬───────────────────┐
+        ▼              ▼                ▼                   ▼
+   MVCC store     Relations         Indexes            BlobStore (Cascade)
+   (time-travel)  (graph, AS OF)    eq/ordered/search  CDC+dedup+tiers, Merkle roots
+```
+
+One Rust core (`nedb-core`) → **PyO3** wheels (PyPI) and **napi-rs** binaries (npm), plus a future `nedbd` server (RESP-compatible) and a WASM build for browser/edge.
+
+Full design: [`docs/SPEC.md`](docs/SPEC.md).
+
+---
+
+## Repo layout
+
+```
+nedb/            pure-Python reference engine (this is what `pip install` ships today)
+rust/            production core — nedb-core + nedb-py (PyO3) + nedb-node (napi-rs)
+examples/demo.py end-to-end walkthrough
+tests/           invariant tests
+bench/           embedded micro-bench + Redis head-to-head harness
+docs/SPEC.md     architecture specification
+.github/         release CI → PyPI + npm on tag
+```
+
+## Roadmap
+
+- [x] Reference engine: log, MVCC, relations, indexes, NQL, Cascade, Merkle
+- [ ] Rust core parity + criterion benches + `cargo test`
+- [ ] PyO3 wheels + napi-rs binaries published on tag
+- [ ] `nedbd` server: RESP-compatible + native protocol
+- [ ] Similarity-picked deltas + schema-aware columnar transforms
+- [ ] On-chain (ITC) root anchoring; WASM build
+
+## License
+
+Apache-2.0. Part of the [Interchained](https://github.com/interchained) ecosystem.

nedb_engine-0.1.0/nedb/__init__.py

@@ -0,0 +1,23 @@
+"""
+NEDB — a versioned, self-compressing, time-traveling embedded database.
+
+  * Replay-protected & idempotent: every write carries a monotonic nonce and an
+    optional idempotency key, enforced by a hash-chained append-only log.
+  * Time-travel: read the database AS OF any past sequence number.
+  * Relational: first-class, time-travel-aware relations with O(1) traversal.
+  * Filterable / sortable / searchable: equality, ordered, and full-text indexes.
+  * Queryable: NQL text queries and a fluent builder that share one plan.
+  * git-style files with Cascade compression: content-defined chunking + dedup +
+    temperature tiers, with a Merkle root per version anchorable on-chain.
+
+This pure-Python package is the reference implementation. The production speed core
+is Rust (see ../rust), exposed to PyPI via PyO3 and to npm via napi-rs.
+"""
+from __future__ import annotations
+
+from .engine import NEDB
+from .log import Op, OpLog, ReplayError
+from .query import Query, parse_nql
+
+__all__ = ["NEDB", "OpLog", "Op", "ReplayError", "Query", "parse_nql"]
+__version__ = "0.1.0"

nedb_engine-0.1.0/nedb/cascade.py

@@ -0,0 +1,130 @@
+"""
+nedb.cascade — the Cascade compression pipeline + content-addressed blob store.
+
+This is what makes NEDB double as a git-style file manager with maximum compression
+WITHOUT inventing a new entropy coder. The novelty is the pipeline composition:
+
+  1. Content-defined chunking (Gear rolling hash) — boundaries follow content, so a
+     one-byte insert only changes the chunk(s) around it, not everything after it.
+  2. Content-addressed dedup (BLAKE) — identical chunks across all files and all
+     versions are stored exactly once.
+  3. Temperature tiers — warm data uses a fast codec (zstd in prod; zlib in this
+     reference), cold/archival history uses a maximum-ratio codec (LZMA).
+
+The production pipeline adds similarity-picked binary deltas (zstd --patch-from) and
+schema-aware columnar transforms before the entropy stage; both are documented in
+docs/SPEC.md and stubbed for the reference engine.
+"""
+from __future__ import annotations
+
+import hashlib
+import lzma
+import random
+import zlib
+from typing import Dict, List
+
+from .merkle import merkle_root
+
+# --- Gear-hash content-defined chunking -------------------------------------
+_MASK = (1 << 13) - 1            # ~8 KiB average chunk
+_MIN = 2 * 1024
+_MAX = 64 * 1024
+_M64 = 0xFFFFFFFFFFFFFFFF
+_GEAR = [random.Random(0x12345678 + i).getrandbits(64) for i in range(256)]
+
+
+def chunk(data: bytes) -> List[bytes]:
+    chunks: List[bytes] = []
+    n = len(data)
+    i = 0
+    while i < n:
+        limit = min(i + _MAX, n)
+        h = 0
+        pos = i
+        cut = limit
+        while pos < limit:
+            h = ((h << 1) + _GEAR[data[pos]]) & _M64
+            pos += 1
+            if (pos - i) >= _MIN and (h & _MASK) == 0:
+                cut = pos
+                break
+        chunks.append(data[i:cut])
+        i = cut
+    return chunks
+
+
+def _blake(b: bytes) -> str:
+    return hashlib.blake2b(b, digest_size=32).hexdigest()
+
+
+# --- temperature tiers ------------------------------------------------------
+def warm_compress(b: bytes) -> bytes:    # zstd stand-in in the reference
+    return zlib.compress(b, 6)
+
+
+def warm_decompress(b: bytes) -> bytes:
+    return zlib.decompress(b)
+
+
+def cold_compress(b: bytes) -> bytes:    # real LZMA — the maximum-ratio archival tier
+    return lzma.compress(b, preset=9 | lzma.PRESET_EXTREME)
+
+
+def cold_decompress(b: bytes) -> bytes:
+    return lzma.decompress(b)
+
+
+class BlobStore:
+    """Content-addressed, deduplicated, tiered blob store with versioned files."""
+
+    def __init__(self, tier: str = "warm") -> None:
+        self.tier = tier
+        self.chunks: Dict[str, bytes] = {}                      # hash -> compressed bytes
+        self.files: Dict[str, Dict[str, list]] = {}            # name -> {versions, roots}
+        self.logical_bytes = 0
+        self.dedup_hits = 0
+
+    def _compress(self, b: bytes) -> bytes:
+        return cold_compress(b) if self.tier == "cold" else warm_compress(b)
+
+    def _decompress(self, b: bytes) -> bytes:
+        return cold_decompress(b) if self.tier == "cold" else warm_decompress(b)
+
+    def put_file(self, name: str, data: bytes) -> int:
+        recipe: List[str] = []
+        for c in chunk(data):
+            hh = _blake(c)
+            recipe.append(hh)
+            if hh in self.chunks:
+                self.dedup_hits += 1
+            else:
+                self.chunks[hh] = self._compress(c)
+        self.logical_bytes += len(data)
+        f = self.files.setdefault(name, {"versions": [], "roots": []})
+        f["versions"].append(recipe)
+        f["roots"].append(merkle_root(recipe))
+        return len(f["versions"]) - 1
+
+    def get_file(self, name: str, version: int = -1) -> bytes:
+        recipe = self.files[name]["versions"][version]
+        out = bytearray()
+        for hh in recipe:
+            out += self._decompress(self.chunks[hh])
+        return bytes(out)
+
+    def root(self, name: str, version: int = -1) -> str:
+        return self.files[name]["roots"][version]
+
+    def stored_bytes(self) -> int:
+        return sum(len(v) for v in self.chunks.values())
+
+    def stats(self) -> dict:
+        stored = self.stored_bytes()
+        return {
+            "tier": self.tier,
+            "unique_chunks": len(self.chunks),
+            "dedup_hits": self.dedup_hits,
+            "logical_bytes": self.logical_bytes,
+            "stored_bytes": stored,
+            "ratio": round(self.logical_bytes / stored, 2) if stored else 0.0,
+        }