logreducer 3.4.0__tar.gz

logreducer-3.4.0/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 HYPERI PTY LIMITED
+
+   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.

logreducer-3.4.0/NOTICE

@@ -0,0 +1,53 @@
+logreducer
+Copyright 2026 HYPERI PTY LIMITED
+
+This product includes software developed at HYPERI PTY LIMITED
+(https://hyperi.io/).
+
+Licensed under the Apache License, Version 2.0 (see LICENSE).
+
+-------------------------------------------------------------------------------
+Third-party data
+-------------------------------------------------------------------------------
+
+The sample log files under data/samples/ are drawn from LogHub, a collection of
+system log datasets for research:
+
+  Jieming Zhu, Shilin He, Pinjia He, Jinyang Liu, Michael R. Lyu.
+  "Loghub: A Large Collection of System Log Datasets for AI-driven Log
+  Analytics." ISSRE 2023.
+  https://github.com/logpai/loghub
+
+Some LogHub datasets originate from public sources, including the USENIX CFDR
+computer failure data repository (BGL and Thunderbird traces, Sandia National
+Laboratories). The datasets are redistributed here unmodified for demonstration
+and testing. See data/samples/README.md for the per-file mapping.
+
+-------------------------------------------------------------------------------
+Integration-test corpora (tests/testdata/)
+-------------------------------------------------------------------------------
+
+The gzipped log corpora under tests/testdata/ are truncated slices of REAL
+public datasets, PII-cleansed (IPs/IPv6/emails/MAC addresses and specific
+hostnames deterministically rewritten to synthetic values; structure and
+repetition preserved). Each is redistributed under its own licence. See
+tests/testdata/manifest.json for the per-dataset source URL, licence, and
+cleansing status. Sources and licences:
+
+  LogHub (loghub_*): Zhu et al., "Loghub", ISSRE 2023.
+    https://github.com/logpai/loghub - Zenodo 10.5281/zenodo.8196385,
+    CC-BY-4.0. BGL/Thunderbird upstream: Oliner and Stearley, DSN 2007.
+
+  The Internet Traffic Archive (ita_*): NASA-HTTP and Calgary-HTTP web-server
+    access logs. https://ita.ee.lbl.gov/ - per-trace "may be freely
+    redistributed". Use is limited to general traffic-pattern analysis.
+
+  Security Repo (secrepo_*): Security Repo by Mike Sconzo, https://www.secrepo.com/
+    - Creative Commons Attribution 4.0 International (CC-BY-4.0).
+
+  elastic/examples (elastic_*): nginx JSON logs from https://github.com/elastic/examples
+    - Apache License, Version 2.0.
+
+These corpora are used only for testing and are not part of the distributed
+package. The build script tests/testdata/build.py records how each was fetched
+and cleansed.

logreducer-3.4.0/PKG-INFO

@@ -0,0 +1,387 @@
+Metadata-Version: 2.4
+Name: logreducer
+Version: 3.4.0
+Summary: Reduce GB-scale logs to a representative sample - streaming Python library and CLI with pattern mining and anomaly detection
+Keywords: log,logging,reduction,analysis,pattern-extraction,memory-efficient,streaming,anomaly-detection
+Author: HyperI Team
+Author-email: HyperI Team <dev@hyperi.io>
+License-Expression: Apache-2.0
+License-File: LICENSE
+License-File: NOTICE
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: System Administrators
+Classifier: Topic :: System :: Logging
+Classifier: Topic :: System :: Systems Administration
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Operating System :: OS Independent
+Requires-Dist: drain3>=0.9.0
+Requires-Dist: psutil>=7.2.0
+Requires-Dist: loguru>=0.7.3
+Requires-Dist: numpy>=2.0.0
+Requires-Dist: scikit-learn>=1.5.0
+Requires-Dist: typer>=0.25.0
+Requires-Dist: clickhouse-connect>=1.0 ; extra == 'clickhouse'
+Requires-Dist: xxhash>=3.0.0 ; extra == 'enhanced'
+Requires-Dist: datasketch>=1.5.0 ; extra == 'enhanced'
+Requires-Dist: confluent-kafka>=2.14.0 ; extra == 'kafka'
+Requires-Dist: sqlalchemy>=2.0.30 ; extra == 'sql'
+Maintainer: HyperI Team
+Maintainer-email: HyperI Team <dev@hyperi.io>
+Requires-Python: >=3.12
+Project-URL: Homepage, https://github.com/hyperi-io/logreducer
+Project-URL: Documentation, https://github.com/hyperi-io/logreducer#readme
+Project-URL: Repository, https://github.com/hyperi-io/logreducer
+Project-URL: Bug Reports, https://github.com/hyperi-io/logreducer/issues
+Project-URL: Changelog, https://github.com/hyperi-io/logreducer/blob/main/CHANGELOG.md
+Provides-Extra: clickhouse
+Provides-Extra: enhanced
+Provides-Extra: kafka
+Provides-Extra: sql
+Description-Content-Type: text/markdown
+
+# LogReducer
+
+[![PyPI](https://img.shields.io/pypi/v/logreducer?logo=pypi)](https://pypi.org/project/logreducer/)
+[![Python Version](https://img.shields.io/badge/python-3.12%2B-blue)](https://www.python.org/)
+[![License](https://img.shields.io/badge/license-Apache--2.0-green)](LICENSE)
+
+Reduce gigabytes of logs to a small, representative sample - keeping the patterns and anomalies that matter and dropping the repetition that does not. Memory-safe streaming, temporal awareness, and ML-based anomaly detection.
+
+**LogReducer is two tools in one package:**
+
+- **A CLI you can use right now.** `logreducer app.log` reduces a file - or a SQL, ClickHouse, or Kafka source - straight from the shell. No code to write.
+- **A library with an IO-agnostic core.** The engine has zero IO dependencies and reduces any re-iterable stream of `str` lines (a `Source`). Embed it in your own pipeline; the engine never manages the connection.
+
+## Features
+
+- **Memory-safe streaming**: near-constant memory on multi-GB inputs; low, container-friendly defaults
+- **Four reduction modes**: pattern (Drain3), anomaly (Isolation Forest), temporal, and hybrid
+- **IO-agnostic core**: reduce a file, a `list[str]`, a database cursor, or a Kafka stream through one `Source` seam
+- **Optional adapters**: SQL (SQLAlchemy), ClickHouse (clickhouse-connect), Kafka (confluent-kafka) - install only what you use
+- **Engine-side sampling**: seeded, dialect-aware SQL sampling and native `TABLESAMPLE` for cheap reduction of huge tables
+- **Embeddable**: injection seams for a host application's own config cascade and logging standard
+
+## Installation
+
+### As a CLI tool
+
+Install it as an isolated tool so its dependencies never clash with your other Python projects (needs Python 3.12+):
+
+```bash
+uv tool install logreducer     # recommended (uv)
+# or
+pipx install logreducer        # recommended (pipx)
+```
+
+To bundle an adapter extra with the tool: `uv tool install "logreducer[clickhouse]"`.
+
+### As a library
+
+```bash
+uv add logreducer
+# or
+pip install logreducer
+```
+
+Optional extras (install only what you need):
+
+```bash
+uv add "logreducer[enhanced]"    # fuzzy dedup, faster hashing
+uv add "logreducer[sql]"         # SQLSource (SQLAlchemy) - bring your own DBAPI driver
+uv add "logreducer[clickhouse]"  # ClickHouseSource (clickhouse-connect)
+uv add "logreducer[kafka]"       # KafkaSource / KafkaSink (confluent-kafka)
+```
+
+> The `logreducer` command works under any install method (project venv, `pip install --user`, pipx/uv tool, system-wide). `pipx` / `uv tool` is the recommendation for end users - isolation without a manual venv.
+
+## Quick Start
+
+### Command line
+
+```bash
+# Reduce a file to stdout, or to a file with -o
+logreducer app.log
+logreducer app.log -o reduced.log -l enhanced -m hybrid
+
+# JSON output, with run stats on stderr
+logreducer app.log --format json -o result.json --stats
+
+# Cap memory, estimate first
+logreducer huge.log --max-memory 2 --estimate
+```
+
+### Library
+
+```python
+from logreducer import LogReducer
+
+reducer = LogReducer(level="standard")
+
+# Reduce a file (writes reduced.log + reduced.meta.json)
+reduced = reducer.process_file("app.log", output_file="reduced.log")
+print(f"{len(reduced)} representative lines")
+
+# Reduce any re-iterable of lines - no file needed
+lines = ["ERROR timeout upstream=payments", "INFO ok", "ERROR timeout upstream=payments"]
+reduced = reducer.reduce(lines)
+```
+
+`reduce()` returns the reduced lines in memory. Pass `return_metadata=True` for a dict of `{"lines", "stats", "config"}`.
+
+## How it works
+
+Everything streams: lines flow through dedup and template mining as one generator pipeline, so the unique-line set is never materialised. Memory stays near-constant regardless of input size.
+
+```mermaid
+flowchart LR
+    subgraph sources ["Source (re-iterable str lines)"]
+        direction TB
+        F[file]
+        L["list[str]"]
+        Q[SQL / ClickHouse query]
+        K[Kafka topic]
+    end
+    sources --> D["exact dedup<br/>(bounded hash cache)"]
+    D --> FZ["fuzzy dedup<br/>(MinHash LSH, enhanced+)"]
+    FZ --> DR["Drain3 template mining<br/>(LRU-bounded clusters)"]
+    DR --> P["rank patterns<br/>(CRITICAL > ERROR > WARN)"]
+    P --> O["top patterns<br/>x examples"]
+    D -. "anomaly / hybrid" .-> A["TF-IDF + Isolation Forest<br/>(batch, capped by anomaly_max_rows)"]
+    A --> O
+    O --> out["stdout / file + meta.json / Sink"]
+```
+
+The anomaly branch is the one part that cannot stream (Isolation Forest is batch ML); cap its input with `anomaly_max_rows` when reducing very high-cardinality sources.
+
+## Choosing a mode and level
+
+```mermaid
+flowchart TD
+    Q{"What matters<br/>in the output?"} -->|"recurring structure,<br/>smallest output"| P["mode=pattern<br/>(default, fastest)"]
+    Q -->|"rare or unusual<br/>events"| A["mode=anomaly"]
+    Q -->|"bursts and<br/>time windows"| T["mode=temporal"]
+    Q -->|"unsure /<br/>maximum coverage"| H["mode=hybrid"]
+    A -.-> N1["needs >= 10 unique lines,<br/>else everything passes through"]
+    P -.-> N2["fuzzy dedup joins in<br/>at enhanced/maximum"]
+```
+
+| Mode | Description | Best for |
+|------|-------------|----------|
+| `pattern` | Drain3 template mining | Structured / application logs (fastest) |
+| `anomaly` | Isolation Forest outlier detection | Security and error logs |
+| `temporal` | Time-aware pattern analysis | Time-series and monitoring logs |
+| `hybrid` | Pattern + anomaly combined | Maximum coverage |
+
+| Level | Speed | Memory cap | Features |
+|-------|-------|-----------|----------|
+| `standard` | Fast | 0.5 GB | Deduplication + pattern extraction |
+| `enhanced` | Moderate | 1 GB | + fuzzy dedup |
+| `maximum` | Thorough | 2 GB | + wider pattern budget |
+
+## Reducing from a database or Kafka
+
+The CLI dispatches on the `--dsn` scheme; a library caller constructs the source directly.
+
+```bash
+# PostgreSQL / MySQL / SQLite via SQLAlchemy (needs logreducer[sql] + a driver)
+logreducer --dsn postgresql://user@host/db --query "SELECT message FROM logs"
+
+# ClickHouse via the native driver (needs logreducer[clickhouse])
+logreducer --dsn clickhouse://user@host:8123/db --query "SELECT message FROM logs"
+
+# Kafka topic (needs logreducer[kafka])
+logreducer --dsn kafka://broker:9092 --topic app-logs --group logreducer
+```
+
+```python
+from logreducer import LogReducer
+from logreducer.clickhouse import ClickHouseSource
+
+reducer = LogReducer(level="enhanced", mode="hybrid")
+with ClickHouseSource("clickhouse://user@host:8123/db", "SELECT message FROM logs") as source:
+    reduced = reducer.reduce(source)
+```
+
+The query selects the log line as its **first column**. Sources are re-iterable (the engine makes multiple passes), so a database source re-runs its query per pass and a Kafka source re-reads from the earliest offset without committing.
+
+## Sampling large sources
+
+For a table too large to scan in full, sample a fraction of rows. SQL sampling is deterministic when you pass a seed (so the reducer's multi-pass modes see a stable input); ClickHouse uses its native `SAMPLE` clause.
+
+```python
+from logreducer.sql import SQLSource
+
+# Wrap any query in a seeded random predicate (PostgreSQL/MySQL)
+source = SQLSource("postgresql://user@host/db", "SELECT msg FROM logs", sample=0.01, sample_seed=42)
+
+# Or sample a TABLE with the engine's native sampler - PostgreSQL
+# TABLESAMPLE SYSTEM is page-level and genuinely sub-linear:
+source = SQLSource.from_table("postgresql://user@host/db", "logs", "msg", sample=0.01, sample_seed=42)
+```
+
+```bash
+logreducer --dsn postgresql://user@host/db --query "SELECT msg FROM logs" --sample 0.01 --sample-seed 42
+```
+
+Notes: SQLite has no seedable RNG, so a seeded sample raises `SamplingNotSupported` (unseeded, best-effort sampling still works). ClickHouse `SAMPLE` needs the table to declare a `SAMPLE BY` key. For an arbitrary complex query, put the sampling clause in your own SQL instead.
+
+## Collecting a target number of lines
+
+When you want *about N* representative lines rather than "reduce everything", `reduce_to_target` pulls fresh random batches and reduces each, accumulating distinct representatives until a stop condition fires. Peak memory is bounded to roughly one batch plus the accumulator.
+
+```mermaid
+flowchart TD
+    PULL["pull fresh random batch<br/>(sample_batch in-engine,<br/>else client-side reservoir)"] --> E{empty?}
+    E -->|yes| SE([stop: exhausted])
+    E -->|no| SIZE["resize next batch from<br/>observed avg row bytes"]
+    SIZE --> RED["reduce the batch"]
+    RED --> ACC["add new distinct<br/>representatives"]
+    ACC --> TGT{"target<br/>reached?"}
+    TGT -->|yes| ST([stop: target])
+    TGT -->|no| PLAT{"no new lines for<br/>plateau_rounds?"}
+    PLAT -->|yes| SP([stop: plateau])
+    PLAT -->|no| MEM{"memory<br/>watchdog"}
+    MEM -->|"soft: shrink batch"| FET
+    MEM -->|"hard limit"| SM([stop: memory])
+    FET{"max_fetches<br/>hit?"} -->|yes| SF([stop: max_fetches])
+    FET -->|no| PULL
+```
+
+```python
+from logreducer import LogReducer, reduce_to_target
+from logreducer.sql import SQLSource
+
+reducer = LogReducer(level="enhanced", mode="hybrid")
+source = SQLSource("postgresql://user@host/db", "SELECT msg FROM logs")
+outcome = reduce_to_target(source, reducer, target_rows=5000, max_batch_memory_gb=1.0)
+print(outcome["stats"]["stop_reason"])   # target / exhausted / max_fetches / plateau / memory
+lines = outcome["lines"]
+```
+
+```bash
+logreducer --dsn postgresql://user@host/db --query "SELECT msg FROM logs" \
+    --target-rows 5000 --max-fetches 50 --max-batch-memory 1.0
+```
+
+## Bounding memory
+
+The core streams, so pattern/temporal modes run in near-constant memory. The knobs:
+
+- `max_memory_gb` - the overall cap (also sizes file read strategy and the watchdog). Presets: 0.5 / 1 / 2 GB by level; values above 70% of available RAM are clamped with a warning.
+- `max_clusters` - LRU-bound the Drain3 template store (unbounded by default).
+- `anomaly_max_rows` - reservoir-cap the rows fed to anomaly detection (off by default; trades anomaly recall for a bounded matrix).
+
+```python
+reducer = LogReducer(level="enhanced", mode="hybrid", max_clusters=50_000, anomaly_max_rows=200_000)
+```
+
+## Sources and sinks
+
+The engine is built around two tiny structural protocols - that is the whole integration surface:
+
+```mermaid
+flowchart LR
+    subgraph inputs ["Sources"]
+        direction TB
+        FS["FileSource"]
+        SS["SQLSource  [sql]"]
+        CS["ClickHouseSource  [clickhouse]"]
+        KS["KafkaSource  [kafka]"]
+        MY["your own re-iterable"]
+    end
+    subgraph core ["LogReducer core"]
+        C["zero IO dependencies<br/>Source in -> list[str] out"]
+    end
+    subgraph outputs ["Sinks"]
+        direction TB
+        FK["FileSink"]
+        KK["KafkaSink  [kafka]"]
+        MS["your own write()"]
+    end
+    inputs -->|"__iter__() -> str<br/>fresh iterator per pass"| core
+    core -->|"write(lines) -> int"| outputs
+```
+
+An application can hand the reducer its own IO - anything that yields `str` and can be iterated more than once is a `Source`:
+
+```python
+class MySource:
+    def __iter__(self):
+        yield from open_my_stream()  # must return a FRESH iterator each call
+
+reducer.reduce(MySource())
+```
+
+Output works the same way through a `Sink` (`write(lines) -> int`):
+
+```python
+from logreducer import LogReducer, FileSink
+
+reducer.reduce(source, sink=FileSink("reduced.jsonl", output_format="jsonl"))
+```
+
+## Embedding in a host application
+
+A host app that owns its own config cascade and logging standard drives logreducer with three seams - no logreducer-side knowledge of the host required:
+
+```python
+import logreducer
+
+# 1. Config: build it from YOUR cascade and inject it (kwargs still win on top)...
+cfg = logreducer.BigDialConfig(max_memory_gb=0.5, max_patterns=800)
+reducer = logreducer.LogReducer(mode="hybrid", config=cfg)
+
+# ...or let logreducer read your env cascade directly: prefixed beats bare.
+cfg = logreducer.BigDialConfig.from_env("MYAPP", "LOGREDUCER")   # MYAPP_MAX_MEMORY_GB wins
+
+# 2. Logging: your app owns the loguru sinks; logreducer registers nothing and
+#    its records flow through YOUR handlers, formatted by YOUR standard.
+logreducer.setup_logging(enable=True, own_sinks=False)
+```
+
+## Configuration
+
+Override any config field as a keyword argument (unknown names raise - typos never silently no-op):
+
+```python
+reducer = LogReducer(
+    level="enhanced",
+    mode="hybrid",
+    max_memory_gb=1.0,          # memory ceiling (clamped to 70% of available RAM)
+    dedup_cache_size=100000,    # bounded dedup cache
+    drain_similarity=0.4,       # pattern similarity threshold
+    fuzzy_threshold=0.8,        # fuzzy-dedup threshold (enhanced/maximum)
+    anomaly_contamination=0.1,  # expected anomaly fraction
+    temporal_window_minutes=60, # grouping window for temporal mode
+    max_patterns=2000,          # cap on extracted patterns
+)
+```
+
+## Logging
+
+Logging is off by default. Enable it and pick a format via env vars:
+
+```bash
+LOG_LEVEL=DEBUG LOG_FORMAT=json logreducer app.log --log
+```
+
+`LOG_FORMAT=json` emits one JSON object per line for log aggregators; the default is human-readable (coloured in a terminal, plain in CI/containers). Embedding? See `own_sinks=False` above.
+
+## Development
+
+```bash
+git clone https://github.com/hyperi-io/logreducer.git
+cd logreducer
+uv sync --all-extras
+```
+
+See [CONTRIBUTING.md](CONTRIBUTING.md) for the toolchain, test layout (including the real-log corpora under `tests/testdata/`) and how the integration tests find their services.
+
+## License
+
+[Apache-2.0](LICENSE). Third-party attributions are recorded in [NOTICE](NOTICE).
+
+Copyright 2026 HYPERI PTY LIMITED.