Metadata-Version: 2.4
Name: contextpress
Version: 0.1.0
Summary: Deterministic context compression for LLM chat, RAG, and agent pipelines
Project-URL: Homepage, https://github.com/Taha-azizi/contextpress
Project-URL: Documentation, https://github.com/Taha-azizi/contextpress#readme
Project-URL: Issues, https://github.com/Taha-azizi/contextpress/issues
Project-URL: Changelog, https://github.com/Taha-azizi/contextpress/blob/main/CHANGELOG.md
License:                                  Apache License
                                   Version 2.0, January 2004
                                http://www.apache.org/licenses/
        
           TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
        
           1. Definitions.
        
              "License" shall mean the terms and conditions for use, reproduction,
              and distribution as defined by Sections 1 through 9 of this document.
        
              "Licensor" shall mean the copyright owner or entity authorized by
              the copyright owner that is granting the License.
        
              "Legal Entity" shall mean the union of the acting entity and all
              other entities that control, are controlled by, or are under common
              control with that entity. For the purposes of this definition,
              "control" means (i) the power, direct or indirect, to cause the
              direction or management of such entity, whether by contract or
              otherwise, or (ii) ownership of fifty percent (50%) or more of the
              outstanding shares, or (iii) beneficial ownership of such entity.
        
              "You" (or "Your") shall mean an individual or Legal Entity
              exercising permissions granted by this License.
        
              "Source" form shall mean the preferred form for making modifications,
              including but not limited to software source code, documentation
              source, and configuration files.
        
              "Object" form shall mean any form resulting from mechanical
              transformation or translation of a Source form, including but
              not limited to compiled object code, generated documentation,
              and conversions to other media types.
        
              "Work" shall mean the work of authorship, whether in Source or
              Object form, made available under the License, as indicated by a
              copyright notice that is included in or attached to the work
              (an example is provided in the Appendix below).
        
              "Derivative Works" shall mean any work, whether in Source or Object
              form, that is based on (or derived from) the Work and for which the
              editorial revisions, annotations, elaborations, or other modifications
              represent, as a whole, an original work of authorship. For the purposes
              of this License, Derivative Works shall not include works that remain
              separable from, or merely link (or bind by name) to the interfaces of,
              the Work and Derivative Works thereof.
        
              "Contribution" shall mean any work of authorship, including
              the original version of the Work and any modifications or additions
              to that Work or Derivative Works thereof, that is intentionally
              submitted to Licensor for inclusion in the Work by the copyright owner
              or by an individual or Legal Entity authorized to submit on behalf of
              the copyright owner. For the purposes of this definition, "submitted"
              means any form of electronic, verbal, or written communication sent
              to the Licensor or its representatives, including but not limited to
              communication on electronic mailing lists, source code control systems,
              and issue tracking systems that are managed by, or on behalf of, the
              Licensor for the purpose of discussing and improving the Work, but
              excluding communication that is conspicuously marked or otherwise
              designated in writing by the copyright owner as "Not a Contribution."
        
              "Contributor" shall mean Licensor and any individual or Legal Entity
              on behalf of whom a Contribution has been received by Licensor and
              subsequently incorporated within the Work.
        
           2. Grant of Copyright License. Subject to the terms and conditions of
              this License, each Contributor hereby grants to You a perpetual,
              worldwide, non-exclusive, no-charge, royalty-free, irrevocable
              copyright license to reproduce, prepare Derivative Works of,
              publicly display, publicly perform, sublicense, and distribute the
              Work and such Derivative Works in Source or Object form.
        
           3. Grant of Patent License. Subject to the terms and conditions of
              this License, each Contributor hereby grants to You a perpetual,
              worldwide, non-exclusive, no-charge, royalty-free, irrevocable
              (except as stated in this section) patent license to make, have made,
              use, offer to sell, sell, import, and otherwise transfer the Work,
              where such license applies only to those patent claims licensable
              by such Contributor that are necessarily infringed by their
              Contribution(s) alone or by combination of their Contribution(s)
              with the Work to which such Contribution(s) was submitted. If You
              institute patent litigation against any entity (including a
              cross-claim or counterclaim in a lawsuit) alleging that the Work
              or a Contribution incorporated within the Work constitutes direct
              or contributory patent infringement, then any patent licenses
              granted to You under this License for that Work shall terminate
              as of the date such litigation is filed.
        
           4. Redistribution. You may reproduce and distribute copies of the
              Work or Derivative Works thereof in any medium, with or without
              modifications, and in Source or Object form, provided that You
              meet the following conditions:
        
              (a) You must give any other recipients of the Work or
                  Derivative Works a copy of this License; and
        
              (b) You must cause any modified files to carry prominent notices
                  stating that You changed the files; and
        
              (c) You must retain, in the Source form of any Derivative Works
                  that You distribute, all copyright, patent, trademark, and
                  attribution notices from the Source form of the Work,
                  excluding those notices that do not pertain to any part of
                  the Derivative Works; and
        
              (d) If the Work includes a "NOTICE" text file as part of its
                  distribution, then any Derivative Works that You distribute must
                  include a readable copy of the attribution notices contained
                  within such NOTICE file, excluding those notices that do not
                  pertain to any part of the Derivative Works, in at least one
                  of the following places: within a NOTICE text file distributed
                  as part of the Derivative Works; within the Source form or
                  documentation, if provided along with the Derivative Works; or,
                  within a display generated by the Derivative Works, if and
                  wherever such third-party notices normally appear. The contents
                  of the NOTICE file are for informational purposes only and
                  do not modify the License. You may add Your own attribution
                  notices within Derivative Works that You distribute, alongside
                  or as an addendum to the NOTICE text from the Work, provided
                  that such additional attribution notices cannot be construed
                  as modifying the License.
        
              You may add Your own copyright statement to Your modifications and
              may provide additional or different license terms and conditions
              for use, reproduction, or distribution of Your modifications, or
              for any such Derivative Works as a whole, provided Your use,
              reproduction, and distribution of the Work otherwise complies with
              the conditions stated in this License.
        
           5. Submission of Contributions. Unless You explicitly state otherwise,
              any Contribution intentionally submitted for inclusion in the Work
              by You to the Licensor shall be under the terms and conditions of
              this License, without any additional terms or conditions.
              Notwithstanding the above, nothing herein shall supersede or modify
              the terms of any separate license agreement you may have executed
              with Licensor regarding such Contributions.
        
           6. Trademarks. This License does not grant permission to use the trade
              names, trademarks, service marks, or product names of the Licensor,
              except as required for 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 Support. 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 support.
        
           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 Taha Azizi
        
           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.
License-File: LICENSE
License-File: NOTICE
Keywords: ai,chatbot,compression,context,context-window,conversation,llm,nlp,rag,token-budget
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Topic :: Text Processing :: Linguistic
Classifier: Typing :: Typed
Requires-Python: >=3.10
Requires-Dist: nltk>=3.8
Requires-Dist: scikit-learn>=1.3
Requires-Dist: sumy>=0.11
Requires-Dist: tiktoken>=0.6
Provides-Extra: dev
Requires-Dist: black; extra == 'dev'
Requires-Dist: pytest-cov>=4.0; extra == 'dev'
Requires-Dist: pytest>=7.0; extra == 'dev'
Requires-Dist: ruff; extra == 'dev'
Provides-Extra: llm
Requires-Dist: anthropic>=0.18; extra == 'llm'
Requires-Dist: ollama>=0.3.0; extra == 'llm'
Requires-Dist: openai>=1.0; extra == 'llm'
Description-Content-Type: text/markdown

# contextpress

Deterministic context compression for LLM chat, RAG, and agent pipelines.
Created and maintained by **[Taha Azizi](https://github.com/Taha-azizi)**.

---

## Project Status

> **Status: Stable for its original use case — maintained at a low cadence.**
>
> - **Built for a specific use case and provided as-is.** I will review bug fixes when time permits, but I am **not actively developing new features**.
> - **PRs are welcome**, but please expect a review cycle of **2–4 weeks**. If you need a feature immediately, **fork the repository** and iterate on your own timeline.
> - **License:** [Apache 2.0](LICENSE) — no warranty, no liability. See §7 (Disclaimer of Warranty) and §8 (Limitation of Liability) of the license for the legal text.
>
> For bug reports, please open a [GitHub issue](https://github.com/Taha-azizi/contextpress/issues) with a minimal reproduction. Feature requests may be closed with a pointer to fork.

---

## Install

```bash
pip install contextpress
```

If you cloned this repository:

```bash
pip install -e .
```

## 30-second quickstart

```python
from contextpress import ContextManager

# Default compression is "medium" (filler + repetition + recency); see below.
cm = ContextManager(type="chat")
messages = [{"role": "user", "content": "Hello!"}]
compressed = cm.compress(messages, token_budget=2000)
```

No API keys are required for Tier 1. Passing **`token_budget`** turns on the **budget** stage; other stages follow the chosen **compression** preset (`low` / `medium` / `high`).

### Minimal examples

```python
from contextpress import ContextManager

# Shortest useful call (default compression=medium, budget on because token_budget set)
out = ContextManager().compress(
    [{"role": "user", "content": "Hello"}, {"role": "assistant", "content": "Hi!"}],
    token_budget=500,
)

# Lighter pass: only filler + repetition (+ budget if token_budget set)
out = ContextManager(compression="low").compress(messages, token_budget=500)

# Full NLP pipeline for this call (+ budget if token_budget set)
out = ContextManager().compress(messages, token_budget=500, compression="high")

# Exact stages only (preset ignored); include "budget" if you pass token_budget and want enforcement
out = ContextManager().compress(
    messages,
    token_budget=500,
    stages=["filler", "repetition", "budget"],
)
```

### Runnable demo in this repo

After `pip install -e .`, run:

```bash
python try_compress.py
```

That script builds a long history and a tight `token_budget` so you can see turn and token counts drop (see comments at the top of `try_compress.py`).

## Context types

- **chat** — Typical back-and-forth dialogue. Filler removal, repetition deduplication, resolution collapsing, recency weighting, and token budgets are tuned for conversational flow.
- **rag_doc** — Document chunks or RAG context. Resolution is off; repetition compares all chunks; recency uses relevance to the latest user query instead of chat recency.
- **agent** — Tool-using or task-oriented threads. Resolution can trigger on a single high-confidence completion signal; filler rules preserve tool-related turns when markers are present.

```python
ContextManager(type="chat")
ContextManager(type="rag_doc")
ContextManager(type="agent")
```

## Pipeline stages

1. **Filler** — Removes low-semantic filler words and (in chat/agent) drops acknowledgement-only assistant turns.
2. **Repetition** — TF-IDF cosine similarity; keeps the more recent of similar turns.
3. **Resolution** — Collapses agreed threads into a single `RESOLVED:` synthetic system turn (chat/agent only).
4. **Recency** — Extractively compresses older turns (or low-relevance chunks in `rag_doc`) while preserving the latest context.
5. **Budget** — Enforces a hard token limit with `tiktoken`, removing oldest turns first while protecting system prompts and recent turns.

## Tier 1 vs Tier 2 (classical NLP vs LLM)

| | **Tier 1** (always available) | **Tier 2** (optional) |
|---|-------------------------------|------------------------|
| **What** | Pipeline stages: filler, repetition, resolution, recency, budget | `LLMBackend`: semantic `deduplicate` + `summarize` after Tier 1 |
| **Where in code** | `contextpress/strategies/`, orchestrated by `pipeline.py` | `contextpress/llm/` (`base.py`, `adapters.py`) |
| **Techniques** | Rules, TF–IDF, cosine similarity, NLTK, Sumy extractive summarization, tiktoken | Your provider’s chat/completions API (you supply the client) |
| **API key** | None | Required for your chosen provider (OpenAI, Anthropic, …) |
| **Determinism** | Deterministic for a fixed input and settings | Non-deterministic (model sampling) |
| **How to enable** | Default: `ContextManager()` runs Tier 1 only | Pass `llm_backend=` (`OpenAIBackend`, `AnthropicBackend`, **`OllamaBackend`**, or custom `LLMBackend`) |

**Note:** `ContextManager(model="gpt-4")` is only for **tiktoken** encoding when counting tokens in the **budget** stage. It does **not** call that model unless you also pass **`llm_backend`**.

## Compression presets and custom stages

**Presets** (`low` / `medium` / `high`, default **`medium`**) control how many NLP stages run. Aliases: `light`→low, `med`/`mid`→medium, `max`→high.

| Preset | Non-budget stages enabled |
|--------|-----------------------------|
| **low** | filler, repetition |
| **medium** | filler, repetition, recency |
| **high** | filler, repetition, resolution, recency |

The **budget** stage is separate: if you pass **`token_budget=<int>`**, the budget stage runs as well (unless you opt out with `disable=["budget"]` or omit `"budget"` from an explicit `stages=` list). If `token_budget` is `None`, the budget stage does not run.

Presets are **merged with the context profile** (for example, **resolution stays off** for `rag_doc` even on `high`, unless you pass an explicit `stages=` list that includes `resolution`).

```python
from contextpress import ContextManager

# Default strength is medium
cm = ContextManager(type="chat", compression="medium")

# Per-call preset
out = cm.compress(messages, token_budget=4000, compression="high")

# Full control: exact stages for this call (preset ignored)
out = cm.compress(
    messages,
    token_budget=4000,
    stages=["filler", "repetition", "budget"],
)

# Preset + skip one stage
out = cm.compress(messages, compression="high", disable=["resolution"])

# Change default for future calls
cm.set_compression("low")
```

## Optional LLM tier (Tier 2)

After **Tier 1** finishes, you can attach an **`LLMBackend`** for semantic compression.

**What it does**

1. Calls **`deduplicate(turn_texts)`** on non-system turns (your backend returns indices to **keep**; default adapters keep all).
2. If the combined transcript is long enough (default **1500** characters; set **`llm_min_input_chars=0`** to always run), calls **`summarize(transcript, max_tokens)`**.
3. **System turns are unchanged** in order and content. **All other turns are replaced** by a **single assistant** message whose content is the LLM summary (metadata includes `source: contextpress_llm_tier`). If the LLM call fails, the Tier 1 conversation is returned and a **warning** is emitted.

Optional constructor knobs: **`llm_min_input_chars`**, **`llm_max_summary_tokens`**.

**Install SDKs** (not bundled): `pip install openai`, `anthropic`, and/or **`ollama`** (for local Ollama), or `pip install "contextpress[llm]"` from this repo’s `pyproject.toml` to pull all optional LLM clients.

```python
from openai import OpenAI
from contextpress import ContextManager
from contextpress.llm.adapters import OpenAIBackend

backend = OpenAIBackend(client=OpenAI(), model="gpt-4o-mini")
cm = ContextManager(
    type="chat",
    llm_backend=backend,
    llm_min_input_chars=1000,
    llm_max_summary_tokens=1024,
)
out = cm.compress(messages, token_budget=4000)
```

**Runnable example** (requires `OPENAI_API_KEY`): [`examples/llm_tier_openai.py`](examples/llm_tier_openai.py).

```bash
pip install openai
set OPENAI_API_KEY=sk-...   # or export on Unix
python examples/llm_tier_openai.py
```

**Local Ollama (no cloud API key)** — install [Ollama](https://ollama.com), run `ollama serve`, pull a model (`ollama pull llama3.2`), then:

```python
from contextpress import ContextManager
from contextpress.llm.adapters import OllamaBackend

backend = OllamaBackend(model="llama3.2")  # optional: host="http://localhost:11434"
cm = ContextManager(type="chat", llm_backend=backend, llm_min_input_chars=500)
out = cm.compress(messages, token_budget=4000)
```

Runnable script: [`examples/llm_tier_ollama.py`](examples/llm_tier_ollama.py).

```bash
pip install ollama
ollama pull llama3.2
python examples/llm_tier_ollama.py
```

## Custom strategies

Subclass `contextpress.strategies.base.BaseStrategy`, implement `process(self, conversation) -> Conversation`, then fork `Pipeline._build_strategy` in a local subclass or contribute a factory that returns your strategy for a custom stage name. Stages must not mutate input turns; return new `Conversation` and `Turn` objects.

## Why contextpress

Long chat histories inflate token usage, bury important facts (lost-in-the-middle), and repeat stale or redundant content. `contextpress` trims noise, merges resolved threads, and enforces budgets with deterministic Tier 1 NLP so applications stay within context limits without extra services.

## Dependencies

- **nltk** — Tokenization, tagging, and light parsing for resolution and NLP helpers.
- **scikit-learn** — TF-IDF vectors and cosine similarity for repetition and RAG relevance.
- **sumy** — Extractive summarization for the recency stage.
- **tiktoken** — Token-accurate budgeting aligned with common model encodings.

## Research and citing

For academic use, cite this package in your paper’s software or methods section. A machine-readable citation file is provided as [`CITATION.cff`](CITATION.cff) (GitHub and Zenodo can ingest it). Replace the placeholder repository URL in that file with your fork’s URL when you publish.

## Extension and growth

- **Custom stages** — Subclass `contextpress.strategies.base.BaseStrategy` and plug in via a custom `Pipeline` subclass or future registry hooks.
- **Tier 2** — Implement `LLMBackend` (`summarize`, `deduplicate`) for provider-specific semantic compression; failures fall back to Tier 1.
- **Presets API** — `from contextpress.compression import VALID_STAGES, STAGE_ORDER` for tooling and experiments.
- **Profiles** — `configure(stage, ...)` adjusts aggressiveness per stage; `type="rag_doc"` vs `chat` changes dedup and recency behavior.

Invalid inputs are rejected early where practical: for example, `token_budget` must be a positive `int` or `None` (booleans are not accepted).

## Typing

The package includes `py.typed` (PEP 561) for static analysis in downstream projects.
