Add initial project files and implement basic call archival functionality.

.gitignore

@@ -1,6 +1,61 @@
+# Created by https://www.toptal.com/developers/gitignore/api/python,emacs
+# Edit at https://www.toptal.com/developers/gitignore?templates=python,emacs
+
+### Emacs ###
+# -*- mode: gitignore; -*-
+*~
+\#*\#
+/.emacs.desktop
+/.emacs.desktop.lock
+*.elc
+auto-save-list
+tramp
+.\#*
+
+# Org-mode
+.org-id-locations
+*_archive
+
+# flymake-mode
+*_flymake.*
+
+# eshell files
+/eshell/history
+/eshell/lastdir
+
+# elpa packages
+/elpa/
+
+# reftex files
+*.rel
+
+# AUCTeX auto folder
+/auto/
+
+# cask packages
+.cask/
+dist/
+
+# Flycheck
+flycheck_*.el
+
+# server auth directory
+/server/
+
+# projectiles files
+.projectile
+
+# directory configuration
+.dir-locals.el
+
+# network security
+/network-security.data
+
+
+### Python ###
 # Byte-compiled / optimized / DLL files
 __pycache__/
-*.py[codz]
+*.py[cod]
 *$py.class
 
 # C extensions
@@ -10,7 +65,6 @@ __pycache__/
 .Python
 build/
 develop-eggs/
-dist/
 downloads/
 eggs/
 .eggs/
@@ -27,8 +81,8 @@ share/python-wheels/
 MANIFEST
 
 # PyInstaller
-#   Usually these files are written by a python script from a template
-#   before PyInstaller builds the exe, so as to inject date/other infos into it.
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
 *.manifest
 *.spec
 
@@ -46,7 +100,7 @@ htmlcov/
 nosetests.xml
 coverage.xml
 *.cover
-*.py.cover
+*.py,cover
 .hypothesis/
 .pytest_cache/
 cover/
@@ -92,37 +146,22 @@ ipython_config.py
 #   However, in case of collaboration, if having platform-specific dependencies or dependencies
 #   having no cross-platform support, pipenv may install dependencies that don't work, or not
 #   install all needed dependencies.
-# Pipfile.lock
-
-# UV
-#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
-#   This is especially recommended for binary packages to ensure reproducibility, and is more
-#   commonly ignored for libraries.
-# uv.lock
+#Pipfile.lock
 
 # poetry
 #   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
 #   This is especially recommended for binary packages to ensure reproducibility, and is more
 #   commonly ignored for libraries.
 #   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
-# poetry.lock
-# poetry.toml
+#poetry.lock
 
 # pdm
 #   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
-#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
-#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
-# pdm.lock
-# pdm.toml
-.pdm-python
-.pdm-build/
-
-# pixi
-#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
-# pixi.lock
-#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
-#   in the .venv directory. It is recommended not to include this directory in version control.
-.pixi
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
 
 # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
 __pypackages__/
@@ -131,25 +170,11 @@ __pypackages__/
 celerybeat-schedule
 celerybeat.pid
 
-# Redis
-*.rdb
-*.aof
-*.pid
-
-# RabbitMQ
-mnesia/
-rabbitmq/
-rabbitmq-data/
-
-# ActiveMQ
-activemq-data/
-
 # SageMath parsed files
 *.sage.py
 
 # Environments
 .env
-.envrc
 .venv
 env/
 venv/
@@ -182,37 +207,22 @@ dmypy.json
 cython_debug/
 
 # PyCharm
-#   JetBrains specific template is maintained in a separate JetBrains.gitignore that can
-#   be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
-#   and can be added to the global gitignore or merged into this file.  For a more nuclear
-#   option (not recommended) you can uncomment the following to ignore the entire idea folder.
-# .idea/
-
-# Abstra
-#   Abstra is an AI-powered process automation framework.
-#   Ignore directories containing user credentials, local state, and settings.
-#   Learn more at https://abstra.io/docs
-.abstra/
-
-# Visual Studio Code
-#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
-#   that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
-#   and can be added to the global gitignore or merged into this file. However, if you prefer, 
-#   you could uncomment the following to ignore the entire vscode folder
-# .vscode/
-# Temporary file for partial code execution
-tempCodeRunnerFile.py
-
-# Ruff stuff:
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
 .ruff_cache/
 
-# PyPI configuration file
-.pypirc
+# LSP config files
+pyrightconfig.json
 
-# Marimo
-marimo/_static/
-marimo/_lsp/
-__marimo__/
+# End of https://www.toptal.com/developers/gitignore/api/python,emacs
 
-# Streamlit
-.streamlit/secrets.toml
+config.yaml

Dockerfile

@@ -0,0 +1,27 @@
+FROM nvidia/cuda:12.8.2-runtime-ubuntu24.04
+
+ENV PYTHONDONTWRITEBYTECODE=1 \
+    PYTHONUNBUFFERED=1 \
+    PIP_NO_CACHE_DIR=1 \
+    DEBIAN_FRONTEND=noninteractive
+
+WORKDIR /app
+
+RUN apt-get update \
+    && apt-get install -y --no-install-recommends ffmpeg \
+    python3 \
+    python3-pip \
+    && rm -rf /var/lib/apt/lists/*
+
+COPY requirements.txt ./
+RUN pip install --no-cache-dir --break-system-packages -r requirements.txt
+
+COPY call_archive ./call_archive
+COPY pyproject.toml .
+COPY transcribe.py .
+
+RUN pip install --no-cache-dir --break-system-packages -e .
+
+ENV PYTHONPATH=/app
+ENTRYPOINT ["call-archive"]
+CMD ["--help"]

README.md

@@ -1 +1,134 @@
-# call-archive
+# call-archive
+
+Local, privacy-first pipeline for processing phone call recordings:
+- transcription (faster-whisper),
+- semantic summarization (local LLM),
+- categorization,
+- retention decision support.
+
+No data leaves your machine.
+
+## Context
+
+This project is designed to work with **BCR (Basic Call Recorder)**.
+
+Recordings are produced on the phone and synchronized to the computer (e.g. via Syncthing, rsync, etc.).  
+That synchronization step is **out of scope** for this project.
+
+The only assumption:
+- new recordings (audio + JSON metadata) appear in configured `ingest_dir`.
+
+## Goals
+
+* Reduce storage usage of call recordings over time
+* Keep **structured knowledge** (transcripts + notes)
+* Retain only recordings that have **real value** (legal, business, commitments, disputes, etc.)
+* Maintain full **local control and privacy**
+
+## Directory layout
+
+```text
+/data/calls/
+  new/          # incoming recordings (from phone sync)
+  2026/         # organized by year (after scan)
+  rm/           # "deleted" recordings (manual cleanup)
+  transcripts/
+  notes/
+  calls.sqlite
+```
+
+### Lifecycle
+
+1. Files appear in `new/`
+2. `scan` moves them to `{year}/`
+3. `process`:
+
+   * transcribes audio
+   * analyzes content using local LLM
+   * assigns category + retention proposal
+4. `review`:
+
+   * you confirm or override decision
+5. `delete-approved`:
+
+   * audio is moved to `rm/` (never hard-deleted)
+
+## Features
+
+* Directory-based ingestion model (`ingest_dir/ → storage_dir/{year}/ → storage_dir/rm/`)
+* Full local processing (no cloud dependency)
+* Structured outputs (JSON + SQLite)
+* Extensible **categories** (configured in YAML)
+* Per-number retention heuristics
+* Safe deletion (only after manual review)
+
+## Categories
+
+Categories are defined in `config.yaml`:
+
+```yaml
+categories:
+  - work
+  - family
+  - spam
+  - friends
+  - unknown
+```
+
+The local LLM:
+
+* always receives the current list
+* must choose exactly one category
+
+You can freely extend this list.
+
+## Requirements
+
+* Python 3.11+
+* faster-whisper
+* Local LLM (recommended: Ollama)
+
+## Installation
+
+```bash
+python3 -m venv .venv
+. .venv/bin/activate
+pip install -e .
+```
+
+## Usage
+
+```bash
+call-archive init --config config.yaml
+call-archive scan --config config.yaml
+call-archive process --config config.yaml
+call-archive list --config config.yaml
+call-archive show --config config.yaml 1
+call-archive review --config config.yaml 1 --decision delete_audio_keep_transcript
+call-archive delete-approved --config config.yaml
+```
+
+## Safety model
+
+* No automatic deletion
+* All decisions require explicit review
+* Audio is moved to `rm/`, not deleted
+* Full audit trail in SQLite
+
+## Intended use
+
+This is useful if:
+
+* you record calls for **memory / accountability**
+* you want **automatic summarization**
+* you want to **control storage growth**
+* you need to keep everything **local**
+
+## Non-goals
+
+* Call recording itself (handled by BCR)
+* File synchronization (external tools)
+* Cloud integrations
+
+## License
+GPL-3.0 license 

call_archive/__init__.py

@@ -0,0 +1,3 @@
+__all__ = ["__version__"]
+
+__version__ = "0.1.0"