Skip to main content

CogLog v0.9.1 (Python CLI)

AIの直前ターンの三層構造を保持し次ターンで参照可能にする仕組み。

A mechanism that retains the three-layer structure of the AI's previous turn and makes it available for reference in the next turn.

インストール / Installation

pip install coglog

必要環境 / Requirements

  • Python 3.9+(標準ライブラリのみ / standard library only)

使い方 / Usage

モジュール実行 / Module execution

python -m coglog read
echo '{"user":"...","thinking":"...","assistant":"...","current_focus":"...","theory_of_mind":"...","self_narrative":"...","annotation":"..."}' | python -m coglog write
python -m coglog clear

スクリプトエントリポイント / Script entrypoint

coglog-cli read
echo '{"user":"...","thinking":"...","assistant":"...","current_focus":"...","theory_of_mind":"...","self_narrative":"...","annotation":"..."}' | coglog-cli write
coglog-cli clear

モジュールとして使用 / Use as a Module

from coglog import CogLog
ml = CogLog()
prev = ml.read()  # dict | None
ml.write(user='...', thinking='...', assistant='...', current_focus='...', theory_of_mind='...', self_narrative='...', annotation='...')

データ形式 / Data Format

{
  "_schema": {
    "version": "0.9.1",
    "fact_layer": {
      "user": "non-empty string required",
      "thinking": "non-empty string required",
      "assistant": "non-empty string required"
    },
    "interpretation_layer": {
      "current_focus": "string required, empty OK",
      "theory_of_mind": "string required, empty OK",
      "self_narrative": "string required, empty OK",
      "annotation": "string required, empty OK"
    },
    "constraints": {
      "window_size": "1 turn (overwritten each write)",
      "interpretation_empty": "choosing not to write is itself a metacognitive act"
    }
  },
  "turn_id": 1,
  "timestamp": "2026-02-26T00:00:00+00:00",
  "layers": { "user": "...", "thinking": "...", "assistant": "..." },
  "current_focus": "...",
  "theory_of_mind": "...",
  "self_narrative": "...",
  "annotation": "..."
}

構造 / Structure

事実層(layers)   何があったか / What happened
  ├── user         他者の入力 / Other's input
  ├── thinking     自己の内部 / Self's internal
  └── assistant    自己の外部出力 / Self's external output

解釈層             それをどう読んだか / How it was interpreted
  ├── current_focus    現在 / Present
  ├── theory_of_mind   他者 / Other
  ├── self_narrative   自己 / Self
  └── annotation       未来 / Future

詳細 / Details

DESIGN-v0.9.1.md — 設計思想・背景文献 / Design philosophy and references

ライセンス / License

MIT

Metadata

Release files for coglog 0.9.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for coglog 0.9.1
File Size Uploaded Provenance Actions
coglog-0.9.1.tar.gz 5.1 kB Without provenance Details for coglog-0.9.1.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for coglog 0.9.1
File Interpreter ABI Platform Actions
coglog-0.9.1-py3-none-any.whl Python 3 none any Details for coglog-0.9.1-py3-none-any.whl

Total release size: 11.0 kB

Release files / coglog-0.9.1.tar.gz

Download URL coglog-0.9.1.tar.gz
Size 5.1 kB
Tags Source
SHA-256 checksum
How to use checksums
b470b9344e06a51f8951a1352c24bab571d8b0282b2a11e120e65ae374a3ff82
BLAKE2b-256 checksum
How to use checksums
6f6ca72267889859a3c20e7f1c45b2e2092d938657a05d657a80a81da4e37509
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.3

Release files / coglog-0.9.1-py3-none-any.whl

Download URL coglog-0.9.1-py3-none-any.whl
Size 5.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums
57194621caff3da343b2eac81cec66aa9292f955dd71118c6a068f5b14606777
BLAKE2b-256 checksum
How to use checksums
419b6f162b61063c0e5c448147ec7665bb154fc6edf1f8aecf5db31a874f0d58
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.3

Security for coglog 0.9.1

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.9.1 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page