Files

AirCoding ae44be31d5 chore: push all design docs, V2 plan specs, and current working state

Includes AirPlan design documents, AircOding-alpha1-plan, AirPlanV2,
AirPlan-ParaV2, AirPlan-Para V1 reference docs, and all working code
changes across packages.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

2026-06-12 17:12:29 +08:00

config.yaml

chore: push all design docs, V2 plan specs, and current working state

2026-06-12 17:12:29 +08:00

README.md

chore: push all design docs, V2 plan specs, and current working state

2026-06-12 17:12:29 +08:00

rules.md

chore: push all design docs, V2 plan specs, and current working state

2026-06-12 17:12:29 +08:00

README.md

AirContext (per-project)

This directory configures AirContext for this project. It was created the first time you ran aircontext here.

Files

config.yaml — backend (LLM), trigger threshold, compaction options
rules.md — compression rules sent to the LLM as system prompt
state.json — runtime state (do not edit; managed by the plugin)
snapshots/ — backup of each JSONL before compaction; keep or delete freely

Getting started

Open config.yaml, set backend.endpoint / backend.model / backend.api_key. The default targets DeepSeek; replace with Ollama or any OpenAI-compatible server as needed. For Ollama set endpoint: http://localhost:11434/v1 and any non-empty api_key.
Tune trigger.threshold (default 0.6 = compact at 60% of model context).
Edit rules.md to bias summaries toward what your project considers important.
Re-run aircontext from this directory.

Disabling auto compaction temporarily

Run /aircontext-pause inside Claude Code, or set safety.dry_run: true in config.yaml.