Evan
d1cab3e33a
* feat: add 4 context engine plugins
- topic-memory: keyword clustering for topic-aware memory recall
- episodic-memory: conversation segmentation and cross-session recall
- user-profile: persistent user profiling from conversation patterns
- context-decay: time-based memory decay with reinforcement dynamics
All plugins use the ingest/after_turn hook protocol with stdin/stdout JSON.
* chore: add plugin scaffolding, update docs and templates
- Add plugin.toml template with {{NAME}} placeholder
- Add new-plugin Makefile target with hooks/ scaffolding
- Update plugins/README.md with all 10 plugins
- Update README.md stats (10 plugins, 220+ models)
- Add Plugin checkbox and checklist to PR template
- Add Plugin to issue template content type dropdown
- Fix CONTRIBUTING.md: last_verified is recommended, not required
* fix: correct model pricing and remove deprecated entries
- openrouter/gemma-2-9b-it: fix pricing from 0.0 to 0.03/0.09 per M tokens
(free variant correctly stays at 0.0)
- github-copilot: remove deprecated copilot/gpt-4 model entry
(GPT-4 retired in favor of GPT-4o for Copilot)
* docs: annotate kimi-coding as membership-gated
Kimi Code CLI uses quota-based membership model (not per-token billing).
Free tier has limited weekly requests; underlying model is K2.5.
Pricing kept at 0.0 consistent with other subscription providers
(chatgpt, github-copilot) but with explanatory comments.
* style: fix trailing newline in github-copilot.toml
* fix: correct Moonshot/Kimi model pricing from official sources
All 5 models had incorrect pricing:
- moonshot-v1-8k: 0.10/0.10 → 0.20/2.00
- moonshot-v1-32k: 0.30/0.30 → 1.00/3.00
- moonshot-v1-128k: 0.80/0.80 → 2.00/5.00
- kimi-k2: 2.00/8.00 → 0.60/2.50
- kimi-k2.5: 2.00/8.00 → 0.45/2.20
Sources: platform.moonshot.ai/docs/pricing/chat, costgoat.com, getmaxim.ai
* feat: add MiniMax M2.7 and M2.7-highspeed models
Released 2026-03-18, MiniMax's latest flagship text model.
10B activated params, 200K context, 128K output, tool use, streaming.
Pricing: $0.30/$1.20 per M tokens (input/output).
Added to both international (minimax.io) and China (minimaxi.com) providers.
context-decay
Time-based memory decay with relevance scoring. Memories lose confidence over time (5% per day) and are only recalled when they pass both a decay threshold and a relevance check against the current message. Implements "use it or lose it" -- recalled memories get their access timestamps refreshed.
How it works
After each turn, the plugin extracts memorable statements from the conversation:
- User preferences ("I prefer...", "I use...")
- Decisions ("let's use...", "we decided...")
- Important facts (names, versions, URLs)
- Corrections ("no, actually...", "that's wrong...")
Similar memories are reinforced (confidence +0.1, cap 1.0). All memories receive a decay pass, and those below 0.1 confidence are pruned.
On ingest, each memory's confidence is decayed based on time elapsed, then scored for relevance to the current message via keyword overlap. The composite score decayed_confidence * (0.5 + 0.5 * relevance) must exceed 0.3 to be recalled. Recalled memories get their last_accessed timestamp updated.
Hooks
| Hook | Script | Description |
|---|---|---|
| ingest | hooks/ingest.py |
Applies decay, scores relevance, returns top 5 memories above threshold |
| after_turn | hooks/after_turn.py |
Extracts new memories, reinforces similar ones, prunes decayed entries |
Storage
Memories are stored at ~/.librefang/plugins/context-decay/{agent_id}.json. Max 100 memories per agent. Decay formula: confidence * 0.95^(hours / 24).
Usage
Installed automatically when enabled in agent configuration.