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.
topic-memory
Topic-aware memory recall using keyword clustering. Tracks conversation topics per agent and recalls related context when similar topics arise in future conversations.
How it works
After each turn, the plugin extracts keywords from user and assistant messages, then either merges them into an existing topic cluster (Jaccard similarity > 0.3) or creates a new one. Each cluster stores a keyword set, a summary, a hit count, and a last-seen timestamp.
On ingest, the plugin scores all stored topic clusters against the incoming message keywords using Jaccard similarity and returns the top 3 matches (threshold > 0.15) as contextual memories.
This gives agents cross-conversation topic awareness -- if a user discussed Python async patterns last week, bringing up asyncio today will recall that context.
Hooks
| Hook | Script | Description |
|---|---|---|
| ingest | hooks/ingest.py |
Scores stored topics against message keywords, returns top matches |
| after_turn | hooks/after_turn.py |
Extracts keywords, merges or creates topic clusters |
Storage
Topic clusters are stored at ~/.librefang/plugins/topic-memory/{agent_id}.json. Max 50 clusters per agent (lowest hit-count evicted when full).
Usage
Installed automatically when enabled in agent configuration.