0 Fork 0

Files

T

Evan d1cab3e33a feat: context engine plugins, scaffolding, and pricing fixes (#6 )

* 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.

2026-03-21 03:36:32 +09:00

1.4 KiB

Raw Blame History

episodic-memory

Episode-based conversation segmentation and cross-session recall. Automatically detects topic shifts to split conversations into discrete episodes, then recalls relevant past episodes when similar topics arise.

How it works

After each turn, the plugin tracks a "current episode" with accumulated keywords. When the Jaccard similarity between the current turn's keywords and the running episode keywords drops below 0.1 (and the episode has at least 4 messages), it marks the episode as completed with a summary and starts a new one.

On ingest, the plugin scores all completed episodes against the incoming message keywords and returns the top 2 matches (overlap > 0.2) as contextual memories including the episode timestamp and summary.

This gives agents episodic recall -- "last time we discussed Docker deployment, we configured nginx as a reverse proxy."

Hooks

Hook	Script	Description
ingest	`hooks/ingest.py`	Scores completed episodes against message keywords, returns top matches
after_turn	`hooks/after_turn.py`	Tracks current episode, detects topic shifts, segments conversations

Storage

Episodes are stored at ~/.librefang/plugins/episodic-memory/{agent_id}.json. Max 30 completed episodes per agent (oldest evicted when full).

Usage

Installed automatically when enabled in agent configuration.

1.4 KiB Raw Blame History