Automated README summary
Automatically summarized from the README on 6 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A fork of astrbot_plugin_group_chat_plus that adds Alibaba Cloud System One (Jev-style) decision model to review whether the bot should interject or start a conversation in group chats, with per-group rate limiting and fallback protection.
How it uses Jev
After the original probability gate, Jev decides if interjecting is worth it. It takes group message state and returns join probability; if P(yes) ≥ threshold, the bot proceeds and suggests a style (question/share/agree). Failures fall back to the original gate.
Primitives:choice
Technique worth stealing
Hybrid mode: keep original probability rhythm, use Jev only to filter quality.
Try it
Set enable_systemone_decision=true, provide API key, set jev_mode=hybrid, restart plugin.
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.13.0- Project signals
jev-1.13.0- Category
jev-1.13.0- Pattern tags
jev-1.13.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectnot found in the excerpt0.34
- Shows a System One patternFound in material0.72
- Describes handling uncertaintynot found in the excerpt0.28
- Reports measured numbersnot found in the excerpt0.30
- Is a runnable toolFound in material0.97
- Top-10 learning shortlist signalnot found in the excerpt0.32
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale1.10 / 2
- About JevFound in material0.98
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 6 Oct 2026.