Automated README summary
Automatically summarized from the README on 3 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
BetterChat is an AstrBot plugin for two things: in private chat it waits for the user to finish a burst of messages and merges them into one reply; in group chat it uses Jev to decide whether the bot should speak.
How it uses Jev
For group messages, after a 1.5s aggregation window, it sends the cached transcript, bot name, and latest message to Jev with three yes/no questions: addressed_to_bot, open_question, already_answered_by_bot. The returned probabilities are checked against thresholds in code to decide RESPOND, IGNORE, or UNKNOWN.
Primitives:noul
Technique worth stealing
Aggregate consecutive group messages before a single Jev call, and keep a local transcript cache so Jev can avoid duplicate replies.
Try it
Clone into AstrBot/data/plugins, reload in WebUI, configure in the plugin panel.
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-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
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 excerpt0.21
- Shows a System One patternFound in material0.80
- Describes handling uncertaintynot found in the excerpt0.11
- Reports measured numbersnot found in the excerpt0.03
- Is a runnable toolFound in material0.96
- Top-10 learning shortlist signalnot found in the excerpt0.35
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale1.07 / 2
- About JevFound in material0.97
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 3 Nov 2026.