Cap #rss get summaries to one mesh packet (v0.20.1) #42

2026-09-25T21:24:56+02:00

kamilkrzywda commented

2026-09-25 21:24:56 +02:00

#rss get <name|#tag> replies were ~330 chars → broadcast fragments into multiple packets, fire-and-forget loss on the air.

Prompt tightened: at most 3 short bullets, each under 45 chars
maxTokens 2500 headroom (reasoning tokens count against the cap on this server; thinking is uncontrollable — observed 32–1776 reasoning tokens)
fitOnePacket() backstop cuts any over-length reply at complete-bullet boundaries to ≤190 chars

Tests 154 → 158, build + oxlint clean.

`#rss get <name|#tag>` replies were ~330 chars → broadcast fragments into multiple packets, fire-and-forget loss on the air. - Prompt tightened: at most 3 short bullets, each under 45 chars - maxTokens 2500 headroom (reasoning tokens count against the cap on this server; thinking is uncontrollable — observed 32–1776 reasoning tokens) - `fitOnePacket()` backstop cuts any over-length reply at complete-bullet boundaries to ≤190 chars Tests 154 → 158, build + oxlint clean.

kamilkrzywda added 1 commit 2026-09-25 21:24:56 +02:00

Cap #rss get summaries to one mesh packet (v0.20.1)

CI / build + unit (pull_request) Successful in 42s

Details

e2d712a26c

Replies >~190 chars fragment into fire-and-forget packets recipients
often never receive; old prompt produced ~326-334 char replies.

Prompt now asks for at most 3 short bullet lines, each under 45 chars,
bullets only (verified live: exactly 3 compliant bullets, ~110 chars).
fitOnePacket() backstop cuts any over-length reply at complete-bullet
boundaries so delivery is one packet even if the model ignores the prompt.

maxTokens 200 -> 2500 on the summary chat(): empirically verified that
this server's reasoning tokens count against max_tokens (cap 150 ->
completion 150 of which 105 were reasoning; cap 500 fully consumed by
reasoning, zero visible content) and thinking is uncontrollable
server-side (/no_think, chat_template_kwargs.enable_thinking,
thinking_budget all ignored), observed 32..1776 tokens for this task.
2500 covers every observed run + ~80 content tokens, worst case ~42 s
under the 60 s LLM timeout.

kamilkrzywda merged commit 172e7bed9c into main

2026-09-25 21:25:02 +02:00

kamilkrzywda deleted branch fix/rss-summary-length

2026-09-25 21:25:02 +02:00

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: OpenCode/MeshBot#42