Lesen

Analyse aus praktischer Erfahrung.

Ausführliche Gedanken zu AI-Native- und Cloud-Native-Systemen, Open Source, Souveränität und den Entscheidungen dahinter.

Karsten Samaschke nachdenklich mit einer Hand am Kinn

Hayate Agent's Hourly Report Kept Posting

A scheduled job in Hayate Agent could post follow-up after follow-up when its model kept proposing another look, and a reply that hit the chat server's rate limit was tried again on every host tick. Core #593 stops a scheduled job from continuing just because its model proposed it, and holds a rejected reply until the wait Matrix asks for has passed, with that request capped at one hour. In a scripted run, one hourly run posted 20 times before the fix and once after.

Artikel lesen

Hayate Agent Read "No" as Yes

Until core PR #583 merged early Tuesday, a Hayate Agent cron job marked enabled: no in its YAML file stayed armed unless a stored pause applied, because the scheduler otherwise paused a job only on the boolean false and its YAML 1.2 parser keeps a bare no as text. The scheduler now refuses any enabled value that is not true or false. A scripted before/after run shows which spellings changed, and why a stale job file can now stop the agent from starting after an upgrade.

Artikel lesen

A 30-Character Message Waited 19 Minutes

A 30-character chat message took 19 minutes to reach Hayate Agent's first tool call, most of it spent on a local model busy with other large prompts. Core #507 lets an installation limit how many requests one runtime sends to a local model at once and puts interactive requests first. A scripted run shows what that changes, and what it does not.

Artikel lesen

Hayate Agent Stopped Calling Silence Done

Until the afternoon of 16 November, Hayate Agent edited a chat's progress bubble to a green "processing completed" check when the model answered NO_REPLY, whether or not any work was done. Five merges make silence a decision about the outgoing message only, limit silent completion claims without work to one recheck, and let a silent task settle as completed when the model records completion, the same turn shows successful tool work, and an independent check confirms it. A scripted before/after run shows what changed.

Artikel lesen

Hayate Agent Counted Bytes and Called Them Tokens

A guard added on Saturday compared JSON bytes with a 131,072-token limit and turned away legitimate requests before any model saw them. Why #467 removes the gate instead of raising the number, how far bytes and tokens really are apart, and the cost question it leaves open.

Artikel lesen

Hayate Agent Kept Summarizing a Context That Fit

Hayate Agent compacted sessions on a byte count compared with a token budget, even where the provider reported plenty of room. Core #498 removes that trigger, leaves pressure to the SDK's token accounting and shows each compaction in chats with progress enabled.

Artikel lesen

Hayate Agent Crashed on Files That Were Fine

An installed agent kept crashing at startup over files that were intact; a volume remount had only made them group-accessible. How the fix keeps the ledger check strict, and the worse bug found on the way: a missing page that could start the agent with an empty ledger.

Artikel lesen

Why Hayate Agent's Saved Tasks Did Not Resume

Hayate Agent keeps unfinished tasks on disk, yet real saved tasks did not resume after restarts. Each one has to pass a judge first, and six blockers around that judge made the tasks wait without anyone saying no. Here is what #433 and #435 changed, and what they still do not prove.

Artikel lesen

Starting Over in Hayate Agent Now Stops the Old Work

Starting a fresh conversation with Hayate Agent used to leave the old tasks, timers, workers and scheduled jobs running. Two fixes make a fresh start stop that work first, and the hard part is deciding which scheduled jobs a conversation actually owns.

Artikel lesen
Wird geladen...