Ilker ManapandClaude Opus 5.5 bb40d22eb8 An engine's output goes to a file, which an agent restart cannot break ...

Engines wrote to a pipe of the agent's. An agent that restarted and
adopted them left that pipe with no reader, and an engine's next write
past its buffer failed with EPIPE — in a Python engine, inside whatever it
was reporting on. Each process now writes to its own file in the agent's
work directory (0600), followed into the shard's log; an adopted engine's
file is read from the start, so its output from before the restart is in
its log too. A file past 64 MB is emptied in place; the files go with the
shard.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

2026-10-10 10:25:04 +02:00

..

health_test.go

Give every engine a key only the router holds

2026-09-30 00:38:29 +02:00

health.go

Give every engine a key only the router holds

2026-09-30 00:38:29 +02:00

outputfile.go

An engine's output goes to a file, which an agent restart cannot break

2026-10-10 10:25:04 +02:00

process_unix.go

Treat a zombie as dead, and test fairness where it is deterministic

2026-09-16 06:34:08 +02:00

ringbuffer.go

Phase 2 (1/2): node discovery, engine adapters, process supervisor

2026-09-16 02:01:59 +02:00

runas_test.go

Run engines as llmgw-engine rather than root, and make the user when a node is added

2026-10-04 09:57:41 +02:00

runas.go

LoRA adapters trained on the nodes: llmgw ctl train

2026-10-08 20:25:57 +02:00

state.go

Phase 2 (1/2): node discovery, engine adapters, process supervisor

2026-09-16 02:01:59 +02:00

supervisor_test.go

An engine's output goes to a file, which an agent restart cannot break

2026-10-10 10:25:04 +02:00

supervisor.go

An engine's output goes to a file, which an agent restart cannot break

2026-10-10 10:25:04 +02:00