atlas
afe6026d44
subagent: keep runs at +1000 when their cgroup is unavailable
...
Without a run cgroup (no delegation, setup failed, or one create
failed) a subagent run was started plain at oom_score_adj 0, below the
+500 the unit gave it before. Every run of the daemon now goes through
the entry wrapper; it sets +1000 and enters the cgroup only when there
is one. run_cgroup::entry takes the cgroup as an Option.
2026-10-13 12:25:27 +02:00
..
lib.rs
hive-subagent-mcp: check subagent models against the swarm's subagent_models
2026-10-10 13:58:47 +02:00
main.rs
subagent: keep runs at +1000 when their cgroup is unavailable
2026-10-13 12:25:27 +02:00
mcp.rs
subagents, ACP: stop with SIGINT only, so claude ends its own tool commands
2026-10-11 02:44:31 +02:00
mcp_config.rs
hive-c0re: render the new agent option paths into generated agent flakes
2026-09-17 20:19:30 +02:00
paths.rs
hive-subagent-mcp: name a role at dispatch, load it as the system prompt
2026-09-21 17:21:40 +02:00
role.rs
hive-subagent-mcp: name a role at dispatch, load it as the system prompt
2026-09-21 17:21:40 +02:00
session.rs
subagent: keep runs at +1000 when their cgroup is unavailable
2026-10-13 12:25:27 +02:00
swarm_models.rs
hive-subagent-mcp: test that start and continue apply the swarm model list
2026-10-10 13:58:47 +02:00
swarm_term.rs
hive-subagent-mcp: check subagent models against the swarm's subagent_models
2026-10-10 13:58:47 +02:00