exe.dev user 52f8661f0c docs(providers): note that container.json provider is what the runner reads ...

The upstream precedence fix (5845a5a) made agent_groups.agent_provider and
sessions.agent_provider authoritative for host-side provider contribution
(per-session mount, env passthrough), but those DB values don't propagate
into the group's container.json — and the in-container runner reads
`provider` from container.json, not from the DB. That caused a confusing
failure mode: flipping the DB column to 'codex', rebuilding, and
restarting still spawned a Claude runner because container.json had no
provider field. The old skill wording ("container receives AGENT_PROVIDER
from the resolved value") overstated the integration.

Update add-codex and add-opencode "Per group / per session" sections to
say: set `"provider": "<name>"` in the group's container.json — that's
the source the runner reads. Keep the DB columns documented for the
host-side contribution they actually drive, and spell out the
session → group → container.json → 'claude' fallback so the precedence
is still discoverable.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

2026-04-24 13:38:05 +00:00

..

SKILL.md

docs(providers): note that container.json provider is what the runner reads

2026-04-24 13:38:05 +00:00