Tianyi Cui be6cf4510b test(tool-bash): make the notice fake's agentId differ from its session token (Codex review) ...

Codex flagged (C) a test-sufficiency gap: the completion-notice fake had
`agent.id === session.header.id`, so the notice test could not distinguish the
code matching on the registry KEY (agentId) from matching on the session TOKEN
(session.header.id). The production code deliberately matches on
`session.header.id` because a config agent has `agentId !== sessionId` — but a
same-value fake passes either way (the "hits the line but not the scenario"
trap).

Give the registered fake a distinct agentId (`agent-<sessionId>`). Verified the
notice test now FAILS if the match is regressed to `a.id` and passes on
`a.session.header.id` — so it actually pins the discriminating behavior.

2026-06-20 09:57:05 +08:00

..

integration.spec.ts

refactor(agent-loop): rename LoopAgent to ReactLoopAgent

2026-06-19 10:13:33 +08:00

tools.spec.ts

test(tool-bash): make the notice fake's agentId differ from its session token (Codex review)

2026-06-20 09:57:05 +08:00