fix(core): preserve queue after provider failure

AGENTS.md

@@ -154,5 +154,6 @@ const table = sqliteTable("session", {
 - Preserve one explicit `llm.stream(request)` call per provider turn and reload projected history before durable continuation. Do not bridge through legacy `SessionPrompt.loop(...)` or delegate orchestration to an in-memory tool loop.
 - Keep local Session drains process-local until clustering is implemented. `SessionRunCoordinator` joins explicit same-Session resumes, coalesces prompt wakeups, and allows different Sessions to run concurrently. Advisory wakes drain eligible durable inbox rows only; post-crash continuation recovery requires a separate explicit design before it may retry provider work. A drain has no durable identity or transcript boundary.
 - Keep delivery vocabulary explicit. Prompts steer by default and promote at the next safe provider-turn boundary while the current drain requires continuation. An explicit `queue` input remains pending until the Session would otherwise become idle; promote one queued input at that boundary, then reevaluate continuation before promoting another. Promoting any new user input resets the selected agent's provider-turn allowance; a batch of steers resets it once.
+- A durably projected terminal provider failure ends the current drain without promoting pending steering or queued input. Preserve that inbox state for an explicit resume instead of silently advancing past the failure.
 - Keep EventV2 replay owner claims separate from clustered Session execution ownership.
 - Keep the System Context algebra, registry, and built-ins in `src/system-context`; keep Context Source producers with their observed domains, and keep Session History selection plus Context Epoch persistence Session-owned.