Why: F14 source half - exec.ProcessEvent lacked CallID and outcome
fields, forcing consumers to pair events by tool name and mark every
end ok; cancellations and failures displayed as success downstream.
Evidence: loop/adapter tests pass (verify-u11a.json); pairing, denial,
cancellation and concurrent-callback cases added.
Impact: new omitempty fields only; legacy events unchanged.
Refs: feature/agent-stack-audit-remediation-b2 U11a
Why: Parallel tool execution makes same-turn tool events interleave, so
consumers can no longer pair starts and ends by order; the kernel Event
needs the call ID. MiniMax interleaved-thinking models stream their
reasoning inside content <think> blocks unless the OpenAI-compatible
request opts in with reasoning_split=true, which forces reasoning into
the dedicated reasoning_content field the SSE layer already captures.
Evidence: go test ./... green; new tests TestLoopToolEventsCarryCallID
and TestOpenAIChatBodyReasoningSplit pin both behaviors (regression
anchors for the backend parallel-work change).
Impact: Additive Event.CallID (empty for non-tool events; existing
consumers unaffected) and an opt-in Client.ReasoningSplit flag that only
adds a request field when set. No default behavior change.
Refs: Agent-System-Dev proposal 2026-10-10-agent-delegation-routing-sandbox.md
(F2/F5), Dev task feature/agent-e1-parallel-fixes.
weichen