feat(executor): introduce AgentChannel seam for runner signals

Defines AgentChannel — the normalized interface by which a runner reports
agent-originated signals (AskUser, ReportSummary, SpawnSubtask,
RecordProgress) — plus a default storeChannel implementation backed by
storage. Runner.Run now takes an AgentChannel; the pool constructs one
per execution.

The file transport routes its post-exit summary detection through
ch.ReportSummary (buffered onto the execution so the pool still applies
its extract/synthesize fallbacks, no double-write). AskUser returns
ErrAgentBlocked since write-and-exit cannot answer in-session; question
persistence stays with the pool's BlockedError handling. SpawnSubtask
and RecordProgress are implemented and tested, ready for the MCP
transport in Phase 2 where the channel becomes fully load-bearing.

Store gains CreateEvent so the channel can emit agent_message events.

https://claude.ai/code/session_01SESwn7kQ7oP62trWw6pc39

1 files changed, 1 insertions, 1 deletions

diff --git a/internal/executor/local.go b/internal/executor/local.go
index 5d874c6..e3c9c2c 100644
--- a/internal/executor/local.go
+++ b/internal/executor/local.go
@@ -40,7 +40,7 @@ func (r *LocalRunner) ExecLogDir(execID string) string {
 // Run streams a chat completion to stdout.log. The response is wrapped in
 // stream-json envelopes line-by-line so downstream parsers (summary,
 // changestats) read it the same way they read Claude output.
-func (r *LocalRunner) Run(ctx context.Context, t *task.Task, e *storage.Execution) error {
+func (r *LocalRunner) Run(ctx context.Context, t *task.Task, e *storage.Execution, _ AgentChannel) error {
 	if r.Client == nil {
 		return fmt.Errorf("local runner: no LLM client configured")
 	}