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, 3 insertions, 3 deletions

diff --git a/internal/executor/claude.go b/internal/executor/claude.go
index 3c87f26..0123754 100644
--- a/internal/executor/claude.go
+++ b/internal/executor/claude.go
@@ -51,7 +51,7 @@ func (r *ClaudeRunner) binaryPath() string {
 // project into a temp sandbox, runs the agent there, then merges committed
 // changes back to project_dir. On failure the sandbox is preserved and its
 // path is included in the error.
-func (r *ClaudeRunner) Run(ctx context.Context, t *task.Task, e *storage.Execution) error {
+func (r *ClaudeRunner) Run(ctx context.Context, t *task.Task, e *storage.Execution, ch AgentChannel) error {
 	projectDir := t.Agent.ProjectDir
 
 	// Validate project_dir exists when set.
@@ -164,7 +164,7 @@ func (r *ClaudeRunner) Run(ctx context.Context, t *task.Task, e *storage.Executi
 		// extract the text as the summary and fall through to normal completion.
 		if isCompletionReport(questionJSON) {
 			r.Logger.Info("treating question file as completion report", "taskID", e.TaskID)
-			e.Summary = extractQuestionText(questionJSON)
+			_ = ch.ReportSummary(ctx, extractQuestionText(questionJSON))
 		} else {
 			// Preserve sandbox on BLOCKED — agent may have partial work and its
 			// Claude session files are stored under the sandbox's project slug.
@@ -177,7 +177,7 @@ func (r *ClaudeRunner) Run(ctx context.Context, t *task.Task, e *storage.Executi
 	summaryFile := filepath.Join(logDir, "summary.txt")
 	if summaryData, readErr := os.ReadFile(summaryFile); readErr == nil {
 		os.Remove(summaryFile) // consumed
-		e.Summary = strings.TrimSpace(string(summaryData))
+		_ = ch.ReportSummary(ctx, strings.TrimSpace(string(summaryData)))
 	}
 
 	// Merge sandbox back to project_dir and clean up.