harness: LiteLLM client, Redmine intake, REPORT writeback, gated bash tool

OpenAI-compatible chat client for the LiteLLM proxy (base_url normalization,
Bearer auth, retry/backoff on 429/5xx/transport, usage accounting) - stdlib
http only. Intake lists issues in scope from /issues.json with the task
class read from a configurable custom field. Writeback lands each turn as
REPORT-<vertical>-<task>-<ts>.md plus REPORT-latest.md (atomic rename) with
model/tier/token telemetry. The bash tool ports maki's permission semantics
without tree-sitter: segment-by-segment compound-command checks, deny beats
allow, word-boundary "cmd *" matching, $()/backtick/subshell denied, output
truncation, per-command timeout with process-group cleanup.

💘 Generated with Crush

Assisted-by: Crush:glm-5.2

internal/intake/demo.go

@@ -0,0 +1,19 @@
+package intake
+
+import (
+	"git.knownelement.com/reachableceo/MOPAC/harness/internal/config"
+	"git.knownelement.com/reachableceo/MOPAC/harness/internal/task"
+)
+
+// DemoTask builds the MVP demo issue from the [demo] config section: the
+// smoke path that exercises the whole loop (intake -> turn -> REPORT) without
+// needing a reachable Redmine.
+func DemoTask(d config.DemoConfig) task.Task {
+	return task.Task{
+		ID:      d.ID,
+		Subject: d.Subject,
+		Prompt:  d.Prompt,
+		Class:   d.Class,
+		Source:  "demo",
+	}
+}