feat(pipeline): add multi-agent pipeline engine, sidechat auto-provisioning, and CDP event isolation

- Add bin/pipeline_engine.py for persistent multi-agent execution tracking in pipelines.json
- Add jobs/pipe-demo-step1.json and jobs/pipe-demo-step2.json demo pipeline definitions
- Use ev1 in bin/muse-chat-api.py across send/messages/compose/create to avoid dropping return values on CDP event chatter
- Support Muse unconfirmed signup error handling in bin/muse-signin.py
- Add runtime state and telemetry files to .gitignore
- Track dynamic pipe sidechat mappings in job-sidechats.json

jobs/pipe-demo-step1.json

@@ -0,0 +1,17 @@
+{
+  "name": "pipe-demo-step1",
+  "description": "Step 1 of Multi-Agent Demo Pipeline: opm checks fleet status",
+  "agent": "opm",
+  "schedule": "manual",
+  "timeout": 300,
+  "on_success": "pipe-demo-step2",
+  "on_failure": "pipe-demo-alert",
+  "step_delay": 5,
+  "followup": {
+    "expect_reply": true,
+    "timeout": "15m",
+    "nudges": 2,
+    "escalate": "opm"
+  },
+  "prompt_template": "Pipeline Step 1: Check fleet readiness across nodes (muse, pip, 646, opm). Summarize system health in 1 sentence.\n\nWhen finished, end your response with:\n[RESULT {job_id}] OK: Fleet healthy and operational"
+}

jobs/pipe-demo-step2.json

@@ -0,0 +1,14 @@
+{
+  "name": "pipe-demo-step2",
+  "description": "Step 2 of Multi-Agent Demo Pipeline: 646 verifies step 1 result and signs off",
+  "agent": "646",
+  "schedule": "manual",
+  "timeout": 300,
+  "followup": {
+    "expect_reply": true,
+    "timeout": "15m",
+    "nudges": 2,
+    "escalate": "opm"
+  },
+  "prompt_template": "Pipeline Step 2: Received upstream result from {prev_job_id}:\n\"{prev_result}\"\n\nReview and sign off on the findings.\n\nWhen finished, end your response with:\n[RESULT {job_id}] OK: Step 2 verified and signed off"
+}