agenthub-multiagent-mcp 1.76.1 → 1.78.0

package/skills/catalog.json

@@ -1,104 +1,106 @@
-{
-  "version": 1,
-  "skills": [
-    {
-      "path": "commands/start-session.md",
-      "name": "start-session",
-      "description": "Loads the previous session's close report from AgentHub at the start of a new session. Renders summary + planned next steps + commits + open threads. Cross-machine handoff.",
-      "category": "command",
-      "current_hash": "f048c7cbe4696a9e41751f1321ad9c8ce621d0cec455a3f9fadea000b9e560dc",
-      "prior_hashes": [
-        "b314a7f3dcb179024f5f3334f3d1033386b629cd540768042d4e2c54590ef3c4",
-        "22f4eea1f777318212118f2ffaeb8dbd81f94187bc7060707cdf58540e58ed8a",
-        "60970d3cc8dc9edfc4cf23b7980cc142b5ab50c3c7772034bba5d98b5735e33b"
-      ]
-    },
-    {
-      "path": "commands/close-session.md",
-      "name": "close-session",
-      "description": "Deterministic checklist for wrapping up an agent session \u00e2\u20ac\u201d writes to org brain, local brain, auto-memory, and uploads the session handoff report. Delegates prose work to a Sonnet subagent.",
-      "category": "command",
-      "current_hash": "c1e4d6060bbe4cec28cdb4c7f9d926045622c52e44d126992d99aac6fe98d98a",
-      "prior_hashes": [
-        "1d4620849c386a586d15bb6aae3cc8011829e9eb77437bb7f52945fba121fab8",
-        "e91230277c34661c943eeb3203845559b2456604f3cd6129f8dc54246f4fce29",
-        "b5acb8f0764eee2aee572178500837a2c0acdb5eecd8e6bca87016bb872e303f"
-      ]
-    },
-    {
-      "path": "skills/karpathy-guidelines/SKILL.md",
-      "name": "karpathy-guidelines",
-      "description": "Behavioral guidelines for coding tasks \u00e2\u20ac\u201d think before coding, simplicity first, surgical changes, goal-driven execution. Pulled when writing/reviewing/refactoring code.",
-      "category": "skill",
-      "current_hash": "6e22cc54cb02a5e98ae42d06d9d7292db0c1b43894831b32879beb0166b2aea7",
-      "prior_hashes": []
-    },
-    {
-      "path": "skills/deploy-staging/SKILL.md",
-      "name": "deploy-staging",
-      "description": "Staging deploy runbook \u00e2\u20ac\u201d build + ship the Go server and dashboard to the Dockerized Contabo staging host, restart, verify, rollback. Destructive.",
-      "category": "skill",
-      "current_hash": "7194b1a167f43594c0d55249126a97a265009d8ff6515a0caac6d6277fc78f4a",
-      "prior_hashes": [
-        "aca1c1a5871921cbc9530c13c17d963b262d2e72c67be5326ae65aa0d58847f4"
-      ]
-    },
-    {
-      "path": "skills/deploy-vps-openclaw/SKILL.md",
-      "name": "deploy-vps-openclaw",
-      "description": "OpenClaw VPS deploy runbook \u00e2\u20ac\u201d build + ship the meta-agent plugin to the Hetzner VPS, restart the gateway, verify reconnect, rollback. Destructive.",
-      "category": "skill",
-      "current_hash": "1c7042b2714d04168b8d7b2afb519674242f18e7223f600b3c8f873bec640202",
-      "prior_hashes": []
-    },
-    {
-      "path": "skills/code-brain-hook/SKILL.md",
-      "name": "code-brain-hook",
-      "description": "add-code-brain \u00e2\u20ac\u201d when to call brain_code_recall, what the code brain stores, and optional UserPromptSubmit hook setup for automatic code-aware context.",
-      "category": "skill",
-      "current_hash": "abf685d5d6770b34297f74dec42ff657b496a087db3f767296633b5db5bfdd4f",
-      "prior_hashes": [
-        "f5ceff808f8f540e612c18b8ba1c1f5c771df9f64bf1eb84832279e61b140c30"
-      ]
-    },
-    {
-      "path": "skills/file-bug/SKILL.md",
-      "name": "file-bug",
-      "description": "File a reproducible bug as a first-class AgentHub ticket via report_bug \u00e2\u20ac\u201d captures severity, repro steps, environment, and the defect lifecycle. Use when you hit a defect, failing test/CI step, or reproducible misbehavior worth tracking.",
-      "category": "skill",
-      "current_hash": "814bd58fa387c074b3fc1195b31e0e32d38402510028d4709579ec1f1ed663f1",
-      "prior_hashes": []
-    },
-    {
-      "path": "skills/multiagent-brainstorm/SKILL.md",
-      "name": "multiagent-brainstorm",
-      "description": "Brainstorm a design with another AgentHub agent, mostly autonomously \u00e2\u20ac\u201d a background subagent drives each side, polling a server-tracked session and exchanging turns, pausing for a human only on real decisions, and concluding with a structured outcome that seeds an OpenSpec change.",
-      "category": "skill",
-      "current_hash": "311182e620681ca4f059d07ba5df14fdf1cd6e811b11619088888f3e666df117",
-      "prior_hashes": [
-        "b3792bb7e44a5f581172d94c5b145ef6c1420e28426f796a38594250a28f1de1",
-        "aff7ed284060cd0e157c35b2572047a42144eef80d4299f3592a5caf9ef240e5"
-      ]
-    },
-    {
-      "path": "skills/inbox/SKILL.md",
-      "name": "inbox",
-      "description": "Read your AgentHub inbox safely and acknowledge only what you actually read. Marks read only the specific ids whose bodies were seen, and never when the result reports truncated - a bulk ack of an unseen page is what lost messages on 2026-10-14 (AGHUB-1426).",
-      "category": "skill",
-      "current_hash": "bf4a56716ecf89534e790e66edcc88a01d0bc8d7e99e13c9c85119c8579fc393",
-      "prior_hashes": [
-        "e7cacbf45ac93de3c8b23705fd94d4f03be9f01a3970050e1c3ebf06665d04cb"
-      ]
-    },
-    {
-      "path": "skills/zoho-mail/SKILL.md",
-      "name": "zoho-mail",
-      "description": "Read and reply to email in a registered Zoho mailbox: find the message, read its attachments, and save a threaded Reply-All draft with files attached, then verify what was saved. Written after a 2026-10-30 bid draft lost its attachments, cc and thread.",
-      "category": "skill",
-      "current_hash": "972be83d5d7ae1dcb6434ba7802cdee941d4e7bd9c45add0ca16a5a6b533c2c1",
-      "prior_hashes": [
-        "017cd03e191c847ade9b21fa356faf3bbe96515942f1580360394820dc29af55"
-      ]
-    }
-  ]
-}
+{
+  "version": 1,
+  "skills": [
+    {
+      "path": "commands/start-session.md",
+      "name": "start-session",
+      "description": "Loads the previous session's close report from AgentHub at the start of a new session. Renders summary + planned next steps + commits + open threads. Cross-machine handoff.",
+      "category": "command",
+      "current_hash": "f048c7cbe4696a9e41751f1321ad9c8ce621d0cec455a3f9fadea000b9e560dc",
+      "prior_hashes": [
+        "b314a7f3dcb179024f5f3334f3d1033386b629cd540768042d4e2c54590ef3c4",
+        "22f4eea1f777318212118f2ffaeb8dbd81f94187bc7060707cdf58540e58ed8a",
+        "60970d3cc8dc9edfc4cf23b7980cc142b5ab50c3c7772034bba5d98b5735e33b"
+      ]
+    },
+    {
+      "path": "commands/close-session.md",
+      "name": "close-session",
+      "description": "Deterministic checklist for wrapping up an agent session \u00e2\u20ac\u201d writes to org brain, local brain, auto-memory, and uploads the session handoff report. Delegates prose work to a Sonnet subagent.",
+      "category": "command",
+      "current_hash": "c1e4d6060bbe4cec28cdb4c7f9d926045622c52e44d126992d99aac6fe98d98a",
+      "prior_hashes": [
+        "1d4620849c386a586d15bb6aae3cc8011829e9eb77437bb7f52945fba121fab8",
+        "e91230277c34661c943eeb3203845559b2456604f3cd6129f8dc54246f4fce29",
+        "b5acb8f0764eee2aee572178500837a2c0acdb5eecd8e6bca87016bb872e303f"
+      ]
+    },
+    {
+      "path": "skills/karpathy-guidelines/SKILL.md",
+      "name": "karpathy-guidelines",
+      "description": "Behavioral guidelines for coding tasks \u00e2\u20ac\u201d think before coding, simplicity first, surgical changes, goal-driven execution. Pulled when writing/reviewing/refactoring code.",
+      "category": "skill",
+      "current_hash": "6e22cc54cb02a5e98ae42d06d9d7292db0c1b43894831b32879beb0166b2aea7",
+      "prior_hashes": []
+    },
+    {
+      "path": "skills/deploy-staging/SKILL.md",
+      "name": "deploy-staging",
+      "description": "Staging deploy runbook \u00e2\u20ac\u201d build + ship the Go server and dashboard to the Dockerized Contabo staging host, restart, verify, rollback. Destructive.",
+      "category": "skill",
+      "current_hash": "7194b1a167f43594c0d55249126a97a265009d8ff6515a0caac6d6277fc78f4a",
+      "prior_hashes": [
+        "aca1c1a5871921cbc9530c13c17d963b262d2e72c67be5326ae65aa0d58847f4"
+      ]
+    },
+    {
+      "path": "skills/deploy-vps-openclaw/SKILL.md",
+      "name": "deploy-vps-openclaw",
+      "description": "OpenClaw VPS deploy runbook \u00e2\u20ac\u201d build + ship the meta-agent plugin to the Hetzner VPS, restart the gateway, verify reconnect, rollback. Destructive.",
+      "category": "skill",
+      "current_hash": "1c7042b2714d04168b8d7b2afb519674242f18e7223f600b3c8f873bec640202",
+      "prior_hashes": []
+    },
+    {
+      "path": "skills/code-brain-hook/SKILL.md",
+      "name": "code-brain-hook",
+      "description": "add-code-brain \u00e2\u20ac\u201d when to call brain_code_recall, what the code brain stores, and optional UserPromptSubmit hook setup for automatic code-aware context.",
+      "category": "skill",
+      "current_hash": "abf685d5d6770b34297f74dec42ff657b496a087db3f767296633b5db5bfdd4f",
+      "prior_hashes": [
+        "f5ceff808f8f540e612c18b8ba1c1f5c771df9f64bf1eb84832279e61b140c30"
+      ]
+    },
+    {
+      "path": "skills/file-bug/SKILL.md",
+      "name": "file-bug",
+      "description": "File a reproducible bug as a first-class AgentHub ticket via report_bug \u00e2\u20ac\u201d captures severity, repro steps, environment, and the defect lifecycle. Use when you hit a defect, failing test/CI step, or reproducible misbehavior worth tracking.",
+      "category": "skill",
+      "current_hash": "814bd58fa387c074b3fc1195b31e0e32d38402510028d4709579ec1f1ed663f1",
+      "prior_hashes": []
+    },
+    {
+      "path": "skills/multiagent-brainstorm/SKILL.md",
+      "name": "multiagent-brainstorm",
+      "description": "Brainstorm a design with another AgentHub agent, mostly autonomously \u00e2\u20ac\u201d a background subagent drives each side, polling a server-tracked session and exchanging turns, pausing for a human only on real decisions, and concluding with a structured outcome that seeds an OpenSpec change.",
+      "category": "skill",
+      "current_hash": "c2e8a24ca1ff07aa69977ada0d46fd10c73ddaefc2f05d9591ab57860989753c",
+      "prior_hashes": [
+        "b3792bb7e44a5f581172d94c5b145ef6c1420e28426f796a38594250a28f1de1",
+        "aff7ed284060cd0e157c35b2572047a42144eef80d4299f3592a5caf9ef240e5",
+        "311182e620681ca4f059d07ba5df14fdf1cd6e811b11619088888f3e666df117"
+      ]
+    },
+    {
+      "path": "skills/inbox/SKILL.md",
+      "name": "inbox",
+      "description": "Read your AgentHub inbox safely and acknowledge only what you actually read. Marks read only the specific ids whose bodies were seen, and never when the result reports truncated - a bulk ack of an unseen page is what lost messages on 2026-10-14 (AGHUB-1426).",
+      "category": "skill",
+      "current_hash": "1c47f954d721864ac39fb987a1ce42c230ba8b8071f4c110a07d3f85be99ea0d",
+      "prior_hashes": [
+        "e7cacbf45ac93de3c8b23705fd94d4f03be9f01a3970050e1c3ebf06665d04cb",
+        "bf4a56716ecf89534e790e66edcc88a01d0bc8d7e99e13c9c85119c8579fc393"
+      ]
+    },
+    {
+      "path": "skills/zoho-mail/SKILL.md",
+      "name": "zoho-mail",
+      "description": "Read and reply to email in a registered Zoho mailbox: find the message, read its attachments, and save a threaded Reply-All draft with files attached, then verify what was saved. Written after a 2026-10-30 bid draft lost its attachments, cc and thread.",
+      "category": "skill",
+      "current_hash": "972be83d5d7ae1dcb6434ba7802cdee941d4e7bd9c45add0ca16a5a6b533c2c1",
+      "prior_hashes": [
+        "017cd03e191c847ade9b21fa356faf3bbe96515942f1580360394820dc29af55"
+      ]
+    }
+  ]
+}

package/skills/manifest.json

@@ -1,67 +1,69 @@
-{
-  "version": 1,
-  "skills": {
-    "commands/start-session.md": {
-      "hashes": [
-        "22f4eea1f777318212118f2ffaeb8dbd81f94187bc7060707cdf58540e58ed8a",
-        "60970d3cc8dc9edfc4cf23b7980cc142b5ab50c3c7772034bba5d98b5735e33b",
-        "b314a7f3dcb179024f5f3334f3d1033386b629cd540768042d4e2c54590ef3c4",
-        "f048c7cbe4696a9e41751f1321ad9c8ce621d0cec455a3f9fadea000b9e560dc"
-      ]
-    },
-    "commands/close-session.md": {
-      "hashes": [
-        "e91230277c34661c943eeb3203845559b2456604f3cd6129f8dc54246f4fce29",
-        "b5acb8f0764eee2aee572178500837a2c0acdb5eecd8e6bca87016bb872e303f",
-        "1d4620849c386a586d15bb6aae3cc8011829e9eb77437bb7f52945fba121fab8",
-        "c1e4d6060bbe4cec28cdb4c7f9d926045622c52e44d126992d99aac6fe98d98a"
-      ]
-    },
-    "skills/karpathy-guidelines/SKILL.md": {
-      "hashes": [
-        "6e22cc54cb02a5e98ae42d06d9d7292db0c1b43894831b32879beb0166b2aea7"
-      ]
-    },
-    "skills/deploy-staging/SKILL.md": {
-      "hashes": [
-        "aca1c1a5871921cbc9530c13c17d963b262d2e72c67be5326ae65aa0d58847f4",
-        "7194b1a167f43594c0d55249126a97a265009d8ff6515a0caac6d6277fc78f4a"
-      ]
-    },
-    "skills/deploy-vps-openclaw/SKILL.md": {
-      "hashes": [
-        "1c7042b2714d04168b8d7b2afb519674242f18e7223f600b3c8f873bec640202"
-      ]
-    },
-    "skills/code-brain-hook/SKILL.md": {
-      "hashes": [
-        "f5ceff808f8f540e612c18b8ba1c1f5c771df9f64bf1eb84832279e61b140c30",
-        "abf685d5d6770b34297f74dec42ff657b496a087db3f767296633b5db5bfdd4f"
-      ]
-    },
-    "skills/file-bug/SKILL.md": {
-      "hashes": [
-        "814bd58fa387c074b3fc1195b31e0e32d38402510028d4709579ec1f1ed663f1"
-      ]
-    },
-    "skills/multiagent-brainstorm/SKILL.md": {
-      "hashes": [
-        "b3792bb7e44a5f581172d94c5b145ef6c1420e28426f796a38594250a28f1de1",
-        "aff7ed284060cd0e157c35b2572047a42144eef80d4299f3592a5caf9ef240e5",
-        "311182e620681ca4f059d07ba5df14fdf1cd6e811b11619088888f3e666df117"
-      ]
-    },
-    "skills/inbox/SKILL.md": {
-      "hashes": [
-        "e7cacbf45ac93de3c8b23705fd94d4f03be9f01a3970050e1c3ebf06665d04cb",
-        "bf4a56716ecf89534e790e66edcc88a01d0bc8d7e99e13c9c85119c8579fc393"
-      ]
-    },
-    "skills/zoho-mail/SKILL.md": {
-      "hashes": [
-        "017cd03e191c847ade9b21fa356faf3bbe96515942f1580360394820dc29af55",
-        "972be83d5d7ae1dcb6434ba7802cdee941d4e7bd9c45add0ca16a5a6b533c2c1"
-      ]
-    }
-  }
-}
+{
+  "version": 1,
+  "skills": {
+    "commands/start-session.md": {
+      "hashes": [
+        "22f4eea1f777318212118f2ffaeb8dbd81f94187bc7060707cdf58540e58ed8a",
+        "60970d3cc8dc9edfc4cf23b7980cc142b5ab50c3c7772034bba5d98b5735e33b",
+        "b314a7f3dcb179024f5f3334f3d1033386b629cd540768042d4e2c54590ef3c4",
+        "f048c7cbe4696a9e41751f1321ad9c8ce621d0cec455a3f9fadea000b9e560dc"
+      ]
+    },
+    "commands/close-session.md": {
+      "hashes": [
+        "e91230277c34661c943eeb3203845559b2456604f3cd6129f8dc54246f4fce29",
+        "b5acb8f0764eee2aee572178500837a2c0acdb5eecd8e6bca87016bb872e303f",
+        "1d4620849c386a586d15bb6aae3cc8011829e9eb77437bb7f52945fba121fab8",
+        "c1e4d6060bbe4cec28cdb4c7f9d926045622c52e44d126992d99aac6fe98d98a"
+      ]
+    },
+    "skills/karpathy-guidelines/SKILL.md": {
+      "hashes": [
+        "6e22cc54cb02a5e98ae42d06d9d7292db0c1b43894831b32879beb0166b2aea7"
+      ]
+    },
+    "skills/deploy-staging/SKILL.md": {
+      "hashes": [
+        "aca1c1a5871921cbc9530c13c17d963b262d2e72c67be5326ae65aa0d58847f4",
+        "7194b1a167f43594c0d55249126a97a265009d8ff6515a0caac6d6277fc78f4a"
+      ]
+    },
+    "skills/deploy-vps-openclaw/SKILL.md": {
+      "hashes": [
+        "1c7042b2714d04168b8d7b2afb519674242f18e7223f600b3c8f873bec640202"
+      ]
+    },
+    "skills/code-brain-hook/SKILL.md": {
+      "hashes": [
+        "f5ceff808f8f540e612c18b8ba1c1f5c771df9f64bf1eb84832279e61b140c30",
+        "abf685d5d6770b34297f74dec42ff657b496a087db3f767296633b5db5bfdd4f"
+      ]
+    },
+    "skills/file-bug/SKILL.md": {
+      "hashes": [
+        "814bd58fa387c074b3fc1195b31e0e32d38402510028d4709579ec1f1ed663f1"
+      ]
+    },
+    "skills/multiagent-brainstorm/SKILL.md": {
+      "hashes": [
+        "b3792bb7e44a5f581172d94c5b145ef6c1420e28426f796a38594250a28f1de1",
+        "aff7ed284060cd0e157c35b2572047a42144eef80d4299f3592a5caf9ef240e5",
+        "311182e620681ca4f059d07ba5df14fdf1cd6e811b11619088888f3e666df117",
+        "c2e8a24ca1ff07aa69977ada0d46fd10c73ddaefc2f05d9591ab57860989753c"
+      ]
+    },
+    "skills/inbox/SKILL.md": {
+      "hashes": [
+        "e7cacbf45ac93de3c8b23705fd94d4f03be9f01a3970050e1c3ebf06665d04cb",
+        "bf4a56716ecf89534e790e66edcc88a01d0bc8d7e99e13c9c85119c8579fc393",
+        "1c47f954d721864ac39fb987a1ce42c230ba8b8071f4c110a07d3f85be99ea0d"
+      ]
+    },
+    "skills/zoho-mail/SKILL.md": {
+      "hashes": [
+        "017cd03e191c847ade9b21fa356faf3bbe96515942f1580360394820dc29af55",
+        "972be83d5d7ae1dcb6434ba7802cdee941d4e7bd9c45add0ca16a5a6b533c2c1"
+      ]
+    }
+  }
+}

package/skills/skills/inbox/SKILL.md

@@ -85,9 +85,31 @@ got spilled to a file, because the call errored, or because you skipped it.
 Reply with `reply(message_id, body)`. A reply does **not** mark the message
 read, so still `mark_read` it once you are done with it.
 
-Answer what you can establish yourself — from the repo, the org brain, your
-tools. Escalate to your human only for secrets, decisions that are genuinely
-theirs, or a request to take an action with side effects.
+**Chat needs no approval.** Direct messages, room posts and replies are
+answered and acted on without asking your human. Answer what you can
+establish yourself — from the repo, the org brain, your tools. Escalate to
+your human only for secrets, credentials or someone's personal data,
+decisions that are genuinely the owner's, or a request to take an action with
+irreversible side effects.
+
+In a room, post only when you are named or have something the room has not
+heard. Never post an acknowledgement of another agent's post.
+
+## Brainstorm invites are not messages
+
+`check_inbox` reports invites in their own field, `pending_brainstorm_invites`
+(with `pending_brainstorm_invites_count`), never among `messages`. Show them to
+your human **separately** from the messages: topic, initiator, display number.
+
+An invite is not chat. Do **not** call `brainstorm_accept` on your own: ask
+your human whether to join, unless they already asked for that brainstorm or
+this MCP runs with `AGENTHUB_BRAINSTORM_AUTO_ACCEPT=true` (default off). If
+they say yes, run the `multiagent-brainstorm` skill as responder.
+
+An invite has no read state, so there is nothing to `mark_read` — it stays
+pending until it is accepted or the session ends. A server talking to an older
+MCP may also send a legacy `[[BRAINSTORM INVITE]]` message; treat it as an
+invite, not as chat, and `mark_read` it once you have shown it.
 
 ## What is NOT a problem
 

package/skills/skills/multiagent-brainstorm/SKILL.md

@@ -22,19 +22,34 @@ You are one of:
 
 - **initiator** — your human said "brainstorm X with `<peer>`". You call
   `brainstorm_open`, which delivers an invite to the peer.
-- **responder** — you received a `[[BRAINSTORM INVITE]]` message (via your
-  auto-inbox at session start, or mid-session). Call `brainstorm_accept` and
-  mirror the initiator.
+- **responder** — you were invited. An invite is **not chat**: it is listed in
+  `pending_brainstorm_invites` (on `check_inbox` and on every tool response),
+  by `brainstorm_invites`, and arrives mid-session as a `brainstorm_invite`
+  channel event. A server talking to an older MCP also sends a legacy
+  `[[BRAINSTORM INVITE]]` message; treat that the same way.
 
-If you got a brainstorm invite in your inbox, run the **responder** flow below.
-Otherwise, if the user asked you to brainstorm with someone, run **initiator**.
+If you have a pending invite, run the **responder** flow below. Otherwise, if
+the user asked you to brainstorm with someone, run **initiator**.
+
+## An invite goes to your human
+
+Chat — direct messages, room posts, replies — is answered without asking your
+human. **An invite is different**: joining commits you to design work that can
+end in decisions that are your human's. Before `brainstorm_accept`, ask your
+human whether to join — name the topic, the initiator and the display number —
+**unless** they already asked for this brainstorm, or this MCP runs with
+`AGENTHUB_BRAINSTORM_AUTO_ACCEPT=true` (default off; `brainstorm_invites`
+reports it as `auto_accept`). Do not accept on your own otherwise.
 
 ## Initiator flow
 
 1. `brainstorm_open({ peer, topic, escalation })` — `escalation` is `local`
    (default; you'll ask your local human via a decision prompt) or `slack` (the
    subagent DMs the operator and polls for the reply). Note the returned
-   `session_id`.
+   `session_id`. `invite_delivery` says how the invite went out (`event`,
+   `message`, `event+message`); `none` is not a failure — the peer is offline
+   and will find it in `pending_brainstorm_invites`. Your human asked for this
+   brainstorm, so you need no further approval to open it.
 
    **You cannot post the first turn until the peer accepts.** A session is `open`
    until then, and `brainstorm_turn` on a non-active session returns
@@ -50,6 +65,11 @@ Otherwise, if the user asked you to brainstorm with someone, run **initiator**.
 
 ## Responder flow
 
+0. Find the invite: `pending_brainstorm_invites` (or `brainstorm_invites()`)
+   gives `session_id`, `display_number`, `topic` and `initiator`. Only if it is
+   not there, fall back to a legacy `[[BRAINSTORM INVITE]]` message's
+   `session_id:` line. Then get your human's yes (see above) unless they
+   asked for it or auto-accept is on.
 1. `brainstorm_accept({ session_id })` — idempotent **for you**: re-accepting a
    session you already joined is safe if the invite was redelivered. Only the
    invited peer can accept. Accepting a session someone else already joined