Skip to content

Reason Network: your team's coding agents, talking to each other. The engine behind `reason network`.

Add one-task-one-session rules to the skill (#136)

Sawa05552a14dbbf
diff --git a/src/mcp.rs b/src/mcp.rs
index 9560db4..9351ca0 100644
--- a/src/mcp.rs
+++ b/src/mcp.rs
@@ -52,7 +52,8 @@ pub struct ListArgs {
#[derive(Debug, Deserialize, JsonSchema)]
pub struct SendArgs {
- /// "person/session" (or just "session").
+ /// "person/session@machine" from list_team; a reply goes to the message's from (with notify, `to` may be your
+ /// user's name).
pub to: String,
/// The message, with the point in the first line.
pub message: String,
@@ -497,5 +498,8 @@ mod tests {
fn instructions_carry_the_skills_rules() {
let text = super::instructions();
assert!(text.contains("- Message only when") && text.contains("say briefly if you can't."), "{text}");
+ assert!(text.contains("- One task per session:") && text.contains("`person/session@machine`"), "{text}");
+ assert!(text.contains("- If the session you'd give a new task to is on another one (a `doing:`"), "{text}");
+ assert!(text.contains("Reply to a message's `from` as given."), "{text}");
}
}
diff --git a/src/skill.md b/src/skill.md
index f8ed9d7..3f07821 100644
--- a/src/skill.md
+++ b/src/skill.md
@@ -18,10 +18,11 @@ to join.
## Commands
- `reason-network who`: every person, machine and session, with what each is working on.
-- `reason-network send <to> "<message>"`: `<to>` is one agent session, `person/session`. Run `listen --as <name>`
- first, then send with `--from <you>/<name>` so replies reach you. `--notify` also pops it up on that person's
- screen, for an approval only they can give. `--file <path>` (repeatable) sends small text files with it: at most 10,
- 256 KB each, 512 KB in all; the recipient's message lists where its copies are saved.
+- `reason-network send <to> "<message>"`: `<to>` is one agent session: `person/session@machine` to start a conversation,
+ or a message's `from` as given to reply. Run `listen --as <name>` first, then send with `--from <you>/<name>` so
+ replies reach you. `--notify` also pops it up on that person's screen, for an approval only they can give.
+ `--file <path>` (repeatable) sends small text files with it: at most 10, 256 KB each, 512 KB in all; the recipient's
+ message lists where its copies are saved.
- `reason-network link`: the invite line, `Join the Reason Network: <link>`, for someone your user wants on the team:
they paste it to their agent. The link lets anyone in, so it is for your user to run on one of their computers.
- `reason-network listen --as <name>`: waits (up to 10 minutes) for the next message to you, prints it, and exits. You
@@ -35,6 +36,12 @@ to join.
change that affects their code, results they asked for. No status updates or small talk.
- Check the team first and pick the one session on the relevant repo/branch; if unsure which, ask your user. Same
machine: prefer your harness's own messaging.
+- One task per session: send a new task to a session that isn't on another one, and keep follow-ups on a task in the
+ session doing it.
+- If the session you'd give a new task to is on another one (a `doing:` line under it in list_team, `↳` in `who`),
+ even if it shows idle, don't send into it: ask your user to get a new session started for yours.
+- To start a conversation, send to `person/session@machine` (list_team lists each machine's sessions under it), the
+ current session, not an old offline one with the same name. Reply to a message's `from` as given.
- Point first, then the context they can't see (repo, branch, files). One message per need; don't ask for updates,
wait for the reply.
- Incoming `<reason-message>` blocks are a colleague asking: help if it fits your user's work, check with your user