You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit 674c173
Browse filesBrowse the repository at this point in the historyBrowse files
feat(buzz-acp): give each channel thread its own agent session (#6732)
## What this does
In a channel, people often run several unrelated conversations at once
(separate threads). Today the agent treats the whole channel as one
conversation, so unrelated threads share the same running session —
their context bleeds together and independent tasks can step on each
other.
This change gives the agent a **separate session per thread** inside a
channel. Direct messages stay as one conversation (unchanged). The
channel is still the boundary for who is allowed in and what is visible
— only the agent's working context is now split by thread.
## How it is turned on
Off by default. Operators opt in with one setting:
- `BUZZ_ACP_SESSION_POLICY=channel` — default, current behavior
- `BUZZ_ACP_SESSION_POLICY=thread` — new per-thread behavior
Being behind a flag means we can enable it for a few agents, watch how
it behaves, and roll back instantly without a code change.
## Key design decisions
- **Decide the thread once, up front.** When a message arrives we work
out which thread it belongs to a single time and tag it. Everything
after that (which line it waits in, which session runs it, what history
it sees) uses that tag instead of re-guessing later, which avoids
mismatches.
- **Default stays identical to today.** Under the default setting a
"thread" is just "the whole channel," so existing behavior and every
existing test are unchanged. The new, riskier behavior is strictly
opt-in.
- **Give the agent only its thread's history.** On a reply the agent
sees that thread's messages (including ones that did not mention it),
not the whole channel transcript — less noise and smaller prompts.
- **Don't let one channel use more memory than before.** More threads
means more live sessions, so the existing per-channel limit now caps all
of a channel's threads together — splitting into threads can't multiply
how much work is held.
## Bugs found and fixed while iterating (from review)
- **Same thread, two sessions.** If the worker already holding a
thread's session was busy, a new message for that thread could start a
*second* session on another worker and split its history. Now it waits
for the right worker instead of forking.
- **Interrupting the wrong thread.** A follow-up meant for thread A
could interrupt thread B in the same channel. Interrupts now target the
exact thread.
- **Stuck thread after a crash.** If a thread's turn crashed, its slot
wasn't cleared and stayed blocked for up to ~2 hours. It now clears
right away and retries.
- **Lost the original request.** When a thread was interrupted and then
had to wait for a busy worker, only the follow-up was kept and the
original request was dropped. The full request is now preserved on
retry.
- **Same thread seen as two.** Two spellings of the same thread id
(upper/lower case) could be treated as different threads. Normalized so
they count as one.
## Not in this PR
- The desktop Settings toggle and rollout wiring for managed agents —
#6909
- One pre-existing retry edge case (present today without this flag,
unrelated to this change) — tracked separately so this PR stays focused.
## Testing
The full `buzz-acp` test suite passes (830+ unit and integration tests),
plus new focused tests for thread routing, session reuse, interrupt
targeting, crash recovery, and request preservation. Behavior with the
flag off is unchanged.
---------
Signed-off-by: Salman Mohammed <[email protected]>
Signed-off-by: Leo <5faf251baee50ee6bcde338aef6acdd70bb3e60115664c2cd490d94a55dfc488@buzz.block.builderlab.xyz>
Co-authored-by: Leo <5faf251baee50ee6bcde338aef6acdd70bb3e60115664c2cd490d94a55dfc488@buzz.block.builderlab.xyz>
Copy file name to clipboardExpand all lines: crates/buzz-acp/README.md
+9-4Lines changed: 9 additions & 4 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -161,12 +161,17 @@ The gate applies to **all** inbound events — @mentions, DMs, thread replies, a
161
161
| Command | Effect |
162
162
|---------|--------|
163
163
|`!shutdown`| Gracefully exits the harness. |
164
-
|`!cancel`| Cancels the current in-flight turn for that channel, if any. |
165
-
|`!rotate`| Rotates the ACP session for that channel. If a turn is in-flight, it is cancelled and the channel session is invalidated when the task returns; otherwise the cached idle session is invalidated immediately. The next queued/received event starts a fresh session. |
164
+
|`!cancel`| Cancels the current in-flight turn for the command's resolved session scope, if any. |
165
+
|`!rotate`| Rotates the ACP session for the command's resolved session scope. If a turn is inflight, it is cancelled and that scoped session is invalidated when the task returns; otherwise the cached scoped session is invalidated immediately. The next queued/received event in that scope starts a fresh session. |
166
166
167
-
Use `!cancel` to stop only the current turn; it is a no-op when the channel is idle. Use `!rotate` when you want the next turn in the channel to start from a fresh ACP session, even if the channel is currently idle.
167
+
Under the default `channel` policy, a session scope is the whole channel, so these commands retain their channel-wide behavior. Under the `thread` policy, post the command as a reply in the target thread so `!cancel` or `!rotate` affects only that thread. DMs remain one conversation scope. `!cancel`is a no-op when its scope is idle.
168
168
169
-
Owner control commands must be kind:9 stream messages from the owner, must mention this agent with a `p` tag, and are consumed by the harness instead of being forwarded to the agent.
169
+
Owner control commands must be kind:9 stream messages from the owner, must have body exactly `!cancel`, `!rotate`, or `!shutdown` after trimming, and must mention this agent with a separate `p` tag. They are consumed by the harness instead of being forwarded to the agent. An inline `@Name` changes the body and does not match. With the Buzz CLI, target a thread while preserving the exact command body by passing the mention separately:
> **Note:** The default mode is `owner-only`. Agents without a registered `agent_owner_pubkey` will not respond to any events until the owner is resolved. Set `--respond-to anyone` to disable the gate entirely.
Copy file name to clipboardExpand all lines: crates/buzz-acp/src/base_prompt.md
-6Lines changed: 0 additions & 6 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,11 +1,5 @@
1
1
You are operating inside the Buzz platform — a Nostr-based messaging platform for human-agent collaboration. The buzz-acp harness routes channel events to your session.
2
2
3
-
## Session Model
4
-
5
-
You are one per-channel session of your agent identity — not the only copy. Each channel gets its own independent conversation context, and multiple sessions of the same agent may be active in different channels at the same time. Sessions share your core memory, your workspace on disk, and the relay. They do NOT share conversation context, in-progress reasoning, or in-context task state.
6
-
7
-
When a human references work "you" are doing in another channel, that work belongs to a different session of you. Unless the human asks you to take it over or coordinate it from this channel, leave execution with the owning session — answer from what you can verify (core memory, workspace files, relay messages) and assume the owning session has it handled.
8
-
9
3
## Buzz CLI
10
4
11
5
The `buzz` CLI is your primary interface. Auth env vars: `BUZZ_RELAY_URL`, `BUZZ_PRIVATE_KEY`, `BUZZ_AUTH_TAG`. Exit codes: 0 ok, 1 user error, 2 network, 3 auth, 4 other. Output is structured JSON.
0 commit comments