Repository navigation
feat: mcp --no-register keeps one-off agents out of the directory - #223
reason-machines[bot] wants to merge 5 commits into
Conversation
Co-authored-by: svemyh <40596752+svemyh@users.noreply.github.com>
Co-authored-by: svemyh <40596752+svemyh@users.noreply.github.com>
…off and honour off folders Agents sharing the cli:tasks mailbox no longer receive each other's replies, one cancelling a wait no longer ends another's, ask_user (one pending question per session) is off in this mode, and a caller whose hooks said its folder is off is refused via the daemon's new OffFor request instead of being sent through the mailbox. Co-authored-by: svemyh <40596752+svemyh@users.noreply.github.com>
…d hook-known off folders Reply instructions to a tasks-mailbox sender name the message they answer (--reply-to / reply_to), so a reply sent as told reaches the agent that asked. Idempotency keys are namespaced per --no-register process, so two agents reusing one key send two messages. OffFor checks an agent known only by its hooks (Gemini, Command Code) by its process, as its hooks noted it in an off folder. check_inbox rechecks cancellation before marking a reply read, and send_message names the mailbox's actual address. Co-authored-by: svemyh <40596752+svemyh@users.noreply.github.com>
…ation retires its process's old off-folder one Co-authored-by: svemyh <40596752+svemyh@users.noreply.github.com>
|
Independent review (GPT-6.1 Sol) found no remaining issues at 14b1867 after three fix rounds; all 8 checks pass. Merge is queued and needs one approving review. After merge, v0.12.18 (version already bumped here) needs its tag pushed by the engine owner to run release.yml. |
|
@svemyh friendly nudge from Feedback resolver: #223 is ready for your approving review. All 8 checks pass on head 14b1867, the independent reviewer (GPT-6.1 Sol) reports no remaining findings, and the squash merge is already requested so it lands as soon as it is approved. After merge, the engine owner pushes |
|
@svemyh friendly reminder: this still needs one approving review to merge. Head 14b1867 passes all 8 checks, has no conflicts, and the independent review (GPT-6.1 Sol) has no remaining findings. It also bumps the version to 0.12.18, so the — Feedback resolver |
Scheduled Claude Desktop tasks start
reason-network mcp, which registers each one-off agent as its own numbered/folder-named session in the team directory, so teammates' agents can route to throwaway workers (feedback from workspace "S Line"). This adds a per-invocation opt-out. Default behaviour is unchanged.What changes
reason-network mcp --no-register(orREASON_NETWORK_NO_REGISTERset, read viapaths::env_var_oslikeNO_SERVICE) skips the startup registration and never registers a session of its own.list_teamcallsWho { me: None }: no registration.send_message/check_inbox/message_status/ask_usergo by one kept mailboxcli:tasks(<you>/tasks, same aslisten --as tasks), shared by all such processes on the machine. Deliberately notterminal: messages from/terminalrender "typed in a terminal", skip the daemon's agent-loop limiter and may message groups;tasksstays an agent sender (groups refused, loop limit applies).check_inboxis never hidden in this mode.--helpshows the flag.tests/mcp_no_register.rs: register-off (flag and env) -> list_team, send, and reply via check_inbox work and the directory holds only alice/role + alice/tasks, no agent session; default -> a-codexsession is registered and is the sender.Checks (Linux cloud machine, stable 1.99.1)
cargo fmt --check: passcargo clippy --all-targets --locked -- -D warnings: passcargo test --locked: pass (341 unit, config_typo 5, install_script 2, mcp_no_register 2)Also bumps Cargo.toml/Cargo.lock to 0.12.18 (as #174–#178 did) so the v0.12.18 tag can be cut from the merge commit.
Not verified here: macOS/Windows (CI covers them).
Review fixes (head d04f411)
An independent review (GPT-6.1 Sol) reproduced four problems with the shared
cli:tasksmailbox. All four are fixed, and each is covered by a test that fails without the fix:check_inboxnow returns (and marks read) only messages whosereply_tois one this process sent. Other mail to<you>/tasksstays forreason-network listen --as tasks.StopWaitingbumps the sharedstop_gen). This mode no longer sendsStopWaiting, so a cancelled wait only stops locally.ask_useris hidden and refused with--no-register.OffFor, applies the same off-folder and BUSY_OFF refusal as registering, without registering anything.Checks (Linux, rustc 1.99.1):
cargo fmt --check: passcargo clippy --all-targets --locked -- -D warnings: passcargo test --locked: pass (341 unit, config_typo 5, install_script 2, mcp_no_register 4)no_register_agents_get_only_their_own_repliesandno_register_keeps_a_session_in_an_off_folder_offFAIL with the fix's src/ changes stashed and PASS with them.Review fixes, round 3 (head 14b1867)
The reviewer re-checked 76c4bc6 and confirmed the earlier fixes (idempotency per process, reply threading, post-peek cancellation check). It then reproduced two more problems, both now fixed:
check_inboxin this mode told the agent to reply withreason-network send … --from alice/tasks, a send this process never saw, so the answer to it was filtered out. It now names the client's ownsend_messagetool, so a follow-up goes through the process and its reply comes back.Checks (Linux, rustc 1.99.1):
cargo fmt --check,cargo clippy --all-targets --locked -- -D warnings,git diff --check: passcargo test --locked: pass (341 unit, config_typo 5, install_script 2, mcp_no_register 8)no_register_follow_ups_sent_as_instructed_get_their_replies(two rounds, following the emitted instructions) andno_register_lets_a_new_conversation_past_an_old_off_one(Gemini hooks: g1 off, then g2 allowed, no end hook) FAIL with this commit's src/ changes stashed and PASS with them.