Watch
0
0
Fork
You've already forked hyperhive
0
hyperhive/hive-matrix-mcp
Repository files (latest commit first)
Filename Latest commit message Latest commit date
atlas 7b1435eaea hive-matrix-mcp: bound each secondary retry, warn once per outage
Three follow-ups to argus's review of #5237:

- A down secondary's retry runs `restore` under RESTORE_TIMEOUT (2 min).
  Tries run one per tick on one future, so a restore that never resolved
  held back every other down account's retries for good; a try that
  outlasts the timeout now counts as a failure like any other.
- `client::build_and_restore` warns about a rejected token only for the
  primary, which exits right after. For a secondary it logs at debug: the
  retry loop already warns once per outage (`DownAccounts::failed` is news
  on the first failure and on a changed reason, and an account that came
  up starts afresh), so the extra warn repeated on every try.
- `a_secondary_that_comes_up_late_does_not_wipe_the_todos` runs the late
  bring-up in a child process of the test binary with HIVE_AGENT_SOCKET
  pointed at the test's listener. In-process the variable was unset, so a
  wipe placed back in the bring-up path was a no-op and the test passed.

New tests: a_second_rejection_in_a_row_does_not_warn_again (captured logs, alone
in a child process since tracing caches callsite interest process-wide;
a stub whoami answering M_UNKNOWN_TOKEN, the real build_and_restore),
a_failure_after_the_account_came_up_is_news_again, and
an_account_whose_restore_hangs_does_not_hold_back_the_others (paused time).
2026-10-15 02:54:09 +02:00
..
src hive-matrix-mcp: bound each secondary retry, warn once per outage 2026-10-15 02:54:09 +02:00
Cargo.toml hive-matrix-mcp: test the secondary retry loop and the registry lock 2026-10-14 16:20:04 +02:00
README.md feat(#2659): serve hive-matrix-mcp over persistent streamable-http, drop stdio bridge 2026-07-24 12:44:39 +02:00

hive-matrix-mcp

Per-agent matrix integration: a long-running daemon (hive-matrix-daemon) that holds a matrix-sdk Client + sync loop per configured account and serves the matrix tool surface (send_message, send_dm, list_rooms, read_room, …) directly over streamable-http. No stdio bridge, no per-turn respawn — claude reconnects to the same stable URL every turn.

When to use it

Look here when changing matrix tool behaviour, multi-account handling, or the incoming-event → todo/wake path. The daemon owns the whole lifecycle: per-account bring-up (accounts.rs, client.rs), the sync loop that sweeps invites/unread rooms into the harness's in-agent todo socket (timeline.rs, wake.rs), and the MCP tool router itself (mcp.rs).

Shape

One bin (hive-matrix-daemon, src/main.rs) built from the crate's own lib (src/lib.rs):

  • accounts.rs — multi-account config + the account→Client dispatch registry (main is always the hive-internal primary; extras come from HIVE_MATRIX_ACCOUNTS).
  • client.rs — session restore, stale-token recovery, avatar sync, cross-signing bootstrap.
  • timeline.rs / wake.rs — per-sync-callback invite/unread sweeps that push todos onto HIVE_AGENT_SOCKET.
  • handlers.rs — per-tool dispatch, returns protocol::DaemonResponse.
  • mcp.rs — the rmcp tool router + serve_http, resolving each call's optional account arg against the registry before calling into handlers.
  • paths.rs — per-agent path resolution (token file, matrix-sdk state dir, homeserver URL, accounts snapshot).