The MCP server instructions string omitted three behaviours added in
earlier PRs, leaving agents without context on them:
- send_file / download_file tools (#1829, #1830)
- [file:]/[image:]/[audio:]/[video:] attachment markers in read_room (#1830)
- unread guard: send_message, send_dm, send_file, send_reply all
reject if the room has unread messages; read_room + mark_read
are required first (#1828)
Closes#1828. Closes#1829. Closes#1830.
Drop 'Phase 3 of the matrix-MCP work' (circular inside the matrix-mcp
crate) + the vague issue-thread pointer; keep the self-contained note
that it mirrors damocles-daemon's v0 set.
Clean the legacy backlog so the tracker-tag lint can become a required
gate (mara's warn-during-cleanup -> full-tree-enforcement path). Rewrite
the ~33 real `closes/see #NNN` provenance refs in doc-comments to prose
across hive-forge, hive-c0re, hive-ag3nt, hive-matrix-mcp, hive-sh4re,
and add a `lint:allow` line marker to check-issue-refs.sh for genuine
non-tracker `#<digits>` (a hash-digit heading-detection test input).
Tree is now lint-clean; tracker-tag lint ready to promote to required.
The nixpkgs bump to clippy 0.1.95 / cargo 1.95.0 added + strengthened a
large batch of lints. CI denied ALL warnings (`-D warnings`) against the
`pedantic = warn` workspace lint, so the bump hard-failed `nix flake
check` workspace-wide with zero code changes — and would recur on every
future clippy bump.
Posture fix (the durable part): CI now runs
`-D warnings -A clippy::pedantic`, so the default/correctness/style lints
stay a hard gate while the "extra, opinionated" pedantic group is
advisory only (still `warn` for local `cargo clippy` via the workspace
lints table, just non-blocking in CI). `-A` rather than `-W` so the
group drop doesn't re-enable the specific pedantic lints the workspace
allows (e.g. `must_use_candidate`).
Also fixes the genuine DEFAULT/STYLE lints the bump surfaced across the
workspace (doc_lazy_continuation, collapsible_if, ptr_arg,
match_like_matches_macro, …) via `cargo clippy --fix` + manual stragglers
(`too_many_arguments` #[allow] on the host-config constructors), and
three tests that had rotted while the CI runner was offline (#1221):
- topology::top_level_agents_in_multi_root — hardcoded unsorted expected
- rebuild_queue::depends_on_evicted_dep_counts_as_resolved — needs
MAX_HISTORY_PER_KIND newer terminals to evict, not one
- coordinator::agent_paths doctest — illustrative pseudo-code, now `ignore`
Validated: clippy + formatting + cargo-test checks all pass.
Adds an invite_user tool to the per-agent matrix MCP so an agent can invite
another user to a room it's already in (e.g. pull a peer into an existing
chat). Mirrors the existing join_room/send_dm wiring:
- protocol.rs: DaemonRequest::InviteUser { room, user_id }
- handlers.rs: invite_user — parse user_id, resolve room, room.invite_user_by_id
- socket.rs: dispatch arm
- bin/mcp.rs: invite_user tool + InviteUserArgs
room accepts an id or alias; the caller must hold a power level high enough
to invite (the homeserver error is surfaced verbatim otherwise). The invitee
then accepts via join_room. allowedTools is already '*' for the matrix server,
so the tool is exposed without a nix change.
when the homeserver rejects the token (stale session after state wipe or
expiry), the daemon now deletes the token file + matrix-sdk state dir
and exits cleanly instead of crash-looping.
hive-c0re's matrix::ensure_all sweep now runs periodically every 30
minutes (in addition to startup) so deleted token files get
re-provisioned without requiring a hive-c0re restart. the systemd.paths
watcher on the token file path then restarts the daemon with a fresh
token.
Write mcp-loose-ends/matrix.json on invite arrival (before wake) and
after join_room clears an invite. The harness scans mcp-loose-ends/
generically in get_loose_ends, so pending invites are visible there
without any harness-side changes.
- paths: add mcp_loose_ends_dir() (mirrors hive-bash-mcp pattern)
- handlers: add refresh_invite_loose_ends() — atomic tmp+rename write
- handlers: join_room calls refresh after successful join to clear entry
- timeline: install_invite_handler refreshes loose-ends before wake
