Commit graph hyperhive/hive-agent-mcp/src/mcp/args.rs
Author SHA1 Message Date
damocles
80f16094f1 hive-sh4re: split inbox, container, journal, and schedule wire shapes into their own modules
Closes the #3110 split — lib.rs is now just the crate doc comment and
the pub mod list.

journal.rs's new doc comment fixes a pre-existing bug: the old
JournalPriority doc text in lib.rs was actually half Capability's doc
(a leftover from an earlier reorder that moved the code but not the
comment above it).
2026-08-10 23:26:15 +02:00
atlas
bed7ae6d5a docs: a config change is a PR from a clone, not an edit in place
Seven places described an authoring flow that does not exist: the
manager editing and committing a child's config in the bind-mounted
config dir. mara, on the snapshot issue: "the pr workflow is the main
one, anything else is legacy … the config dir in agent container is
read only copy to see own config … changes need to go through local
clone and via forge".

Two of the seven are the request_init_config MCP tool description and
its args struct, which are rendered into the system prompt of every
agent holding the approvals tool group. A wrong tool description is not
a stale comment; it is an instruction the whole hive reads as fact,
which is why the claim kept being repeated back.

The init tool creates the repo and seeds it. Nothing else. Tailoring
the seeded template is not a separate mechanism - it is the ordinary
config-change flow, a PR reviewed like any other.

Prose only; the code already implements the PR flow (an approval's
commit_ref is a PR number). Where a doc justified the parent's
read-write mount on the child's config dir with the authoring model,
the justification is removed rather than replaced: that mount is a
defect tracked on its own issue, and it should not read as intentional
while it waits.
2026-08-04 22:40:22 +02:00
damocles
2b5e5a30f4 trim verbose todo-tool descriptions, drop exhaustive subsystem list 2026-08-02 16:41:33 +02:00
damocles
bc69ee3b8f revise bulk-clear to explicit ids per mara's feedback, fix clippy line count 2026-08-02 16:41:33 +02:00
damocles
eb570c003d cap get_loose_ends todo output + add ack_todos_until bulk-clear (#2944) 2026-08-02 16:41:33 +02:00
damocles
ceff662d25 recv: drop wait_seconds from the MCP tool, always an immediate peek 2026-08-02 04:08:14 +02:00
damocles
c4deca99db fix(#2639): cancel_loose_end kind="todo" clears without a bash round-trip
Adds a real MCP-side path for the workaround #2639 documented: dial the
in-container HIVE_AGENT_SOCKET directly from cancel_loose_end (kind:"todo")
instead of shelling out via a tracked bash task (nc -U ...), which is what
was spawning a fresh completion todo on every clear and cascading forever.

hive-agent-mcp/src/mcp/render.rs: renamed local_todos's socket-dial guts
into a shared dial_agent_socket(req) helper, added mark_local_todo_done(id)
on top of it (MarkTodoDone request already existed server-side, unused
until now). mod.rs wires kind:"todo" into cancel_loose_end ahead of the
question/reminder/approval parse. args.rs + render.rs + docs/tools/bash.md
text updated to point at the new path instead of the old raw nc invocation.
2026-07-22 21:46:16 +02:00
damocles
c2bd7db998 refactor(#2416): remove the non-pr config-change flow (request_apply_commit / applycommit) 2026-07-15 21:03:52 +02:00
damocles
e7f8254788 refactor(#2455): split hive-agent-mcp into its own bin crate 2026-07-14 23:49:22 +02:00
Renamed from hive-ag3nt/src/mcp/args.rs (Browse further)