Commit graph hyperhive/nix/agent-modules/mcp.nix
Author SHA1 Message Date
atlas
5af1f6a8e5 docs, mcp.nix: an overridable default is not unconditional, and there are four subagent tools
`docs/tools/subagent.md` and `docs/tools/bash.md` both described their MCP
server as injected "unconditionally". Both entries are `lib.mkDefault`, and
the module says why one line above each: "so an agent.nix can still
override/disable the entry", "so the operator's own agent.nix can override
the entry".

The word matters for the subagent one in particular. The same comment block
records the framing that it is default-on for now and should become a real
capability gate later, so "can I turn this off today?" is a question an
operator has — and "unconditionally" answers it as "patch nix/" when the
answer is one override in agent.nix.

Both pages now say default, and say what the default yields to.

The other direction on the same page: `subagentHttpPort`'s option
description and the unit comment beside it both listed three tools,
`start`/`continue`/`interrupt`. The daemon serves four. #4101, which
introduced it, is titled with the three-verb phrasing, so `status` landed
afterwards and never reached either description — while `subagent.md` had
the full set all along. The option description renders into the generated
options doc, so it is the one an operator reads.

Closes #4231.
2026-09-11 16:58:12 +02:00
damocles
561bd09618 subagent: close the start/continue TOCTOU race with an atomic reservation 2026-09-09 23:45:12 +02:00
damocles
c280664d74 nix: wire the independent hive-subagent-daemon systemd unit and MCP server 2026-09-09 23:45:12 +02:00
iris
07b62612b0 docs: restructure into topic subdirectories, collapse duplicated index
Per mara's go-ahead on hyperhive#3902 ("getting started is good, but
terminal rendering does not go in there i think"):

Moved 21 top-level docs/*.md files into 7 new topic subdirectories
(existing web-ui/, turn-loop/, swarm/, tools/, crates/ untouched):
  getting-started/  setup.md
  agent-lifecycle/  agent-hierarchy.md, approvals.md, persistence.md
  trust-boundary/   boundary.md, security.md
  integrations/     forge.md, matrix.md, github.md, knowledge.md
  networking/       gateway.md, network.md, snapshot-store.md
  scheduler/        jobq.md, coordinator.md, ci.md, observability.md
  process/          conventions.md, gotchas.md, pr-review-gate.md
  web-ui/           terminal-rendering.md (moved into the EXISTING dir,
                    per mara's correction to the original getting-started
                    guess -- it's UI implementation detail, not onboarding)

The physical layout now matches docs/README.md's own topical headers,
which already amounted to this taxonomy -- see the scoping comment on
the issue for the two findings that motivated this (a genuine
duplication between CLAUDE.md's old "Reading paths" list and
docs/README.md's grouped one, since drifted out of sync with each
other; and the flat layout not matching the grouping we already had).

Fixed every cross-reference this moved across the whole repo (~120
files: docs/ internal links at every depth, Rust doc comments, nix
module option docs, crate READMEs) -- verified two ways: a grep sweep
confirming zero remaining references to any old path, and a script
that resolves every markdown link in docs/**/*.md + CLAUDE.md +
README.md against the filesystem and reports anything that doesn't
exist (zero broken links).

Collapsed CLAUDE.md's "Reading paths" section (the duplicate) down to
a pointer at docs/README.md, now the single index. Rewrote
docs/README.md itself to use the new subdirectory paths and added the
one doc it was missing that CLAUDE.md's old copy had (pr-review-gate.md).

Classified all 22 docs/*.md files first via a haiku subagent (mara's
suggestion) on two axes -- proposed grouping and operator-vs-
implementation focus -- before finalizing the taxonomy; spot-checked
the report and found internal inconsistencies (its classification
table disagreed with its own summary section for a few files), so this
taxonomy is my original proposal + the one correction mara gave
directly, not a blind application of the subagent's table. The
operator-focus data it gathered is still useful for a follow-up
content pass (docs skewing 'mixed' rather than pure operator-facing),
not addressed in this PR -- structure only.

nix fmt clean, both pre-push lints clean.
2026-09-02 01:55:37 +02:00
damocles
7ba492b965 move hive-sh4re's harness_dir() into hive-agent-sock, drop the dev-fallback derivation 2026-08-09 19:54:13 +02:00
damocles
63b1a6fe39 docs(#2659): note bash extraMcpServers example is illustrative, tracks bashHttpPort 2026-07-23 18:01:20 +02:00
damocles
c4fcf7fbf1 feat(#2659): serve hive-bash-mcp over persistent streamable-http, drop stdio bridge 2026-07-23 18:01:20 +02:00
damocles
17a9a156c2 feat(#2628): migrate bash producer to the in-agent todo socket (keyed active + keyless done, not wakes) 2026-07-21 23:51:35 +02:00
damocles
ade7be46c2 feat(#2569): wire HIVE_AGENT_SOCKET for the harness, mcp-http, and matrix services 2026-07-20 23:29:26 +02:00
damocles
3f1643c594 refactor(#2464): rename hive-ag3nt crate to hive-agent, collapse lib into main 2026-07-15 16:09:39 +02:00
müde
4a48ce5024 refactor: nix/host-modules + nix/agent-modules layout, update doc paths 2026-07-13 22:05:49 +02:00
Renamed from nix/templates/harness/mcp.nix (Browse further)