Commit Graph
5 Commits
Author SHA1 Message Date
HermenixandClaude Opus 5 f83717ba71 Merge feat/mcp-server (9708154) into feat/mcp-auth
The base branch moved twelve commits while this work was in flight --
including the per-session live stream and its own contract bump -- so this
integrates rather than leaving a PR nobody can merge.  Six files
conflicted; the interesting resolutions are the two that were not
textual.

**The contract is mcp-v3.1, not v2.1.**  This branch bumped v2 -> v2.1 for
an additive change; `feat/mcp-server` bumped v2 -> v3 for the live stream,
also additive.  Both point releases, both correct, and they cannot both be
the same document.  So v3 stands as written and the HTTP transport is the
point release on top of it, by the same rule each of us applied
independently: v2 is still the only major bump, because it is still the
only one that removed anything.

**The counts are no longer literals.**  This branch asserted `21 tools` and
`5 resources` in `checks/vm-mcp-http.nix` and `5` in `test_mcp_http.py`;
the stream added two tools and one fixed resource, so the surface is 23
and 6.  Rather than re-hardcode numbers that will go stale again, the
check now counts against `--list-tools` and `--list-resources` -- the
server's own table -- and the unit test against `resources.FIXED`.  That
is the lesson 9708154 ("count the unnarrowed resources against the
listing, not a literal") had already learned on the other side of this
merge, arrived at twice.  A stale number here would have failed in a way
indistinguishable from the HTTP transport dropping tools, which is the
one thing those subtests exist to catch.

The rest were additive on both sides and both halves are kept: the TODO
table, the checks wiring, the README check rows, the architecture diagram
(their 23/10 counts with this branch's two-transport annotation).
`nix/module.nix` needed reconstructing -- git interleaved the bodies of
`hhstream-live` and `hhstream-mcp` because both units land between the
same surrounding lines -- so the live unit is taken verbatim and the MCP
unit placed after it, with this branch's options, tmpfiles entry,
firewall rule, two assertions and two warnings re-applied on top.

One thing deliberately NOT touched: the v3 change table cites `§6` for the
idle-clock exception, but the rule it means is `§8`. That is the other
branch's prose and its author's call, not something to quietly rewrite in
a merge.

Verified after resolution: 394 unit tests pass, and the module evaluates
with both units, the right ExecStart, one firewall port and both
warnings.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01KchcvnbfhhZhUHy83YL3Ya
2026-10-12 00:47:14 +00:00
HermenixandClaude Opus 5 8a0c9ca74d fix(mcp): declare the HTTP transport's dependencies, and forbid its tests to skip
`starlette` and `uvicorn` arrive through the MCP SDK today -- measured,
both of them -- and relying on that is exactly the trap this project
already wrote down twice.  `src/hhstream_mcp/pyproject.toml` declares
`anyio` rather than taking it for granted through the SDK because
`server.py` uses it by name; `http.py` imports `uvicorn` by name and sits
on Starlette's `Request` through the SDK's `TransportSecuritySettings`,
so both belong in the metadata on the same argument.  An SDK release that
moved its HTTP transport behind an optional extra would otherwise break
`serve --http` with an ImportError naming somebody else's package.
`nix/mcp.nix` carries them for the same reason.

The worse half was in the gate.  `tests/unit/test_mcp_http.py` opened
with `pytest.importorskip("starlette.testclient")`, which is the pattern
`checks/unit.nix`'s own comment argues against in as many words: "a file
that skipped when the SDK was absent would be green in exactly the build
where that mattered".  It would not skip today -- `mcp` propagates
starlette and httpx -- but the day it did, 43 tests would leave the gate
and nothing would say so, because pytest exits 0 when every test was
skipped.

So the import is unconditional now, `checks/unit.nix` declares `starlette`
and `httpx` explicitly, and the check proves them importable before
pytest runs, beside the lines that already do that for `hhstream` and the
tool table.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01KchcvnbfhhZhUHy83YL3Ya
2026-10-11 22:49:44 +00:00
HermenixandClaude Opus 5 5f5726c02e feat(mcp): the stream, as two tools and two resources
The split mcp-v2 froze, applied to the stream: switching one on is an act, so
it is a tool; what is being published is state, so it is a resource. 23 tools
and 10 resources.

Tools: `session_stream_enable` (returns the URL, takes an optional `phrase` and
`fps`), `session_stream_disable`, and `session_start` gains `stream`,
`stream_phrase` and `stream_fps` -- the last because a stream needs the
container output that starting creates, so one call is the shape an agent
actually wants.

Resources: `hhstream://streams` (every stream, with `available` so "no streams"
is not confused with "no daemon") and `hhstream://sessions/{id}/stream`.

What the descriptions carry is the part that matters here, because an agent
reads them and nothing else:

* **CREDENTIAL.** The phrase in the URL is the stream's only protection. The
  resource descriptions say outright not to put the URL where a session's own
  screen can see it -- an agent that pastes it into the browser it is driving
  has published the desktop.
* **ACTIVITY.** The stream tools do *not* reset the idle clock, but a connected
  viewer does, which is the first exception to that rule this surface has had
  to state. `session_touch` is still the only thing an agent can do about it.
* `session_start`'s summary prints `stream url:` beside the id, and a stream
  that could not be opened is reported loudly as `stream: NOT enabled -- …`,
  because the call succeeded and an agent must not read that as a stream.

`nix/mcp.nix` counts the new surface in `entryPointCheckPhase` (23 and 10),
which is the only place those numbers are asserted against the *wrapped* binary.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_011ZeH65zd6pFTgBSu52W9PE
2026-10-11 22:48:45 +00:00
HermenixandClaude Opus 5 0a63c9b7fc feat(mcp)!: state as resources, acts as tools, and --toolsets for the rest
BREAKING: `status`, `session_list`, `session_status`, `session_logs` and
`pointer_state` are no longer tools. They are `hhstream://…` resources. 26
tools became 21, and eight resources appeared beside them.

The reason is the split the protocol itself draws, which the first cut ignored.
A resource is **application**-controlled context: the host decides what to put
in front of the model, and "what is on this machine right now" is the host's
question. A tool is **model**-controlled: an act the model chooses to perform.
Nothing in those five verbs acts. So the line between the halves is *who
decides*, not what a call costs.

    hhstream://status                     text, the units and the frame socket
    hhstream://sessions          {?all}   the broker's own list object
    hhstream://pointer                    the lease holder, buttons and keys
    hhstream://containers                 every container, plus the orphans
    hhstream://screen                     a frame, as an image blob
    hhstream://sessions/{id}     {?events}
    hhstream://sessions/{id}/logs {?lines}
    hhstream://outputs/{name}             one output's frame, as a blob

What did *not* move is the interesting part. `shot` and `record` stay tools
though neither changes the desktop: capturing is an act at a moment, and an
agent in a loop has to be able to decide to look *now* -- in many clients a
resource is something a person attaches rather than something a model can
fetch. The same frames are readable as `hhstream://screen` and
`hhstream://outputs/{name}` as well, for a host that wants one in context
itself. `session_container` stays a tool for a harder reason: with an id the
CLI runs `container.reconcile`, which writes the record back, so it is not a
read at all. Only the no-id listing is a resource. **A resource read must never
write**, and `resources.py` says so where it would be tempting.

Three consequences worth naming:

* A refusal cannot be content. `ReadResourceResult` has no `isError`, so a CLI
  refusal is raised as `-32602` with the same remedy text in `message` and the
  same `{ok, exit_code, error, reason, hint, remedy}` in `data`. Returning the
  broker's failure object as the *body* would make "no such session" read as a
  successful read of a session.
* Arguments become query parameters, and only declared ones are accepted -- for
  the reason every tool schema sets `additionalProperties: false`. A parameter
  silently ignored is a read that answered a different question.
* A v1 tool name is told where it went: `session_list` comes back with "It is a
  RESOURCE now ... read hhstream://sessions instead". "No such tool" alone
  reads as a broken server rather than a moved surface.

`--toolsets frames,sessions,pointer,keyboard` lands with it, because 21 flat
tools is the same problem one size smaller. There is **no grouping primitive in
MCP** -- `Tool` carries name, title, description, inputSchema, outputSchema,
icons, annotations, _meta and execution, and nowhere to put a family -- so the
only honest lever is which tools the *server* lists, chosen at launch. An
unknown name is argparse's exit 2, never a silently empty server, and a tool
outside the selection is unreachable rather than merely unlisted. Resources are
deliberately not filtered by it: they are the host's context, not the model's
budget.

`--list-resources` joins `--list-tools`; both are in the package's own
entry-point check, with `--toolsets` beside them.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_011ZeH65zd6pFTgBSu52W9PE
2026-10-11 11:49:46 +00:00
HermenixandClaude Opus 5 549c73e8ae feat(nix): hhstream-mcp as its own derivation, and an option to install it
`packages.hhstream-mcp` (`nix/mcp.nix`), separate from `packages.hhstream` and
the separation is the point: the frame socket, the CLI and the broker are
stdlib-only by policy, the MCP SDK is a third-party dependency, and
`packages.hhstream` runs as the compositor's own units. Verified: the hhstream
closure gains no `mcp`, no `pydantic` and no `httpx`, and `hhstream_mcp` is not
in its site-packages.

The join to `hhstream` is a *library* one -- `toPythonModule`, because the
tools call `hhstream.cli`'s handlers in process. `grim` and `ffmpeg` are
prefixed onto the wrapper's PATH, because the CLI spawns them and the server is
launched by an MCP client whose PATH is not ours to predict.

The entry point is smoke-tested with `--list-tools` in a `postPhases` phase,
not `postInstall`: the script is wrapped in `fixupPhase`, so any earlier and
the check runs against a script with no PYTHONPATH and tests the wrong thing.
(`installCheckPhase` is no use either -- `buildPythonPackage` does not include
that phase at all.)

`services.hyprland-headless-stream.mcp.enable` (default false) puts the binary
on the system PATH, which is the whole of the option: the server is stdio and
spawned per client, so there is no unit, no socket and no state directory.
`mcp.package` defaults to this flake's build against `cfg.package`, so the
server and the CLI it runs are one build. A warning, not an assertion, when it
is enabled with `sessions.enable` off: 22 of the 26 tools then answer exit 5,
but the four frame tools are genuinely useful alone.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_011ZeH65zd6pFTgBSu52W9PE
2026-10-11 06:32:34 +00:00