## Summary Raven's host acts as the user's agent manager: it delegates production work, including small edits, to the agent whose ownership or description fits the task -- or, on a turn bound to a Worker Table, to the worker whose brief covers it -- keeps track of the task and its instance, routes follow-ups back to that instance, and gathers the results for the user. Its own tools support briefing, checking and coordination. - Add the resident `multi-agent-coding` skill for choosing coding agents, keeping one instance per task, passing results by file, isolating concurrent edits in worktrees, and handing over work when an agent exhausts its quota. - Keep the new host role authoritative in both the DAG skill's resident description and its full guide. A single task uses `spawn`, or a one-node graph when only the DAG dispatch path is available. - Rename the generic sub-agent to `Raven-General`, with `Raven` and `raven` retained as compatibility aliases. Instance records, handle locks, live activity, cancellation, preferences and RPC lookups use the same canonical identity. Historical spawn and DAG readers normalize names before liveness checks and serialization, so tasks and transcripts join the current instance roster. Concurrent alias calls preserve both turns instead of overwriting one conversation snapshot. The instance registry reads former-name rows under the current name and, on its next write, saves every loaded row under it; transcripts, direct chats and stored graphs stay as written. - Resolve built-in configuration aliases before merging fields: `Raven-General` wins over `Raven`, then `raven`, regardless of file order. Discard older rows wholesale with a warning, preventing stale model, permission or transport settings from leaking into the selected row. - Resume the most recently written message state and instance log across former names. Saved messages take precedence over an empty chat directory; equal timestamps prefer the current name and then the most recent former name. Existing files stay in place. Legacy spawn records, completed DAG manifests and unfinished graphs remain readable through the current name. - Emit the agent roster once at the end of `spawn`'s description. The registry places `run_subagent_dag` and then `spawn` last, including after late MCP or session tools. The graph tool renders the roster itself when `spawn` is unavailable. With a Worker Table bound, dispatch guidance selects worker labels from the live enum; the roster explains underlying capabilities. The tool descriptions and resident DAG guide follow the same rule. - On a turn bound to a Worker Table, such as a Persona session, `spawn` and the DAG nodes offer worker labels alone, and a generated Persona never includes the generic agent. The host role on such a turn routes production work to the worker whose brief covers it, by label, and puts work no worker covers to the user, who can add a worker or give the conversation another Harness, instead of doing it itself or naming an agent outside the enum. Ordinary turns render byte for byte as before. A Harness that `load_playbook` binds mid-turn takes effect after the identity was assembled, so that call's result carries the same routing as this system's trusted note, after the untrusted fence. The coding skill picks worker labels on such a turn, for its first pick and for a quota takeover. ## Type - [ ] Fix - [x] Feature - [ ] Docs - [ ] CI / tooling - [ ] Refactor - [ ] Other ## Verification Measured at this head on Linux/Python 3.12.13. - `UV_NO_SYNC=1 uv run --no-sync pytest -q -n 12`: **33,767 passed, 178 skipped, 2 xfailed; 9 failed and 1 error.** Eight of the failures are bound to this box and fail the same way on current main, measured the same day: five provider tests that read the box's proxy environment, a Node.js path case, a LibreOffice conversion, and a fixture that root can read anyway. The ninth, with its teardown error, is the `remote_runs` race tracked in #990; that test passed 5 of 5 runs alone, and its file 58 of 58. - 13 new regression tests for Worker Table routing: 12 fail against the previous head's source and all pass now; the thirteenth checks that a Harness loaded mid-turn leaves the next turn's role plain, and passes on both by design. The end-to-end case drives a real Persona-bound turn: both enums offer `research-a` alone, dispatching `Raven-General` is refused, and the role must name neither that agent nor the roster fallback. - Nine single-construct mutants, each applied to an isolated copy of the tree, each fail at least one new test: the role ignoring the table, the default path not reading the turn's table, the uncovered-work rule removed, the generic fallback kept in the worker routing, the coding skill reverted, and the mid-turn note never added, added on every call, added without a dispatch path, or phrased apart from the role. - The host identity on ordinary turns is byte-identical to the previous head in all 16 rendered shapes: a launched sub-agent process or not, with or without ownership lines, and every combination of the two dispatch tools. - Instance registry probe, run with this head and with main on one synthetic file: reads leave the file byte-identical; one unrelated `upsert_spawn` saves every former-name row as `Raven-General`, keeping the more recently updated of two colliding spellings and the later one in the file on a tie; main then finds none of those rows under `Raven` or `raven`. - `uv run --no-sync python scripts/coverage_gate.py --coverage-json <coverage.json> diff --base-ref origin/main --threshold 90`, over a coverage run of 225 test files (8,952 passed): **99.40%**, 167/168 executable changed lines covered. - `UV_NO_SYNC=1 make lint-types lint-imports check-large-files check-source-language COMMIT_RANGE=origin/main...HEAD`: passed; all 10 import contracts kept. - `UV_NO_SYNC=1 make check-commits`: both commit-message validators passed; each also refused a dangling control commit with a malformed subject. - `ruff check` and `ruff format --check` over the branch's Python files passed. `node ui-tui/scripts/gen-i18n.mjs --check` passed after the rebase onto #1015, which also changed the i18n catalogue. - `uv run --no-sync pre-commit run --from-ref origin/main --to-ref HEAD`: every hook passed except the whole-TUI Prettier hook, which reports only `newInstancePicker.tsx` and `subagentsHub.tsx`; both are byte-identical to current main. - Live-model replay and native Windows/macOS testing were not repeated for these fixes. - [x] Relevant tests pass locally - [x] Relevant lint / type checks pass locally - [x] User-facing docs or screenshots are updated when needed ## Risk - The host delegates work it previously performed itself, including small scripts. Task-to-instance routing remains prompt-based; a task can still stay with the host after it has already answered a follow-up itself. - In a conversation bound to a Persona or another Harness with workers, work no worker's brief covers now waits for the user to add a worker or change the conversation's Harness, rather than being carried out by the host. - Old agent spellings remain accepted. The instance registry's first write after the upgrade, of any row for any session, saves every former-name row in `subagent_instances.json` as `Raven-General`, and keeps only the more recently updated row where two spellings of one instance collide. Builds from before the rename cannot look those rows up, so reverting the squash commit alone does not restore their instance bindings: that needs the registry file as it stood before that first write. Renaming rows back by hand cannot recover a colliding row the write dropped. Transcripts, direct chats and stored graphs are not rewritten. - When multiple generic-agent configuration spellings coexist, only the newest row contributes overrides. Fields supplied exclusively by an older row are intentionally discarded. - Moving the dispatch tools changes the tool-array cache prefix once after upgrade. - A plugin participant that removes `spawn` through `select_tools` can still leave the graph tool pointing at an absent roster, because that selection occurs after the registry's offer check. No bundled participant does this. - [x] Security impact considered - [x] Backward compatibility considered - [x] Rollback path is clear for risky changes ## Related Issues N/A
117 lines
4.8 KiB
Python
117 lines
4.8 KiB
Python
"""How the host lays out the two tools that hand work to sub-agents.
|
|
|
|
``spawn`` and ``run_subagent_dag`` pick from one roster, and it used to be
|
|
rendered into both descriptions -- 566 tokens each on a real install, paid twice
|
|
on every model call. It is rendered once now, as the end of the tool array:
|
|
``spawn`` is listed last and its description ends with the roster, and
|
|
``run_subagent_dag``, listed just before it, points there. With ``spawn``
|
|
switched off the graph tool is the one left to say it, so it does.
|
|
|
|
Asserted through the assembled array, because that is what a turn sends. The
|
|
halves have their own files: ``test_tool_registry_order.py`` for the placement,
|
|
the spawn and DAG description tests for the wording.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
from pathlib import Path
|
|
|
|
from raven.agent.loop.main import AgentLoop
|
|
from raven.agent.subagent.backends import format_agent_listing
|
|
from raven.config.schema import ThirdPartyCliSubagentConfig
|
|
from tests._wiring import wire
|
|
|
|
|
|
class _StubProvider:
|
|
"""Construction reads the default model; no turn is ever run here."""
|
|
|
|
def get_default_model(self) -> str:
|
|
return "stub-model"
|
|
|
|
async def chat_with_retry(self, **kwargs): # pragma: no cover - never invoked
|
|
raise NotImplementedError
|
|
|
|
|
|
def _write_switches(path: Path, names: list[str]) -> None:
|
|
path.write_text(json.dumps({"tools": {"disabledTools": names}}), encoding="utf-8")
|
|
|
|
|
|
def _loop(tmp_path: Path, monkeypatch, *, disabled: list[str] | None = None) -> AgentLoop:
|
|
cfg = tmp_path / "config.json"
|
|
_write_switches(cfg, disabled or [])
|
|
monkeypatch.setattr("raven.home._current_config_path", cfg)
|
|
agents = [
|
|
ThirdPartyCliSubagentConfig(
|
|
name="Scribe", command="scribe {prompt}", description='turns a "source" document into a deck'
|
|
),
|
|
ThirdPartyCliSubagentConfig(name="Surveyor", command="survey {prompt}", description="reads the live web"),
|
|
]
|
|
return AgentLoop(provider=_StubProvider(), workspace=tmp_path / "ws", **wire(agents=agents))
|
|
|
|
|
|
def _functions(loop: AgentLoop) -> list[dict]:
|
|
return [d["function"] for d in loop.tools.get_definitions()]
|
|
|
|
|
|
def _roster(loop: AgentLoop) -> str:
|
|
roster = format_agent_listing(loop.subagents.list_agents())
|
|
assert "Scribe" in roster and "Surveyor" in roster
|
|
return roster
|
|
|
|
|
|
def _times_in_the_array(loop: AgentLoop, text: str) -> int:
|
|
# Counted in the serialized array, the form a provider is sent, so a copy
|
|
# hiding in a parameter description counts as much as one in a description.
|
|
serialized = json.dumps(loop.tools.get_definitions(), ensure_ascii=False)
|
|
return serialized.count(json.dumps(text, ensure_ascii=False)[1:-1])
|
|
|
|
|
|
class TestTheRosterIsSaidOnceAtTheEnd:
|
|
def test_the_two_dispatch_tools_close_the_array(self, tmp_path: Path, monkeypatch) -> None:
|
|
names = [fn["name"] for fn in _functions(_loop(tmp_path, monkeypatch))]
|
|
|
|
assert names[-2:] == ["run_subagent_dag", "spawn"]
|
|
|
|
def test_spawn_s_description_ends_with_it(self, tmp_path: Path, monkeypatch) -> None:
|
|
loop = _loop(tmp_path, monkeypatch)
|
|
|
|
assert _functions(loop)[-1]["description"].endswith(_roster(loop) + ".")
|
|
|
|
def test_nothing_else_in_the_array_repeats_it(self, tmp_path: Path, monkeypatch) -> None:
|
|
loop = _loop(tmp_path, monkeypatch)
|
|
|
|
assert _times_in_the_array(loop, _roster(loop)) == 1
|
|
|
|
def test_the_graph_tool_points_there_and_its_enum_still_names_every_agent(
|
|
self, tmp_path: Path, monkeypatch
|
|
) -> None:
|
|
loop = _loop(tmp_path, monkeypatch)
|
|
dag = _functions(loop)[-2]
|
|
|
|
assert "the roster at the end of the `spawn` tool's description" in dag["description"]
|
|
node = dag["parameters"]["properties"]["nodes"]["items"]["properties"]
|
|
assert set(node["subagent"]["enum"]) == set(loop.subagents.registry.names())
|
|
|
|
|
|
class TestWithSpawnSwitchedOffTheGraphToolSaysItItself:
|
|
def test_the_graph_tool_closes_the_array_with_the_roster(self, tmp_path: Path, monkeypatch) -> None:
|
|
loop = _loop(tmp_path, monkeypatch, disabled=["spawn"])
|
|
functions = _functions(loop)
|
|
|
|
assert "spawn" not in [fn["name"] for fn in functions]
|
|
assert functions[-1]["name"] == "run_subagent_dag"
|
|
assert functions[-1]["description"].endswith(_roster(loop) + ".")
|
|
assert _times_in_the_array(loop, _roster(loop)) == 1
|
|
|
|
def test_and_points_again_once_spawn_is_back(self, tmp_path: Path, monkeypatch) -> None:
|
|
"""Asked per assembly, like the switch itself: a graph tool that kept the
|
|
roster after spawn came back would put the second copy back on every call."""
|
|
loop = _loop(tmp_path, monkeypatch, disabled=["spawn"])
|
|
_write_switches(tmp_path / "config.json", [])
|
|
|
|
functions = _functions(loop)
|
|
|
|
assert functions[-1]["name"] == "spawn"
|
|
assert _times_in_the_array(loop, _roster(loop)) == 1
|