Raven-1/tests/test_subagent_instance_log.py
Dizhan Xue 14edd7bdb2
feat(*): run the host as an agent manager that hands work, coding included, to sub-agents (#1010)
## 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
2026-10-20 17:56:05 +08:00

165 lines
7.4 KiB
Python

"""build_turn is the one recipe for a finished turn's message rows."""
from __future__ import annotations
import json
import os
from pathlib import Path
import pytest
from raven.agent.subagent.instance_log import (
append_turn,
build_turn,
instance_root,
instance_title,
open_instance_log,
transcript_path,
)
from raven.config.agent_names import GENERIC_AGENT
def test_turn_is_prompt_then_work_then_answer() -> None:
turn = build_turn(
prompt="read the readme",
messages=[{"role": "assistant", "content": "looking"}],
answer="there is no readme",
)
assert [row["role"] for row in turn] == ["user", "assistant", "assistant"]
assert turn[0]["content"] == "read the readme"
assert turn[-1]["content"] == "there is no readme"
def test_rows_built_by_turn_are_timestamped() -> None:
turn = build_turn(prompt="hi", answer="hello")
assert len(turn) == 2
assert all(row["timestamp"] for row in turn)
def test_messages_rows_pass_through_with_or_without_timestamp() -> None:
# Transcript producers attach a timestamp only when the underlying event
# carries a wall clock. Rows arriving without one are legitimate.
row_with_timestamp = {"role": "assistant", "content": "x", "timestamp": "2026-01-01T00:00:00"}
row_without_timestamp = {"role": "assistant", "content": "y"}
turn = build_turn(prompt="ask", messages=[row_with_timestamp, row_without_timestamp])
assert turn[1] == row_with_timestamp
assert turn[2] == row_without_timestamp
def test_non_dict_messages_are_dropped() -> None:
turn = build_turn(prompt="hi", messages=["not a dict", {"role": "tool", "content": "x"}]) # type: ignore[list-item]
assert [row["role"] for row in turn] == ["user", "tool"]
def test_error_is_recorded_as_a_failed_answer() -> None:
turn = build_turn(prompt="hi", error="boom")
assert turn[-1]["role"] == "assistant"
assert turn[-1]["content"] == "[failed] boom"
def test_omitted_parts_add_no_rows() -> None:
assert build_turn() == []
assert [row["role"] for row in build_turn(messages=[{"role": "tool", "content": "x"}])] == ["tool"]
def test_append_turn_writes_exactly_what_build_turn_returns(tmp_path: Path) -> None:
# The whole point of the extraction: the payload handed to everos and the
# rows written to the log must be the same turn, or the memory would
# describe a conversation no file on disk agrees with.
kwargs = {
"prompt": "read the readme",
"messages": [{"role": "assistant", "content": "looking"}],
"answer": "there is no readme",
}
append_turn(tmp_path, agent="Coder", handle="h1", session_key="s1", kind="spawn", **kwargs)
written = [
json.loads(line)
for line in transcript_path(tmp_path, "Coder", "h1").read_text(encoding="utf-8").splitlines()
if line.strip()
]
rows = [row for row in written if row.get("_type") != "metadata"]
expected = build_turn(**kwargs)
assert [(r["role"], r["content"]) for r in rows] == [(e["role"], e["content"]) for e in expected]
def test_an_instance_is_named_before_it_has_said_anything(tmp_path: Path) -> None:
# The title used to arrive with the first turn, and the first turn is
# written when the dispatch *finishes*. Every surface that heads a panel by
# what the instance was dispatched for therefore fell back to the handle --
# an id -- for exactly as long as the run was still going.
open_instance_log(tmp_path, agent="Coder", handle="h1", session_key="s1", kind="spawn", title="Draft a deck")
assert instance_title(tmp_path, "Coder", "h1") == "Draft a deck"
def test_opening_an_instance_twice_writes_one_header(tmp_path: Path) -> None:
# An instance is reached through several lanes and a later dispatch of the
# same handle joins its conversation. It must not rename it, and must not
# leave a second metadata row in the middle of the file.
open_instance_log(tmp_path, agent="Coder", handle="h1", session_key="s1", kind="spawn", title="first")
open_instance_log(tmp_path, agent="Coder", handle="h1", session_key="s1", kind="dag", title="second")
append_turn(tmp_path, agent="Coder", handle="h1", session_key="s1", kind="dag", prompt="go", answer="done")
written = [
json.loads(line)
for line in transcript_path(tmp_path, "Coder", "h1").read_text(encoding="utf-8").splitlines()
if line.strip()
]
assert [row.get("_type") for row in written].count("metadata") == 1
assert instance_title(tmp_path, "Coder", "h1") == "first"
def test_an_unnamed_instance_still_opens(tmp_path: Path) -> None:
# A direct chat has no line saying what the instance is for, and must not
# invent one -- but the header it opens is still the file's first row.
open_instance_log(tmp_path, agent="Coder", handle="h1", session_key="s1", kind="chat")
assert transcript_path(tmp_path, "Coder", "h1").is_file()
assert instance_title(tmp_path, "Coder", "h1") == ""
def test_an_instance_logged_under_a_former_name_keeps_its_file(tmp_path: Path) -> None:
"""The generic agent was renamed without moving the logs written before. A
continued instance appends where its earlier turns are, rather than opening a
second file under the new name that the viewer would show as a new instance."""
legacy = instance_root(tmp_path, "Raven") / "h1.jsonl"
legacy.parent.mkdir(parents=True)
legacy.write_text(json.dumps({"_type": "metadata", "metadata": {"title": "Draft"}}) + "\n", encoding="utf-8")
assert transcript_path(tmp_path, GENERIC_AGENT, "h1") == legacy
append_turn(tmp_path, agent=GENERIC_AGENT, handle="h1", session_key="s1", kind="spawn", prompt="go", answer="ok")
assert not instance_root(tmp_path, GENERIC_AGENT).exists()
assert "ok" in legacy.read_text(encoding="utf-8")
@pytest.mark.parametrize("latest", ["raven", "Raven"])
def test_two_legacy_transcripts_choose_the_latest_write_for_every_alias(tmp_path: Path, latest: str) -> None:
older = instance_root(tmp_path, "raven") / "h1.jsonl"
newer = instance_root(tmp_path, "Raven") / "h1.jsonl"
older.parent.mkdir(parents=True)
newer.parent.mkdir(parents=True, exist_ok=True)
if older.parent.samefile(newer.parent):
pytest.skip("Two casing generations require a case-sensitive filesystem")
for path, title in ((older, "Older"), (newer, "Newer")):
path.write_text(json.dumps({"_type": "metadata", "metadata": {"title": title}}) + "\n", encoding="utf-8")
chosen = older if latest == "raven" else newer
other = newer if latest == "raven" else older
for path in (older, newer):
stamp = 2_000_000_000 if path == chosen else 1_000_000_000
os.utime(path, ns=(stamp, stamp))
for name in (GENERIC_AGENT, "Raven", "raven"):
assert transcript_path(tmp_path, name, "h1") == chosen
assert instance_title(tmp_path, name, "h1") == ("Older" if latest == "raven" else "Newer")
append_turn(tmp_path, agent=name, handle="h1", session_key="s1", answer=name)
assert len(chosen.read_text(encoding="utf-8").splitlines()) == 4
assert len(other.read_text(encoding="utf-8").splitlines()) == 1
def test_a_new_instance_is_logged_under_the_current_name(tmp_path: Path) -> None:
open_instance_log(tmp_path, agent="Raven", handle="old", session_key="s1", kind="spawn", title="Draft")
assert transcript_path(tmp_path, GENERIC_AGENT, "fresh").parent == instance_root(tmp_path, GENERIC_AGENT)