Jaroslav Beneš
816f2ae957
Six smaller things, all of them about the interface not saying what is true.
The @ button only ever inserted the character, which the @ key already does
without a button. It becomes the scope menu: what this chat may use, switched
off per chat. Chat.scope_json is filtered inside resolve_tools AFTER the
capability, permission and instance gates -- exactly as chat.knowledge_bases
narrows knowledge_search -- so a crafted POST turning something on reaches a
tool the gates already removed, and there is a test that writes the column
directly to prove it. Absent means on, for every key, so "why is this off?" has
one answer. It is keyed on the gate rather than the tool name, so notes is one
switch rather than five. The switches carry no role="menuitem", deliberately:
ui.js closes a picker when a menuitem is clicked, which is right for an action
menu and wrong for a list you want to set several of -- which is why the menu
needs no JavaScript at all. Typing @ is untouched.
With no skills, nothing should mention them. tool.skills was gated on the family
alone, so somebody with an empty library was told "the list below gives each
one's name" above no list, handed skill_get, and watched the model spend a round
finding out. It requires skills now; the writing half moved to
tool.skills_write, which is deliberately not gated, because saving the first one
is what somebody with none most needs. And core.tool_list finally reads
tool_names, which had been resolved and documented with no fragment using it.
The composer's toolbar is one row again. .composer__actions is last in the DOM
with margin-left:auto, so the moment an agent chat added a connection, a
directory and a mode, Send and the microphone dropped to a second line.
chat.css has no media queries by design and the fix is not to add one:
.composer__context is the single child allowed to shrink and scroll sideways.
There is a test asserting the file still contains no @media.
The effort picker shows the level in force. "Effort: default" named no level and
was true of nothing in particular; chat.resolved_effort is the chat's own value
and build_request reads the same field, so what is shown is what is sent. The
model's default is a seed, copied onto the row at creation and on a model
change, and never consulted at request time -- a fallback would resurrect it
underneath a cleared effort and make "off" silently do nothing. "off" is a
sentinel and not an empty value, because start_chat declares Form("") and cannot
tell absent from empty: with value="" the reader picks off and gets high.
Alt+M dictates, Alt+R reads the last reply aloud, Ctrl+Enter sends from
anywhere. All three click the button that already does the job, so audio.js
keeps its one delegated listener. Alt+M and not Alt+D, which is the address bar
in Chrome and Firefox. Ctrl+Enter never means Stop -- Send and Stop are the same
element, and Esc already stops. Driven under a DOM stub before committing, per
the rule in CLAUDE.md, and tests/test_commands_js.py pins that every key has a
row in SHORTCUTS, since /help reads that list.
And the memory tooling, which had seven defects. The worst: memory_forget was a
case-insensitive substring first-match delete with nothing warning about it, so
forgetting "coffee" against "Drinks coffee black" and "Allergic to coffee"
silently removed whichever was older -- a wrong deletion nobody would ever find
out about, from a tool whose description invited exactly the short fragment that
misfires. It matches exactly first, then by substring, and refuses an ambiguous
one while naming what it matched. add() refuses an exact duplicate. The
at-the-limit refusal no longer tells the model to delete one to make room: past
the block's budget it is not shown all of them and would be guessing, which
feeds straight back into the first defect. And context.memories no longer claims
the memories "still apply", which nothing checks and which taught a model to
trust a stale one over what the person had just said.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
1090 lines
40 KiB
Python
1090 lines
40 KiB
Python
"""The agent tools: when they are offered, and what stops them running.
|
|
|
|
Everything here goes through a real SSH server on 127.0.0.1, so the gate and the
|
|
approval loop are exercised against something that genuinely executes rather
|
|
than a stub that always agrees.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import asyncio
|
|
import json as _json
|
|
import time
|
|
|
|
import pytest
|
|
|
|
from lembas.db.models import (
|
|
KIND_AGENT,
|
|
ROLE_ASSISTANT,
|
|
Chat,
|
|
Connection,
|
|
Message,
|
|
Model,
|
|
SshProfile,
|
|
User,
|
|
)
|
|
from lembas.services import generation as generation_service
|
|
from lembas.services import interaction, settings_store
|
|
from lembas.services import tools as tools_service
|
|
from lembas.services.agent import policy, session
|
|
from lembas.services.agent import ssh as ssh_service
|
|
|
|
asyncssh = pytest.importorskip("asyncssh")
|
|
|
|
|
|
# --- A machine to act on --------------------------------------------------------
|
|
class _Server(asyncssh.SSHServer):
|
|
def begin_auth(self, username: str) -> bool:
|
|
return False
|
|
|
|
|
|
async def _handler(process):
|
|
command = process.command or ""
|
|
process.stdout.write(f"ran: {command}\n")
|
|
process.exit(0)
|
|
|
|
|
|
@pytest.fixture
|
|
async def machine(tmp_path):
|
|
"""A real sshd, and a profile pointing at it with its key already pinned."""
|
|
project = tmp_path / "project"
|
|
project.mkdir()
|
|
|
|
server = await asyncssh.create_server(
|
|
_Server,
|
|
"127.0.0.1",
|
|
0,
|
|
server_host_keys=[asyncssh.generate_private_key("ssh-ed25519")],
|
|
process_factory=_handler,
|
|
sftp_factory=True,
|
|
)
|
|
port = next(iter(server.sockets)).getsockname()[1]
|
|
line, fingerprint = await ssh_service.capture_host_key("127.0.0.1", port)
|
|
try:
|
|
yield {"port": port, "host_key": line, "fingerprint": fingerprint, "dir": str(project)}
|
|
finally:
|
|
server.close()
|
|
await server.wait_closed()
|
|
|
|
|
|
def _setup(db, user_id, machine, *, mode=policy.MODE_MANUAL, enabled=True, kind=KIND_AGENT):
|
|
"""An agent chat pointed at the machine, with the feature switched on."""
|
|
settings_store.update(db, {"enabled": enabled}, key=settings_store.AGENTS)
|
|
|
|
profile = SshProfile(
|
|
owner_id=user_id,
|
|
name="Test box",
|
|
host="127.0.0.1",
|
|
port=machine["port"],
|
|
username="tester",
|
|
host_key=machine["host_key"],
|
|
host_fingerprint=machine["fingerprint"],
|
|
default_dir=machine["dir"],
|
|
)
|
|
db.add(profile)
|
|
db.commit()
|
|
|
|
connection = Connection(name="c", base_url="http://127.0.0.1:1", api_key_encrypted="")
|
|
db.add(connection)
|
|
db.commit()
|
|
db.add(
|
|
Model(
|
|
connection_id=connection.id,
|
|
model_id="m",
|
|
capabilities_json={"tools": True},
|
|
)
|
|
)
|
|
db.commit()
|
|
|
|
chat = Chat(
|
|
user_id=user_id,
|
|
model_id="m",
|
|
connection_id=connection.id,
|
|
kind=kind,
|
|
ssh_profile_id=profile.id,
|
|
project_dir=machine["dir"],
|
|
agent_mode=mode,
|
|
)
|
|
db.add(chat)
|
|
db.commit()
|
|
return chat, profile
|
|
|
|
|
|
def _offered(db, chat, user) -> set[str]:
|
|
return set(tools_service.resolve_tools(db, chat, user).by_name)
|
|
|
|
|
|
# --- The gate --------------------------------------------------------------------
|
|
async def test_the_agent_tools_are_offered_to_an_agent_chat(db, user_id, machine):
|
|
chat, _profile = _setup(db, user_id, machine)
|
|
names = _offered(db, chat, db.get(User, user_id))
|
|
|
|
assert {"shell_run", "file_read", "file_write", "file_list"} <= names
|
|
|
|
|
|
async def test_an_ordinary_chat_gets_none_of_them(db, user_id, machine):
|
|
"""A plain conversation can never shell out, whatever it is asked."""
|
|
chat, _profile = _setup(db, user_id, machine, kind="chat")
|
|
assert "shell_run" not in _offered(db, chat, db.get(User, user_id))
|
|
|
|
|
|
async def test_nothing_is_offered_while_the_feature_is_off(db, user_id, machine):
|
|
chat, _profile = _setup(db, user_id, machine, enabled=False)
|
|
assert "shell_run" not in _offered(db, chat, db.get(User, user_id))
|
|
|
|
|
|
async def test_nothing_is_offered_without_the_permission(db, user_id, machine):
|
|
chat, _profile = _setup(db, user_id, machine)
|
|
user = db.get(User, user_id)
|
|
user.role = "user" # administrators pass everything
|
|
settings_store.update(db, {"default_permissions": {"tools.agent": False}})
|
|
db.commit()
|
|
|
|
assert "shell_run" not in _offered(db, chat, user)
|
|
|
|
|
|
async def test_nothing_is_offered_without_the_model_capability(db, user_id, machine):
|
|
chat, _profile = _setup(db, user_id, machine)
|
|
model = db.scalar(tools_service.select(Model))
|
|
model.capabilities_json = {"tools": True, "tool_agent": False}
|
|
db.commit()
|
|
|
|
assert "shell_run" not in _offered(db, chat, db.get(User, user_id))
|
|
|
|
|
|
async def test_a_disabled_connection_takes_the_tools_away(db, user_id, machine):
|
|
"""Offering a tool that fails on its first call is worse than not offering
|
|
it, so every "no" collapses to an empty list."""
|
|
chat, profile = _setup(db, user_id, machine)
|
|
profile.enabled = False
|
|
db.commit()
|
|
|
|
assert "shell_run" not in _offered(db, chat, db.get(User, user_id))
|
|
|
|
|
|
async def test_somebody_elses_connection_is_not_reachable(db, user_id, machine):
|
|
from lembas.security.passwords import hash_password
|
|
|
|
chat, profile = _setup(db, user_id, machine)
|
|
intruder = User(name="Sam", email="s@shire.test", password_hash=hash_password("x"))
|
|
intruder.role = "user"
|
|
db.add(intruder)
|
|
db.commit()
|
|
|
|
assert session.resolve(db, chat, intruder) is None
|
|
|
|
|
|
# --- Running something -----------------------------------------------------------
|
|
async def test_a_command_runs_on_the_machine(db, user_id, machine):
|
|
chat, _profile = _setup(db, user_id, machine, mode=policy.MODE_AUTO)
|
|
user = db.get(User, user_id)
|
|
resolved = tools_service.resolve_tools(db, chat, user)
|
|
context = tools_service.context_for(db, user, chat, tools=resolved)
|
|
|
|
outcome = await tools_service.run_tool(
|
|
context, "shell_run", '{"command": "echo hello"}'
|
|
)
|
|
assert outcome.event["status"] == "ok"
|
|
assert "echo hello" in outcome.content
|
|
|
|
|
|
async def test_files_are_written_and_read_back(db, user_id, machine, tmp_path):
|
|
chat, _profile = _setup(db, user_id, machine, mode=policy.MODE_AUTO)
|
|
user = db.get(User, user_id)
|
|
resolved = tools_service.resolve_tools(db, chat, user)
|
|
context = tools_service.context_for(db, user, chat, tools=resolved)
|
|
|
|
await tools_service.run_tool(
|
|
context, "file_write", '{"path": "note.txt", "content": "a mallorn tree"}'
|
|
)
|
|
assert (tmp_path / "project" / "note.txt").read_text() == "a mallorn tree"
|
|
|
|
read = await tools_service.run_tool(context, "file_read", '{"path": "note.txt"}')
|
|
assert "mallorn" in read.content
|
|
|
|
listed = await tools_service.run_tool(context, "file_list", "{}")
|
|
assert "note.txt" in listed.content
|
|
|
|
|
|
# --- Changing part of a file -------------------------------------------------------
|
|
def _context(db, user_id, machine, **kwargs):
|
|
chat, _profile = _setup(db, user_id, machine, mode=policy.MODE_AUTO, **kwargs)
|
|
user = db.get(User, user_id)
|
|
resolved = tools_service.resolve_tools(db, chat, user)
|
|
return tools_service.context_for(db, user, chat, tools=resolved)
|
|
|
|
|
|
async def test_editing_a_file_that_was_not_read_is_refused(db, user_id, machine, tmp_path):
|
|
"""Both halves matter. The wording is what the model acts on; that nothing
|
|
was written is the actual guarantee."""
|
|
(tmp_path / "project" / "note.txt").write_text("alpha\nbeta\n")
|
|
context = _context(db, user_id, machine)
|
|
|
|
outcome = await tools_service.run_tool(
|
|
context,
|
|
"file_edit",
|
|
_json.dumps({"path": "note.txt", "patch": "@@ -1,2 +1,2 @@\n alpha\n-beta\n+BETA\n"}),
|
|
)
|
|
|
|
assert outcome.content.startswith("Read the file first!")
|
|
assert outcome.event["status"] == "error"
|
|
assert (tmp_path / "project" / "note.txt").read_text() == "alpha\nbeta\n"
|
|
|
|
|
|
async def test_reading_then_editing_writes_the_new_text(db, user_id, machine, tmp_path):
|
|
(tmp_path / "project" / "note.txt").write_text("alpha\nbeta\ngamma\n")
|
|
context = _context(db, user_id, machine)
|
|
|
|
await tools_service.run_tool(context, "file_read", '{"path": "note.txt"}')
|
|
outcome = await tools_service.run_tool(
|
|
context,
|
|
"file_edit",
|
|
_json.dumps(
|
|
{"path": "note.txt", "patch": "@@ -1,3 +1,3 @@\n alpha\n-beta\n+BETA\n gamma\n"}
|
|
),
|
|
)
|
|
|
|
assert outcome.event["status"] == "ok"
|
|
assert (tmp_path / "project" / "note.txt").read_text() == "alpha\nBETA\ngamma\n"
|
|
|
|
|
|
async def test_a_relative_and_an_absolute_path_are_the_same_file(db, user_id, machine, tmp_path):
|
|
"""`./note.txt` read and `note.txt` edited has to count as having read it,
|
|
or the check refuses the very thing it was meant to permit."""
|
|
target = tmp_path / "project" / "note.txt"
|
|
target.write_text("alpha\nbeta\n")
|
|
context = _context(db, user_id, machine)
|
|
|
|
await tools_service.run_tool(context, "file_read", '{"path": "./note.txt"}')
|
|
outcome = await tools_service.run_tool(
|
|
context,
|
|
"file_edit",
|
|
_json.dumps({"path": str(target), "patch": "@@ -1,2 +1,2 @@\n alpha\n-beta\n+BETA\n"}),
|
|
)
|
|
|
|
assert outcome.event["status"] == "ok", outcome.content
|
|
|
|
|
|
async def test_a_failed_hunk_names_it_and_writes_nothing(db, user_id, machine, tmp_path):
|
|
(tmp_path / "project" / "note.txt").write_text("alpha\nbeta\n")
|
|
context = _context(db, user_id, machine)
|
|
|
|
await tools_service.run_tool(context, "file_read", '{"path": "note.txt"}')
|
|
outcome = await tools_service.run_tool(
|
|
context,
|
|
"file_edit",
|
|
_json.dumps({"path": "note.txt", "patch": "@@ -1,2 +1,2 @@\n nope\n-wrong\n+x\n"}),
|
|
)
|
|
|
|
assert outcome.event["status"] == "error"
|
|
assert "Hunk 1" in outcome.content
|
|
assert (tmp_path / "project" / "note.txt").read_text() == "alpha\nbeta\n"
|
|
|
|
|
|
async def test_a_write_counts_as_having_read_it(db, user_id, machine, tmp_path):
|
|
"""`_run_write` reads the old content for its diff anyway, so write-then-edit
|
|
works in one reply without a second round trip."""
|
|
context = _context(db, user_id, machine)
|
|
|
|
await tools_service.run_tool(
|
|
context, "file_write", '{"path": "new.txt", "content": "one\\ntwo\\n"}'
|
|
)
|
|
outcome = await tools_service.run_tool(
|
|
context,
|
|
"file_edit",
|
|
_json.dumps({"path": "new.txt", "patch": "@@ -1,2 +1,2 @@\n one\n-two\n+TWO\n"}),
|
|
)
|
|
|
|
assert outcome.event["status"] == "ok", outcome.content
|
|
assert (tmp_path / "project" / "new.txt").read_text() == "one\nTWO\n"
|
|
|
|
|
|
async def test_the_read_set_survives_an_approval(db, user_id, machine, tmp_path):
|
|
"""`as_approved` is `dataclasses.replace`, which copies field *references*,
|
|
so the set is shared with the per-call copy a runner actually gets. That is
|
|
wanted, and it is not obvious enough to leave unpinned."""
|
|
from dataclasses import replace
|
|
|
|
(tmp_path / "project" / "note.txt").write_text("alpha\nbeta\n")
|
|
context = _context(db, user_id, machine)
|
|
approved = replace(context, agent=context.agent.as_approved())
|
|
|
|
await tools_service.run_tool(approved, "file_read", '{"path": "note.txt"}')
|
|
|
|
assert context.agent.read_paths, "the read done under approval is not visible"
|
|
|
|
|
|
async def test_an_edit_that_changes_nothing_says_so(db, user_id, machine, tmp_path):
|
|
(tmp_path / "project" / "note.txt").write_text("alpha\nbeta\n")
|
|
context = _context(db, user_id, machine)
|
|
|
|
await tools_service.run_tool(context, "file_read", '{"path": "note.txt"}')
|
|
outcome = await tools_service.run_tool(
|
|
context,
|
|
"file_edit",
|
|
_json.dumps({"path": "note.txt", "patch": "@@ -1,2 +1,2 @@\n alpha\n-beta\n+beta\n"}),
|
|
)
|
|
|
|
assert outcome.event["status"] == "ok"
|
|
assert "changes nothing" in outcome.content
|
|
|
|
|
|
# --- The diff on the event ------------------------------------------------------------
|
|
async def test_an_edit_carries_a_diff(db, user_id, machine, tmp_path):
|
|
(tmp_path / "project" / "note.txt").write_text("alpha\nbeta\ngamma\n")
|
|
context = _context(db, user_id, machine)
|
|
|
|
await tools_service.run_tool(context, "file_read", '{"path": "note.txt"}')
|
|
outcome = await tools_service.run_tool(
|
|
context,
|
|
"file_edit",
|
|
_json.dumps(
|
|
{"path": "note.txt", "patch": "@@ -1,3 +1,3 @@\n alpha\n-beta\n+BETA\n gamma\n"}
|
|
),
|
|
)
|
|
|
|
diff = outcome.event["diff"]
|
|
assert "-beta" in diff
|
|
assert "+BETA" in diff
|
|
|
|
|
|
async def test_writing_a_new_file_shows_it_as_all_additions(db, user_id, machine):
|
|
"""Which is what git does, and the right display."""
|
|
context = _context(db, user_id, machine)
|
|
|
|
outcome = await tools_service.run_tool(
|
|
context, "file_write", '{"path": "fresh.txt", "content": "one\\ntwo\\n"}'
|
|
)
|
|
|
|
body = [
|
|
line
|
|
for line in outcome.event["diff"].split("\n")
|
|
if line and not line.startswith(("@@", "+++", "---"))
|
|
]
|
|
assert body and all(line.startswith("+") for line in body), body
|
|
|
|
|
|
async def test_overwriting_a_file_shows_what_changed(db, user_id, machine, tmp_path):
|
|
(tmp_path / "project" / "note.txt").write_text("alpha\nbeta\n")
|
|
context = _context(db, user_id, machine)
|
|
|
|
outcome = await tools_service.run_tool(
|
|
context, "file_write", '{"path": "note.txt", "content": "alpha\\nBETA\\n"}'
|
|
)
|
|
|
|
assert "-beta" in outcome.event["diff"]
|
|
assert "+BETA" in outcome.event["diff"]
|
|
|
|
|
|
async def test_a_file_too_big_to_read_is_written_without_a_diff(db, user_id, machine, tmp_path):
|
|
"""A truncated original would invent deletions of the tail, which is worse
|
|
than showing no diff at all."""
|
|
from lembas.services import settings_store as store
|
|
|
|
store.update(db, {"max_output_bytes": 1024}, key=store.AGENTS)
|
|
(tmp_path / "project" / "big.txt").write_text("x" * 4000)
|
|
context = _context(db, user_id, machine)
|
|
|
|
outcome = await tools_service.run_tool(
|
|
context, "file_write", '{"path": "big.txt", "content": "small"}'
|
|
)
|
|
|
|
assert outcome.event["status"] == "ok"
|
|
assert "diff" not in outcome.event
|
|
|
|
|
|
async def test_writing_a_file_drops_the_project_listing(db, user_id, machine):
|
|
"""Otherwise the model is shown a five-minute-old tree that it knows is
|
|
wrong, and concludes the file it has just created does not exist.
|
|
|
|
The TTL is for drift nobody can see coming. This is not that: it is this
|
|
process changing the tree it has just described.
|
|
"""
|
|
from lembas.services.agent import index as index_service
|
|
|
|
chat, profile = _setup(db, user_id, machine, mode=policy.MODE_AUTO)
|
|
user = db.get(User, user_id)
|
|
resolved = tools_service.resolve_tools(db, chat, user)
|
|
context = tools_service.context_for(db, user, chat, tools=resolved)
|
|
|
|
index_service._CACHE[(profile.id, machine["dir"])] = index_service.ProjectIndex(
|
|
paths=("stale.txt",), total=1, source="git", built_at=time.monotonic()
|
|
)
|
|
|
|
await tools_service.run_tool(
|
|
context, "file_write", '{"path": "fresh.txt", "content": "hi"}'
|
|
)
|
|
|
|
assert index_service.cached(profile.id, machine["dir"]) is None
|
|
|
|
|
|
# --- The runner backstop ----------------------------------------------------------
|
|
async def test_a_runner_refuses_what_the_mode_forbids(db, user_id, machine):
|
|
"""`_authorise` is the real gate and runs first. This is the belt to that
|
|
brace: a call arriving by some other path -- a retry, a re-run button --
|
|
must not walk past it."""
|
|
chat, _profile = _setup(db, user_id, machine, mode=policy.MODE_PLAN)
|
|
user = db.get(User, user_id)
|
|
resolved = tools_service.resolve_tools(db, chat, user)
|
|
context = tools_service.context_for(db, user, chat, tools=resolved)
|
|
|
|
outcome = await tools_service.run_tool(context, "shell_run", '{"command": "rm -rf /"}')
|
|
assert outcome.event["status"] == "error"
|
|
assert "not allowed" in outcome.content.lower()
|
|
|
|
|
|
async def test_plan_mode_still_reads(db, user_id, machine, tmp_path):
|
|
(tmp_path / "project" / "readme.txt").write_text("contents")
|
|
chat, _profile = _setup(db, user_id, machine, mode=policy.MODE_PLAN)
|
|
user = db.get(User, user_id)
|
|
resolved = tools_service.resolve_tools(db, chat, user)
|
|
context = tools_service.context_for(db, user, chat, tools=resolved)
|
|
|
|
outcome = await tools_service.run_tool(context, "file_read", '{"path": "readme.txt"}')
|
|
assert outcome.event["status"] == "ok"
|
|
assert "contents" in outcome.content
|
|
|
|
|
|
async def test_edit_mode_writes_but_will_not_run(db, user_id, machine):
|
|
chat, _profile = _setup(db, user_id, machine, mode=policy.MODE_EDIT)
|
|
user = db.get(User, user_id)
|
|
resolved = tools_service.resolve_tools(db, chat, user)
|
|
context = tools_service.context_for(db, user, chat, tools=resolved)
|
|
|
|
wrote = await tools_service.run_tool(
|
|
context, "file_write", '{"path": "x.txt", "content": "hi"}'
|
|
)
|
|
assert wrote.event["status"] == "ok"
|
|
|
|
ran = await tools_service.run_tool(context, "shell_run", '{"command": "ls"}')
|
|
assert ran.event["status"] == "error"
|
|
|
|
|
|
# --- The approval card in the loop -------------------------------------------------
|
|
def _chunk(name: str, arguments: str, *, call_id="c1", index=0):
|
|
return {
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"tool_calls": [
|
|
{
|
|
"index": index,
|
|
"id": call_id,
|
|
"function": {"name": name, "arguments": arguments},
|
|
}
|
|
]
|
|
}
|
|
}
|
|
]
|
|
}
|
|
|
|
|
|
def _text(text: str) -> dict:
|
|
return {"choices": [{"delta": {"content": text}}]}
|
|
|
|
|
|
def _stub_stream(rounds, seen):
|
|
async def stream_chat(_endpoint, payload):
|
|
seen.append(payload)
|
|
for chunk in rounds[min(len(seen) - 1, len(rounds) - 1)]:
|
|
yield chunk
|
|
|
|
return stream_chat
|
|
|
|
|
|
async def _until_paused(generation, *, timeout: float = 3.0):
|
|
deadline = asyncio.get_running_loop().time() + timeout
|
|
while asyncio.get_running_loop().time() < deadline:
|
|
if generation.pending is not None:
|
|
return generation.pending
|
|
await asyncio.sleep(0.01)
|
|
raise AssertionError("the reply never paused for approval")
|
|
|
|
|
|
def _pending_reply(db, chat):
|
|
db.add(Message(chat_id=chat.id, role="user", content="do it", complete=True))
|
|
db.commit()
|
|
assistant = Message(chat_id=chat.id, role=ROLE_ASSISTANT, content="", complete=False)
|
|
db.add(assistant)
|
|
db.commit()
|
|
return assistant.id
|
|
|
|
|
|
async def test_a_command_waits_for_approval_and_the_card_shows_it(
|
|
db, user_id, machine, monkeypatch
|
|
):
|
|
chat, _profile = _setup(db, user_id, machine, mode=policy.MODE_MANUAL)
|
|
message_id = _pending_reply(db, chat)
|
|
monkeypatch.setattr(
|
|
generation_service,
|
|
"stream_chat",
|
|
_stub_stream(
|
|
[[_chunk("shell_run", '{"command": "rm -rf /tmp/x"}')], [_text("Done.")]], []
|
|
),
|
|
)
|
|
|
|
generation = generation_service.Generation(chat_id=chat.id, message_id=message_id)
|
|
task = asyncio.create_task(generation_service._run(generation))
|
|
pending = await _until_paused(generation)
|
|
|
|
assert pending.kind == interaction.KIND_APPROVAL
|
|
item = pending.items[0]
|
|
# The exact command, verbatim. A card that paraphrased it would be
|
|
# approving something other than what runs.
|
|
assert item.detail == "rm -rf /tmp/x"
|
|
assert "Test box" in item.title
|
|
assert "Manual" in item.reason
|
|
|
|
pending.resolve(interaction.DENY)
|
|
await task
|
|
|
|
|
|
async def test_denying_reaches_the_model_as_words_and_runs_nothing(
|
|
db, user_id, machine, monkeypatch, tmp_path
|
|
):
|
|
chat, _profile = _setup(db, user_id, machine, mode=policy.MODE_MANUAL)
|
|
message_id = _pending_reply(db, chat)
|
|
payloads: list[dict] = []
|
|
monkeypatch.setattr(
|
|
generation_service,
|
|
"stream_chat",
|
|
_stub_stream(
|
|
[
|
|
[_chunk("file_write", '{"path": "never.txt", "content": "nope"}')],
|
|
[_text("Understood.")],
|
|
],
|
|
payloads,
|
|
),
|
|
)
|
|
|
|
generation = generation_service.Generation(chat_id=chat.id, message_id=message_id)
|
|
task = asyncio.create_task(generation_service._run(generation))
|
|
pending = await _until_paused(generation)
|
|
pending.resolve(interaction.DENY)
|
|
await task
|
|
|
|
turns = [m for m in payloads[1]["messages"] if m.get("role") == "tool"]
|
|
assert "declined" in turns[0]["content"].lower()
|
|
# And it says not to look for another way round, because a model reads
|
|
# "not allowed" as "not allowed like that" otherwise.
|
|
assert "another way" in turns[0]["content"]
|
|
assert not (tmp_path / "project" / "never.txt").exists()
|
|
|
|
|
|
async def test_allowing_runs_it(db, user_id, machine, monkeypatch, tmp_path):
|
|
chat, _profile = _setup(db, user_id, machine, mode=policy.MODE_MANUAL)
|
|
message_id = _pending_reply(db, chat)
|
|
payloads: list[dict] = []
|
|
monkeypatch.setattr(
|
|
generation_service,
|
|
"stream_chat",
|
|
_stub_stream(
|
|
[
|
|
[_chunk("file_write", '{"path": "yes.txt", "content": "written"}')],
|
|
[_text("Done.")],
|
|
],
|
|
payloads,
|
|
),
|
|
)
|
|
|
|
generation = generation_service.Generation(chat_id=chat.id, message_id=message_id)
|
|
task = asyncio.create_task(generation_service._run(generation))
|
|
pending = await _until_paused(generation)
|
|
pending.resolve(interaction.ALLOW)
|
|
await task
|
|
|
|
assert (tmp_path / "project" / "yes.txt").read_text() == "written"
|
|
|
|
|
|
async def test_auto_mode_never_pauses(db, user_id, machine, monkeypatch, tmp_path):
|
|
chat, _profile = _setup(db, user_id, machine, mode=policy.MODE_AUTO)
|
|
message_id = _pending_reply(db, chat)
|
|
monkeypatch.setattr(
|
|
generation_service,
|
|
"stream_chat",
|
|
_stub_stream(
|
|
[
|
|
[_chunk("file_write", '{"path": "auto.txt", "content": "no asking"}')],
|
|
[_text("Done.")],
|
|
],
|
|
[],
|
|
),
|
|
)
|
|
|
|
generation = generation_service.Generation(chat_id=chat.id, message_id=message_id)
|
|
await asyncio.wait_for(generation_service._run(generation), timeout=10)
|
|
|
|
assert generation.pending is None
|
|
assert (tmp_path / "project" / "auto.txt").read_text() == "no asking"
|
|
|
|
|
|
async def test_the_credential_is_cleared_when_the_reply_ends(db, user_id, machine, monkeypatch):
|
|
"""A finished Generation lingers five minutes so late followers get the
|
|
final frames. A private key should not linger with it."""
|
|
chat, _profile = _setup(db, user_id, machine, mode=policy.MODE_AUTO)
|
|
message_id = _pending_reply(db, chat)
|
|
|
|
captured = {}
|
|
original = tools_service.context_for
|
|
|
|
def capture(*args, **kwargs):
|
|
context = original(*args, **kwargs)
|
|
captured["context"] = context
|
|
return context
|
|
|
|
monkeypatch.setattr(tools_service, "context_for", capture)
|
|
monkeypatch.setattr(
|
|
generation_service, "stream_chat", _stub_stream([[_text("Nothing to do.")]], [])
|
|
)
|
|
|
|
generation = generation_service.Generation(chat_id=chat.id, message_id=message_id)
|
|
await generation_service._run(generation)
|
|
|
|
assert captured["context"].agent is not None
|
|
assert captured["context"].agent.spec == {}, "the decrypted credential is dropped"
|
|
|
|
|
|
# --- The harness has to be able to name the machine ---------------------------
|
|
def test_the_registry_maps_the_agent_tools_to_their_family(db):
|
|
"""`harness._families` maps an offered tool *name* back to a family to
|
|
decide which fragments apply, and it has no chat to resolve against. Without
|
|
the agent tools listed here, `shell_run` resolves to no family and an agent
|
|
chat is told nothing about the machine it is working on -- the same omission
|
|
that cost custom tools their guidance once already."""
|
|
book = tools_service.registry(db)
|
|
for name in ("shell_run", "file_read", "file_write", "file_list"):
|
|
assert name in book, name
|
|
assert book[name].family == "agent"
|
|
|
|
|
|
async def test_the_harness_says_where_and_under_what_rules(db, user_id, machine):
|
|
from lembas.services import harness
|
|
|
|
chat, _profile = _setup(db, user_id, machine, mode=policy.MODE_MANUAL)
|
|
user = db.get(User, user_id)
|
|
offered = tools_service.resolve_tools(db, chat, user).schemas
|
|
text = harness.compose(db, user, offered, chat)
|
|
|
|
assert "Test box" in text, "which machine"
|
|
assert machine["dir"] in text, "which directory"
|
|
assert "Manual" in text, "what the mode permits"
|
|
# The single most likely cause of "the agent seems stupid": `cd build`
|
|
# followed by `make` fails silently otherwise.
|
|
assert "fresh shell" in text
|
|
|
|
|
|
async def test_an_ordinary_chat_is_told_none_of_it(db, user_id, machine):
|
|
from lembas.services import harness
|
|
|
|
chat, _profile = _setup(db, user_id, machine, kind="chat")
|
|
user = db.get(User, user_id)
|
|
offered = tools_service.resolve_tools(db, chat, user).schemas
|
|
text = harness.compose(db, user, offered, chat)
|
|
|
|
assert "Test box" not in text
|
|
assert "fresh shell" not in text
|
|
|
|
|
|
async def test_an_agent_chat_is_told_its_real_round_budget(db, user_id, machine):
|
|
"""MAX_ROUNDS is one. An agent chat gets hundreds, and telling it one would
|
|
be a false fact about its own budget on every turn."""
|
|
from lembas.services import harness
|
|
|
|
settings_store.update(db, {"max_steps": 25}, key=settings_store.AGENTS)
|
|
chat, _profile = _setup(db, user_id, machine)
|
|
user = db.get(User, user_id)
|
|
values = harness.context_variables(
|
|
db, user, tools_service.resolve_tools(db, chat, user).schemas, chat
|
|
)
|
|
assert values["max_rounds"] == "25"
|
|
|
|
|
|
async def test_an_agent_chat_gets_the_rounds_it_was_promised(db, user_id, machine, monkeypatch):
|
|
"""And is then allowed to use them, which is the half that was missing.
|
|
|
|
The budget sizes the loop and names itself in the out-of-rounds message, and
|
|
the harness above tells the model the same number. But the comparison that
|
|
ends the loop read the global `MAX_ROUNDS` of three. So an agent chat
|
|
allowed forty rounds stopped after three and reported that it had taken
|
|
forty: two wrong answers to "why did it stop", with no way to tell them
|
|
apart from the outside.
|
|
"""
|
|
settings_store.update(db, {"max_steps": 5}, key=settings_store.AGENTS)
|
|
chat, _profile = _setup(db, user_id, machine, mode=policy.MODE_AUTO)
|
|
assistant = Message(chat_id=chat.id, role=ROLE_ASSISTANT, content="", complete=False)
|
|
db.add(assistant)
|
|
db.commit()
|
|
|
|
payloads: list[dict] = []
|
|
|
|
async def stream_chat(_endpoint, payload):
|
|
payloads.append(payload)
|
|
yield {
|
|
"choices": [
|
|
{"delta": {"tool_calls": [{"index": 0, "id": "c1", "function": {
|
|
"name": "file_list", "arguments": '{"path": "."}'}}]}}
|
|
]
|
|
}
|
|
|
|
monkeypatch.setattr(generation_service, "stream_chat", stream_chat)
|
|
|
|
async def _no_title(*_args, **_kwargs):
|
|
return ""
|
|
|
|
monkeypatch.setattr("lembas.services.chat.generate_title", _no_title)
|
|
|
|
generation = generation_service.Generation(chat_id=chat.id, message_id=assistant.id)
|
|
await generation_service._run(generation)
|
|
|
|
# Five rounds that may call tools, then the one that gives up.
|
|
assert len(payloads) == 6
|
|
assert "after 5 rounds" in generation.tool_events[-1]["error"]
|
|
|
|
|
|
async def test_a_reply_stops_when_it_has_written_too_much(db, user_id, machine, monkeypatch):
|
|
"""The bound that is meant to end a long piece of work.
|
|
|
|
Steps are a runaway backstop now (200), so something has to say when enough
|
|
has been written. Asserted on the loop, not on the wording: the count of
|
|
requests must be far short of the step budget.
|
|
"""
|
|
settings_store.update(
|
|
db, {"max_steps": 200, "max_completion_tokens": 40}, key=settings_store.AGENTS
|
|
)
|
|
chat, _profile = _setup(db, user_id, machine, mode=policy.MODE_AUTO)
|
|
message_id = _pending_reply(db, chat)
|
|
|
|
payloads: list[dict] = []
|
|
monkeypatch.setattr(
|
|
generation_service,
|
|
"stream_chat",
|
|
_stub_stream(
|
|
[[_text("x" * 400), _chunk("file_list", '{"path": "."}')]],
|
|
payloads,
|
|
),
|
|
)
|
|
|
|
async def _no_title(*_args, **_kwargs):
|
|
return ""
|
|
|
|
monkeypatch.setattr("lembas.services.chat.generate_title", _no_title)
|
|
|
|
generation = generation_service.Generation(chat_id=chat.id, message_id=message_id)
|
|
await generation_service._run(generation)
|
|
|
|
assert len(payloads) < 5, "it should have stopped long before the step backstop"
|
|
assert "tokens" in generation.tool_events[-1]["error"]
|
|
|
|
|
|
async def test_the_token_ceiling_fires_on_an_endpoint_that_reports_no_usage(
|
|
db, user_id, machine, monkeypatch
|
|
):
|
|
"""The half that would otherwise be silently broken.
|
|
|
|
`generation.completion_tokens` is only populated when the endpoint sends a
|
|
usage block, and llama.cpp, Ollama and friends never do -- the fallback
|
|
estimate is computed once, in `_run`'s `finally:`, long after the loop that
|
|
needs it. A ceiling reading only the reported figure would work on OpenAI
|
|
and do nothing at all everywhere else. The stub above sends no usage, so
|
|
this asserts the estimate path directly.
|
|
"""
|
|
settings_store.update(
|
|
db, {"max_steps": 200, "max_completion_tokens": 40}, key=settings_store.AGENTS
|
|
)
|
|
chat, _profile = _setup(db, user_id, machine, mode=policy.MODE_AUTO)
|
|
message_id = _pending_reply(db, chat)
|
|
|
|
payloads: list[dict] = []
|
|
monkeypatch.setattr(
|
|
generation_service,
|
|
"stream_chat",
|
|
_stub_stream([[_text("y" * 400), _chunk("file_list", '{"path": "."}')]], payloads),
|
|
)
|
|
|
|
async def _no_title(*_args, **_kwargs):
|
|
return ""
|
|
|
|
monkeypatch.setattr("lembas.services.chat.generate_title", _no_title)
|
|
|
|
generation = generation_service.Generation(chat_id=chat.id, message_id=message_id)
|
|
await generation_service._run(generation)
|
|
|
|
assert not any("usage" in str(p) for p in payloads), "the stub reports no usage"
|
|
assert "tokens" in generation.tool_events[-1]["error"]
|
|
|
|
|
|
async def test_a_zero_ceiling_means_no_ceiling(db, user_id, machine, monkeypatch):
|
|
"""Zero is how an administrator says "no limit", the same as index_chars.
|
|
Read with `or 0` on the wrong side it would silently become 200_000."""
|
|
settings_store.update(db, {"max_completion_tokens": 0}, key=settings_store.AGENTS)
|
|
chat, _profile = _setup(db, user_id, machine, mode=policy.MODE_AUTO)
|
|
user = db.get(User, user_id)
|
|
context = session.resolve(db, chat, user)
|
|
assert context.limits.completion_tokens == 0
|
|
|
|
|
|
# --- Interjecting while it works --------------------------------------------------
|
|
async def test_a_queued_prompt_is_taken_in_between_rounds(db, user_id, machine, monkeypatch):
|
|
"""The point of queueing in an agent chat: steering work already under way.
|
|
|
|
An agent that has just finished one loop and is about to start another is
|
|
exactly when "actually, do it the other way" is worth having, and making it
|
|
wait for the whole reply would mean it arrives after the thing it was meant
|
|
to change.
|
|
"""
|
|
from lembas.services import chat as chat_service
|
|
|
|
chat, _profile = _setup(db, user_id, machine, mode=policy.MODE_AUTO)
|
|
message_id = _pending_reply(db, chat)
|
|
chat_service.create_message(
|
|
db, chat, "user", "actually, check the other directory first", queued=True
|
|
)
|
|
|
|
payloads: list[dict] = []
|
|
monkeypatch.setattr(
|
|
generation_service,
|
|
"stream_chat",
|
|
_stub_stream(
|
|
[[_chunk("file_list", '{"path": "."}')], [_text("Done.")]],
|
|
payloads,
|
|
),
|
|
)
|
|
|
|
generation = generation_service.Generation(chat_id=chat.id, message_id=message_id)
|
|
await generation_service._run(generation)
|
|
|
|
# Verbatim, in the user role, with nothing wrapped around it: this genuinely
|
|
# is the person at the keyboard, and quoting it would teach the model that a
|
|
# user turn can be a quotation -- the distinction `execute_plan` relies on.
|
|
assert payloads[1]["messages"][-1] == {
|
|
"role": "user",
|
|
"content": "actually, check the other directory first",
|
|
}
|
|
|
|
|
|
async def test_an_interjection_is_delivered_only_once(db, user_id, machine, monkeypatch):
|
|
"""Marked delivered before the request goes out, so a crash loses it rather
|
|
than asking the same thing twice and letting an agent act on it twice."""
|
|
from lembas.services import chat as chat_service
|
|
|
|
chat, _profile = _setup(db, user_id, machine, mode=policy.MODE_AUTO)
|
|
message_id = _pending_reply(db, chat)
|
|
waiting = chat_service.create_message(db, chat, "user", "one more thing", queued=True)
|
|
|
|
monkeypatch.setattr(
|
|
generation_service,
|
|
"stream_chat",
|
|
_stub_stream(
|
|
[
|
|
[_chunk("file_list", '{"path": "."}')],
|
|
[_chunk("file_list", '{"path": "src"}')],
|
|
[_text("Done.")],
|
|
],
|
|
[],
|
|
),
|
|
)
|
|
|
|
generation = generation_service.Generation(chat_id=chat.id, message_id=message_id)
|
|
await generation_service._run(generation)
|
|
|
|
db.expire_all()
|
|
assert db.get(Message, waiting.id).queued is False
|
|
assert generation.injected_ids == [waiting.id]
|
|
|
|
|
|
async def test_the_reply_sorts_before_the_prompt_it_took_in(db, user_id, machine, monkeypatch):
|
|
"""Otherwise the next request reads "answer, then the question it answered",
|
|
and a small model dutifully answers it a second time."""
|
|
from lembas.services import chat as chat_service
|
|
|
|
chat, _profile = _setup(db, user_id, machine, mode=policy.MODE_AUTO)
|
|
message_id = _pending_reply(db, chat)
|
|
waiting = chat_service.create_message(db, chat, "user", "and this", queued=True)
|
|
|
|
monkeypatch.setattr(
|
|
generation_service,
|
|
"stream_chat",
|
|
_stub_stream([[_chunk("file_list", '{"path": "."}')], [_text("Done.")]], []),
|
|
)
|
|
|
|
generation = generation_service.Generation(chat_id=chat.id, message_id=message_id)
|
|
await generation_service._run(generation)
|
|
|
|
db.expire_all()
|
|
reply = db.get(Message, message_id)
|
|
assert reply.created_at > db.get(Message, waiting.id).created_at
|
|
|
|
|
|
# --- Plan mode's artifact ---------------------------------------------------------
|
|
def test_plan_submit_is_offered_only_in_plan_mode(db, user_id, machine):
|
|
"""It ends the reply. A model in Auto mode that proposed a plan instead of
|
|
doing the work would be obeying the wrong instinct at the wrong moment."""
|
|
user = db.get(User, user_id)
|
|
planning, _p = _setup(db, user_id, machine, mode=policy.MODE_PLAN)
|
|
assert "plan_submit" in _offered(db, planning, user)
|
|
|
|
planning.agent_mode = policy.MODE_AUTO
|
|
db.commit()
|
|
assert "plan_submit" not in _offered(db, planning, user)
|
|
|
|
|
|
async def test_a_plan_ends_the_reply_and_lands_on_the_message(
|
|
db, user_id, machine, monkeypatch
|
|
):
|
|
chat, _profile = _setup(db, user_id, machine, mode=policy.MODE_PLAN)
|
|
message_id = _pending_reply(db, chat)
|
|
|
|
plan = {"title": "Tidy the logs", "steps": ["Read the log", "Rotate it", "Restart"]}
|
|
rounds = [
|
|
[_chunk("plan_submit", _json.dumps(plan))],
|
|
# The model gets one wordless round to explain itself. If it tries to
|
|
# act in it -- as this one does -- there are no tools to act with.
|
|
[_chunk("shell_run", '{"command": "rm -rf /"}'), _text("Here is what I would do.")],
|
|
]
|
|
seen: list[dict] = []
|
|
monkeypatch.setattr(generation_service, "stream_chat", _stub_stream(rounds, seen))
|
|
|
|
generation = generation_service.Generation(chat_id=chat.id, message_id=message_id)
|
|
await asyncio.wait_for(generation_service._run(generation), timeout=10)
|
|
|
|
# A bare `steps` list is still accepted and becomes one phase -- a small
|
|
# model sends it, and refusing would cost a whole round trip.
|
|
assert generation.plan["title"] == "Tidy the logs"
|
|
assert generation.plan["steps"] == plan["steps"]
|
|
assert [t["text"] for t in generation.plan["phases"][0]["tasks"]] == plan["steps"]
|
|
assert len(seen) == 2, "one round to plan, one to say what it proposed"
|
|
assert "tools" not in seen[1], "the second round is offered nothing to act with"
|
|
assert len(generation.tool_events) == 1, "the shell call had no tool to reach"
|
|
|
|
db.expire_all()
|
|
message = db.get(Message, message_id)
|
|
assert message.plan_json["steps"] == plan["steps"]
|
|
# And the chat now points at it, which is what puts the plan in front of the
|
|
# model on the next turn and offers plan_update.
|
|
assert db.get(Chat, chat.id).plan_message_id == message_id
|
|
|
|
|
|
async def test_a_plan_with_no_steps_is_sent_back(db, user_id, machine, monkeypatch):
|
|
chat, _profile = _setup(db, user_id, machine, mode=policy.MODE_PLAN)
|
|
message_id = _pending_reply(db, chat)
|
|
monkeypatch.setattr(
|
|
generation_service,
|
|
"stream_chat",
|
|
_stub_stream(
|
|
[[_chunk("plan_submit", '{"title": "Nothing", "steps": []}')], [_text("Sorry.")]],
|
|
[],
|
|
),
|
|
)
|
|
|
|
generation = generation_service.Generation(chat_id=chat.id, message_id=message_id)
|
|
await asyncio.wait_for(generation_service._run(generation), timeout=10)
|
|
|
|
assert generation.plan is None
|
|
assert generation.tool_events[0]["status"] == "error"
|
|
|
|
|
|
# --- Carrying a plan out ------------------------------------------------------------
|
|
def test_executing_a_plan_switches_to_edit_and_quotes_it(client, db, registered, machine):
|
|
"""Edit, never Auto. The plan was written under a mode where every command
|
|
stopped for approval, and a button that also removed the asking is not the
|
|
button anybody pressed."""
|
|
from sqlalchemy import select as _select
|
|
|
|
user = db.scalar(_select(User))
|
|
chat, _profile = _setup(db, user.id, machine, mode=policy.MODE_PLAN)
|
|
message = Message(
|
|
chat_id=chat.id,
|
|
role=ROLE_ASSISTANT,
|
|
content="Here is what I would do.",
|
|
complete=True,
|
|
plan_json={"title": "Tidy the logs", "steps": ["Read the log", "Rotate it"]},
|
|
)
|
|
db.add(message)
|
|
db.commit()
|
|
|
|
response = client.post(f"/api/chats/{chat.id}/messages/{message.id}/execute-plan")
|
|
assert response.status_code == 200
|
|
|
|
db.refresh(chat)
|
|
assert chat.agent_mode == policy.MODE_EDIT
|
|
|
|
sent = db.scalars(
|
|
_select(Message).where(Message.chat_id == chat.id, Message.role == "user")
|
|
).all()[-1]
|
|
assert "Tidy the logs" in sent.content
|
|
assert "Read the log" in sent.content
|
|
# Quoted rather than stated. A plan whose text came out of a file the model
|
|
# read must not arrive wearing the reader's authority.
|
|
assert sent.content.lstrip().startswith("Carry out the plan you proposed above")
|
|
assert "> " in sent.content
|
|
|
|
|
|
def test_a_message_with_no_plan_cannot_be_executed(client, db, registered, machine):
|
|
from sqlalchemy import select as _select
|
|
|
|
user = db.scalar(_select(User))
|
|
chat, _profile = _setup(db, user.id, machine)
|
|
message = Message(chat_id=chat.id, role=ROLE_ASSISTANT, content="hi", complete=True)
|
|
db.add(message)
|
|
db.commit()
|
|
|
|
assert (
|
|
client.post(f"/api/chats/{chat.id}/messages/{message.id}/execute-plan").status_code
|
|
== 404
|
|
)
|
|
|
|
|
|
# --- Rewind ---------------------------------------------------------------------------
|
|
def test_editing_a_turn_records_that_the_machine_did_not_rewind(
|
|
client, db, registered, machine
|
|
):
|
|
"""The transcript goes back; the project directory does not. Deleting
|
|
somebody's real working tree to match would be far worse than the
|
|
inconsistency, so the model is told instead."""
|
|
from sqlalchemy import select as _select
|
|
|
|
user = db.scalar(_select(User))
|
|
chat, _profile = _setup(db, user.id, machine)
|
|
first = Message(chat_id=chat.id, role="user", content="do a thing", complete=True)
|
|
db.add(first)
|
|
db.commit()
|
|
|
|
assert chat.rewound_at is None
|
|
client.post(
|
|
f"/api/chats/{chat.id}/messages/{first.id}/edit", data={"content": "do another thing"}
|
|
)
|
|
db.refresh(chat)
|
|
assert chat.rewound_at is not None
|
|
|
|
|
|
def test_an_ordinary_chat_records_no_rewind(client, db, registered, machine):
|
|
from sqlalchemy import select as _select
|
|
|
|
user = db.scalar(_select(User))
|
|
chat, _profile = _setup(db, user.id, machine, kind="chat")
|
|
first = Message(chat_id=chat.id, role="user", content="hello", complete=True)
|
|
db.add(first)
|
|
db.commit()
|
|
|
|
client.post(f"/api/chats/{chat.id}/messages/{first.id}/edit", data={"content": "hi"})
|
|
db.refresh(chat)
|
|
assert chat.rewound_at is None
|
|
|
|
|
|
async def test_the_harness_warns_after_a_rewind(db, user_id, machine):
|
|
from datetime import UTC, datetime
|
|
|
|
from lembas.services import harness
|
|
|
|
chat, _profile = _setup(db, user_id, machine)
|
|
user = db.get(User, user_id)
|
|
offered = tools_service.resolve_tools(db, chat, user).schemas
|
|
|
|
assert "was rewound" not in harness.compose(db, user, offered, chat)
|
|
|
|
chat.rewound_at = datetime.now(UTC)
|
|
db.commit()
|
|
text = harness.compose(db, user, offered, chat)
|
|
assert "was rewound" in text
|
|
assert "still there" in text
|