Files
LLeMbas/tests/test_harness.py
T
Jaroslav Beneš bc141eae10 One round for a chat, as many as it takes for an agent
Two different jobs were sharing one number. A plain conversation asking a
question is one round of looking things up and then an answer; the rounds after
that were a small model that had decided searching was the answer searching
until the context ran out, at a full request each. MAX_ROUNDS is 1 now. Several
tools can still be called within that round, which is the thing worth telling
the model.

The trade is real and worth naming: a plain chat can no longer search and then
read one of the results, because reading is a second round. That is what an
agent chat is for.

An agent chat is sized by Limits instead, where steps is now a runaway backstop
and not a working budget. It was 40 and it was reached -- a step count low
enough to be the thing that ends a reply is a count that ends it halfway. What
bounds one now is the wall clock and a new completion-token ceiling, with zero
meaning no ceiling, the same convention index_chars already uses.

That ceiling would have been decorative. 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. So _written takes the larger of reported and
estimated, and there is a test that runs the whole thing against a stream
reporting no usage at all. A limit that works on OpenAI and silently does
nothing everywhere else is the worst kind: one that looks configured.

core.rounds could not stay one fragment. "You get at most N rounds" is not the
same sentence with a different number in it -- a model told it has a budget
rations it and stops early to report progress, which is exactly the behaviour
that strands a long piece of work. So it splits: core.rounds keeps the
one-round case and gates on a new round_budget variable that _agent_values
blanks, and core.keep_working says the other thing to an agent chat.

A queued message during a one-round reply is now never taken mid-reply -- there
is no work under way to steer -- and falls through to _drain, which gives it a
reply of its own. No code change went with that; it falls out of the guard, and
there is a test so that "it happens to work" and "it is meant to work" stop
looking the same.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-03 11:11:05 +02:00

383 lines
14 KiB
Python

"""The operational preamble, and how it sits beside the authored prompt."""
from __future__ import annotations
import pytest
from lembas.db.models import Chat, Connection, Model, User
from lembas.security.passwords import hash_password
from lembas.services import chat as chat_service
from lembas.services import harness, prompts, settings_store
from lembas.services import tools as tools_service
from lembas.services.library import memories as memories_service
from lembas.services.library import skills as skills_service
@pytest.fixture
def owner(db):
user = User(name="Frodo", email="f@shire.test", password_hash=hash_password("x"))
db.add(user)
db.commit()
return user
def _tools(*names):
return [tools_service.REGISTRY[name].schema for name in names]
# --- Composition -------------------------------------------------------------
def test_no_tools_means_no_tool_guidance(db, owner):
"""The core fragments still go out -- a model with no tools has no clock
either, and telling it the date is not "tokens that say nothing". What it
must not get is instructions about tools it was never offered."""
text = harness.compose(db, owner, [])
assert "Today is" in text
assert "You have tools" not in text
assert "Look things up" not in text
assert harness.compose(db, owner, None) == text
def test_clearing_the_core_fragments_restores_an_empty_harness(db, owner):
"""The behaviour change is a default, not a rule: an administrator who wants
nothing sent to a tool-less model can still have exactly that."""
prompts.save(
db,
{f.key: "" for f in prompts.BUILTIN if f.group == prompts.GROUP_CORE},
)
assert harness.compose(db, owner, []) == ""
def test_only_the_guidance_for_offered_tools_appears(db, owner):
text = harness.compose(db, owner, _tools("web_search"))
assert "Look things up" in text
assert "You keep notes" not in text
assert "Skills are procedures" not in text
def test_a_custom_tools_guidance_appears_only_when_it_is_offered(db, owner):
"""The row supplies the default, and the fragment is gated on the tool's own
family -- which is why the registry had to stop being a module constant."""
from lembas.db.models import CustomTool
db.add(
CustomTool(
slug="weather",
name="Weather",
description="Look up the weather.",
url_template="https://api.test/{{city}}",
guidance="- Check the weather rather than guessing at it.",
)
)
db.commit()
offered = tools_service.registry(db)["weather"].schema
assert "Check the weather" in harness.compose(db, owner, [offered])
assert "Check the weather" not in harness.compose(db, owner, _tools("web_search"))
def test_the_memory_block_is_included_when_memory_is_offered(db, owner):
memories_service.add(db, owner=owner, content="Prefers metric units.")
text = harness.compose(db, owner, _tools("memory_add"))
assert "What you know about this person" in text
assert "Prefers metric units." in text
def test_memories_are_absent_without_the_memory_tool(db, owner):
"""A model not given the memory tool has no business being told them."""
memories_service.add(db, owner=owner, content="Prefers metric units.")
text = harness.compose(db, owner, _tools("web_search"))
assert "Prefers metric units." not in text
def test_the_skill_index_is_names_and_descriptions_only(db, owner):
skills_service.create(
db, owner=owner, name="weekly-report", description="When asked.", body="SECRET"
)
text = harness.compose(db, owner, _tools("skill_get"))
assert "weekly-report: When asked." in text
assert "SECRET" not in text
def test_an_empty_store_contributes_no_heading(db, owner):
"""And the guidance must not point at a heading that is not there: telling a
model to consult an absent section is a good way to make it invent one."""
text = harness.compose(db, owner, _tools("memory_add", "skill_get"))
assert "### What you know about this person" not in text
assert "### Skills available" not in text
assert "was remembered earlier" not in text
assert "You can remember durable facts" in text
def test_the_harness_is_capped(db, owner, monkeypatch):
monkeypatch.setattr(harness, "MAX_HARNESS_CHARS", 200)
for index in range(50):
skills_service.create(
db, owner=owner, name=f"skill-{index}", description="x" * 200, body="y"
)
assert len(harness.compose(db, owner, _tools("skill_get"))) <= 202
# --- Joining -----------------------------------------------------------------
def test_the_authored_prompt_comes_last():
"""It is closest to the conversation, and it is what the user actually
wrote."""
joined = harness.join("HARNESS", "AUTHORED")
assert joined.index("HARNESS") < joined.index("AUTHORED")
def test_either_half_alone_is_returned_unchanged():
assert harness.join("", "AUTHORED") == "AUTHORED"
assert harness.join("HARNESS", "") == "HARNESS"
assert harness.join("", "") == ""
# --- Through build_request ---------------------------------------------------
def _chat(db, owner, *, capabilities, model_prompt="", chat_prompt=""):
connection = Connection(name="c", base_url="http://h", api_key_encrypted="")
db.add(connection)
db.commit()
db.add(
Model(
connection_id=connection.id,
model_id="m",
capabilities_json=capabilities,
system_prompt=model_prompt,
)
)
db.commit()
chat = Chat(
user_id=owner.id, model_id="m", connection_id=connection.id, system_prompt=chat_prompt
)
db.add(chat)
db.commit()
return chat
def _system(body):
first = body["messages"][0] if body["messages"] else {}
return first.get("content", "") if first.get("role") == "system" else ""
def test_a_request_without_tools_carries_no_tool_guidance_and_no_tools_key(db, owner):
chat = _chat(db, owner, capabilities={})
body = chat_service.build_request(db, chat, tools=[], user=owner)
assert "tools" not in body
assert "You have tools" not in _system(body)
def test_the_harness_precedes_the_authored_prompt(db, owner):
settings_store.update(db, {"enabled": True}, key=settings_store.SEARCH)
chat = _chat(db, owner, capabilities={"tools": True}, chat_prompt="Speak as Gandalf.")
offered = tools_service.enabled_tools(db, chat, owner)
system = _system(chat_service.build_request(db, chat, tools=offered, user=owner))
assert system.index("How to work") < system.index("Speak as Gandalf.")
def test_precedence_between_the_authored_layers_is_untouched(db, owner):
"""The harness is a different axis. Exactly one authored layer still wins,
and it is still the most specific one."""
settings_store.update(db, {"system_prompt": "Instance."})
settings_store.update(db, {"enabled": True}, key=settings_store.SEARCH)
chat = _chat(
db, owner, capabilities={"tools": True}, model_prompt="Model.", chat_prompt="Chat."
)
offered = tools_service.enabled_tools(db, chat, owner)
system = _system(chat_service.build_request(db, chat, tools=offered, user=owner))
assert "Chat." in system
assert "Model." not in system
assert "Instance." not in system
# And the resolver on its own is unchanged.
assert chat_service.effective_system_prompt(db, chat) == "Chat."
def test_a_model_prompt_wins_when_the_chat_has_none(db, owner):
settings_store.update(db, {"system_prompt": "Instance."})
chat = _chat(db, owner, capabilities={}, model_prompt="Model.")
system = _system(chat_service.build_request(db, chat, user=owner))
assert system.endswith("Model.")
assert "Instance." not in system
assert chat_service.effective_system_prompt(db, chat) == "Model."
def test_the_seam_line_only_appears_when_there_is_something_to_hand_over_to(db, owner):
"""It introduces the authored prompt. With no authored prompt it would be
pointing at nothing, which is the failure the whole `requires` idea exists
to avoid."""
bare = _chat(db, owner, capabilities={})
assert "was written by whoever set up" not in _system(
chat_service.build_request(db, bare, user=owner)
)
authored = _chat(db, owner, capabilities={}, chat_prompt="Speak as Gandalf.")
assert "was written by whoever set up" in _system(
chat_service.build_request(db, authored, user=owner)
)
def test_an_administrators_wording_replaces_the_default(db, owner):
prompts.save(db, {"core.today": "The date is {{today}}, more or less."})
text = harness.compose(db, owner, [])
assert "more or less." in text
assert "Your training data stops well before this" not in text
def test_the_attached_files_are_named_and_explained(db, owner):
from lembas.db.models import Attachment
chat = _chat(db, owner, capabilities={})
db.add(
Attachment(
user_id=owner.id,
chat_id=chat.id,
filename="report.txt",
stored_name="x.txt",
media_type="text/plain",
size_bytes=10,
kind="text",
)
)
db.commit()
text = harness.compose(db, owner, [], chat)
assert "report.txt" in text
assert "<document name=" in text
def test_a_chat_with_no_attachments_says_nothing_about_documents(db, owner):
chat = _chat(db, owner, capabilities={})
assert "<document name=" not in harness.compose(db, owner, [], chat)
def test_the_tools_array_rides_along(db, owner):
settings_store.update(db, {"enabled": True}, key=settings_store.SEARCH)
chat = _chat(db, owner, capabilities={"tools": True})
offered = tools_service.enabled_tools(db, chat, owner)
body = chat_service.build_request(db, chat, tools=offered, user=owner)
assert body["tools"] == offered
# --- The project listing -----------------------------------------------------
# Injected from a cache that something else fills, because this module runs
# synchronously on the request path and an SFTP round trip here would hold a
# request open while somebody's machine thought about it.
def _agent_chat(db, owner):
from lembas.db.models import KIND_AGENT, SshProfile
settings_store.update(db, {"enabled": True}, key=settings_store.AGENTS)
profile = SshProfile(
owner_id=owner.id,
name="Test box",
host="127.0.0.1",
port=22,
username="tester",
host_key="host key",
host_fingerprint="SHA256:x",
default_dir="/work",
)
db.add(profile)
db.commit()
chat = Chat(
user_id=owner.id,
kind=KIND_AGENT,
ssh_profile_id=profile.id,
project_dir="/work",
)
db.add(chat)
db.commit()
return chat, profile
def _agent_tools(db):
"""The agent tools as offered, which REGISTRY does not carry.
`REGISTRY` is built at import time and holds the built-ins alone; the agent
tools are listed by `registry(db)`, unbound to any chat. That is the same
lookup the harness does to map `shell_run` back to the `agent` family, and
the reason it exists at all.
"""
book = tools_service.registry(db)
return [book["shell_run"].schema]
def _cache(profile_id, paths):
import time
from lembas.services.agent import index as index_service
index_service._CACHE[(profile_id, "/work")] = index_service.ProjectIndex(
paths=tuple(paths), total=len(paths), source="git", built_at=time.monotonic()
)
def test_the_project_listing_reaches_the_model(db, owner):
chat, profile = _agent_chat(db, owner)
_cache(profile.id, ["README.md", "src/main.py"])
text = harness.compose(db, owner, _agent_tools(db), chat=chat)
assert "Files in /work" in text
assert "README.md" in text
def test_nothing_cached_means_no_section_at_all(db, owner):
"""Not an empty heading. `Fragment.requires` makes the whole thing vanish,
which is what lets the first reply in a new chat outrun the first walk
without saying anything strange."""
chat, _profile = _agent_chat(db, owner)
text = harness.compose(db, owner, _agent_tools(db), chat=chat)
assert "Files in" not in text
def test_a_budget_of_zero_keeps_the_listing_out_of_the_prompt(db, owner):
"""The listing is still built and the file picker still uses it. This is
the only way to say "index it, but do not spend context on it"."""
chat, profile = _agent_chat(db, owner)
_cache(profile.id, ["README.md"])
settings_store.update(db, {"index_chars": 0}, key=settings_store.AGENTS)
assert "Files in" not in harness.compose(db, owner, _agent_tools(db), chat=chat)
def test_switching_the_listing_off_keeps_it_out(db, owner):
chat, profile = _agent_chat(db, owner)
_cache(profile.id, ["README.md"])
settings_store.update(db, {"index_enabled": False}, key=settings_store.AGENTS)
assert "Files in" not in harness.compose(db, owner, _agent_tools(db), chat=chat)
def test_a_plain_chat_is_told_nothing_about_files(db, owner):
chat = Chat(user_id=owner.id)
db.add(chat)
db.commit()
assert "Files in" not in harness.compose(db, owner, _tools("web_search"), chat=chat)
# --- One round, or as many as it takes ----------------------------------------
def test_a_plain_chat_is_told_it_has_one_round(db, owner):
"""And is told to ask for everything at once, which is the advice that
matters when there is only one."""
text = harness.compose(db, owner, _tools("web_search"))
assert "one round of tool calls" in text
assert "Keep working until the task is actually done" not in text
def test_an_agent_chat_is_told_to_keep_going_instead(db, owner):
"""The two cannot be one fragment with a number in it. A model told it has
a budget rations it; the step count is a runaway backstop, and rationing
against it is exactly the behaviour that stops a long piece of work
halfway."""
chat, _profile = _agent_chat(db, owner)
text = harness.compose(db, owner, _agent_tools(db), chat=chat)
assert "Keep working until the task is actually done" in text
assert "one round of tool calls" not in text