Files
LLeMbas/tests/test_harness.py
T
Jaroslav Beneš 5984d90fb0 Two controls that did nothing, and instructions worth reading
**Switching mode mid-reply did nothing.** The mode was snapshotted when the
reply began, so changing to Auto during a long agent reply went on asking about
every call until the next turn. The same snapshot held the chat's allow list,
which means "Always allow this" was accepted, written to the row, and then
ignored for the rest of the reply that had just asked about it -- the same bug,
in the quieter place nobody reported.

`agent/session.py:refresh` re-reads exactly those two, between rounds and never
within one. A round's calls are authorised together, so a switch must not
retroactively approve what is already queued -- which is the property the
reply-long snapshot was protecting by accident, and the reason this is not
simply moved into `_authorise`. It mutates in place, because `as_approved`
copies field references and a replacement would leave the round's approved copy
pointing at the old context.

**The composer's highlighting stayed behind after sending.** htmx fires
afterSwap and afterSettle *before* afterRequest, and the composer empties itself
from `hx-on::after-request` -- so every repaint ran while the box still held the
message. It repaints on afterRequest and on `reset` as well now, deferred a
frame: a form's reset event fires before its fields are actually cleared, so
reading the value in the same turn paints the text that is about to vanish.
Driven under a DOM stub reproducing htmx's real ordering, and confirmed to fail
without the fix.

**plan_update, audited.** It never said to mark a task `doing`, so the plan only
ever showed work already finished, which is the opposite of "what somebody reads
to see where you are". It never said several changes fit in one call, so a model
spends a round per task. And `done` now means checked rather than written.

**New: core.engineering**, an agent-chat fragment about conduct rather than
about any language -- run what you write, find the project's own build and test
commands rather than guessing, read before editing, change one thing at a time,
read the error instead of guessing at a fix, do not broaden an except to make
output clean, and say what you did not check. Every line is about the gap
between having written something and knowing it works, which is the gap a model
closes by asserting.

That pushed the shipped harness to within 1,300 characters of its ceiling, where
crossing it silently severs the project's own AGENTS.md. The ceiling is 20,000
and the test pins a margin as well as a fit -- the headroom is also where an
administrator's own wording goes, and an override is usually longer than the
default it replaces.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-04 12:36:50 +02:00

491 lines
19 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_its_real_ceiling(db, owner):
"""The number it is actually given, not a constant -- a model told it has
five rounds and cut off after three has been lied to about its own budget."""
settings_store.update(db, {"max_chat_rounds": 3})
text = harness.compose(db, owner, _tools("web_search"))
assert "at most 3 rounds" in text
assert "Keep working until the task is actually done" not in text
def test_no_ceiling_means_no_round_budget_is_claimed(db, owner):
"""Zero is "no ceiling", and a fragment promising zero rounds would be worse
than none at all."""
settings_store.update(db, {"max_chat_rounds": 0})
text = harness.compose(db, owner, _tools("web_search"))
# `core.interjection` also mentions rounds, so this asserts on the budget
# sentence rather than on the word.
assert "at most" 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
def test_the_fetch_guidance_appears_only_with_the_tool(db, owner):
assert "read one web page at a time" in harness.compose(db, owner, _tools("fetch"))
assert "read one web page at a time" not in harness.compose(db, owner, _tools("web_search"))
def test_the_background_guidance_appears_only_when_enabled(db, owner):
"""Gated on the feature, so an agent chat without background commands is not
told about a tool it does not have."""
from lembas.db.models import Chat, Connection, Model, SshProfile
owner.role = "admin" # agent tools need tools.agent, which admins pass
db.commit()
profile = SshProfile(
owner_id=owner.id, name="Box", host="127.0.0.1", port=22, username="t",
host_key="k", host_fingerprint="f", default_dir="/work",
)
connection = Connection(name="cbg", base_url="http://127.0.0.1:1", api_key_encrypted="")
db.add_all([profile, connection])
db.commit()
db.add(Model(connection_id=connection.id, model_id="mbg", capabilities_json={"tools": True}))
db.commit()
settings_store.update(db, {"enabled": True}, key=settings_store.AGENTS)
chat = Chat(
user_id=owner.id, model_id="mbg", connection_id=connection.id, kind="agent",
ssh_profile_id=profile.id, project_dir="/work",
)
db.add(chat)
db.commit()
def _text():
offered = tools_service.resolve_tools(db, chat, owner).schemas
return harness.compose(db, owner, offered, chat)
settings_store.update(db, {"background_enabled": False}, key=settings_store.AGENTS)
assert "run in the background" not in _text()
settings_store.update(db, {"background_enabled": True}, key=settings_store.AGENTS)
assert "run in the background" in _text()
# --- The ceiling has to fit what the defaults already grant --------------------
def test_the_shipped_defaults_fit_under_the_ceiling(db, owner):
"""An agent chat's whole preamble, at the budgets this ships with.
It did not fit. The fragments alone are about 7,900 characters, and on top
of them `index_chars` grants a 2,000 character project listing and
`instructions_chars` a 4,000 character AGENTS.md -- both on by default. The
ceiling was 8,000, and `assemble` cuts the tail, which by fragment order is
the context worth having: the listing was severed mid-tree and
`context.agent_instructions` was dropped whole. So on a default install the
one path by which a project's own instructions reach a model did not.
"""
values = settings_store.agents(db)
# Every name the harness knows about, so a variable added later is covered
# here without anybody remembering to add it.
variables = dict.fromkeys(harness.context_variables(db, owner, [], None), "")
variables.update(
{
"today": "Monday 3 August 2026",
"instance_name": "LLeMbas",
"user_name": "Frodo",
"agent_target": "homeserver",
"agent_dir": "/srv/project",
"agent_mode": "You are in **Edit** mode.",
"tool_names": "shell_run, file_read, file_write, file_edit, file_list",
"background": "on",
"max_rounds": "200",
# Each at exactly the budget its own setting allows.
"project_files": "L" * int(values["index_chars"]),
"agent_instructions": "A" * int(values["instructions_chars"]),
"agent_instructions_file": "AGENTS.md",
"plan": "P" * 600,
"memories": "M" * 400,
}
)
out = harness.compose_from(
db, variables=variables, families=["agent"], has_tools=True, overrides={}
)
assert not out.endswith("…"), f"the preamble was truncated at {len(out):,} characters"
assert "A" * 100 in out, "the project's own instructions were cut off entirely"
assert "L" * 100 in out, "the project listing was cut off"
# Fitting is not enough. It fitted with 1,300 characters to spare once, and
# a ceiling that close to the content is one the next fragment crosses --
# silently, and by cutting the tail, which is the project's own AGENTS.md.
# The margin is also what an administrator's own wording goes in: an
# override is usually longer than the default it replaces.
room = harness.MAX_HARNESS_CHARS - len(out)
assert room >= harness.MAX_HARNESS_CHARS * harness.HARNESS_MARGIN, (
f"only {room:,} characters of headroom left under "
f"{harness.MAX_HARNESS_CHARS:,}; raise the ceiling or shorten a fragment"
)