CI / checks (push) Skipped
CI / checks (pull_request) Failing after 5m7s
- Config: `projects: {name: entry}` with repo, base_branch, workspace,
build_host, push credential, labels (defaults added to every issue),
secrets by ${VAR} reference with visibility (commands | harness), and
egress (recorded, not enforced). Every problem in every entry is
reported at once; an inline secret, a bad visibility, a repeated repo or
a non-slug name is an error.
- The old loop runs exactly one project (only_project) and refuses more.
- The new loop is per project: each its own clone, workspace (with its
commands-visible secrets, redacted on return), push credential and
milestones; intake polls every project's repository; items are scoped
to their project for every run, publish and PR watch. Issues are named
project#14 when there is more than one project, and a bare #14 that
matches two is asked about. Switching projects parks the one worked on
last (all others after a boot).
- A restatement that ends in a question is sent back to the driver, not
posted: the e2e driver kept asking "Is this the right interpretation?",
which a plain yes can't answer.
Tests: config entries and errors, two-project assembly, two-project loop
tests (intake, own workspaces and repos, #14 in both, do-next, label
defaults, parking across projects), the property walk over two projects
with a new own_repository_only property (an item using the first
project's repo fails 15 of 16 seeds), and the restatement check.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
481 lines
17 KiB
Python
481 lines
17 KiB
Python
import copy
|
|
from pathlib import Path
|
|
from typing import Any
|
|
|
|
import pytest
|
|
|
|
from nisse_dev.config import AgentConfig, ConfigError
|
|
from nisse_dev.llm import DEFAULT_REQUEST_TIMEOUT_S
|
|
|
|
# A complete config as the YAML file would give it, with secrets by reference.
|
|
COMPLETE: dict[str, Any] = {
|
|
"state_db": "~/demo/state.db",
|
|
"projects": {
|
|
"greet": {
|
|
"repo": "don/demo",
|
|
"workspace": "~/demo/work",
|
|
"build_host": {"address": "build.test", "key": "~/.ssh/nisse-dev"},
|
|
}
|
|
},
|
|
"llm": {"base_url": "https://litellm.test", "token": "${TEST_LLM_TOKEN}"},
|
|
"roles": {
|
|
"executor": "claude-haiku-4-5",
|
|
"planner": "claude-opus-5",
|
|
"helper": "claude-opus-5",
|
|
"expert": "claude-haiku-4-5",
|
|
},
|
|
"matrix": {
|
|
"homeserver": "https://matrix.test/",
|
|
"user_id": "@nisse-dev-testing:test",
|
|
"token": "${TEST_MATRIX_TOKEN}",
|
|
"room_id": "!room:test",
|
|
"operators": ["@don:test"],
|
|
},
|
|
"gitea": {
|
|
"url": "https://gitea.test",
|
|
"token": "${TEST_GITEA_TOKEN}",
|
|
"operators": ["don"],
|
|
},
|
|
}
|
|
P = "projects__greet__" # the one project's keys, for tree()
|
|
SECRETS = {
|
|
"TEST_LLM_TOKEN": "sk-x",
|
|
"TEST_MATRIX_TOKEN": "syt_x",
|
|
"TEST_GITEA_TOKEN": "gt",
|
|
}
|
|
|
|
|
|
def tree(**changes: Any) -> dict[str, Any]:
|
|
"""COMPLETE with dotted keys changed; a value of None removes the key."""
|
|
result = copy.deepcopy(COMPLETE)
|
|
for dotted, value in changes.items():
|
|
*parents, leaf = dotted.split("__")
|
|
node = result
|
|
for part in parents:
|
|
node = node.setdefault(part, {})
|
|
if value is None:
|
|
node.pop(leaf, None)
|
|
else:
|
|
node[leaf] = value
|
|
return result
|
|
|
|
|
|
def build(**changes: Any) -> AgentConfig:
|
|
return AgentConfig.from_tree(tree(**changes), SECRETS)
|
|
|
|
|
|
def test_complete_config_builds_with_secrets_by_reference() -> None:
|
|
config = build()
|
|
assert config.project == "greet"
|
|
assert config.llm_token == "sk-x"
|
|
assert config.gitea_token == "gt"
|
|
assert config.roles.planner == "claude-opus-5"
|
|
assert config.matrix.room_id == "!room:test"
|
|
assert config.matrix.homeserver == "https://matrix.test"
|
|
assert config.gitea_repo == "don/demo"
|
|
assert config.base_branch == "main"
|
|
assert config.tuning.executor.max_turns == 40 # absent section: defaults
|
|
|
|
|
|
def test_paths_expand_the_home_directory() -> None:
|
|
config = build()
|
|
assert config.workspace.is_absolute()
|
|
assert "~" not in str(config.state_db)
|
|
|
|
|
|
def test_every_missing_setting_is_reported_at_once() -> None:
|
|
# Failing at first use would surface a missing token twenty minutes into
|
|
# a milestone, on the call that mattered.
|
|
with pytest.raises(ConfigError) as excinfo:
|
|
build(matrix__token=None, **{f"{P}repo": None})
|
|
message = str(excinfo.value)
|
|
assert "matrix.token" in message
|
|
assert "projects.greet: unset or empty — repo" in message
|
|
|
|
|
|
def test_empty_is_treated_as_missing() -> None:
|
|
with pytest.raises(ConfigError, match="projects.greet: unset or empty — repo"):
|
|
build(**{f"{P}repo": " "})
|
|
|
|
|
|
def test_a_reference_to_an_unset_variable_is_an_error() -> None:
|
|
# Never an empty string: an empty token would pass for a value and fail
|
|
# at the first request.
|
|
env = {k: v for k, v in SECRETS.items() if k != "TEST_GITEA_TOKEN"}
|
|
with pytest.raises(ConfigError, match=r"gitea.token: references \$\{TEST_GITEA"):
|
|
AgentConfig.from_tree(tree(), env)
|
|
|
|
|
|
def test_operator_lists_drop_blanks() -> None:
|
|
config = build(matrix__operators=[" @don:test ", "@other:test", " "])
|
|
assert config.operators == {"@don:test", "@other:test"}
|
|
# A blank entry must not admit an empty identity into an allowlist.
|
|
assert "" not in config.operators
|
|
|
|
|
|
def test_an_operator_list_of_only_blanks_is_missing() -> None:
|
|
with pytest.raises(ConfigError, match="gitea.operators"):
|
|
build(gitea__operators=[" "])
|
|
|
|
|
|
def test_base_branch_is_configurable() -> None:
|
|
assert build(**{f"{P}base_branch": "trunk"}).base_branch == "trunk"
|
|
|
|
|
|
def test_max_output_tokens_is_configurable_and_checked() -> None:
|
|
assert build(llm__max_output_tokens=8192).max_output_tokens == 8192
|
|
with pytest.raises(ConfigError, match="llm.max_output_tokens"):
|
|
build(llm__max_output_tokens=0)
|
|
|
|
|
|
def test_request_timeout_is_configurable_and_checked() -> None:
|
|
assert build().request_timeout_s == DEFAULT_REQUEST_TIMEOUT_S
|
|
assert build(llm__request_timeout_s=900).request_timeout_s == 900.0
|
|
for bad in (0, -5, "soon"):
|
|
with pytest.raises(ConfigError, match="llm.request_timeout_s"):
|
|
build(llm__request_timeout_s=bad)
|
|
|
|
|
|
def test_the_request_timeout_reaches_both_clients() -> None:
|
|
from nisse_dev.agent import make_llm_clients
|
|
from nisse_dev.catalog import ModelCatalog
|
|
|
|
normalized, passthrough = make_llm_clients(
|
|
build(llm__request_timeout_s=42), ModelCatalog({})
|
|
)
|
|
for client in (normalized, passthrough):
|
|
assert client._inner._http.timeout.read == 42.0
|
|
|
|
|
|
def test_redacted_summary_carries_no_secrets() -> None:
|
|
summary = build().redacted()
|
|
flat = " ".join(summary.values())
|
|
for secret in SECRETS.values():
|
|
assert secret not in flat
|
|
assert "greet (don/demo, build.test:" in summary["projects"]
|
|
|
|
|
|
def test_tuning_is_read() -> None:
|
|
config = build(
|
|
tuning={
|
|
"executor": {"max_turns": 40, "failure_limit": 3},
|
|
"expert": {"consult_budget": 5},
|
|
"delegation": {"max_turns": 20, "max_tokens": 100000, "wall_clock_s": 600},
|
|
"tools": {"command_timeout_s": 300, "max_output_chars": 2000},
|
|
"loop": {"bug_grace_s": 120},
|
|
}
|
|
)
|
|
tuning = config.tuning
|
|
assert (tuning.executor.max_turns, tuning.executor.failure_limit) == (40, 3)
|
|
assert tuning.expert.consult_budget == 5
|
|
assert tuning.delegation.max_tokens == 100_000
|
|
assert tuning.delegation.wall_clock_s == 600.0
|
|
assert tuning.tools.max_output_chars == 2000
|
|
assert tuning.loop.bug_grace_s == 120.0
|
|
|
|
|
|
def test_a_partly_given_tuning_section_keeps_the_other_defaults() -> None:
|
|
tuning = build(tuning={"executor": {"max_turns": 40}}).tuning
|
|
assert tuning.executor.failure_limit == 2
|
|
|
|
|
|
def test_every_problem_is_reported_at_once() -> None:
|
|
# A misspelt knob that was silently ignored would look exactly like a knob
|
|
# with no effect, so unknown keys are errors.
|
|
bad = tree(llm_extra=1, **{f"{P}workspace": None})
|
|
bad["tuning"] = {
|
|
"executor": {"max_turn": 40, "failure_limit": 0},
|
|
"expert": {"consult_budget": True},
|
|
"bogus": {"x": 1},
|
|
}
|
|
with pytest.raises(ConfigError) as excinfo:
|
|
AgentConfig.from_tree(bad, SECRETS)
|
|
message = str(excinfo.value)
|
|
for expected in (
|
|
"projects.greet: unset or empty — workspace",
|
|
"llm_extra: unknown setting",
|
|
"tuning.executor.max_turn: unknown setting",
|
|
"tuning.executor.failure_limit: must be a positive number",
|
|
"tuning.expert.consult_budget: must be a positive number",
|
|
"tuning.bogus: unknown section",
|
|
):
|
|
assert expected in message
|
|
|
|
|
|
def test_a_whole_number_is_required_where_one_is_meant() -> None:
|
|
with pytest.raises(ConfigError, match="tuning.executor.max_turns"):
|
|
build(tuning={"executor": {"max_turns": 2.5}})
|
|
|
|
|
|
# --- the file --------------------------------------------------------------
|
|
|
|
FILE = """
|
|
state_db: ~/demo/state.db
|
|
projects:
|
|
greet:
|
|
repo: don/demo
|
|
workspace: ~/demo/work
|
|
build_host:
|
|
address: build.test
|
|
key: ~/.ssh/nisse-dev
|
|
llm: {base_url: "https://litellm.test", token: "${TEST_LLM_TOKEN}"}
|
|
roles:
|
|
executor: local-fast
|
|
planner: claude-opus-5
|
|
helper: claude-opus-5
|
|
expert: claude-haiku-4-5
|
|
matrix:
|
|
homeserver: https://matrix.test
|
|
user_id: "@nisse-dev-testing:test"
|
|
token: ${TEST_MATRIX_TOKEN}
|
|
room_id: "!room:test"
|
|
operators: ["@don:test"]
|
|
gitea:
|
|
url: https://gitea.test
|
|
token: ${TEST_GITEA_TOKEN}
|
|
operators: [don]
|
|
"""
|
|
|
|
|
|
def write(directory: Path, text: str = FILE) -> Path:
|
|
path = directory / "nisse-dev.yaml"
|
|
path.write_text(text)
|
|
return path
|
|
|
|
|
|
def test_a_file_is_read(tmp_path: Path) -> None:
|
|
config = AgentConfig.from_file(write(tmp_path), SECRETS)
|
|
assert config.roles.executor == "local-fast"
|
|
assert config.config_file == tmp_path / "nisse-dev.yaml"
|
|
|
|
|
|
def test_invalid_yaml_is_reported(tmp_path: Path) -> None:
|
|
with pytest.raises(ConfigError, match="not valid YAML"):
|
|
AgentConfig.from_file(write(tmp_path, "roles: [unclosed"), SECRETS)
|
|
|
|
|
|
def test_load_uses_nisse_config(tmp_path: Path) -> None:
|
|
path = write(tmp_path)
|
|
assert AgentConfig.load({**SECRETS, "NISSE_CONFIG": str(path)}).project == "greet"
|
|
|
|
|
|
def test_load_defaults_to_the_working_directory(
|
|
tmp_path: Path, monkeypatch: pytest.MonkeyPatch
|
|
) -> None:
|
|
write(tmp_path)
|
|
monkeypatch.chdir(tmp_path)
|
|
assert AgentConfig.load(SECRETS).project == "greet"
|
|
|
|
|
|
def test_load_without_a_file_says_how_to_make_one(
|
|
tmp_path: Path, monkeypatch: pytest.MonkeyPatch
|
|
) -> None:
|
|
monkeypatch.chdir(tmp_path)
|
|
with pytest.raises(ConfigError, match="nisse-dev.example.yaml"):
|
|
AgentConfig.load(SECRETS)
|
|
|
|
|
|
def test_the_example_file_is_valid() -> None:
|
|
# The example documents every knob; it must not drift out of loading.
|
|
example = Path(__file__).resolve().parents[2] / "nisse-dev.example.yaml"
|
|
env = {
|
|
"NISSE_LLM_TOKEN": "sk-x",
|
|
"NISSE_MATRIX_TOKEN": "syt_x",
|
|
"NISSE_GITEA_TOKEN": "gt",
|
|
}
|
|
config = AgentConfig.from_file(example, env)
|
|
assert config.tuning.executor.max_turns == 40
|
|
assert config.roles.executor == "qwen3.8-27b"
|
|
|
|
|
|
# --- nothing that carries secrets may sit inside the clone -----------------
|
|
|
|
|
|
def test_state_db_and_workspace_are_separate() -> None:
|
|
# L8: build artefacts must not share a volume with agent state.
|
|
config = build()
|
|
assert config.state_db.parent != config.workspace
|
|
|
|
|
|
def test_state_db_inside_the_clone_is_refused(tmp_path: Path) -> None:
|
|
# git add -A would commit it, and the push would publish the agent's
|
|
# own state alongside the project.
|
|
work = tmp_path / "project"
|
|
with pytest.raises(ConfigError, match="inside the workspace"):
|
|
build(state_db=str(work / "state.db"), **{f"{P}workspace": str(work)})
|
|
|
|
|
|
def test_env_file_inside_the_clone_is_refused(tmp_path: Path) -> None:
|
|
# The severe case: the agent would commit and push its own credentials
|
|
# as a side effect of working correctly.
|
|
work = tmp_path / "project"
|
|
with pytest.raises(ConfigError, match="NISSE_ENV"):
|
|
AgentConfig.from_tree(
|
|
tree(state_db=str(tmp_path / "state.db"), **{f"{P}workspace": str(work)}),
|
|
{**SECRETS, "NISSE_ENV": str(work / ".env")},
|
|
)
|
|
|
|
|
|
def test_a_config_file_inside_the_clone_is_refused(tmp_path: Path) -> None:
|
|
work = tmp_path / "project"
|
|
work.mkdir()
|
|
text = FILE.replace("workspace: ~/demo/work", f"workspace: {work}")
|
|
assert text != FILE
|
|
with pytest.raises(ConfigError, match="NISSE_CONFIG"):
|
|
AgentConfig.from_file(write(work, text), SECRETS)
|
|
|
|
|
|
def test_sibling_paths_are_fine(tmp_path: Path) -> None:
|
|
config = AgentConfig.from_tree(
|
|
tree(
|
|
state_db=str(tmp_path / "state.db"),
|
|
**{f"{P}workspace": str(tmp_path / "project")},
|
|
),
|
|
{**SECRETS, "NISSE_ENV": str(tmp_path / ".env")},
|
|
)
|
|
assert config.workspace.name == "project"
|
|
|
|
|
|
def test_context_tuning_is_read_and_checked() -> None:
|
|
config = build(tuning={"context": {"keep_recent_turns": 4, "safety_margin": 0.2}})
|
|
assert config.tuning.context.keep_recent_turns == 4
|
|
assert config.tuning.context.safety_margin == 0.2
|
|
assert build().tuning.context.keep_recent_turns == 6
|
|
with pytest.raises(ConfigError, match="safety_margin: must be less than 1"):
|
|
build(tuning={"context": {"safety_margin": 1}})
|
|
|
|
|
|
def test_the_build_host_is_required_and_defaults_to_root_on_22() -> None:
|
|
config = build()
|
|
assert (config.build_host.address, config.build_host.user) == ("build.test", "root")
|
|
assert config.build_host.port == 22
|
|
assert config.build_host.key.is_absolute()
|
|
with pytest.raises(ConfigError, match="build_host.address"):
|
|
build(**{f"{P}build_host__address": None})
|
|
|
|
|
|
def test_a_bad_build_host_port_is_reported() -> None:
|
|
with pytest.raises(ConfigError, match="build_host.port"):
|
|
build(**{f"{P}build_host__port": "ssh"})
|
|
|
|
|
|
def test_the_push_key_is_optional_and_a_path() -> None:
|
|
assert build().push_key is None
|
|
assert build(**{f"{P}push_key": "~/k"}).push_key == Path("~/k").expanduser()
|
|
|
|
|
|
def test_a_push_token_needs_its_user_and_excludes_a_key() -> None:
|
|
token = {f"{P}push_user": "pusher", f"{P}push_token": "${TEST_GITEA_TOKEN}"}
|
|
config = build(**token)
|
|
assert (config.push_user, config.push_token) == ("pusher", "gt")
|
|
with pytest.raises(ConfigError, match="set both or neither"):
|
|
build(**{f"{P}push_user": "pusher"})
|
|
with pytest.raises(ConfigError, match="not both"):
|
|
build(**token, **{f"{P}push_key": "~/k"})
|
|
|
|
|
|
def test_no_credential_appears_in_the_config_repr() -> None:
|
|
config = build(
|
|
**{f"{P}push_user": "pusher", f"{P}push_token": "${TEST_GITEA_TOKEN}"},
|
|
**{
|
|
f"{P}secrets": {"DB": {"value": "${TEST_LLM_TOKEN}", "visible": "commands"}}
|
|
},
|
|
)
|
|
text = repr(config)
|
|
for secret in SECRETS.values():
|
|
assert secret not in text
|
|
|
|
|
|
def test_the_loop_defaults_to_old_and_takes_new() -> None:
|
|
assert build().loop == "old"
|
|
assert build(loop="new").loop == "new"
|
|
with pytest.raises(ConfigError, match="loop: must be old or new"):
|
|
build(loop="newer")
|
|
|
|
|
|
# --- projects (D8) -----------------------------------------------------------
|
|
|
|
SECOND = {
|
|
"repo": "don/other",
|
|
"workspace": "~/demo/other",
|
|
"build_host": {"address": "build2.test", "key": "~/.ssh/nisse-dev"},
|
|
}
|
|
|
|
|
|
def test_a_second_project_is_a_second_entry() -> None:
|
|
config = build(projects__other=SECOND)
|
|
assert [p.name for p in config.projects] == ["greet", "other"]
|
|
other = config.projects[1]
|
|
assert (other.repo, other.build_host.address) == ("don/other", "build2.test")
|
|
assert other.base_branch == "main" and other.labels == () and other.secrets == {}
|
|
|
|
|
|
def test_the_old_loop_refuses_more_than_one_project() -> None:
|
|
config = build(projects__other=SECOND)
|
|
with pytest.raises(ConfigError, match="exactly one project"):
|
|
config.only_project()
|
|
with pytest.raises(ConfigError, match="exactly one project"):
|
|
_ = config.gitea_repo
|
|
|
|
|
|
def test_at_least_one_project_is_needed() -> None:
|
|
with pytest.raises(ConfigError, match="projects: must name at least one"):
|
|
build(projects={})
|
|
|
|
|
|
def test_project_problems_are_named_by_project() -> None:
|
|
bad = tree(projects__other={**SECOND, "repo": "don/demo", "colour": "red"})
|
|
with pytest.raises(ConfigError) as excinfo:
|
|
AgentConfig.from_tree(bad, SECRETS)
|
|
message = str(excinfo.value)
|
|
assert "projects.other.colour: unknown setting" in message
|
|
assert "projects.other.repo: don/demo is also project greet's" in message
|
|
|
|
|
|
def test_a_project_name_is_a_slug() -> None:
|
|
with pytest.raises(ConfigError, match="lowercase letters, digits"):
|
|
build(projects__Other_Project=SECOND)
|
|
|
|
|
|
def test_labels_and_egress_are_lists_of_names() -> None:
|
|
config = build(**{f"{P}labels": ["discuss"], f"{P}egress": ["pypi.org"]})
|
|
assert config.only_project().labels == ("discuss",)
|
|
assert config.only_project().egress == ("pypi.org",)
|
|
with pytest.raises(ConfigError, match="projects.greet.labels: must be a list"):
|
|
build(**{f"{P}labels": "discuss"})
|
|
|
|
|
|
def test_secrets_are_by_reference_with_a_visibility() -> None:
|
|
config = build(
|
|
**{
|
|
f"{P}secrets": {
|
|
"DB_URL": {"value": "${TEST_LLM_TOKEN}", "visible": "commands"},
|
|
"DEPLOY": {"value": "${TEST_GITEA_TOKEN}", "visible": "harness"},
|
|
}
|
|
}
|
|
)
|
|
project = config.only_project()
|
|
assert project.command_secrets() == {"DB_URL": "sk-x"}
|
|
assert project.secrets["DEPLOY"].visible == "harness"
|
|
|
|
|
|
def test_a_secret_written_inline_is_refused() -> None:
|
|
with pytest.raises(ConfigError, match="must be a \\$\\{VAR\\} reference"):
|
|
build(**{f"{P}secrets": {"DB": {"value": "hunter2", "visible": "commands"}}})
|
|
|
|
|
|
def test_a_secret_needs_a_known_visibility() -> None:
|
|
with pytest.raises(ConfigError, match="visible: must be one of commands, harness"):
|
|
build(
|
|
**{f"{P}secrets": {"DB": {"value": "${TEST_LLM_TOKEN}", "visible": "all"}}}
|
|
)
|
|
|
|
|
|
def test_a_workspace_of_any_project_inside_is_refused(tmp_path: Path) -> None:
|
|
work = tmp_path / "other"
|
|
with pytest.raises(ConfigError, match="project other"):
|
|
build(
|
|
state_db=str(work / "state.db"),
|
|
projects__other={**SECOND, "workspace": str(work)},
|
|
)
|