Make the config file the only home for settings
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 51s

With no production instance yet, there is no reason to carry two ways
of configuring the agent. Every environment variable that duplicated a
config key is gone; the environment now supplies only the secrets the
file references by ${…}, plus NISSE_CONFIG and NISSE_ENV to find the
files.

- AgentConfig loads from a file (load, from_file) or a parsed tree
  (from_tree, for tests); a missing file is an error naming the example
- The from_env constructors on LiteLLMClient, AnthropicPassthroughClient,
  GiteaClient, MatrixConfig and RoleMap are removed, with the env
  reading for max output tokens; clients take their settings from config
- The live integration tests share a committed agent config,
  tests/integration/nisse-test.yaml, aimed at test resources, and one
  conftest that loads it and builds clients. NISSE_LIVE_PLANNER_MODEL
  becomes its planner role; NISSE_CAPABILITY_MODELS stays as a per-run
  switch
- A missing secret now fails the live tests instead of skipping them
- CI passes only the three tokens
- .env.example is secrets only; spec A5 says config comes from the file

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
dongarandClaude Opus 5.5 committed 2026-09-23 23:25:58 +00:00
1 parent df449c7e34
commit 15d69799bf
28 files changed
+571 -777

No files matched your search

+2 -2
View File
@@ -121,8 +121,8 @@ class ModelCatalog:
Reported together rather than one per boot: an operator fixing a
config wants the whole list, not to rediscover the next typo on the
next start (the same reason ``AgentConfig.from_env`` batches its
missing variables).
next start (the same reason ``AgentConfig`` reports every missing
setting at once).
"""
unknown = {
role: alias for role, alias in roles.items() if alias not in self._facts
+37 -68
View File
@@ -1,14 +1,11 @@
"""Agent configuration (spec A5: nothing hardcoded).
Configuration comes from a YAML file plus the environment:
- **The file carries structure.** Roles, connections, and the tuning knobs
(see docs/Tuning-Guide.md). It holds no secrets: a credential is written as
a reference, ``token: ${NISSE_LLM_TOKEN}``, and resolved from the
environment, so the file can be reviewed or shared without leaking.
- **The environment wins.** Every setting that existed as an environment
variable still does, and overrides the file. The file is optional, so a
deployment or CI run configured purely from the environment works as before.
Configuration is a YAML file: roles, connections, and the tuning knobs (see
docs/Tuning-Guide.md). It holds no secrets. A credential is written as a
reference, ``token: ${NISSE_LLM_TOKEN}``, and resolved from the environment,
so the file can be reviewed, shared, or committed without leaking. The
environment supplies those references and nothing else: every setting has
exactly one home.
Every value is collected and validated **before** anything is built, and a
single error names every problem at once. The alternative — failing at first
@@ -31,32 +28,6 @@ from nisse_dev.matrix import MatrixConfig
DEFAULT_CONFIG_FILE = "nisse-dev.yaml"
# Each environment variable and the key it overrides. The names are the ones
# the agent has always used, so existing .env files and CI keep working.
ENV_KEYS: dict[str, str] = {
"NISSE_STATE_DB": "state_db",
"NISSE_WORKSPACE": "workspace",
"NISSE_PROJECT": "project",
"NISSE_LLM_BASE_URL": "llm.base_url",
"NISSE_LLM_TOKEN": "llm.token",
"NISSE_MAX_OUTPUT_TOKENS": "llm.max_output_tokens",
"NISSE_ROLE_EXECUTOR": "roles.executor",
"NISSE_ROLE_PLANNER": "roles.planner",
"NISSE_ROLE_DELEGATE": "roles.delegate",
"NISSE_ROLE_CONSULTANT": "roles.consultant",
"NISSE_MATRIX_HOMESERVER": "matrix.homeserver",
"NISSE_MATRIX_USER_ID": "matrix.user_id",
"NISSE_MATRIX_TOKEN": "matrix.token",
"NISSE_MATRIX_ROOM_ID": "matrix.room_id",
"NISSE_MATRIX_OPERATORS": "matrix.operators",
"NISSE_GITEA_URL": "gitea.url",
"NISSE_GITEA_TOKEN": "gitea.token",
"NISSE_GITEA_REPO": "gitea.repo",
"NISSE_GITEA_OPERATORS": "gitea.operators",
"NISSE_BASE_BRANCH": "gitea.base_branch",
}
KEY_ENV = {key: env for env, key in ENV_KEYS.items()}
REQUIRED_KEYS = (
"state_db",
"workspace",
@@ -78,8 +49,6 @@ REQUIRED_KEYS = (
"gitea.operators",
)
OPTIONAL_KEYS = ("llm.max_output_tokens", "gitea.base_branch")
# Kept for callers that list what a pure-environment deployment must set.
REQUIRED = tuple(KEY_ENV[key] for key in REQUIRED_KEYS)
_REFERENCE = re.compile(r"\$\{([A-Za-z_][A-Za-z0-9_]*)\}")
@@ -226,11 +195,6 @@ def _read_file(path: Path, errors: list[str]) -> dict[str, Any]:
return loaded
def _describe(key: str) -> str:
env = KEY_ENV.get(key)
return f"{key} ({env})" if env else key
@dataclass(frozen=True)
class AgentConfig:
state_db: Path
@@ -252,28 +216,39 @@ class AgentConfig:
@classmethod
def load(cls, env: Mapping[str, str] = os.environ) -> "AgentConfig":
"""The file named by NISSE_CONFIG, or ./nisse-dev.yaml if present,
overlaid by the environment. Naming a file that does not exist is an
error; the default file is simply optional."""
named = env.get("NISSE_CONFIG")
path = Path(named or DEFAULT_CONFIG_FILE).expanduser()
if named and not path.is_file():
"""The file named by NISSE_CONFIG, or ./nisse-dev.yaml."""
path = Path(env.get("NISSE_CONFIG") or DEFAULT_CONFIG_FILE).expanduser()
if not path.is_file():
raise ConfigError(
f"cannot start: NISSE_CONFIG names {path}, which is missing"
f"cannot start: no config file at {path}; create it from "
"nisse-dev.example.yaml, or point NISSE_CONFIG at one"
)
return cls.from_sources(env, path if path.is_file() else None)
return cls.from_file(path, env)
@classmethod
def from_env(cls, env: Mapping[str, str] = os.environ) -> "AgentConfig":
"""Environment only, with no file."""
return cls.from_sources(env, None)
@classmethod
def from_sources(
cls, env: Mapping[str, str], config_file: Path | None
def from_file(
cls, path: Path, env: Mapping[str, str] = os.environ
) -> "AgentConfig":
errors: list[str] = []
tree = _read_file(config_file, errors) if config_file else {}
tree = _read_file(path, errors)
return cls._build(tree, env, errors, config_file=path)
@classmethod
def from_tree(
cls, tree: Mapping[str, Any], env: Mapping[str, str] = os.environ
) -> "AgentConfig":
"""From an already-parsed config, as the file would give it."""
return cls._build(tree, env, [], config_file=None)
@classmethod
def _build(
cls,
tree: Mapping[str, Any],
env: Mapping[str, str],
errors: list[str],
*,
config_file: Path | None,
) -> "AgentConfig":
tuning = _parse_tuning(tree.get("tuning"), errors)
flat = _flatten(tree)
flat.pop("tuning", None)
@@ -281,20 +256,16 @@ class AgentConfig:
known = set(REQUIRED_KEYS) | set(OPTIONAL_KEYS)
for key in sorted(set(flat) - known):
errors.append(f"{key}: unknown setting")
overrides = {key: env[var] for var, key in ENV_KEYS.items() if var in env}
# A key the environment overrides is not resolved from the file, so a
# reference there to an unset variable is not an error.
values = {
key: _resolve(value, key, env, errors)
for key, value in flat.items()
if key in known and key not in overrides
if key in known
}
values.update(overrides)
# Whitespace-only counts as missing: a token of spaces would pass a
# truthiness check and fail at the first request instead.
missing = [
_describe(key)
key
for key in REQUIRED_KEYS
if values.get(key) is None
or (isinstance(values[key], str) and not values[key].strip())
@@ -309,9 +280,7 @@ class AgentConfig:
if max_output <= 0:
raise ValueError
except (TypeError, ValueError):
errors.append(
f"{_describe('llm.max_output_tokens')}: must be a positive integer"
)
errors.append("llm.max_output_tokens: must be a positive integer")
if errors:
raise ConfigError("cannot start: " + "; ".join(errors))
@@ -357,7 +326,7 @@ class AgentConfig:
"""
workspace = self.workspace.expanduser().resolve()
candidates = [
("NISSE_STATE_DB", self.state_db),
("state_db", self.state_db),
("NISSE_ENV", Path(env.get("NISSE_ENV", ".env"))),
]
if self.config_file is not None:
-10
View File
@@ -10,8 +10,6 @@ idempotent across a crash: boot reconciliation (A3) asks Gitea whether the
effect already happened rather than repeating it.
"""
import os
from collections.abc import Mapping
from dataclasses import dataclass
from typing import Any
@@ -60,14 +58,6 @@ class GiteaClient:
transport=transport,
)
@classmethod
def from_env(cls, env: Mapping[str, str] = os.environ) -> "GiteaClient":
base_url = env.get("NISSE_GITEA_URL")
token = env.get("NISSE_GITEA_TOKEN")
if not base_url or not token:
raise GiteaError("set NISSE_GITEA_URL and NISSE_GITEA_TOKEN")
return cls(base_url, token)
def _request(self, method: str, path: str, **kwargs: Any) -> Any:
try:
response = self._http.request(method, path, **kwargs)
+9 -46
View File
@@ -2,18 +2,16 @@
One client interface, present from the first real LLM call. All traffic goes
to the LiteLLM proxy — the VM's single LLM destination; the agent holds one
LiteLLM token and no vendor credentials. Config comes from the environment
(``NISSE_LLM_BASE_URL``, ``NISSE_LLM_TOKEN``), nothing hardcoded.
LiteLLM token and no vendor credentials. The base URL and token come from the
agent's config (nisse_dev.config), nothing hardcoded.
Model identity is expressed as roles (A11), resolved to concrete model strings
from env config; the resolved mapping is pinned at task start so a mid-task
from config; the resolved mapping is pinned at task start so a mid-task
config change cannot split a task across two planners.
"""
import json
import os
import time
from collections.abc import Mapping
from dataclasses import asdict, dataclass
from typing import Any, ClassVar, Protocol
@@ -49,11 +47,6 @@ RATE_LIMIT_RETRY_S = 20.0
DEFAULT_MAX_OUTPUT_TOKENS = 16384
def max_output_tokens(env: Mapping[str, str] = os.environ) -> int:
raw = env.get("NISSE_MAX_OUTPUT_TOKENS")
return int(raw) if raw else DEFAULT_MAX_OUTPUT_TOKENS
class UpstreamUnavailable(LLMError):
"""The proxy or provider could not be reached, or refused for reasons
unrelated to what was asked: a network blip, a timeout, a 5xx, a rate
@@ -113,22 +106,10 @@ class RoleMap:
delegate: str
consultant: str
_ENV_VARS: ClassVar[dict[str, str]] = {
"executor": "NISSE_ROLE_EXECUTOR",
"planner": "NISSE_ROLE_PLANNER",
"delegate": "NISSE_ROLE_DELEGATE",
"consultant": "NISSE_ROLE_CONSULTANT",
}
@classmethod
def from_env(cls, env: Mapping[str, str] = os.environ) -> "RoleMap":
missing = [var for var in cls._ENV_VARS.values() if not env.get(var)]
if missing:
raise LLMError(f"role mapping incomplete; set: {', '.join(missing)}")
return cls(**{role: env[var] for role, var in cls._ENV_VARS.items()})
ROLES: ClassVar[tuple[str, ...]] = ("executor", "planner", "delegate", "consultant")
def resolve(self, role: str) -> str:
if role not in self._ENV_VARS:
if role not in self.ROLES:
raise LLMError(f"unknown role: {role!r}")
return str(getattr(self, role))
@@ -156,20 +137,12 @@ class LiteLLMClient:
)
self._renderer = OpenAIChatRenderer()
self._sleep = sleep
self._max_tokens = max_tokens or max_output_tokens()
self._max_tokens = max_tokens or DEFAULT_MAX_OUTPUT_TOKENS
# Set after each call so a caller can meter itself (A13 caps);
# a side channel rather than a return value, so the LLMClient
# protocol stays the same for every implementation.
self.last_usage: dict[str, int] = {}
@classmethod
def from_env(cls, env: Mapping[str, str] = os.environ) -> "LiteLLMClient":
base_url = env.get("NISSE_LLM_BASE_URL")
token = env.get("NISSE_LLM_TOKEN")
if not base_url or not token:
raise LLMError("set NISSE_LLM_BASE_URL and NISSE_LLM_TOKEN")
return cls(base_url, token)
def complete(
self,
events: list[StoredEvent],
@@ -203,7 +176,7 @@ class LiteLLMClient:
if choice.get("finish_reason") == "length":
raise TruncatedResponse(
f"{requested_model} hit its output limit mid-answer; "
"raise NISSE_MAX_OUTPUT_TOKENS"
"raise llm.max_output_tokens"
)
produced_by = data.get("model") or requested_model
usage = data.get("usage") or {}
@@ -275,20 +248,10 @@ class AnthropicPassthroughClient:
transport=transport,
)
self._renderer = AnthropicMessagesRenderer()
self._max_tokens = max_tokens or max_output_tokens()
self._max_tokens = max_tokens or DEFAULT_MAX_OUTPUT_TOKENS
self._sleep = sleep
self.last_usage: dict[str, int] = {}
@classmethod
def from_env(
cls, env: Mapping[str, str] = os.environ
) -> "AnthropicPassthroughClient":
base_url = env.get("NISSE_LLM_BASE_URL")
token = env.get("NISSE_LLM_TOKEN")
if not base_url or not token:
raise LLMError("set NISSE_LLM_BASE_URL and NISSE_LLM_TOKEN")
return cls(base_url, token)
def complete(
self,
events: list[StoredEvent],
@@ -315,7 +278,7 @@ class AnthropicPassthroughClient:
if data.get("stop_reason") == "max_tokens":
raise TruncatedResponse(
f"{requested_model} hit the output limit of {self._max_tokens} "
f"tokens mid-answer; raise NISSE_MAX_OUTPUT_TOKENS"
f"tokens mid-answer; raise llm.max_output_tokens"
)
content = data.get("content")
if not isinstance(content, list):
+1 -26
View File
@@ -11,12 +11,10 @@ loop backs off (capped) and retries indefinitely — an outage delays reactions
but never fails anything.
"""
import os
import threading
import uuid
from collections.abc import Callable, Mapping
from collections.abc import Callable
from dataclasses import dataclass
from typing import ClassVar
import httpx
@@ -34,29 +32,6 @@ class MatrixConfig:
token: str
room_id: str
_ENV: ClassVar[tuple[str, ...]] = (
"NISSE_MATRIX_HOMESERVER",
"NISSE_MATRIX_USER_ID",
"NISSE_MATRIX_TOKEN",
)
@classmethod
def from_env(
cls,
env: Mapping[str, str] = os.environ,
room_var: str = "NISSE_MATRIX_ROOM_ID",
) -> "MatrixConfig":
needed = (*cls._ENV, room_var)
missing = [var for var in needed if not env.get(var)]
if missing:
raise TransportError(f"matrix config incomplete; set: {', '.join(missing)}")
return cls(
homeserver=env["NISSE_MATRIX_HOMESERVER"].rstrip("/"),
user_id=env["NISSE_MATRIX_USER_ID"],
token=env["NISSE_MATRIX_TOKEN"],
room_id=env[room_var],
)
class MatrixTransport:
def __init__(
+13 -12
View File
@@ -8,7 +8,7 @@ from typing import Any
import httpx
import pytest
from test_config import COMPLETE
from test_config import SECRETS, tree
from nisse_dev.agent import build_agent, discover_models, prepare_workspace
from nisse_dev.catalog import ModelCatalog, UnknownModel
@@ -34,14 +34,15 @@ TEST_CATALOG = ModelCatalog.from_payload(
)
def config_for(tmp_path: Path, **overrides: str) -> AgentConfig:
env = {
**COMPLETE,
"NISSE_STATE_DB": str(tmp_path / "state.db"),
"NISSE_WORKSPACE": str(tmp_path / "work"),
**overrides,
}
return AgentConfig.from_env(env)
def config_for(tmp_path: Path, **changes: str) -> AgentConfig:
return AgentConfig.from_tree(
tree(
state_db=str(tmp_path / "state.db"),
workspace=str(tmp_path / "work"),
**changes,
),
SECRETS,
)
@pytest.fixture
@@ -59,7 +60,7 @@ def origin(tmp_path: Path) -> Path:
def test_workspace_is_cloned_when_absent(tmp_path: Path, origin: Path) -> None:
config = config_for(tmp_path, NISSE_GITEA_URL=f"file://{origin}")
config = config_for(tmp_path, gitea__url=f"file://{origin}")
# authenticated_url would mangle a file:// remote, so clone directly.
GitRepo(tmp_path).clone(str(origin), config.workspace)
repo = prepare_workspace(config, "nisse-dev-testing")
@@ -206,7 +207,7 @@ def test_httpx_clients_are_not_shared_between_routes(
def test_a_typod_role_refuses_to_boot(tmp_path: Path, monkeypatch) -> None:
# Misconfiguration should cost a second at startup, not be discovered ten
# minutes into a milestone.
config = config_for(tmp_path, NISSE_ROLE_PLANNER="clause-opus-5")
config = config_for(tmp_path, roles__planner="clause-opus-5")
monkeypatch.setattr(
"nisse_dev.agent.ModelCatalog.discover",
classmethod(lambda cls, *a, **kw: TEST_CATALOG),
@@ -220,7 +221,7 @@ def test_a_role_this_key_cannot_reach_refuses_to_boot(
) -> None:
# /model/info is scoped per key, so the same check catches a role pointed
# at a real model that this token has no access to.
config = config_for(tmp_path, NISSE_ROLE_EXECUTOR="local-fast")
config = config_for(tmp_path, roles__executor="local-fast")
monkeypatch.setattr(
"nisse_dev.agent.ModelCatalog.discover",
classmethod(lambda cls, *a, **kw: TEST_CATALOG),
+225 -235
View File
@@ -1,163 +1,37 @@
import copy
from pathlib import Path
from typing import Any
import pytest
from nisse_dev.config import AgentConfig, ConfigError
COMPLETE = {
"NISSE_STATE_DB": "~/demo/state.db",
"NISSE_WORKSPACE": "~/demo/work",
"NISSE_PROJECT": "greet",
"NISSE_LLM_BASE_URL": "https://litellm.test",
"NISSE_LLM_TOKEN": "sk-x",
"NISSE_ROLE_EXECUTOR": "claude-haiku-4-5",
"NISSE_ROLE_PLANNER": "claude-opus-5",
"NISSE_ROLE_DELEGATE": "claude-opus-5",
"NISSE_ROLE_CONSULTANT": "claude-haiku-4-5",
"NISSE_MATRIX_HOMESERVER": "https://matrix.test",
"NISSE_MATRIX_USER_ID": "@nisse-dev-testing:test",
"NISSE_MATRIX_TOKEN": "syt_x",
"NISSE_MATRIX_ROOM_ID": "!room:test",
"NISSE_MATRIX_OPERATORS": "@don:test",
"NISSE_GITEA_URL": "https://gitea.test",
"NISSE_GITEA_TOKEN": "gt",
"NISSE_GITEA_REPO": "don/demo",
"NISSE_GITEA_OPERATORS": "don",
# A complete config as the YAML file would give it, with secrets by reference.
COMPLETE: dict[str, Any] = {
"state_db": "~/demo/state.db",
"workspace": "~/demo/work",
"project": "greet",
"llm": {"base_url": "https://litellm.test", "token": "${TEST_LLM_TOKEN}"},
"roles": {
"executor": "claude-haiku-4-5",
"planner": "claude-opus-5",
"delegate": "claude-opus-5",
"consultant": "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}",
"repo": "don/demo",
"operators": ["don"],
},
}
def test_complete_environment_builds() -> None:
config = AgentConfig.from_env(COMPLETE)
assert config.project == "greet"
assert config.roles.planner == "claude-opus-5"
assert config.matrix.room_id == "!room:test"
assert config.gitea_repo == "don/demo"
assert config.base_branch == "main"
def test_paths_expand_the_home_directory() -> None:
config = AgentConfig.from_env(COMPLETE)
assert config.workspace.is_absolute()
assert "~" not in str(config.state_db)
def test_every_missing_variable_is_reported_at_once() -> None:
# Failing at first use would surface a missing token twenty minutes into
# a milestone, on the call that mattered.
partial = {k: v for k, v in COMPLETE.items() if k != "NISSE_MATRIX_TOKEN"}
partial.pop("NISSE_GITEA_REPO")
with pytest.raises(ConfigError) as excinfo:
AgentConfig.from_env(partial)
message = str(excinfo.value)
assert "NISSE_MATRIX_TOKEN" in message
assert "NISSE_GITEA_REPO" in message
def test_empty_is_treated_as_missing() -> None:
with pytest.raises(ConfigError, match="NISSE_GITEA_TOKEN"):
AgentConfig.from_env({**COMPLETE, "NISSE_GITEA_TOKEN": " "})
def test_operator_lists_are_split_and_trimmed() -> None:
config = AgentConfig.from_env(
{
**COMPLETE,
"NISSE_MATRIX_OPERATORS": " @don:test , @other:test ,",
"NISSE_GITEA_OPERATORS": "don,",
}
)
assert config.operators == {"@don:test", "@other:test"}
# A trailing comma must not admit an empty identity into an allowlist.
assert "" not in config.operators
assert config.gitea_operators == {"don"}
def test_base_branch_is_overridable() -> None:
config = AgentConfig.from_env({**COMPLETE, "NISSE_BASE_BRANCH": "trunk"})
assert config.base_branch == "trunk"
def test_redacted_summary_carries_no_secrets() -> None:
summary = AgentConfig.from_env(COMPLETE).redacted()
flat = " ".join(summary.values())
for secret in ("sk-x", "syt_x", "gt"):
assert secret not in flat
assert summary["project"] == "greet"
def test_state_db_and_workspace_are_separate(tmp_path: Path) -> None:
# A2: build artefacts must not share a volume with agent state.
config = AgentConfig.from_env(COMPLETE)
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"):
AgentConfig.from_env(
{
**COMPLETE,
"NISSE_WORKSPACE": str(work),
"NISSE_STATE_DB": str(work / "state.db"),
}
)
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_env(
{
**COMPLETE,
"NISSE_WORKSPACE": str(work),
"NISSE_STATE_DB": str(tmp_path / "state.db"),
"NISSE_ENV": str(work / ".env"),
}
)
def test_sibling_paths_are_fine(tmp_path: Path) -> None:
config = AgentConfig.from_env(
{
**COMPLETE,
"NISSE_WORKSPACE": str(tmp_path / "project"),
"NISSE_STATE_DB": str(tmp_path / "state.db"),
"NISSE_ENV": str(tmp_path / ".env"),
}
)
assert config.workspace.name == "project"
# --- the YAML file (#32) ---------------------------------------------------
FILE = """
state_db: ~/demo/state.db
workspace: ~/demo/work
project: greet
llm:
base_url: https://litellm.test
token: ${TEST_LLM_TOKEN}
roles:
executor: local-fast
planner: claude-opus-5
delegate: claude-opus-5
consultant: 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}
repo: don/demo
operators: [don]
"""
SECRETS = {
"TEST_LLM_TOKEN": "sk-x",
"TEST_MATRIX_TOKEN": "syt_x",
@@ -165,86 +39,133 @@ SECRETS = {
}
def write(tmp_path: Path, text: str) -> Path:
path = tmp_path / "nisse-dev.yaml"
path.write_text(text)
return path
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 test_a_file_configures_everything_with_secrets_by_reference(
tmp_path: Path,
) -> None:
config = AgentConfig.from_sources(SECRETS, write(tmp_path, FILE))
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.executor == "local-fast"
assert config.operators == {"@don:test"} # a blank entry admits no one
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 == 24 # absent section: defaults
def test_the_environment_wins_over_the_file(tmp_path: Path) -> None:
config = AgentConfig.from_sources(
{**SECRETS, "NISSE_ROLE_EXECUTOR": "claude-haiku-4-5"}, write(tmp_path, FILE)
)
assert config.roles.executor == "claude-haiku-4-5"
def test_paths_expand_the_home_directory() -> None:
config = build()
assert config.workspace.is_absolute()
assert "~" not in str(config.state_db)
def test_an_overridden_key_needs_no_resolvable_reference(tmp_path: Path) -> None:
env = {k: v for k, v in SECRETS.items() if k != "TEST_LLM_TOKEN"}
config = AgentConfig.from_sources(
{**env, "NISSE_LLM_TOKEN": "sk-env"}, write(tmp_path, FILE)
)
assert config.llm_token == "sk-env"
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, gitea__repo=None)
message = str(excinfo.value)
assert "matrix.token" in message
assert "gitea.repo" in message
def test_a_reference_to_an_unset_variable_is_an_error(tmp_path: Path) -> None:
def test_empty_is_treated_as_missing() -> None:
with pytest.raises(ConfigError, match="gitea.repo"):
build(gitea__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_sources(env, write(tmp_path, FILE))
AgentConfig.from_tree(tree(), env)
def test_tuning_is_read_from_the_file(tmp_path: Path) -> None:
text = (
FILE
+ """
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}
"""
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(gitea__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_redacted_summary_carries_no_secrets() -> None:
summary = build().redacted()
flat = " ".join(summary.values())
for secret in SECRETS.values():
assert secret not in flat
assert summary["project"] == "greet"
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},
}
)
tuning = AgentConfig.from_sources(SECRETS, write(tmp_path, text)).tuning
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
# A section that is only partly given keeps defaults for the rest.
partial = FILE + "\ntuning:\n executor: {max_turns: 40}\n"
tuning = AgentConfig.from_sources(SECRETS, write(tmp_path, partial)).tuning
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_in_a_file_is_reported_at_once(tmp_path: Path) -> None:
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.
text = (
FILE.replace("project: greet\n", "")
+ """
llm_extra: 1
tuning:
executor: {max_turn: 40, failure_limit: 0}
expert: {consult_budget: true}
bogus: {x: 1}
"""
)
bad = tree(project=None, llm_extra=1)
bad["tuning"] = {
"executor": {"max_turn": 40, "failure_limit": 0},
"expert": {"consult_budget": True},
"bogus": {"x": 1},
}
with pytest.raises(ConfigError) as excinfo:
AgentConfig.from_sources(SECRETS, write(tmp_path, text))
AgentConfig.from_tree(bad, SECRETS)
message = str(excinfo.value)
for expected in (
"project (NISSE_PROJECT)",
"project",
"llm_extra: unknown setting",
"tuning.executor.max_turn: unknown setting",
"tuning.executor.failure_limit: must be a positive number",
@@ -254,50 +175,76 @@ tuning:
assert expected in message
def test_a_whole_number_is_required_where_one_is_meant(tmp_path: Path) -> None:
text = FILE + "\ntuning:\n executor: {max_turns: 2.5}\n"
def test_a_whole_number_is_required_where_one_is_meant() -> None:
with pytest.raises(ConfigError, match="tuning.executor.max_turns"):
AgentConfig.from_sources(SECRETS, write(tmp_path, text))
build(tuning={"executor": {"max_turns": 2.5}})
def test_max_output_tokens_comes_from_the_file_or_the_environment(
tmp_path: Path,
) -> None:
text = FILE.replace(
" base_url: https://litellm.test\n",
" base_url: https://litellm.test\n max_output_tokens: 8192\n",
)
path = write(tmp_path, text)
assert AgentConfig.from_sources(SECRETS, path).max_output_tokens == 8192
env = {**SECRETS, "NISSE_MAX_OUTPUT_TOKENS": "4096"}
assert AgentConfig.from_sources(env, path).max_output_tokens == 4096
# --- the file --------------------------------------------------------------
FILE = """
state_db: ~/demo/state.db
workspace: ~/demo/work
project: greet
llm: {base_url: "https://litellm.test", token: "${TEST_LLM_TOKEN}"}
roles:
executor: local-fast
planner: claude-opus-5
delegate: claude-opus-5
consultant: 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}
repo: don/demo
operators: [don]
"""
def test_load_finds_the_named_file_and_refuses_a_missing_one(tmp_path: Path) -> None:
path = write(tmp_path, FILE)
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"
with pytest.raises(ConfigError, match="missing"):
AgentConfig.load({**SECRETS, "NISSE_CONFIG": str(tmp_path / "absent.yaml")})
def test_load_without_a_file_uses_the_environment(
def test_load_defaults_to_the_working_directory(
tmp_path: Path, monkeypatch: pytest.MonkeyPatch
) -> None:
monkeypatch.chdir(tmp_path) # no ./nisse-dev.yaml here
assert AgentConfig.load(COMPLETE).config_file is None
write(tmp_path)
monkeypatch.chdir(tmp_path)
assert AgentConfig.load(SECRETS).project == "greet"
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}")
path = work / "nisse-dev.yaml"
path.write_text(text)
with pytest.raises(ConfigError, match="NISSE_CONFIG"):
AgentConfig.from_sources(SECRETS, path)
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(tmp_path: Path) -> None:
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 = {
@@ -305,5 +252,48 @@ def test_the_example_file_is_valid(tmp_path: Path) -> None:
"NISSE_MATRIX_TOKEN": "syt_x",
"NISSE_GITEA_TOKEN": "gt",
}
config = AgentConfig.from_sources(env, example)
assert config.tuning.executor.max_turns == 24
assert AgentConfig.from_file(example, env).tuning.executor.max_turns == 24
# --- nothing that carries secrets may sit inside the clone -----------------
def test_state_db_and_workspace_are_separate() -> None:
# A2: 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(workspace=str(work), state_db=str(work / "state.db"))
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(workspace=str(work), state_db=str(tmp_path / "state.db")),
{**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}")
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(workspace=str(tmp_path / "project"), state_db=str(tmp_path / "state.db")),
{**SECRETS, "NISSE_ENV": str(tmp_path / ".env")},
)
assert config.workspace.name == "project"
+7 -9
View File
@@ -2,25 +2,23 @@ from pathlib import Path
import pytest
from nisse_dev.config import REQUIRED
from nisse_dev.main import main
def test_main_refuses_to_start_without_configuration(
def test_main_refuses_to_start_without_a_config_file(
monkeypatch: pytest.MonkeyPatch,
capsys: pytest.CaptureFixture[str],
tmp_path: Path,
) -> None:
# Clear the real variables rather than swapping os.environ: from_env binds
# the environment object as a default argument, so a replacement would be
# ignored. And point NISSE_ENV at a file that does not exist, because the
# working directory's .env holds live credentials.
for name in REQUIRED:
monkeypatch.delenv(name, raising=False)
# Run from an empty directory, and point NISSE_ENV at a file that does not
# exist: the repository's .env holds live credentials, and a test must
# never be one cwd away from starting a real agent.
monkeypatch.chdir(tmp_path)
monkeypatch.delenv("NISSE_CONFIG", raising=False)
monkeypatch.setenv("NISSE_ENV", str(tmp_path / "absent.env"))
assert main() == 2
err = capsys.readouterr().err
assert "cannot start" in err
assert "NISSE_LLM_TOKEN" in err
assert "nisse-dev.example.yaml" in err
-5
View File
@@ -162,11 +162,6 @@ def test_list_comments_passes_since() -> None:
assert seen["since"] == "2026-09-07T00:00:00Z"
def test_from_env_requires_config() -> None:
with pytest.raises(GiteaError, match="NISSE_GITEA_URL"):
GiteaClient.from_env({})
# --- reconciler (A3 external truth) --------------------------------------
+11 -23
View File
@@ -21,7 +21,6 @@ from nisse_dev.llm import (
RoleMap,
TruncatedResponse,
UpstreamUnavailable,
max_output_tokens,
)
EVENTS = [StoredEvent(id=1, ts="t", event=UserMessage(text="hi", source="m:1"))]
@@ -165,16 +164,16 @@ def test_malformed_response_raises_llm_error() -> None:
client.complete(EVENTS, tools=None, model="local/qwen")
ROLE_ENV = {
"NISSE_ROLE_EXECUTOR": "local/qwen",
"NISSE_ROLE_PLANNER": "anthropic/claude-opus-5",
"NISSE_ROLE_DELEGATE": "anthropic/claude-opus-5",
"NISSE_ROLE_CONSULTANT": "anthropic/claude-opus-5",
}
ROLES = RoleMap(
executor="local/qwen",
planner="anthropic/claude-opus-5",
delegate="anthropic/claude-opus-5",
consultant="anthropic/claude-opus-5",
)
def test_role_map_resolves_and_pins() -> None:
roles = RoleMap.from_env(ROLE_ENV)
roles = ROLES
assert roles.resolve("executor") == "local/qwen"
assert roles.pinned() == {
"executor": "local/qwen",
@@ -184,19 +183,9 @@ def test_role_map_resolves_and_pins() -> None:
}
def test_role_map_missing_env_raises() -> None:
with pytest.raises(LLMError, match="NISSE_ROLE_PLANNER"):
RoleMap.from_env({"NISSE_ROLE_EXECUTOR": "local/qwen"})
def test_unknown_role_raises() -> None:
with pytest.raises(LLMError, match="unknown role"):
RoleMap.from_env(ROLE_ENV).resolve("boss")
def test_client_from_env_requires_config() -> None:
with pytest.raises(LLMError, match="NISSE_LLM_BASE_URL"):
LiteLLMClient.from_env({})
ROLES.resolve("boss")
def test_load_env_file(tmp_path: Path) -> None:
@@ -306,12 +295,11 @@ def test_a_complete_answer_is_not_mistaken_for_truncation() -> None:
assert call.arguments["content"] == "a real plan"
def test_output_ceiling_is_configurable_and_generous_by_default() -> None:
def test_output_ceiling_is_generous_by_default() -> None:
# Output is billed by what is produced, so a low ceiling buys nothing and
# costs silent truncation.
# costs silent truncation. The configured value is tested in test_config.
assert DEFAULT_MAX_OUTPUT_TOKENS >= 8192
assert max_output_tokens({}) == DEFAULT_MAX_OUTPUT_TOKENS
assert max_output_tokens({"NISSE_MAX_OUTPUT_TOKENS": "2048"}) == 2048
assert LiteLLMClient("http://x", "t")._max_tokens == DEFAULT_MAX_OUTPUT_TOKENS
def test_truncation_is_an_llm_error_so_callers_already_handle_it() -> None:
-17
View File
@@ -143,20 +143,3 @@ def test_start_without_handler_raises() -> None:
)
with pytest.raises(TransportError, match="no message handler"):
transport.start()
def test_config_from_env_reports_missing() -> None:
with pytest.raises(TransportError, match="NISSE_MATRIX_TOKEN"):
MatrixConfig.from_env({"NISSE_MATRIX_HOMESERVER": "https://m"})
def test_config_from_env_custom_room_var() -> None:
env = {
"NISSE_MATRIX_HOMESERVER": "https://m/",
"NISSE_MATRIX_USER_ID": "@nisse-dev:test",
"NISSE_MATRIX_TOKEN": "t",
"NISSE_MATRIX_TEST_ROOM_ID": "!t:test",
}
config = MatrixConfig.from_env(env, room_var="NISSE_MATRIX_TEST_ROOM_ID")
assert config.room_id == "!t:test"
assert config.homeserver == "https://m" # trailing slash stripped