Make the config file the only home for settings

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>

nisse-dev/src/nisse_dev/catalog.py

@@ -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

nisse-dev/src/nisse_dev/config.py

@@ -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:

nisse-dev/src/nisse_dev/gitea.py

@@ -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)

nisse-dev/src/nisse_dev/llm.py

@@ -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):

nisse-dev/src/nisse_dev/matrix.py

@@ -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__(