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>

tests/integration/test_expert_live.py

@@ -5,40 +5,34 @@ that parses against our local schema, since no API-level enforcement exists.
 """
 
 import io
-import os
 from pathlib import Path
 
 import pytest
 
-from nisse_dev.envfile import load_env_file
 from nisse_dev.evals import collect
 from nisse_dev.expert import BudgetExhausted, ExpertDesk
 from nisse_dev.llm import LiteLLMClient, RoleMap
 from nisse_dev.oplog import OpLog
 from nisse_dev.state import StateStore
 
-load_env_file(Path(__file__).resolve().parents[2] / ".env")
-
-SENTINEL = "NISSE_LIVE_PLANNER_MODEL"
-
-pytestmark = [
-    pytest.mark.integration,
-    pytest.mark.skipif(
-        not os.environ.get(SENTINEL),
-        reason=f"no live frontier route configured ({SENTINEL} unset)",
-    ),
-]
+pytestmark = pytest.mark.integration
 
 
-def desk(tmp_path: Path, budget: int = 2) -> tuple[ExpertDesk, StateStore]:
-    model = os.environ[SENTINEL]
-    roles = RoleMap(executor=model, planner=model, delegate=model, consultant=model)
-    store = StateStore(tmp_path / "state.db", oplog=OpLog("nisse-dev", io.StringIO()))
-    return ExpertDesk(LiteLLMClient.from_env(), store, roles, budget=budget), store
+@pytest.fixture
+def desk(tmp_path: Path, litellm: LiteLLMClient, live_model: str):
+    def make(budget: int = 2) -> tuple[ExpertDesk, StateStore]:
+        model = live_model
+        roles = RoleMap(executor=model, planner=model, delegate=model, consultant=model)
+        store = StateStore(
+            tmp_path / "state.db", oplog=OpLog("nisse-dev", io.StringIO())
+        )
+        return ExpertDesk(litellm, store, roles, budget=budget), store
+
+    return make
 
 
-def test_live_consult_parses_against_the_local_schema(tmp_path: Path) -> None:
-    expert, store = desk(tmp_path)
+def test_live_consult_parses_against_the_local_schema(desk) -> None:
+    expert, store = desk()
 
     answer = expert.ask(
         "For a single-process agent storing a few thousand rows of task state, "
@@ -53,8 +47,8 @@ def test_live_consult_parses_against_the_local_schema(tmp_path: Path) -> None:
     assert record.exit_status == "answered"
 
 
-def test_live_budget_stops_a_circling_caller(tmp_path: Path) -> None:
-    expert, _ = desk(tmp_path, budget=1)
+def test_live_budget_stops_a_circling_caller(desk) -> None:
+    expert, _ = desk(budget=1)
     expert.ask("Name one advantage of WAL mode in SQLite. Be brief.")
     with pytest.raises(BudgetExhausted):
         expert.ask("And another?")