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_model_capability.py

@@ -14,7 +14,6 @@ because it spends real tokens across several models.
 """
 
 import os
-from pathlib import Path
 
 import pytest
 
@@ -26,14 +25,12 @@ from nisse_dev.canonical import (
     UserMessage,
 )
 from nisse_dev.catalog import ModelCatalog, select_client
-from nisse_dev.envfile import load_env_file
+from nisse_dev.config import AgentConfig
 from nisse_dev.expert import parse_answer
 from nisse_dev.llm import AnthropicPassthroughClient, LiteLLMClient, LLMError
 from nisse_dev.planner import PLANNER_TOOLS
 from nisse_dev.tools import EXECUTOR_TOOLS
 
-load_env_file(Path(__file__).resolve().parents[2] / ".env")
-
 SENTINEL = "NISSE_CAPABILITY_MODELS"
 MODELS = [m.strip() for m in os.environ.get(SENTINEL, "").split(",") if m.strip()]
 
@@ -45,17 +42,18 @@ pytestmark = [
 ]
 
 
-def clients() -> tuple[LiteLLMClient, AnthropicPassthroughClient]:
-    return LiteLLMClient.from_env(), AnthropicPassthroughClient.from_env()
+@pytest.fixture
+def routes(
+    litellm: LiteLLMClient, passthrough: AnthropicPassthroughClient
+) -> tuple[LiteLLMClient, AnthropicPassthroughClient]:
+    return litellm, passthrough
 
 
 @pytest.fixture(scope="module")
-def catalog() -> ModelCatalog:
+def catalog(live_config: AgentConfig) -> ModelCatalog:
     """The live catalog this key can see. /model/info is scoped per key, so
     the probe list and the key have to agree."""
-    return ModelCatalog.discover(
-        os.environ["NISSE_LLM_BASE_URL"], os.environ["NISSE_LLM_TOKEN"]
-    )
+    return ModelCatalog.discover(live_config.llm_base_url, live_config.llm_token)
 
 
 def user(text: str) -> list[StoredEvent]:
@@ -63,8 +61,8 @@ def user(text: str) -> list[StoredEvent]:
 
 
 @pytest.mark.parametrize("model", MODELS)
-def test_model_answers_at_all(model: str, catalog: ModelCatalog) -> None:
-    normalized, passthrough = clients()
+def test_model_answers_at_all(model: str, catalog: ModelCatalog, routes) -> None:
+    normalized, passthrough = routes
     client = select_client(model, normalized, passthrough, catalog)
     produced = client.complete(
         user("Reply with exactly one word: pong"), None, model, system="Be terse."
@@ -74,10 +72,12 @@ def test_model_answers_at_all(model: str, catalog: ModelCatalog) -> None:
 
 
 @pytest.mark.parametrize("model", MODELS)
-def test_model_holds_the_planner_contract(model: str, catalog: ModelCatalog) -> None:
+def test_model_holds_the_planner_contract(
+    model: str, catalog: ModelCatalog, routes
+) -> None:
     """A4's gating is structural at the tool layer: a model that answers in
     prose cannot be gated, because there is no plan to approve."""
-    normalized, passthrough = clients()
+    normalized, passthrough = routes
     client = select_client(model, normalized, passthrough, catalog)
     produced = client.complete(
         user("Draft an architecture plan for a command-line slug generator."),
@@ -101,10 +101,12 @@ def test_model_holds_the_planner_contract(model: str, catalog: ModelCatalog) ->
 
 
 @pytest.mark.parametrize("model", MODELS)
-def test_model_round_trips_a_tool_result(model: str, catalog: ModelCatalog) -> None:
+def test_model_round_trips_a_tool_result(
+    model: str, catalog: ModelCatalog, routes
+) -> None:
     """The executor loop feeds results back; a model that cannot consume its
     own tool result cannot run a milestone."""
-    normalized, passthrough = clients()
+    normalized, passthrough = routes
     client = select_client(model, normalized, passthrough, catalog)
     events = user("List the files in the current directory using your tools.")
     produced = client.complete(events, EXECUTOR_TOOLS, model, system="Use a tool.")
@@ -130,11 +132,11 @@ def test_model_round_trips_a_tool_result(model: str, catalog: ModelCatalog) -> N
 
 @pytest.mark.parametrize("model", MODELS)
 def test_model_holds_the_prompt_level_json_contract(
-    model: str, catalog: ModelCatalog
+    model: str, catalog: ModelCatalog, routes
 ) -> None:
     """A14 contracts structured output at the prompt level because vendors
     differ on JSON enforcement. This measures whether that holds per model."""
-    normalized, passthrough = clients()
+    normalized, passthrough = routes
     client = select_client(model, normalized, passthrough, catalog)
     produced = client.complete(
         user("Is SQLite sufficient for a single-process agent's task state?"),
@@ -153,11 +155,13 @@ def test_model_holds_the_prompt_level_json_contract(
 
 
 @pytest.mark.parametrize("model", MODELS)
-def test_route_selection_matches_the_model(model: str, catalog: ModelCatalog) -> None:
+def test_route_selection_matches_the_model(
+    model: str, catalog: ModelCatalog, routes
+) -> None:
     """A non-Anthropic model must not be sent Anthropic-shaped bodies. This
     was hardcoded until gpt-6-astra made it observable, and name-sniffed until
     semantic aliases made the name stop meaning anything."""
-    normalized, passthrough = clients()
+    normalized, passthrough = routes
     facts = catalog.facts(model)
     chosen = select_client(model, normalized, passthrough, catalog)
     if facts.provider == "anthropic":