feat(agents): configurable LLM model + effort per-agent and per-project (ORCH-41) (#36)

tests/test_resolve_agent_effort.py

@@ -0,0 +1,138 @@
+"""ORCH-41: tests for resolve_agent_effort + effort validation + flag assembly.
+
+Mirrors test_resolve_agent_model's 4-level priority for the --effort lever, and
+adds:
+  - validation: a value outside {low,medium,high,xhigh,max} is dropped -> ""
+  - flag assembly: --model / --effort / --fallback-model are present/absent in
+    the built command exactly when the resolved value is non-empty.
+"""
+import os
+import tempfile
+
+import pytest
+
+os.environ.setdefault("ORCH_DB_PATH",
+                      os.path.join(tempfile.gettempdir(), "test_orch41_effort.db"))
+os.environ.setdefault("ORCH_GITEA_TOKEN", "test-token")
+os.environ.setdefault("ORCH_PLANE_API_TOKEN", "test-token")
+
+from src.agents.launcher import (
+    resolve_agent_effort, resolve_agent_model, VALID_EFFORTS,
+)
+from src.config import settings
+from src import projects as P
+from src.projects import ProjectConfig, reload_projects
+
+ORCH_PLANE_ID = "8da6aa25-a60e-44d6-a1e2-d8ae59aa7d6a"
+
+
+@pytest.fixture(autouse=True)
+def _clean_settings(monkeypatch):
+    monkeypatch.setattr(settings, "agent_effort_default", "high")
+    for a in ("analyst", "architect", "developer", "reviewer"):
+        monkeypatch.setattr(settings, f"agent_effort_{a}", "high")
+    for a in ("tester", "deployer"):
+        monkeypatch.setattr(settings, f"agent_effort_{a}", "medium")
+    monkeypatch.setattr(P.settings, "projects_json", "")
+    reload_projects()
+    yield
+    reload_projects()
+
+
+def _install_registry(monkeypatch, agent_efforts):
+    reg = [ProjectConfig(
+        plane_project_id=ORCH_PLANE_ID, repo="orchestrator",
+        work_item_prefix="ORCH", name="orchestrator",
+        agent_efforts=agent_efforts,
+    )]
+    monkeypatch.setattr(P, "PROJECTS", reg)
+    monkeypatch.setattr(P, "_BY_PLANE_ID", {p.plane_project_id: p for p in reg})
+    monkeypatch.setattr(P, "_BY_REPO", {p.repo: p for p in reg})
+
+
+# ---- default split ----------------------------------------------------------
+def test_default_split():
+    assert resolve_agent_effort("developer") == "high"
+    assert resolve_agent_effort("architect") == "high"
+    assert resolve_agent_effort("tester") == "medium"
+    assert resolve_agent_effort("deployer") == "medium"
+
+
+# ---- level 4: nothing -> "" -------------------------------------------------
+def test_no_config_returns_empty(monkeypatch):
+    monkeypatch.setattr(settings, "agent_effort_default", "")
+    monkeypatch.setattr(settings, "agent_effort_tester", "")
+    assert resolve_agent_effort("tester") == ""
+
+
+# ---- level 2: per-agent env beats default -----------------------------------
+def test_per_agent_env(monkeypatch):
+    monkeypatch.setattr(settings, "agent_effort_tester", "low")
+    assert resolve_agent_effort("tester") == "low"
+
+
+# ---- level 1: project override wins -----------------------------------------
+def test_project_override(monkeypatch):
+    monkeypatch.setattr(settings, "agent_effort_developer", "high")
+    _install_registry(monkeypatch, {"developer": "xhigh"})
+    assert resolve_agent_effort("developer", ORCH_PLANE_ID) == "xhigh"
+    assert resolve_agent_effort("developer") == "high"
+
+
+# ---- validation: invalid value dropped --------------------------------------
+def test_invalid_default_dropped(monkeypatch):
+    monkeypatch.setattr(settings, "agent_effort_developer", "")
+    monkeypatch.setattr(settings, "agent_effort_default", "turbo")
+    assert resolve_agent_effort("developer") == ""
+
+
+def test_invalid_env_dropped(monkeypatch):
+    monkeypatch.setattr(settings, "agent_effort_reviewer", "ultra")
+    assert resolve_agent_effort("reviewer") == ""
+
+
+def test_invalid_project_override_dropped(monkeypatch):
+    _install_registry(monkeypatch, {"developer": "bogus"})
+    assert resolve_agent_effort("developer", ORCH_PLANE_ID) == ""
+
+
+def test_all_valid_efforts_pass(monkeypatch):
+    monkeypatch.setattr(settings, "agent_effort_developer", "")
+    for e in VALID_EFFORTS:
+        monkeypatch.setattr(settings, "agent_effort_default", e)
+        assert resolve_agent_effort("developer") == e
+
+
+# ---- flag assembly (mirror of launcher cmd construction) --------------------
+def _build_flags(model, effort, fb):
+    model_flag = f"--model {model} " if model else ""
+    effort_flag = f"--effort {effort} " if effort else ""
+    fb_flag = f"--fallback-model {fb} " if fb else ""
+    return f"{model_flag}{effort_flag}{fb_flag}"
+
+
+def test_flags_present_when_configured(monkeypatch):
+    monkeypatch.setattr(settings, "agent_fallback_model", "claude-sonnet-4-6")
+    model = resolve_agent_model("developer")
+    effort = resolve_agent_effort("developer")
+    fb = settings.agent_fallback_model
+    flags = _build_flags(model, effort, fb)
+    assert "--model claude-opus-4-8 " in flags
+    assert "--effort high " in flags
+    assert "--fallback-model claude-sonnet-4-6 " in flags
+
+
+def test_flags_absent_when_empty(monkeypatch):
+    monkeypatch.setattr(settings, "agent_model_default", "")
+    monkeypatch.setattr(settings, "agent_model_developer", "")
+    monkeypatch.setattr(settings, "agent_effort_default", "")
+    monkeypatch.setattr(settings, "agent_effort_developer", "")
+    monkeypatch.setattr(settings, "agent_fallback_model", "")
+    model = resolve_agent_model("developer")
+    effort = resolve_agent_effort("developer")
+    fb = settings.agent_fallback_model
+    flags = _build_flags(model, effort, fb)
+    assert flags == ""
+    assert "--model" not in flags
+    assert "--effort" not in flags
+    assert "--fallback-model" not in flags