agy تنها ارائه‌دهندهٔ مدل؛ حذف بخش ارائه‌دهنده‌ها و افزودن زنجیرهٔ انتخاب مدل

- حذف کامل providerهای mock و openai_compatible: دامنه، آداپوترها، رجیستری، کانفیگ، seed و رابطٔ مدیریت
- بخش «ارائه‌دهنده‌ها» از کنسول حذف شد؛ ورود اکانت‌ها فقط از صفحهٔ اکانت‌های agy
- صفحهٔ مدل‌ها بازطراحی شد: ارائه‌دهنده → اکانت → مدل (کاتالوگ لحظه‌ای و زندهٔ همان اکانت از Google) → افورت استدلال؛ بدون هیچ ورود دستی نام مدل
- مدل‌ها ستون reasoning_effort گرفتند؛ آداپتور آن را به thinkingConfig (بودجهٔ ۱۰۲۴ تا ۳۲۷۶۸) ترجمه می‌کند و فقط به مدل‌های استدلالی می‌فرستد
- مهاجرت c2d3e4f5b6a7: افزودن reasoning_effort و حذف ردیف‌های providerهای قدیمی
- تست‌ها: ۲۴۶ تست بک‌اند و ۵۱ تست فرانت سبز؛ ruff و mypy و tsc و eslint تمیز

apps/api/tests/test_agy.py

@@ -344,41 +344,42 @@ async def test_seed_creates_agy_catalog(client, seeded_install, session_factory)
         "claude-opus-4-5-thinking",
         "gpt-oss-120b-medium",
     }
-    # Default deployment keeps routing on mock: agy models wait inactive.
-    assert all(active is False for _, active in models)
-
-
-async def test_seed_activates_agy_when_it_is_default(
-    monkeypatch, client, seeded_install, session_factory
-):
-    from app.core.config import settings
-
-    monkeypatch.setattr(settings, "ai_default_provider", "agy")
-    await seeded_install.seed()
-    models = await _agy_models(session_factory)
+    # agy is the only provider: the catalog is routable from the first run.
     assert all(active is True for _, active in models)
 
 
-async def test_seed_deactivates_mock_when_agy_is_default(
-    monkeypatch, client, seeded_install, session_factory
-):
+async def test_seed_round_trips_efforts(client, seeded_install, session_factory):
+    """The seed's effort column is what the adapter later sends to Google."""
     from sqlalchemy import select
 
-    from app.core.config import settings
     from app.infrastructure.db.models import AiModelRow, AiProviderRow
 
-    monkeypatch.setattr(settings, "ai_default_provider", "agy")
-    await seeded_install.seed()
-
     async with session_factory() as session:
         rows = (
             await session.execute(
                 select(AiModelRow)
                 .join(AiProviderRow, AiModelRow.provider_id == AiProviderRow.id)
-                .where(AiProviderRow.name == "mock")
+                .where(AiProviderRow.name == "agy")
             )
         ).scalars()
-        assert all(row.is_active is False for row in rows)
+        efforts = {row.internal_name: row.reasoning_effort for row in rows}
+    assert efforts["gemini-3-pro-high"] == "high"
+    assert efforts["claude-sonnet-4-5-thinking"] == "high"
+    assert efforts["gemini-3-flash"] == ""
+
+
+async def test_seed_leaves_no_legacy_providers(client, seeded_install, session_factory):
+    """agy is the only provider row a seeded install may carry."""
+    from sqlalchemy import select
+
+    from app.infrastructure.db.models import AiProviderRow
+
+    async with session_factory() as session:
+        rows = (await session.execute(select(AiProviderRow))).scalars()
+        types = {row.type for row in rows}
+        names = {row.name for row in rows}
+    assert types == {"agy"}
+    assert "mock" not in names
 
 
 # ---------------------------------------------------------------------------
@@ -519,6 +520,64 @@ def test_payload_translation(decrypted):
     assert all(s["threshold"] == "OFF" for s in payload["request"]["safetySettings"])
 
 
+def test_effort_becomes_a_thinking_config_on_a_thinking_model():
+    """Effort is translated, not forwarded: high → a 16384-token budget."""
+    account = agy.AgyAccount(
+        credential_id="c1", email="a@b.c", project_id="proj-1", refresh_token="refresh-1"
+    )
+    payload = agy._build_generate_payload(
+        account,
+        "claude-sonnet-4-5-thinking",
+        [ChatMessage(role="user", content="سلام")],
+        system="",
+        temperature=0.4,
+        max_tokens=512,
+        reasoning_effort="high",
+    )
+    generation = payload["request"]["generationConfig"]
+    assert generation["thinkingConfig"] == {
+        "thinkingBudget": 16384,
+        "includeThoughts": True,
+    }
+    # The budget must fit inside the answer window.
+    assert generation["maxOutputTokens"] == 16384 + 8000
+
+
+def test_effort_is_not_sent_to_a_non_thinking_model():
+    """``thinkingConfig`` on a model that cannot think is a hard 400."""
+    account = agy.AgyAccount(
+        credential_id="c1", email="a@b.c", project_id="proj-1", refresh_token="refresh-1"
+    )
+    payload = agy._build_generate_payload(
+        account,
+        "claude-sonnet-4-5",
+        [ChatMessage(role="user", content="سلام")],
+        system="",
+        temperature=0.4,
+        max_tokens=512,
+        reasoning_effort="high",
+    )
+    assert "thinkingConfig" not in payload["request"]["generationConfig"]
+    assert payload["request"]["generationConfig"]["maxOutputTokens"] == 512
+
+
+def test_unknown_effort_falls_back_to_medium():
+    account = agy.AgyAccount(
+        credential_id="c1", email="a@b.c", project_id="proj-1", refresh_token="refresh-1"
+    )
+    payload = agy._build_generate_payload(
+        account,
+        "claude-opus-4-5-thinking",
+        [ChatMessage(role="user", content="سلام")],
+        system="",
+        temperature=0.4,
+        max_tokens=512,
+        reasoning_effort="turbo",
+    )
+    budget = payload["request"]["generationConfig"]["thinkingConfig"]["thinkingBudget"]
+    assert budget == 8192
+
+
 def test_response_parsing_skips_thoughts():
     model = AiModel(provider_id="p", internal_name="m", display_name_for_admin="m")
     response = agy._parse_generate_response(
@@ -713,3 +772,96 @@ async def test_available_models(google, decrypted):
     adapter = agy.AgyModelAdapter(loader=loader)
     models = await adapter.available_models()
     assert models == ["claude-sonnet-4-5", "gemini-3-flash"]
+
+
+# ---------------------------------------------------------------------------
+# Live per-account model catalog (the console's model dropdown source)
+# ---------------------------------------------------------------------------
+
+
+async def test_available_models_for_one_account(google, decrypted):
+    """The console asks for a specific account, so the fetch is per-account."""
+    adapter = agy.AgyModelAdapter()
+    models = await adapter.available_models_for(
+        _agy_credential(email="one@gmail.com")
+    )
+    assert models == ["claude-sonnet-4-5", "gemini-3-flash"]
+    # The list is fetched from Google every call — no cached catalog.
+    fetches = [c for c in google if c["url"].endswith("fetchAvailableModels")]
+    assert len(fetches) == 1
+
+
+async def test_available_models_for_account_without_material():
+    """A credential with no refresh token can never list models."""
+    adapter = agy.AgyModelAdapter()
+    credential = ModelCredential(
+        provider_id="p",
+        name="empty@gmail.com",
+        encrypted_api_key="PLAINTEXT::{}",
+        email="empty@gmail.com",
+    )
+    with pytest.raises(ProviderUnavailableError):
+        await adapter.available_models_for(credential)
+
+
+async def test_account_models_endpoint(client, google, platform_owner_token):
+    """GET /accounts/{id}/models returns that account's live catalog."""
+    started = await client.post(
+        "/api/admin/agy/accounts/login/start",
+        headers=auth_header(platform_owner_token),
+    )
+    state = parse_qs(urlparse(started.json()["auth_url"]).query)["state"][0]
+    account_id = (
+        await client.post(
+            "/api/admin/agy/accounts/login/complete",
+            headers=auth_header(platform_owner_token),
+            json={
+                "login_id": started.json()["login_id"],
+                "callback_url": (
+                    f"http://localhost:51121/oauth-callback?code=c&state={state}"
+                ),
+            },
+        )
+    ).json()["id"]
+
+    response = await client.get(
+        f"/api/admin/agy/accounts/{account_id}/models",
+        headers=auth_header(platform_owner_token),
+    )
+    assert response.status_code == 200, response.text
+    assert response.json() == ["claude-sonnet-4-5", "gemini-3-flash"]
+
+    missing = await client.get(
+        "/api/admin/agy/accounts/does-not-exist/models",
+        headers=auth_header(platform_owner_token),
+    )
+    assert missing.status_code == 404
+
+
+async def test_completion_carries_the_model_effort(monkeypatch, decrypted):
+    """The end-to-end path: effort on the model row reaches the payload."""
+    async def handler(method, url, json_body, headers, data):
+        if url.endswith("/token"):
+            return _token_response()
+        if url.endswith("/v1internal:generateContent"):
+            return _FakeResponse(json_data=GOOD_GENERATE)
+        return await default_handler(method, url, json_body, headers, data)
+
+    calls = patch_google(monkeypatch, handler)
+    model = AiModel(
+        provider_id="p",
+        internal_name="claude-sonnet-4-5-thinking",
+        display_name_for_admin="f",
+        reasoning_effort="low",
+    )
+    adapter = agy.AgyModelAdapter()
+    await adapter.complete(
+        model=model,
+        credentials=[_agy_credential(email="one@gmail.com")],
+        messages=_MESSAGES,
+    )
+    generate = [c for c in calls if c["url"].endswith("generateContent")]
+    assert generate[0]["json"]["request"]["generationConfig"]["thinkingConfig"] == {
+        "thinkingBudget": 4096,
+        "includeThoughts": True,
+    }