hermes-agent/tests/gateway/test_telegram_model_picker.py
Teknium 93e6a05efc
feat(model-picker): group multi-endpoint providers under one row (#35227)
* Inspired by Claude Code: /compress here [N] — boundary-aware 'summarize up to here'

Adds a user-chosen compression boundary to the existing /compress command.
/compress here [N] summarizes everything except the most recent N exchanges
(default 2), which are preserved verbatim — letting the user pick the
compression boundary instead of relying on the automatic token-budget heuristic.

Inspired by Claude Code's Rewind 'Summarize up to here' action (v2.1.139,
Week 20, May 2026): https://code.claude.com/docs/en/whats-new/2026-w20

- hermes_cli/partial_compress.py: pure split/parse helpers + seam-alternation
  guard (shared by CLI and gateway).
- cli.py / gateway/run.py: route 'here [N]' / '--keep N' to partial compression;
  compress only the head, re-append the verbatim tail through the seam guard.
- Preserves message-flow role alternation (seam guard merges any illegal
  user->user / assistant->assistant adjacency).
- Reuses the existing _compress_context session-rotation/lock machinery — no
  changes to the compression core.
- Bare /compress (full) and /compress <focus> behavior unchanged.

Tests: 12 helper unit tests + 5 CLI integration tests + E2E (interleaved
tool-call transcript, degenerate/multimodal seams, real handler path).

* feat(model-picker): group multi-endpoint providers under one row

The interactive provider pickers (hermes model, setup wizard, Telegram
/model) listed every provider slug flat, so vendors with several endpoints
(Kimi/Moonshot, MiniMax, xAI Grok, Google Gemini, OpenAI, OpenCode, GitHub
Copilot) each occupied multiple top-level rows. Now related slugs fold into
one top-level row that drills down to the specific endpoint.

- models.py: add PROVIDER_GROUPS table + group_providers() fold (display
  only — CANONICAL_PROVIDERS, slugs, --provider, /model <provider:model>
  all unchanged and individually addressable).
- hermes model (main.py): group rows drill into a member sub-picker, then
  dispatch to the existing _model_flow_* unchanged. setup wizard inherits it.
- Telegram /model: new mpg:<group> callback expands to member mp:<slug>
  buttons; single authenticated member degrades to a direct button.
- Grouping is the single shared fold across all three surfaces.

Validation: 163 targeted tests pass; E2E confirms group->member->model
resolves to the correct concrete slug for all families.
2026-05-30 01:41:33 -07:00

251 lines
9.2 KiB
Python

"""Tests for Telegram model picker thread fallback."""
import sys
from types import SimpleNamespace
from unittest.mock import AsyncMock, MagicMock
import pytest
def _ensure_telegram_mock():
if "telegram" in sys.modules and hasattr(sys.modules["telegram"], "__file__"):
return
mod = MagicMock()
mod.ext.ContextTypes.DEFAULT_TYPE = type(None)
mod.constants.ParseMode.MARKDOWN = "Markdown"
mod.constants.ParseMode.MARKDOWN_V2 = "MarkdownV2"
mod.constants.ParseMode.HTML = "HTML"
mod.constants.ChatType.PRIVATE = "private"
mod.constants.ChatType.GROUP = "group"
mod.constants.ChatType.SUPERGROUP = "supergroup"
mod.constants.ChatType.CHANNEL = "channel"
mod.error.NetworkError = type("NetworkError", (OSError,), {})
mod.error.TimedOut = type("TimedOut", (OSError,), {})
mod.error.BadRequest = type("BadRequest", (Exception,), {})
for name in ("telegram", "telegram.ext", "telegram.constants", "telegram.request"):
sys.modules.setdefault(name, mod)
sys.modules.setdefault("telegram.error", mod.error)
_ensure_telegram_mock()
from gateway.config import PlatformConfig
from gateway.platforms.telegram import TelegramAdapter
def _make_adapter():
adapter = TelegramAdapter(PlatformConfig(enabled=True, token="test-token"))
adapter._bot = AsyncMock()
adapter._app = MagicMock()
return adapter
class TestTelegramModelPicker:
@pytest.mark.asyncio
async def test_send_model_picker_escapes_dynamic_provider_label(self):
adapter = _make_adapter()
sent = {}
async def mock_send_message(**kwargs):
sent.update(kwargs)
return SimpleNamespace(message_id=101)
adapter._bot.send_message = AsyncMock(side_effect=mock_send_message)
result = await adapter.send_model_picker(
chat_id="12345",
providers=[
{"slug": "provider_one", "name": "Provider One", "total_models": 1, "is_current": True}
],
current_model="model_1",
current_provider="provider_one",
session_key="s",
on_model_selected=AsyncMock(),
metadata={"thread_id": "99999"},
)
assert result.success is True
assert "MARKDOWN_V2" in repr(sent["parse_mode"])
assert "provider\\_one" in sent["text"]
assert "`model_1`" in sent["text"]
@pytest.mark.asyncio
async def test_back_button_escapes_dynamic_provider_label(self):
adapter = _make_adapter()
adapter._model_picker_state["12345"] = {
"providers": [{"slug": "provider_one", "name": "Provider One", "total_models": 1, "is_current": True}],
"current_model": "model_1",
"current_provider": "provider_one",
"session_key": "s",
"on_model_selected": AsyncMock(),
"msg_id": 42,
}
query = AsyncMock()
query.data = "mb"
query.message = MagicMock()
query.message.chat_id = 12345
query.from_user = MagicMock()
query.answer = AsyncMock()
query.edit_message_text = AsyncMock()
update = MagicMock()
update.callback_query = query
context = MagicMock()
await adapter._handle_model_picker_callback(query, "mb", "12345")
edit_kwargs = query.edit_message_text.call_args[1]
assert "MARKDOWN_V2" in repr(edit_kwargs["parse_mode"])
assert "provider\\_one" in edit_kwargs["text"]
assert "`model_1`" in edit_kwargs["text"]
@pytest.mark.asyncio
async def test_model_selected_edits_message_on_success(self):
"""Regression: the mm: (model selected → switch) success path must
edit the picker message to show the confirmation and remove the
buttons. An earlier revision of this PR over-indented the
edit_message_text block so it lived inside the except branch and
only fired when the callback raised."""
adapter = _make_adapter()
callback = AsyncMock(return_value="Switched to `gpt-5`")
adapter._model_picker_state["12345"] = {
"providers": [
{"slug": "openai", "name": "OpenAI", "total_models": 1, "is_current": True}
],
"current_model": "model_1",
"current_provider": "openai",
"session_key": "s",
"on_model_selected": callback,
"selected_provider": "openai",
"model_list": ["gpt-5"],
"msg_id": 42,
}
query = AsyncMock()
query.data = "mm:0"
query.message = MagicMock()
query.message.chat_id = 12345
query.answer = AsyncMock()
query.edit_message_text = AsyncMock()
await adapter._handle_model_picker_callback(query, "mm:0", "12345")
# The callback was invoked with the selected model
callback.assert_awaited_once()
# edit_message_text MUST be called on the success path (this is the
# regression we're guarding).
query.edit_message_text.assert_awaited()
edit_kwargs = query.edit_message_text.call_args[1]
assert "MARKDOWN_V2" in repr(edit_kwargs["parse_mode"])
# The dynamic result text was routed through format_message
# (backtick code blocks survive escaping).
assert "`gpt-5`" in edit_kwargs["text"]
# State is cleaned up after a successful switch.
assert "12345" not in adapter._model_picker_state
@pytest.mark.asyncio
async def test_provider_group_folds_and_drills_down(self, monkeypatch):
"""A provider family (e.g. MiniMax) collapses to one mpg: button at
the top level; tapping it expands to its authenticated members as
mp: buttons. A group reduced to a single authenticated member shows
no submenu (direct mp: button).
Inspects callback_data by recording every InlineKeyboardButton built,
which is robust to whether `telegram` is the real SDK or the module
mock (the SDK markup objects don't expose a plain iterable under the
mock)."""
import gateway.platforms.telegram as tg
built: list = []
class _RecordingButton:
def __init__(self, text, callback_data=None, **kw):
self.text = text
self.callback_data = callback_data
built.append(callback_data)
class _RecordingMarkup:
def __init__(self, rows):
self.inline_keyboard = rows
monkeypatch.setattr(tg, "InlineKeyboardButton", _RecordingButton)
monkeypatch.setattr(tg, "InlineKeyboardMarkup", _RecordingMarkup)
adapter = _make_adapter()
async def mock_send_message(**kwargs):
return SimpleNamespace(message_id=101)
adapter._bot.send_message = AsyncMock(side_effect=mock_send_message)
providers = [
{"slug": "minimax", "name": "MiniMax", "total_models": 2},
{"slug": "minimax-cn", "name": "MiniMax (China)", "total_models": 3},
{"slug": "xai", "name": "xAI", "total_models": 1}, # lone group member
]
await adapter.send_model_picker(
chat_id="12345",
providers=providers,
current_model="m",
current_provider="minimax",
session_key="s",
on_model_selected=AsyncMock(),
metadata=None,
)
# Top-level keyboard: MiniMax family folded into one group button;
# xai (lone member) degraded to a direct provider button.
assert "mpg:minimax" in built
assert "mp:xai" in built
assert "mp:minimax" not in built
assert "mp:minimax-cn" not in built
# Drill into the MiniMax group → members appear as mp: buttons + back.
built.clear()
query = AsyncMock()
query.message = MagicMock()
query.message.chat_id = 12345
query.answer = AsyncMock()
query.edit_message_text = AsyncMock()
await adapter._handle_model_picker_callback(query, "mpg:minimax", "12345")
assert "mp:minimax" in built
assert "mp:minimax-cn" in built
assert "mb" in built # back-to-providers button present
@pytest.mark.asyncio
async def test_retries_without_thread_when_thread_not_found(self):
adapter = _make_adapter()
providers = [{"slug": "openai", "name": "OpenAI", "total_models": 2, "is_current": True}]
call_log = []
class FakeBadRequest(Exception):
pass
async def mock_send_message(**kwargs):
call_log.append(dict(kwargs))
if kwargs.get("message_thread_id") is not None:
raise FakeBadRequest("Message thread not found")
return SimpleNamespace(message_id=99)
adapter._bot.send_message = AsyncMock(side_effect=mock_send_message)
result = await adapter.send_model_picker(
chat_id="12345",
providers=providers,
current_model="gpt-5",
current_provider="openai",
session_key="s",
on_model_selected=AsyncMock(),
metadata={"thread_id": "99999"},
)
assert result.success is True
assert len(call_log) == 2
assert call_log[0]["message_thread_id"] == 99999
assert "message_thread_id" not in call_log[1] or call_log[1]["message_thread_id"] is None