Files
hermes-webui/tests/test_issue1240_generic_cli_catalog_sync.py
T
nesquena-hermes e3a7c93dc6 [HELD — independent review pending] Release v0.51.294 — stage-3401 (live-to-final redesign #3401 + 4 deep-review fixes) (#3741)
* Harden interrupted recovery control filtering

* Redesign live-to-final assistant replies

* Fix live activity anchor test fixture

* Fix CI lint issues for live reply tests

* Strengthen live progress prompt contract

* Recover PR #3401 refresh on origin/master

* Repair live-to-final refresh regressions

* Fix live worklog refresh regressions

* Show live footer timer on initial stream start

* Restore live stream shell after reload

* Preserve per-frame live SSE replay cursors

* Preserve reasoning as Worklog Thinking cards

* Quiet Worklog Thinking card styling

* Align Worklog Thinking card styling

* Scope live Worklog Thinking cards by segment

* Suppress exact duplicate settled Thinking

* Close #3401 merge review test gaps

* fix(#3401): resolve 4 deep-review regressions (inline-think, reconnect-dup, neon skin, busy-gate worklog)

Deep review (Codex diff-vs-master + live-browser drive) of the live-to-final refactor
surfaced 4 regressions vs master that the rewritten suite no longer guarded:

1. Inline <think>…</think>answer reasoning vanished — _assistantReasoningPayloadText
   used $-anchored regexes so a leading think block + visible answer extracted nothing
   and the Thinking card never rendered. Removed the 3 $ anchors to match the
   (non-anchored) display stripper. Live: inline-think thinking-only turn now renders.
2. (CORE) reconnect/reload duplicated the live reply — _rememberRunJournalCursor advanced
   a closure-local seq but never wrote INFLIGHT[activeSid].lastRunJournalSeq, so a reload
   replayed the journal from after_seq=0 over restored lastAssistantText. Now mirrors the
   cursor onto INFLIGHT + schedules a throttled persist.
3. Neon skin silently broke — PR deleted the :root[data-skin="neon"] CSS but left Neon in
   the picker. Restored the neon CSS block from master.
4. Settled tool-worklog rebuild gated purely on !S.busy — dropped every prior settled
   turn's worklog when renderMessages re-ran during an active stream (switch-back to an
   in-progress session). Restored master's !S.busy || (S.toolCalls && S.toolCalls.length).
   Live: busy re-render now preserves tool cards (4→4, was 4→0).

Live-verified all 4 + confirmed #3709/#3592 invariants still hold (1 thinking card, none
below footer; distinct siblings preserved). + tests/test_issue3401_deep_review_fixes.py (7).

* test(#3401): realign 3 stale source-shape assertions to the deep-review fixes

Fix commit changed two source literals that existing stage tests scanned for:
- test_live_activity_timeline.py (x2): split anchor 'if(!S.busy){' → the restored
  'if(!S.busy || (S.toolCalls&&S.toolCalls.length)){' guard (fix 4).
- test_run_journal_frontend_static.py: 'after_seq=0' not in source — fix 2's comment
  contained that literal; rephrased the comment to 'the zero floor (after_seq of 0)'.
Intent of all three assertions unchanged; only the matched string updated. No code
behavior change.

* docs(changelog): v0.51.294 — Release JJ (stage-3401, #3401 live-to-final redesign)

---------

Co-authored-by: Frank Song <franksong2702@gmail.com>
Co-authored-by: Nathan-Hermes <nesquena-hermes@users.noreply.github.com>
Co-authored-by: nesquena-hermes <[email protected]>
2026-06-06 12:12:37 -07:00

168 lines
5.5 KiB
Python

"""Regression tests for #1240 — WebUI model catalog should delegate to Hermes CLI.
The WebUI picker should not freeze ordinary providers to its static
``_PROVIDER_MODELS`` snapshot when Hermes CLI can return a fresher provider
catalog. Static lists remain a fallback only.
"""
from __future__ import annotations
import sys
import types
import api.config as config
import api.profiles as profiles
_PROVIDER_ENV_VARS = (
"ANTHROPIC_API_KEY",
"OPENAI_API_KEY",
"OPENROUTER_API_KEY",
"GOOGLE_API_KEY",
"GEMINI_API_KEY",
"GLM_API_KEY",
"KIMI_API_KEY",
"DEEPSEEK_API_KEY",
"XIAOMI_API_KEY",
"OPENCODE_ZEN_API_KEY",
"OPENCODE_GO_API_KEY",
"MINIMAX_API_KEY",
"MINIMAX_CN_API_KEY",
"XAI_API_KEY",
"MISTRAL_API_KEY",
"OLLAMA_CLOUD_API_KEY",
"OLLAMA_API_KEY",
"NOUS_API_KEY",
"NVIDIA_API_KEY",
)
def _scrub_provider_env(monkeypatch):
for name in _PROVIDER_ENV_VARS:
monkeypatch.delenv(name, raising=False)
def _install_fake_hermes_cli(monkeypatch, *, provider_id: str, live_ids, raise_on_lookup: bool = False):
"""Install a hermes_cli stub that reports one authenticated provider."""
fake_pkg = types.ModuleType("hermes_cli")
fake_pkg.__path__ = []
fake_models = types.ModuleType("hermes_cli.models")
fake_models.list_available_providers = lambda: [
{"id": provider_id, "authenticated": True}
]
calls: list[str] = []
def provider_model_ids(pid):
calls.append(pid)
if raise_on_lookup:
raise RuntimeError("simulated provider_model_ids failure")
return list(live_ids) if pid == provider_id else []
fake_models.provider_model_ids = provider_model_ids
fake_auth = types.ModuleType("hermes_cli.auth")
def get_auth_status(pid):
if pid == provider_id:
return {"logged_in": True, "key_source": ""}
return {"logged_in": False, "key_source": ""}
fake_auth.get_auth_status = get_auth_status
monkeypatch.setitem(sys.modules, "hermes_cli", fake_pkg)
monkeypatch.setitem(sys.modules, "hermes_cli.models", fake_models)
monkeypatch.setitem(sys.modules, "hermes_cli.auth", fake_auth)
monkeypatch.delitem(sys.modules, "agent.credential_pool", raising=False)
monkeypatch.delitem(sys.modules, "agent", raising=False)
config.invalidate_models_cache()
return calls
def _configure(monkeypatch, tmp_path, *, provider: str, default: str = ""):
hermes_home = tmp_path / "hermes-home"
hermes_home.mkdir()
monkeypatch.setattr(profiles, "get_active_hermes_home", lambda: hermes_home)
monkeypatch.setattr(config, "_get_config_path", lambda: tmp_path / "missing-config.yaml")
monkeypatch.setattr(config, "_models_cache_path", tmp_path / "models_cache.json")
monkeypatch.setattr(
config,
"cfg",
{
"model": {"provider": provider, "default": default},
"providers": {},
"fallback_providers": [],
},
)
monkeypatch.setattr(config, "_cfg_mtime", 0.0)
config.invalidate_models_cache()
def _provider_group(result: dict, provider_id: str) -> dict:
return next(g for g in result["groups"] if g.get("provider_id") == provider_id)
def _ids(group: dict) -> list[str]:
return [m.get("id") for m in group.get("models", [])]
def test_generic_provider_uses_hermes_cli_catalog_before_static_snapshot(monkeypatch, tmp_path):
"""A normal provider should show fresh CLI-discovered models.
``claude-sonnet-5.0`` is intentionally absent from WebUI's static Anthropic
list. Before this fix the group came entirely from ``_PROVIDER_MODELS`` and
this model was invisible even though Hermes CLI knew about it.
"""
_scrub_provider_env(monkeypatch)
calls = _install_fake_hermes_cli(
monkeypatch,
provider_id="anthropic",
live_ids=["claude-opus-4.7", "claude-sonnet-5.0"],
)
_configure(monkeypatch, tmp_path, provider="anthropic", default="claude-opus-4.7")
result = config.get_available_models()
group = _provider_group(result, "anthropic")
assert calls == ["anthropic"]
assert _ids(group) == ["claude-opus-4.7", "claude-sonnet-5.0"]
assert group["models"][1]["label"] == "Claude Sonnet 5.0"
def test_generic_provider_keeps_static_catalog_as_cli_failure_fallback(monkeypatch, tmp_path):
_scrub_provider_env(monkeypatch)
calls = _install_fake_hermes_cli(
monkeypatch,
provider_id="anthropic",
live_ids=[],
raise_on_lookup=True,
)
_configure(monkeypatch, tmp_path, provider="anthropic", default="claude-opus-4.7")
result = config.get_available_models()
group = _provider_group(result, "anthropic")
assert calls == ["anthropic"]
assert "claude-opus-4.7" in _ids(group)
assert "claude-sonnet-4.6" in _ids(group)
def test_generic_provider_prefixes_live_ids_when_not_active_provider(monkeypatch, tmp_path):
"""Provider-qualified live IDs must route through the selected provider."""
_scrub_provider_env(monkeypatch)
calls = _install_fake_hermes_cli(
monkeypatch,
provider_id="anthropic",
live_ids=["claude-sonnet-5.0"],
)
# Anthropic is authenticated via Hermes CLI, but OpenAI is the active
# default. The Anthropic row still has to be pickable/routable.
_configure(monkeypatch, tmp_path, provider="openai", default="gpt-5.5")
result = config.get_available_models()
group = _provider_group(result, "anthropic")
assert "anthropic" in calls
assert _ids(group) == ["@anthropic:claude-sonnet-5.0"]