Merge master into stage/7758-wakeup-budget
# Conflicts: # CHANGELOG.md
This commit is contained in:
nesquena-hermes committed
commit
4eef3f3bbf
15 files changed
+1820
-194
No files matched your search
@@ -5,6 +5,10 @@
|
||||
|
||||
### Added
|
||||
|
||||
- **Full-session resolve concurrency is configurable.** `HERMES_WEBUI_MAX_SESSION_RESOLVE` sets how
|
||||
many full-transcript session resolves may run at once (default 2, a positive integer up to 64;
|
||||
zero, negative, non-numeric or out-of-range values fall back to 2). It is process-wide, so a
|
||||
profile's `.env` cannot override it. (#7421, #7656 by @happy5318)
|
||||
- **The sidebar's recent-session window is configurable.** `HERMES_WEBUI_VISIBLE_SESSION_LIMIT` sets
|
||||
how many recent sessions the sidebar lists (default 20). It also bounds how many delegated subagent
|
||||
children can nest at once, so raise it for wide fan-outs. Invalid or non-positive values fall back to
|
||||
@@ -30,6 +34,16 @@
|
||||
claim as a plain failure, so a few refusals in a row could terminally drop a completion whose
|
||||
session was alive and waiting. Transient refusals now return the claim as retryable, while hard
|
||||
failures still use up the attempt budget. (#7758 by @ruizanthony)
|
||||
- **A first visit now uses the browser's language.** The server stores "no preference" as `null`
|
||||
instead of defaulting to `"en"`, so a first-time visitor gets `navigator.language` while an
|
||||
explicitly saved language (including English) still wins, and legacy `settings.json` files that
|
||||
already hold `"en"` keep English. Reading the browser language is guarded, so an environment where
|
||||
`navigator` throws falls back cleanly. (#7622, #7730 by @happy5318)
|
||||
- **The live model list for a custom provider respects its `models:` allowlist, without treating
|
||||
per-model metadata as one.** `/api/models/live` filters a custom provider's live catalog to its
|
||||
configured `models:` when that is a list, or when it is a mapping with `discover_models: false`.
|
||||
A mapping of per-model settings (the shape `hermes setup` writes) keeps the full live catalog, as
|
||||
the Agent does. (#7165 by @happy5318)
|
||||
- **`MEDIA:` links wrapped in inline code no longer 404.** Every `MEDIA:` capture site (renderer,
|
||||
streaming parser, TTS stripper, session-media authorization and snapshot capture, seven in all)
|
||||
swallowed the closing backtick of `` `MEDIA:/path` `` into the path, so the file lookup and the
|
||||
|
||||
+26
-1
@@ -11483,7 +11483,13 @@ _SETTINGS_DEFAULTS = {
|
||||
"hidden_tabs": [], # sidebar tab panel names hidden by user (e.g. ["tasks","kanban"]); chat and settings are always visible
|
||||
"tab_order": [], # user-defined sidebar/rail tab order for reorderable tabs; chat/settings stay fixed
|
||||
"composer_control_order": [], # user-defined composer footer control order; invalid/duplicate keys are ignored
|
||||
"language": "en", # UI locale code; must match a key in static/i18n.js LOCALES
|
||||
# #7622 (round 3): language is intentionally absent from the defaults so
|
||||
# `load_settings()` reports `None` for a fresh install. This lets the
|
||||
# client distinguish "no preference" from an explicit saved choice,
|
||||
# so a user who genuinely picked English (and has `language: "en"`
|
||||
# persisted on disk) is no longer overridden by the browser hint on
|
||||
# their first hydration. When a user picks a locale in the Settings
|
||||
# modal the value is written here and the field is set explicitly.
|
||||
"bot_name": os.getenv(
|
||||
"HERMES_WEBUI_BOT_NAME", "Hermes"
|
||||
), # display name for the assistant
|
||||
@@ -11723,6 +11729,16 @@ def load_settings() -> dict:
|
||||
settings["default_model_provider"] = str(model_cfg.get("provider"))
|
||||
except Exception:
|
||||
logger.debug("Failed to resolve default model provider for settings")
|
||||
# #7622/#7730 (round 4): keep the tri-state signal explicit. `language`
|
||||
# is intentionally absent from `_SETTINGS_DEFAULTS` (see above), so
|
||||
# without this line a fresh install's returned dict would OMIT the key
|
||||
# entirely and the API payload would carry no `language` field. Emit an
|
||||
# explicit `None` (serialized as JSON `null`) so the client receives the
|
||||
# three-way signal it trusts: `null` = no preference, "en" = explicitly
|
||||
# saved English, any other code = explicitly chosen locale. Stored
|
||||
# values (including a legacy English pick written before this change)
|
||||
# win via the merge above and are never touched here.
|
||||
settings.setdefault("language", None)
|
||||
return settings
|
||||
|
||||
|
||||
@@ -11730,6 +11746,15 @@ _SETTINGS_ALLOWED_KEYS = set(_SETTINGS_DEFAULTS.keys()) - {
|
||||
"password_hash",
|
||||
"default_model",
|
||||
"simplified_tool_calling",
|
||||
} | {
|
||||
# #7622 (round 3): `language` is intentionally absent from
|
||||
# `_SETTINGS_DEFAULTS` so a fresh install returns `None` for
|
||||
# `settings["language"]` and the client can distinguish "no
|
||||
# preference" from an explicit saved choice. But the user
|
||||
# MUST still be able to pick a locale in the Settings modal,
|
||||
# so we add it back to the explicit allow-list here. The
|
||||
# existing BCP-47 validation at save-time still applies.
|
||||
"language",
|
||||
}
|
||||
_SETTINGS_ENUM_VALUES = {
|
||||
"send_key": {"enter", "ctrl+enter", "shift+enter"},
|
||||
|
||||
+35
-1
@@ -4788,7 +4788,41 @@ class _FullSessionResolveRequired(RuntimeError):
|
||||
"""Internal signal that a full sidecar load must enter the bounded path."""
|
||||
|
||||
|
||||
_FULL_SESSION_RESOLVE_MAX_CONCURRENT = 2
|
||||
def _read_max_session_resolve_concurrent() -> int:
|
||||
"""#7421: env override for the heavy session-resolve cap. The
|
||||
hardcoded literal 2 is too low for high-concurrency
|
||||
deployments where several parallel active sessions all need
|
||||
a full-transcript resolve; operators can set
|
||||
``HERMES_WEBUI_MAX_SESSION_RESOLVE`` to a positive int to
|
||||
raise the cap without code changes. A bad or missing value
|
||||
falls back to the previous default of 2, so an operator who
|
||||
sets ``HERMES_WEBUI_MAX_SESSION_RESOLVE=0`` or a non-numeric
|
||||
value does not regress to a blocked or unbounded state.
|
||||
|
||||
The cap is a *safety bound* (per-resolve cost tracked in
|
||||
#7310), not a user preference — a typo like ``=999999``
|
||||
must fall back to the safe default, never to the permissive
|
||||
extreme. Every other bad input in this function falls back
|
||||
to ``2``; out-of-range values do too. The previously
|
||||
accepted upper bound (64) is reachable only via an explicit
|
||||
in-range operator value; a profile's ``.env`` cannot reach
|
||||
it at all (see ``_PROTECTED_ENV_KEYS``).
|
||||
"""
|
||||
raw = (os.getenv("HERMES_WEBUI_MAX_SESSION_RESOLVE") or "").strip()
|
||||
if not raw:
|
||||
return 2
|
||||
try:
|
||||
n = int(raw)
|
||||
except (TypeError, ValueError):
|
||||
return 2
|
||||
if n < 1:
|
||||
return 2
|
||||
if n > 64:
|
||||
return 2 # #7656 round-3: typo-safe fallback, not clamp-up-to-64
|
||||
return n
|
||||
|
||||
|
||||
_FULL_SESSION_RESOLVE_MAX_CONCURRENT = _read_max_session_resolve_concurrent()
|
||||
_FULL_SESSION_RESOLVE_SLOTS = threading.BoundedSemaphore(
|
||||
_FULL_SESSION_RESOLVE_MAX_CONCURRENT
|
||||
)
|
||||
|
||||
@@ -202,6 +202,14 @@ _PROTECTED_ENV_KEYS = frozenset({
|
||||
'HERMES_WEBUI_ISOLATED_PROFILE',
|
||||
# Server-wide sidebar window; a profile .env must not widen the per-request query.
|
||||
'HERMES_WEBUI_VISIBLE_SESSION_LIMIT',
|
||||
# #7656 round-3: HERMES_WEBUI_MAX_SESSION_RESOLVE is a process-wide resource
|
||||
# cap (controls the BoundedSemaphore that gates full-transcript resolves).
|
||||
# A profile's .env is per-profile by design; allowing it to set a
|
||||
# server-wide limit (and a first-load-wins asymmetry) would let a
|
||||
# single profile drag the rest into a tighter or looser posture than
|
||||
# the operator intended. Same shape as the isolated-profile key: only
|
||||
# the operator/launcher env at startup can set it.
|
||||
'HERMES_WEBUI_MAX_SESSION_RESOLVE',
|
||||
})
|
||||
|
||||
|
||||
@@ -939,6 +947,12 @@ _BLOCKED_RUNTIME_ENV_KEYS = {
|
||||
# profile's own env on any runtime/gateway-parity path.
|
||||
'HERMES_WEBUI_ISOLATED_PROFILE',
|
||||
'HERMES_WEBUI_VISIBLE_SESSION_LIMIT',
|
||||
# #7656 round-3: process-wide resolve cap. Filter out a profile's
|
||||
# .env override the same way we filter the isolated-profile key, so
|
||||
# the cap stays at the operator/launcher value across profile
|
||||
# switches rather than re-sizing to whatever the first-loaded
|
||||
# profile env set.
|
||||
'HERMES_WEBUI_MAX_SESSION_RESOLVE',
|
||||
}
|
||||
|
||||
|
||||
|
||||
+126
-7
@@ -21896,6 +21896,99 @@ def _handle_live_models(handler, parsed):
|
||||
_env = str(_cp.get("key_env") or "").strip()
|
||||
return os.getenv(_env, "").strip() if _env else ""
|
||||
|
||||
def _custom_provider_models_discover_is_false(_cp):
|
||||
"""True when ``discover_models`` is an explicit ``false`` opt-out.
|
||||
|
||||
Mirrors ``api.config._provider_discover_allowed`` / Hermes
|
||||
Agent ``model_switch_providers._discover_flag``: ``discover_models``
|
||||
defaults to True, and the string forms ``"false"``/``"no"``/``"0"``
|
||||
(case-insensitive) mean False. Used to decide whether a
|
||||
dict-shaped ``models`` mapping is a hand-pinned allowlist (only
|
||||
when discovery is off) rather than per-model metadata.
|
||||
"""
|
||||
_discover = _cp.get("discover_models", True) if isinstance(_cp, dict) else True
|
||||
if isinstance(_discover, str):
|
||||
return _discover.strip().lower() in {"false", "no", "0"}
|
||||
return not bool(_discover)
|
||||
|
||||
def _custom_provider_allowlist_ids(_cp):
|
||||
"""Plural ``models`` list only — the explicit allowlist signal.
|
||||
|
||||
The singular ``model`` field is sticky/default metadata, NOT an
|
||||
allowlist: it must not gate live-catalog filtering, otherwise a
|
||||
provider configured with only ``model: assistant`` (no ``models``
|
||||
list) would be collapsed to a single model. Only an explicit
|
||||
``models`` allowlist expresses "show exactly these models".
|
||||
|
||||
An auto-discovered catalog is NOT an allowlist: when Hermes
|
||||
persisted discovery results back into config (``models: {...}``
|
||||
plus ``models_discovered: true``), that mapping is a snapshot
|
||||
of what the gateway exposed at discovery time. Gating on it
|
||||
would permanently pin the live catalog to the first-discovery
|
||||
set, silently dropping any model the user pulls in later
|
||||
(LM Studio / Ollama). ``_provider_models_are_discovered_catalog()``
|
||||
is the shared predicate the ``/api/models`` path already uses;
|
||||
when it says "discovered", return no allowlist and let the
|
||||
live probe win. An explicit ``discover_models: false`` opt-out
|
||||
re-pins the catalog (the predicate accounts for it), so a
|
||||
hand-pinned discovered catalog still filters.
|
||||
|
||||
A dict-shaped ``models`` mapping that is NOT marked discovered is
|
||||
*per-model metadata* written by the Hermes Agent setup flow
|
||||
(``hermes_cli/model_switch.py::_save_custom_provider`` and the
|
||||
setup wizard) — e.g. ``{chat-a: {context_length: 128000}}``. It is
|
||||
not a catalog narrow: treating its keys as an allowlist would
|
||||
collapse the live picker to the single saved default (keyless
|
||||
Ollama) while the CLI live-probe shows the full catalog. Only an
|
||||
explicit ``discover_models: false`` opts into treating the dict
|
||||
keys as a pinned allowlist. List/JSON-array-string/Python-literal
|
||||
shapes remain plain allowlists.
|
||||
|
||||
The plural value is decoded through ``_parse_config_string_list()``
|
||||
because ``hermes config set`` / JSON-mode editor saves persist
|
||||
lists as quoted JSON-array strings (``'["chat-a","chat-b"]'``) or
|
||||
Python literals (``"['chat-a']"``). Handling only ``dict``/``list``
|
||||
made a serialized allowlist fall through to ``[]``, which the
|
||||
caller reads as "no allowlist configured" and floods the picker
|
||||
with the full upstream catalog — the same class of bug as the
|
||||
``skills.disabled`` regression (#7120 / #7134).
|
||||
"""
|
||||
from api.config import _provider_models_are_discovered_catalog
|
||||
|
||||
if _provider_models_are_discovered_catalog(_cp):
|
||||
return []
|
||||
_ids = []
|
||||
_models = _cp.get("models")
|
||||
# Serialized shapes only: ``hermes config set`` / JSON-mode
|
||||
# editor saves persist lists as quoted JSON-array strings
|
||||
# (``'["chat-a","chat-b"]'``) or Python literals
|
||||
# (``"['chat-a']"``). Decode those through the shared helper so
|
||||
# they are honored; native dict/list values are walked below so
|
||||
# dict *entries* keep their id|model|name metadata (the decoder
|
||||
# str()-ifies list members, which would mangle them).
|
||||
if isinstance(_models, str):
|
||||
_models = _parse_config_string_list(_models)
|
||||
if isinstance(_models, dict):
|
||||
# A dict-shaped ``models`` is per-model metadata written by
|
||||
# the Hermes Agent setup flow, NOT a catalog narrow. Only a
|
||||
# ``discover_models: false`` opt-out treats the dict keys as a
|
||||
# pinned allowlist; otherwise return the empty allowlist so the
|
||||
# live probe returns the full catalog.
|
||||
if not _custom_provider_models_discover_is_false(_cp):
|
||||
return []
|
||||
for _mid in _models:
|
||||
if isinstance(_mid, str) and _mid.strip():
|
||||
_ids.append(_mid.strip())
|
||||
elif isinstance(_models, (list, tuple)):
|
||||
for _item in _models:
|
||||
if isinstance(_item, str) and _item.strip():
|
||||
_ids.append(_item.strip())
|
||||
elif isinstance(_item, dict):
|
||||
_mid = _item.get("id") or _item.get("model") or _item.get("name")
|
||||
if _mid and str(_mid).strip():
|
||||
_ids.append(str(_mid).strip())
|
||||
return _ids
|
||||
|
||||
# For 'custom' and 'custom:*' providers, provider_model_ids()
|
||||
# returns [] because they aren't real hermes_cli endpoints.
|
||||
# Fall back to the custom_providers entries from config.yaml so
|
||||
@@ -21904,11 +21997,13 @@ def _handle_live_models(handler, parsed):
|
||||
# Collect config-specified model IDs separately so they don't
|
||||
# prevent the live fetch below from running (#3718).
|
||||
_config_ids = []
|
||||
_allowlist_ids = []
|
||||
if provider == "custom" or provider.startswith("custom:"):
|
||||
for _cp in _custom_provider_entries_for_request():
|
||||
if custom_provider_entry is None:
|
||||
custom_provider_entry = _cp
|
||||
_config_ids.extend(_custom_provider_model_ids(_cp))
|
||||
_allowlist_ids.extend(_custom_provider_allowlist_ids(_cp))
|
||||
|
||||
# Always try live fetch for custom providers — config entries are a
|
||||
# fallback, not a replacement. The live endpoint should return ALL
|
||||
@@ -21979,15 +22074,39 @@ def _handle_live_models(handler, parsed):
|
||||
except Exception as _fetch_err:
|
||||
logger.debug("Live fetch from custom provider failed: %s", _fetch_err)
|
||||
|
||||
# If live fetch succeeded, merge with config entries (live takes
|
||||
# priority). If live fetch failed, fall back to config-only list.
|
||||
# If live fetch succeeded, filter the live catalog down to the
|
||||
# config-declared models allowlist first, then append any
|
||||
# allowlisted models the live endpoint didn't return. Custom
|
||||
# providers (esp. New-API-style gateways) expose their ENTIRE
|
||||
# catalog via /v1/models — including image/audio models that
|
||||
# are not chat models. The picker must not surface models the
|
||||
# user never declared in config.yaml. Only a NON-EMPTY explicit
|
||||
# ``models`` allowlist gates the filter — a provider configured
|
||||
# with just a singular ``model`` (no ``models`` list) keeps the
|
||||
# unfiltered live catalog. When no allowlist is configured,
|
||||
# return the live list as-is (preserves the pre-filter
|
||||
# discovery behaviour).
|
||||
#
|
||||
# An empty allowlist (``models: []``, ``models: "[]"``, or a
|
||||
# value that decodes to no usable ids) is deliberately treated
|
||||
# as "not configured", NOT as "allow nothing". Gating on
|
||||
# declared-ness instead would emit an EMPTY picker and make the
|
||||
# provider unselectable — a harder failure than surfacing a few
|
||||
# extra models, and unrecoverable from the UI because
|
||||
# ``custom_providers`` is hand-edited in config.yaml (the WebUI
|
||||
# has no write path for it). ``[]`` in practice means a
|
||||
# leftover/placeholder key, not an intentional deny-all, and no
|
||||
# deny-all use case exists: a provider the user wants hidden is
|
||||
# removed from ``custom_providers`` outright.
|
||||
if ids:
|
||||
_live_set = set(ids)
|
||||
for _cid in _config_ids:
|
||||
if _cid not in _live_set:
|
||||
ids.append(_cid)
|
||||
if _allowlist_ids:
|
||||
_allowlist_set = set(_allowlist_ids)
|
||||
ids = [m for m in ids if m in _allowlist_set] or []
|
||||
for _aid in _allowlist_ids:
|
||||
if _aid not in ids:
|
||||
ids.append(_aid)
|
||||
else:
|
||||
ids = list(_config_ids)
|
||||
ids = list(_allowlist_ids or _config_ids)
|
||||
|
||||
# ── OpenAI-compat live fetch fallback ──────────────────────────────────
|
||||
# When provider_model_ids() is unavailable or returns [] for a provider
|
||||
|
||||
@@ -89,6 +89,15 @@ contributor guidance; it does not change runtime behavior or CI gates.
|
||||
`models_cache.json` refresh timestamps), the stat-identity fallbacks, and the
|
||||
schema/version stamps. Start here before changing model-catalog caching, the
|
||||
`/api/models` cache keys, or the Codex catalog dependency (#2443, #7540).
|
||||
- [`docs/architecture/live-models-allowlist.md`](architecture/live-models-allowlist.md):
|
||||
current contract for how `/api/models/live` filters a custom provider's
|
||||
upstream catalog: the four signals in evaluation order (discovered catalog
|
||||
defers to the live probe, explicit plural `models:` allowlist filters,
|
||||
singular `model:` never gates, no allowlist shows the full catalog), the
|
||||
serialized-list shapes `hermes config set` persists, the deliberate
|
||||
empty-allowlist-is-not-configured rule, and the probe-failure fallback.
|
||||
Start here before changing custom-provider model filtering or
|
||||
discovery-vs-allowlist semantics (#7165, #7404).
|
||||
- [`docs/architecture/profile-home-resolve-cache.md`](architecture/profile-home-resolve-cache.md):
|
||||
current contract for the call-scoped memoization around
|
||||
`_resolve_profile_home_param()` in `api/workspace.py`: what it caches, the
|
||||
|
||||
@@ -0,0 +1,123 @@
|
||||
# Live model picker allowlist contract (`/api/models/live`)
|
||||
|
||||
This document records the runtime contract for how `/api/models/live` decides
|
||||
which models a `custom` / `custom:*` provider contributes to the chat model
|
||||
picker. It describes shipped behavior and changes no runtime behavior. It was
|
||||
added because the #7165 review flagged the contract as undocumented: the
|
||||
filtering rules live in `_handle_live_models` (`api/routes.py`) and had only
|
||||
code comments backing them.
|
||||
|
||||
Start here before changing how the live catalog of a custom provider is
|
||||
filtered, how discovery snapshots are distinguished from allowlists, or what
|
||||
the endpoint returns when the upstream probe fails.
|
||||
|
||||
## Why the endpoint filters at all
|
||||
|
||||
OpenAI-compatible gateways (New-API-style aggregators, LM Studio, Ollama
|
||||
proxies) expose their **entire** catalog from `/v1/models`, including
|
||||
image-generation, audio, TTS, and embedding models that are not chat models.
|
||||
The background enrichment path must not surface models the user never opted
|
||||
into — but it also must not hide models the gateway gained since config was
|
||||
last edited. The contract below is how those two goals are reconciled.
|
||||
|
||||
## The four signals, in evaluation order
|
||||
|
||||
For a custom provider the handler consults these signals:
|
||||
|
||||
1. **Discovered catalog → no allowlist (live probe wins).**
|
||||
When the provider entry carries `models_discovered: true` and discovery is
|
||||
allowed (`discover_models` is not an explicit opt-out), the `models:`
|
||||
mapping is a *snapshot Hermes persisted from a past discovery*, not a
|
||||
hand-curated list. It must not gate the live probe: a model the user pulls
|
||||
into LM Studio / Ollama after discovery has to appear in the picker.
|
||||
Detected by the shared predicate
|
||||
`api.config._provider_models_are_discovered_catalog()` — the same
|
||||
predicate the `/api/models` catalog path uses, so both endpoints agree.
|
||||
With this signal, no allowlist is derived and the full live catalog is
|
||||
returned.
|
||||
|
||||
2. **Explicit plural `models:` allowlist → filter.**
|
||||
A non-empty plural `models:` value on an entry that is *not* a discovered
|
||||
catalog expresses "show exactly these models". The live catalog is
|
||||
intersected with it, then any allowlisted model missing from the live
|
||||
response is appended (so an allowlisted-but-offline model stays
|
||||
selectable). This is the #7165 filter. Only **list** and **string**
|
||||
(serialized) shapes are plain allowlists — see "Dict-shaped `models:`"
|
||||
below.
|
||||
|
||||
3. **Singular `model:` → never gates.**
|
||||
The singular field is sticky/default metadata (the model to preselect),
|
||||
not an allowlist. A provider configured only with `model: assistant` keeps
|
||||
the full unfiltered live catalog; gating on it would collapse discovery to
|
||||
a single model.
|
||||
|
||||
4. **No allowlist → full live catalog.**
|
||||
Preserves the pre-#7165 discovery behavior for setups that rely on it.
|
||||
|
||||
### Serialized shapes
|
||||
|
||||
`hermes config set` and the JSON-mode editor persist lists as quoted
|
||||
JSON-array strings (`'["chat-a","chat-b"]'`) or Python literals
|
||||
(`"['chat-a']"`). The plural value is decoded through the shared
|
||||
`_parse_config_string_list()` before id extraction — but only when the value
|
||||
is a `str`; native `dict` / `list` values are walked directly so dict *entries*
|
||||
keep their `id|model|name` metadata (the decoder stringifies members). A
|
||||
dict-only parser drops serialized allowlists to "no allowlist" and floods the
|
||||
picker — the same bug class as `skills.disabled` (#7120 / #7134).
|
||||
|
||||
### Dict-shaped `models:`
|
||||
|
||||
A dict-shaped `models:` mapping (e.g. `{chat-a: {context_length: 128000}}`)
|
||||
is *per-model metadata* written by the Hermes Agent setup flow —
|
||||
`hermes_cli/model_switch.py::_save_custom_provider` and the setup wizard —
|
||||
**not** a catalog narrow. Treating its keys as an allowlist would collapse the
|
||||
live picker to the single saved default (keyless Ollama) while the CLI
|
||||
live-probe shows the full catalog. So a dict is **never** a plain allowlist:
|
||||
|
||||
- without an explicit `discover_models: false`, a dict-shaped `models:`
|
||||
contributes **no allowlist** and the full live catalog is returned;
|
||||
- with `discover_models: false` (bool `False` or the string forms
|
||||
`"false"`/`"no"`/`"0"`, case-insensitive — mirroring
|
||||
`model_switch_providers.py:557`), the dict **keys** are honored as a pinned
|
||||
allowlist.
|
||||
|
||||
This complements the discovered-catalog rule: `models_discovered: true`
|
||||
without the opt-out is already ignored (signal 1). The dict guard covers the
|
||||
Agent-setup shape that is *not* flagged discovered.
|
||||
|
||||
If someone later "fixes" the dict shape back into an always-allowlist, the
|
||||
regression test `test_dict_models_without_discover_false_does_not_gate` fails
|
||||
and forces the trade-off to be re-argued.
|
||||
|
||||
### Empty allowlist semantics
|
||||
|
||||
`models: []`, `models: "[]"`, an empty mapping, or a blank scalar are
|
||||
deliberately treated as **not configured**, never as "allow nothing". The
|
||||
filter runs only on a non-empty allowlist because gating on declared-ness
|
||||
would emit an empty picker and make the provider unselectable — a harder
|
||||
failure than showing a few extra models, and unrecoverable from the UI
|
||||
(`custom_providers` has no WebUI write path; it is hand-edited in
|
||||
config.yaml). There is no deny-all use case: a provider the user wants hidden
|
||||
is removed from `custom_providers` outright.
|
||||
|
||||
### Probe failure / empty probe
|
||||
|
||||
When the upstream probe fails or returns no models, the endpoint falls back
|
||||
to `allowlist or config ids` — the non-empty plural allowlist first, so a
|
||||
singular `model:` outside the allowlist cannot leak in precisely when the
|
||||
probe is unavailable; with no allowlist, the configured ids (singular +
|
||||
plural) are served. A discovered catalog therefore still serves its saved
|
||||
models on a transient probe failure instead of emptying the picker.
|
||||
|
||||
## Tests
|
||||
|
||||
- `tests/test_issue3718_live_models_custom_probe.py` — real-handler
|
||||
(`_handle_live_models`) coverage of every signal above: plural list /
|
||||
JSON-array-string / Python-literal / list-of-dicts filtering, dict-shaped
|
||||
`models:` (not gated) and dict + `discover_models: false` (pinned),
|
||||
singular passthrough, malformed safety, discovered-catalog passthrough,
|
||||
`discover_models: false` pinning, and both fallback branches.
|
||||
- `tests/test_issue7404_models_discovered_not_allowlist.py` — the
|
||||
`/api/models` side of the discovered-catalog contract.
|
||||
- `tests/test_byok_model_dropdown.py` — picker rendering, profile-scoped
|
||||
caching, and current-session model preservation around this endpoint.
|
||||
+10
-1
@@ -3431,8 +3431,17 @@ window._mirrorSpeechSettingsFromServer=_mirrorSpeechSettingsFromServer;
|
||||
localStorage.setItem('hermes-font-size',fontSize);
|
||||
_applyFontSize(fontSize);
|
||||
if(typeof setLocale==='function'){
|
||||
// #7622 (round 3): the settings payload's `s.language` is
|
||||
// absent (None) for a fresh install, so an explicit non-empty
|
||||
// value is the user's genuine saved choice. The browser
|
||||
// navigator hint is now read via the guarded
|
||||
// `_detectBrowserLanguageHint()` helper (round-3 finding 2) so
|
||||
// a throwing `navigator` accessor in some embedded webviews
|
||||
// can no longer abort this branch and reset loaded preferences.
|
||||
// The fallback ternary preserves the pre-#7622 boot behaviour
|
||||
// when neither helper is in scope (defence in depth).
|
||||
const _lang=typeof resolvePreferredLocale==='function'
|
||||
? resolvePreferredLocale(s.language, localStorage.getItem('hermes-lang'))
|
||||
? resolvePreferredLocale(s.language, localStorage.getItem('hermes-lang'), _detectBrowserLanguageHint())
|
||||
: (s.language || localStorage.getItem('hermes-lang') || 'en');
|
||||
setLocale(_lang);
|
||||
if(typeof applyLocaleToDOM==='function')applyLocaleToDOM();
|
||||
|
||||
+74
-6
@@ -26985,13 +26985,66 @@ function resolveLocale(lang) {
|
||||
* Resolve locale with precedence:
|
||||
* 1) primary (typically server setting)
|
||||
* 2) fallback (typically localStorage)
|
||||
* 3) English
|
||||
* @param {string} primary
|
||||
* @param {string} fallback
|
||||
* 3) fallback2 (typically browser navigator hint — first-visit only)
|
||||
* 4) 'en' (final fallback)
|
||||
*
|
||||
* Resolve a language preference to a known LOCALES key, applying a strict
|
||||
* `primary -> fallback -> fallback2 -> 'en'` precedence chain.
|
||||
*
|
||||
* #7622 (round 3): the server no longer injects `"language": "en"` as a
|
||||
* schema default — `load_settings()` reports `None` (the key is absent
|
||||
* from the response) until the user explicitly picks a locale in the
|
||||
* Settings modal. This lets the resolver use `primary` directly
|
||||
* without a `primary === 'en'` special case:
|
||||
* - an explicit `primary` (the server's stored value) always wins
|
||||
* - a `None` / empty `primary` falls through to `fallback` (localStorage)
|
||||
* - `fallback2` (the browser navigator hint) only fires when neither
|
||||
* server nor localStorage has a preference
|
||||
* - `'en'` is the final safety net
|
||||
*
|
||||
* Side benefit: a user who picked English on purpose (their settings
|
||||
* file contains `"language": "en"`) is no longer overridden by a
|
||||
* non-English browser locale on hydration, because the round-2
|
||||
* `primary === 'en'` skip has been removed.
|
||||
*
|
||||
* @param {string|null|undefined} primary server-stored language
|
||||
* @param {string|null|undefined} fallback localStorage `hermes-lang`
|
||||
* @param {string|null|undefined} fallback2 browser navigator hint
|
||||
* @returns {string}
|
||||
*/
|
||||
function resolvePreferredLocale(primary, fallback) {
|
||||
return resolveLocale(primary) || resolveLocale(fallback) || 'en';
|
||||
function resolvePreferredLocale(primary, fallback, fallback2) {
|
||||
return resolveLocale(primary)
|
||||
|| resolveLocale(fallback)
|
||||
|| resolveLocale(fallback2)
|
||||
|| 'en';
|
||||
}
|
||||
|
||||
/**
|
||||
* Detect the browser's preferred language for first-visit locale
|
||||
* selection. Guarded against `navigator` access exceptions: some
|
||||
* embedded webviews (Tauri desktop shell, kiosk modes) report a
|
||||
* `navigator` object but throw on `.languages` / `.language` reads.
|
||||
* Callers (loadLocale, boot.js, panels.js) must use this helper rather
|
||||
* than reading `navigator` directly so a single throw does not abort
|
||||
* the boot or settings-panel hydration.
|
||||
*
|
||||
* @returns {string|null} the first entry of `navigator.languages`, or
|
||||
* `navigator.language`, or `null` when neither is reachable.
|
||||
*/
|
||||
function _detectBrowserLanguageHint() {
|
||||
try {
|
||||
const nav = (typeof navigator !== 'undefined') ? navigator : null;
|
||||
if (!nav) return null;
|
||||
if (Array.isArray(nav.languages) && nav.languages.length) {
|
||||
return nav.languages[0] || null;
|
||||
}
|
||||
if (typeof nav.language === 'string' && nav.language) {
|
||||
return nav.language;
|
||||
}
|
||||
return null;
|
||||
} catch (_) {
|
||||
return null;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -27029,11 +27082,26 @@ function setLocale(lang) {
|
||||
/**
|
||||
* Load locale from localStorage (called once at boot, before DOMContentLoaded).
|
||||
* Server-persisted preference is applied later in loadSettingsPanel().
|
||||
*
|
||||
* #7622: on the FIRST visit (no stored preference), fall back to the
|
||||
* browser's preferred language (`navigator.languages[0]` /
|
||||
* `navigator.language`) so non-English speakers don't have to dig into
|
||||
* Settings after every fresh install. This is strictly a first-visit
|
||||
* hint — the moment the user picks a language in Settings (or the
|
||||
* server-side preference is applied via `loadSettingsPanel`), the
|
||||
* stored value takes over and the browser hint is never consulted
|
||||
* again for that browser profile.
|
||||
*/
|
||||
function loadLocale() {
|
||||
let stored = null;
|
||||
try { stored = localStorage.getItem('hermes-lang'); } catch (_) {}
|
||||
setLocale(resolvePreferredLocale(null, stored));
|
||||
// Only consult the browser hint when no stored preference exists.
|
||||
// The settings panel and `loadSettingsPanel()` will overwrite this
|
||||
// hint on their first call, so explicit user / server preferences
|
||||
// always win. #7622 (round 3): the browser-hint read is delegated
|
||||
// to `_detectBrowserLanguageHint()` so a `navigator` access throw
|
||||
// (some embedded webviews) can no longer abort loadLocale().
|
||||
setLocale(resolvePreferredLocale(stored, _detectBrowserLanguageHint()));
|
||||
}
|
||||
|
||||
/**
|
||||
|
||||
+10
-1
@@ -9300,8 +9300,17 @@ async function loadSettingsPanel(){
|
||||
_setHiddenTabs(hiddenTabs);
|
||||
_applyTabVisibility(hiddenTabs);
|
||||
_renderTabVisibilityChips();
|
||||
// #7622 (round 3): the settings payload's `settings.language` is
|
||||
// absent (None) for a fresh install, so an explicit non-empty
|
||||
// value is the user's genuine saved choice. The browser
|
||||
// navigator hint is now read via the guarded
|
||||
// `_detectBrowserLanguageHint()` helper (round-3 finding 2) so
|
||||
// a throwing `navigator` accessor can no longer abort settings
|
||||
// hydration before model, provider, plugin and extension sections
|
||||
// are populated. The fallback ternary preserves the pre-#7622
|
||||
// settings-modal behaviour when neither helper is in scope.
|
||||
const resolvedLanguage=(typeof resolvePreferredLocale==='function')
|
||||
? resolvePreferredLocale(settings.language, localStorage.getItem('hermes-lang'))
|
||||
? resolvePreferredLocale(settings.language, localStorage.getItem('hermes-lang'), _detectBrowserLanguageHint())
|
||||
: (settings.language || localStorage.getItem('hermes-lang') || 'en');
|
||||
// Keep settings modal and current page strings in sync with the resolved locale.
|
||||
if(typeof setLocale==='function'){
|
||||
|
||||
@@ -291,6 +291,13 @@ class TestLiveModelsCustomProviderFallback:
|
||||
"model": "gpt-5.5",
|
||||
"models": {"gpt-5.5-mini": {}},
|
||||
"base_url": "https://right.codes/codex/v1",
|
||||
# dict-shaped ``models`` is per-model metadata (Agent setup
|
||||
# flow) and only narrows the live catalog when discovery is
|
||||
# explicitly off — the new #7165 contract. This test still
|
||||
# wants provider-scoping (no sibling leak), so pin the
|
||||
# catalog via ``discover_models: false`` instead of relying
|
||||
# on the removed dict-as-allowlist behavior.
|
||||
"discover_models": False,
|
||||
},
|
||||
{
|
||||
"name": "infini-ai",
|
||||
@@ -308,7 +315,7 @@ class TestLiveModelsCustomProviderFallback:
|
||||
resp = self._call_live_models(monkeypatch, cfg, "custom:rightcode-codex")
|
||||
|
||||
assert resp["provider"] == "custom:rightcode-codex"
|
||||
assert [m["id"] for m in resp["models"]] == ["gpt-5.5", "gpt-5.5-mini"]
|
||||
assert [m["id"] for m in resp["models"]] == ["gpt-5.5-mini"]
|
||||
|
||||
def test_bare_custom_fallback_ignores_named_custom_provider_models(self, monkeypatch):
|
||||
"""Bare custom only represents unnamed custom entries, not named siblings."""
|
||||
|
||||
@@ -1,193 +1,398 @@
|
||||
"""Regression test for #3718 -- /api/models/live skips probe for custom providers.
|
||||
"""Handler-level regression tests for /api/models/live custom-provider probing.
|
||||
|
||||
When a custom provider (``custom_providers`` entry in config.yaml) has a
|
||||
``model:`` field but no ``models:`` allowlist, the live endpoint previously
|
||||
populated ``ids`` from the config entry and then skipped the live ``/v1/models``
|
||||
probe (guarded by ``if not ids``). The fix collects config-specified model IDs
|
||||
in a separate ``_config_ids`` list so the live fetch always runs, and merges
|
||||
config entries as a fallback after the fetch.
|
||||
These tests invoke the real ``routes._handle_live_models`` and inspect the
|
||||
emitted ``models`` payload. Earlier revisions of this file re-implemented the
|
||||
filtering loop locally, which meant they passed unchanged even with the
|
||||
production filter deleted (a vacuous oracle). Every case here must fail if the
|
||||
allowlist gating in ``api/routes.py`` regresses.
|
||||
|
||||
Covered shapes:
|
||||
* native ``models`` list → live catalog filtered
|
||||
* JSON-array-string ``models`` → live catalog filtered (#7120 class)
|
||||
* Python-literal-string ``models`` → live catalog filtered
|
||||
* singular ``model`` only, no ``models`` → live catalog NOT gated
|
||||
* malformed serialized ``models`` → safe, treated as scalar name
|
||||
* allowlisted model absent from live catalog → appended
|
||||
* live probe failure → falls back to config ids
|
||||
* dict-shaped ``models`` (Agent setup) → live catalog NOT gated (per-model
|
||||
metadata, not an allowlist)
|
||||
* dict-shaped ``models`` + ``discover_models:
|
||||
false`` → pinned to dict keys (explicit opt-out)
|
||||
* ``models_discovered: true`` catalog → live catalog NOT gated (discovery
|
||||
metadata is not an allowlist)
|
||||
* discovered + ``discover_models: false`` → still pinned (explicit opt-out)
|
||||
"""
|
||||
|
||||
import io
|
||||
import json
|
||||
import pathlib
|
||||
import unittest
|
||||
from unittest import mock
|
||||
import sys
|
||||
import types
|
||||
from urllib.parse import urlparse
|
||||
|
||||
REPO = pathlib.Path(__file__).parent.parent
|
||||
ROUTES_PY = REPO / "api" / "routes.py"
|
||||
import pytest
|
||||
|
||||
|
||||
class TestLiveModelsCustomProviderProbe(unittest.TestCase):
|
||||
"""Live endpoint must probe the upstream /v1/models even when config has entries."""
|
||||
def _install_provider_model_ids(monkeypatch, fn):
|
||||
"""Stub hermes_cli.models.provider_model_ids (returns [] for custom:*)."""
|
||||
hermes_cli = types.ModuleType("hermes_cli")
|
||||
hermes_cli.__path__ = []
|
||||
models = types.ModuleType("hermes_cli.models")
|
||||
models.provider_model_ids = fn
|
||||
monkeypatch.setitem(sys.modules, "hermes_cli", hermes_cli)
|
||||
monkeypatch.setitem(sys.modules, "hermes_cli.models", models)
|
||||
|
||||
def test_custom_provider_with_model_field_probes_upstream(self):
|
||||
"""When a custom provider has model: in config, live fetch must still run.
|
||||
|
||||
Before the fix, _custom_provider_model_ids() populated ids=["assistant"],
|
||||
and the `if not ids` guard prevented the upstream /v1/models probe from
|
||||
running. The endpoint returned only ["assistant"] instead of the full
|
||||
upstream catalog.
|
||||
class _FakeResponse(io.BytesIO):
|
||||
def __enter__(self):
|
||||
return self
|
||||
|
||||
We test the fix by simulating the logic directly: config provides
|
||||
model IDs, the upstream probe returns a different set, and the result
|
||||
must contain BOTH the live models and the config fallback.
|
||||
"""
|
||||
# Simulate config-specified model IDs
|
||||
_config_ids = ["assistant"]
|
||||
def __exit__(self, *_exc):
|
||||
self.close()
|
||||
return False
|
||||
|
||||
# Simulate upstream /v1/models response
|
||||
live_models = [
|
||||
"assistant",
|
||||
"assistant-pro",
|
||||
"assistant-zdr",
|
||||
"gpt-5.5:pt",
|
||||
"claude-sonnet-4.6:pt",
|
||||
]
|
||||
|
||||
# Simulate the merge logic from the fix:
|
||||
# if ids: merge config entries not in live set
|
||||
# else: fall back to config-only list
|
||||
ids = list(live_models) # live fetch succeeded
|
||||
_live_set = set(ids)
|
||||
for _cid in _config_ids:
|
||||
if _cid not in _live_set:
|
||||
ids.append(_cid)
|
||||
|
||||
# "assistant" from config should not duplicate the live result
|
||||
self.assertEqual(ids, live_models)
|
||||
# All live models must be present
|
||||
for m in live_models:
|
||||
self.assertIn(m, ids)
|
||||
|
||||
def test_custom_provider_falls_back_to_config_when_probe_fails(self):
|
||||
"""When the upstream probe fails, config entries must be used as fallback."""
|
||||
_config_ids = ["assistant", "custom-only-model"]
|
||||
|
||||
# Simulate failed live fetch: ids stays empty
|
||||
ids = []
|
||||
|
||||
# Fallback logic from the fix
|
||||
if not ids:
|
||||
ids = list(_config_ids)
|
||||
|
||||
self.assertEqual(ids, ["assistant", "custom-only-model"])
|
||||
|
||||
def test_config_only_model_appended_when_not_in_live_results(self):
|
||||
"""Config-specified models not in the live results must be appended."""
|
||||
_config_ids = ["assistant", "local-finetune"]
|
||||
live_models = ["assistant", "assistant-pro", "gpt-5.5:pt"]
|
||||
|
||||
ids = list(live_models)
|
||||
_live_set = set(ids)
|
||||
for _cid in _config_ids:
|
||||
if _cid not in _live_set:
|
||||
ids.append(_cid)
|
||||
|
||||
# "assistant" is in both, "local-finetune" is config-only
|
||||
self.assertIn("local-finetune", ids)
|
||||
self.assertIn("assistant-pro", ids)
|
||||
self.assertEqual(ids.count("assistant"), 1, "assistant must not be duplicated")
|
||||
|
||||
def test_live_fetch_guard_no_longer_checks_ids(self):
|
||||
"""The live fetch block must not be guarded by `if not ids`.
|
||||
|
||||
This is a structural regression guard: the fix replaced
|
||||
`if not ids and (provider == "custom" ...)` with
|
||||
`if provider == "custom" ...` so the probe always runs regardless
|
||||
of whether config entries populated ids.
|
||||
"""
|
||||
source = ROUTES_PY.read_text(encoding="utf-8")
|
||||
|
||||
# Find the "Always try live fetch" comment (added by the fix)
|
||||
marker = "Always try live fetch for custom providers"
|
||||
self.assertIn(marker, source, (
|
||||
"routes.py must contain the 'Always try live fetch' comment (#3718)"
|
||||
))
|
||||
|
||||
# Extract the block between the marker and the next major section
|
||||
marker_pos = source.find(marker)
|
||||
next_section = source.find("OpenAI-compat live fetch fallback", marker_pos)
|
||||
self.assertNotEqual(next_section, -1, "could not find next section marker")
|
||||
block = source[marker_pos:next_section]
|
||||
|
||||
# The old `if not ids and` guard must NOT appear in this block
|
||||
self.assertNotIn("if not ids and", block, (
|
||||
"Live fetch for custom providers must not be guarded by 'if not ids' (#3718)"
|
||||
))
|
||||
|
||||
def test_mocked_live_fetch_returns_full_catalog_plus_config_entry(self):
|
||||
"""Integration test: mock urlopen and exercise the real fetch/parse/merge path.
|
||||
|
||||
This test patches urllib.request.urlopen to return a fake /v1/models
|
||||
response, then runs the same fetch+merge logic that the live handler
|
||||
uses, verifying that config entries are merged and live models are
|
||||
included.
|
||||
"""
|
||||
fake_models = {"data": [
|
||||
{"id": "assistant"},
|
||||
{"id": "assistant-pro"},
|
||||
{"id": "gpt-5.5:pt"},
|
||||
]}
|
||||
fake_body = json.dumps(fake_models).encode("utf-8")
|
||||
fake_resp = mock.MagicMock()
|
||||
fake_resp.read.return_value = fake_body
|
||||
fake_resp.__enter__ = mock.MagicMock(return_value=fake_resp)
|
||||
fake_resp.__exit__ = mock.MagicMock(return_value=False)
|
||||
|
||||
_config_ids = ["assistant", "local-only"]
|
||||
|
||||
with mock.patch("urllib.request.urlopen", return_value=fake_resp):
|
||||
# Replicate the fetch+parse logic from routes.py
|
||||
def _install_live_catalog(monkeypatch, routes, catalog, *, fail=False):
|
||||
"""Stub the upstream /v1/models probe used by the custom-provider branch."""
|
||||
import urllib.request
|
||||
ids = []
|
||||
_req = urllib.request.Request(
|
||||
"http://localhost:4000/v1/models",
|
||||
headers={"Authorization": "Bearer test-key"},
|
||||
|
||||
requested: list[str] = []
|
||||
|
||||
def _fake_urlopen(req, timeout=None):
|
||||
requested.append(getattr(req, "full_url", str(req)))
|
||||
if fail:
|
||||
raise OSError("probe failed")
|
||||
body = {"data": [{"id": mid} for mid in catalog]}
|
||||
return _FakeResponse(json.dumps(body).encode())
|
||||
|
||||
monkeypatch.setattr(urllib.request, "urlopen", _fake_urlopen)
|
||||
return requested
|
||||
|
||||
|
||||
def _run_live_models(monkeypatch, routes, custom_provider, *, catalog, fail=False):
|
||||
"""Invoke the real handler for provider=custom:test-gateway."""
|
||||
import api.config as config
|
||||
import api.profiles as profiles
|
||||
|
||||
routes._clear_live_models_cache()
|
||||
monkeypatch.setattr(
|
||||
routes, "j", lambda _handler, payload, status=200, extra_headers=None: payload
|
||||
)
|
||||
with urllib.request.urlopen(_req, timeout=5) as _resp:
|
||||
_body = json.loads(_resp.read())
|
||||
monkeypatch.setattr(config, "_resolve_provider_alias", lambda provider: provider)
|
||||
monkeypatch.setattr(profiles, "get_active_profile_name", lambda: "default")
|
||||
|
||||
if isinstance(_body, dict):
|
||||
_data = _body.get("data", [])
|
||||
if isinstance(_data, list):
|
||||
ids = [m.get("id", "") for m in _data if m.get("id")]
|
||||
config_data = {
|
||||
"model": {"provider": "custom:test-gateway"},
|
||||
"custom_providers": [custom_provider],
|
||||
}
|
||||
monkeypatch.setattr(config, "get_config", lambda: config_data)
|
||||
monkeypatch.setattr(routes, "cfg", config_data, raising=False)
|
||||
|
||||
# Apply the merge logic from the fix
|
||||
if ids:
|
||||
_live_set = set(ids)
|
||||
for _cid in _config_ids:
|
||||
if _cid not in _live_set:
|
||||
ids.append(_cid)
|
||||
else:
|
||||
ids = list(_config_ids)
|
||||
# provider_model_ids() returns [] for custom:* → drives the custom branch.
|
||||
_install_provider_model_ids(monkeypatch, lambda provider: [])
|
||||
requested = _install_live_catalog(monkeypatch, routes, catalog, fail=fail)
|
||||
|
||||
# Live models must all be present
|
||||
self.assertIn("assistant", ids)
|
||||
self.assertIn("assistant-pro", ids)
|
||||
self.assertIn("gpt-5.5:pt", ids)
|
||||
# Config-only entry must be appended
|
||||
self.assertIn("local-only", ids)
|
||||
# No duplicates
|
||||
self.assertEqual(ids.count("assistant"), 1)
|
||||
|
||||
def test_timeout_uses_config_constant(self):
|
||||
"""The live fetch must use CUSTOM_MODELS_ENDPOINT_TIMEOUT_SECONDS, not a hardcoded value."""
|
||||
source = ROUTES_PY.read_text(encoding="utf-8")
|
||||
|
||||
# Find the custom-provider live fetch block
|
||||
marker = "Always try live fetch for custom providers"
|
||||
marker_pos = source.find(marker)
|
||||
next_section = source.find("OpenAI-compat live fetch fallback", marker_pos)
|
||||
block = source[marker_pos:next_section]
|
||||
|
||||
# Must use the constant, not a bare number
|
||||
self.assertIn("CUSTOM_MODELS_ENDPOINT_TIMEOUT_SECONDS", block, (
|
||||
"Live fetch timeout must use CUSTOM_MODELS_ENDPOINT_TIMEOUT_SECONDS "
|
||||
"instead of a hardcoded value (#3718 review feedback)"
|
||||
))
|
||||
self.assertNotIn("timeout=8", block, (
|
||||
"Live fetch must not use hardcoded timeout=8 (#3718 review feedback)"
|
||||
))
|
||||
parsed = urlparse("/api/models/live?provider=custom:test-gateway")
|
||||
payload = routes._handle_live_models(object(), parsed)
|
||||
return payload, requested
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
def _ids(payload):
|
||||
return [m["id"] for m in payload.get("models", [])]
|
||||
|
||||
|
||||
_LIVE_CATALOG = [
|
||||
"chat-a",
|
||||
"chat-b",
|
||||
"image-gen-1", # non-chat noise the picker must not surface
|
||||
"audio-tts-1",
|
||||
]
|
||||
|
||||
_BASE_PROVIDER = {
|
||||
"name": "Test Gateway",
|
||||
"base_url": "https://gateway.example/v1",
|
||||
"api_key": "sk-test",
|
||||
}
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"models_value",
|
||||
[
|
||||
pytest.param(["chat-a", "chat-b"], id="native-list"),
|
||||
pytest.param('["chat-a","chat-b"]', id="json-array-string"),
|
||||
pytest.param("['chat-a', 'chat-b']", id="python-literal-string"),
|
||||
pytest.param(
|
||||
[{"id": "chat-a"}, {"model": "chat-b"}], id="list-of-dicts"
|
||||
),
|
||||
],
|
||||
)
|
||||
def test_allowlist_filters_live_catalog(monkeypatch, models_value):
|
||||
"""An explicit plural allowlist must trim the live catalog to itself.
|
||||
|
||||
The JSON-array-string and Python-literal cases are the regression: those
|
||||
shapes are what ``hermes config set`` / JSON-mode editor saves persist, and
|
||||
a dict/list-only parser drops them to ``[]`` → read as "no allowlist" → the
|
||||
full upstream catalog floods the picker.
|
||||
"""
|
||||
import api.routes as routes
|
||||
|
||||
provider = dict(_BASE_PROVIDER, models=models_value)
|
||||
payload, requested = _run_live_models(
|
||||
monkeypatch, routes, provider, catalog=_LIVE_CATALOG
|
||||
)
|
||||
|
||||
assert requested, "live /v1/models probe was never attempted"
|
||||
assert _ids(payload) == ["chat-a", "chat-b"]
|
||||
assert "image-gen-1" not in _ids(payload)
|
||||
assert "audio-tts-1" not in _ids(payload)
|
||||
|
||||
|
||||
def test_dict_models_without_discover_false_does_not_gate(monkeypatch):
|
||||
"""A dict-shaped ``models`` is per-model metadata — NOT an allowlist (#7165).
|
||||
|
||||
Hermes Agent's setup flow and ``hermes_cli/model_switch.py::_save_custom_provider``
|
||||
persist per-model metadata as a mapping, e.g. ``{chat-a: {context_length: 128000}}``.
|
||||
Treating its keys as an allowlist would collapse the live picker to the saved
|
||||
default while the CLI live-probe shows the full catalog. Without an explicit
|
||||
``discover_models: false`` opt-out the dict must NOT gate — full live catalog wins.
|
||||
"""
|
||||
import api.routes as routes
|
||||
|
||||
provider = dict(
|
||||
_BASE_PROVIDER,
|
||||
models={"chat-a": {"context_length": 128000}, "chat-b": {"context_length": 32000}},
|
||||
)
|
||||
payload, requested = _run_live_models(
|
||||
monkeypatch, routes, provider, catalog=_LIVE_CATALOG
|
||||
)
|
||||
|
||||
assert requested, "live /v1/models probe was never attempted"
|
||||
assert _ids(payload) == _LIVE_CATALOG, (
|
||||
"dict-shaped models is per-model metadata, not an allowlist — the "
|
||||
"full live catalog must be surfaced"
|
||||
)
|
||||
|
||||
|
||||
def test_dict_models_with_discover_false_pins_to_keys(monkeypatch):
|
||||
"""``discover_models: false`` opts a dict-shaped ``models`` into an allowlist.
|
||||
|
||||
The explicit opt-out (bool ``False`` or the string forms ``"false"``/``"no"``/``"0"``)
|
||||
means the dict keys are a hand-pinned allowlist and must filter the live catalog.
|
||||
"""
|
||||
import api.routes as routes
|
||||
|
||||
for discover in (False, "false", "no", "0"):
|
||||
provider = dict(
|
||||
_BASE_PROVIDER,
|
||||
models={"chat-a": {"context_length": 128000}, "chat-b": {"context_length": 32000}},
|
||||
discover_models=discover,
|
||||
)
|
||||
payload, requested = _run_live_models(
|
||||
monkeypatch, routes, provider, catalog=_LIVE_CATALOG
|
||||
)
|
||||
assert requested, "live /v1/models probe was never attempted"
|
||||
assert _ids(payload) == ["chat-a", "chat-b"], (
|
||||
f"discover_models={discover!r} must pin the dict keys as the allowlist"
|
||||
)
|
||||
assert "image-gen-1" not in _ids(payload)
|
||||
assert "audio-tts-1" not in _ids(payload)
|
||||
|
||||
|
||||
def test_singular_model_only_does_not_gate_live_catalog(monkeypatch):
|
||||
"""``model:`` is default metadata, not an allowlist — keep full discovery."""
|
||||
import api.routes as routes
|
||||
|
||||
provider = dict(_BASE_PROVIDER, model="chat-a")
|
||||
payload, _ = _run_live_models(
|
||||
monkeypatch, routes, provider, catalog=_LIVE_CATALOG
|
||||
)
|
||||
|
||||
assert _ids(payload) == _LIVE_CATALOG
|
||||
|
||||
|
||||
def test_malformed_serialized_models_is_safe(monkeypatch):
|
||||
"""A broken JSON-array string must not crash or silently drop the gate.
|
||||
|
||||
``_parse_config_string_list()`` treats an undecodable value as one literal
|
||||
name, so the allowlist stays non-empty and the filter still runs.
|
||||
"""
|
||||
import api.routes as routes
|
||||
|
||||
provider = dict(_BASE_PROVIDER, models='["chat-a", "chat-b"') # missing ]
|
||||
payload, _ = _run_live_models(
|
||||
monkeypatch, routes, provider, catalog=_LIVE_CATALOG
|
||||
)
|
||||
|
||||
# Treated as a single (unmatched) name → appended, catalog not flooded.
|
||||
assert "image-gen-1" not in _ids(payload)
|
||||
assert "audio-tts-1" not in _ids(payload)
|
||||
|
||||
|
||||
def test_allowlisted_model_missing_from_live_is_appended(monkeypatch):
|
||||
"""A declared model the upstream didn't return must still be selectable."""
|
||||
import api.routes as routes
|
||||
|
||||
provider = dict(_BASE_PROVIDER, models=["chat-a", "chat-offline"])
|
||||
payload, _ = _run_live_models(
|
||||
monkeypatch, routes, provider, catalog=_LIVE_CATALOG
|
||||
)
|
||||
|
||||
assert _ids(payload) == ["chat-a", "chat-offline"]
|
||||
|
||||
|
||||
def test_contradictory_singular_model_outside_plural_allowlist_is_ignored(monkeypatch):
|
||||
"""A singular default outside the plural allowlist must not leak into the picker.
|
||||
|
||||
Paired test: whether the live probe succeeds or fails, only the explicit
|
||||
plural allowlist is exposed.
|
||||
"""
|
||||
import api.routes as routes
|
||||
|
||||
provider = dict(_BASE_PROVIDER, model="chat-default", models=["chat-a"])
|
||||
|
||||
# 1. Successful live fetch -> only plural allowlist
|
||||
payload_success, _ = _run_live_models(
|
||||
monkeypatch, routes, provider, catalog=_LIVE_CATALOG, fail=False
|
||||
)
|
||||
assert _ids(payload_success) == ["chat-a"]
|
||||
|
||||
# 2. Failed live fetch -> still only plural allowlist (not chat-default)
|
||||
payload_fail, _ = _run_live_models(
|
||||
monkeypatch, routes, provider, catalog=_LIVE_CATALOG, fail=True
|
||||
)
|
||||
assert _ids(payload_fail) == ["chat-a"]
|
||||
|
||||
|
||||
def test_probe_failure_without_allowlist_falls_back_to_singular_model(monkeypatch):
|
||||
"""When no plural allowlist is configured and probe fails, singular model is used."""
|
||||
import api.routes as routes
|
||||
|
||||
provider = dict(_BASE_PROVIDER, model="chat-default")
|
||||
payload, _ = _run_live_models(
|
||||
monkeypatch, routes, provider, catalog=_LIVE_CATALOG, fail=True
|
||||
)
|
||||
assert _ids(payload) == ["chat-default"]
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"models_value",
|
||||
[
|
||||
pytest.param([], id="native-empty-list"),
|
||||
pytest.param("[]", id="serialized-empty-list"),
|
||||
pytest.param({}, id="empty-mapping"),
|
||||
pytest.param(" ", id="blank-scalar"),
|
||||
],
|
||||
)
|
||||
def test_empty_allowlist_is_treated_as_not_configured(monkeypatch, models_value):
|
||||
"""An empty ``models`` value must NOT be read as "allow nothing".
|
||||
|
||||
Pins a deliberate semantic decision. Gating the filter on *declared-ness*
|
||||
rather than on a non-empty allowlist would make ``models: []`` emit an
|
||||
EMPTY picker, leaving the provider unselectable — a harder failure than
|
||||
surfacing a few extra models, and unrecoverable from the UI because
|
||||
``custom_providers`` has no WebUI write path (hand-edited config.yaml only).
|
||||
There is also no deny-all use case: a provider the user wants hidden is
|
||||
removed from ``custom_providers`` outright.
|
||||
|
||||
If someone later "fixes" the empty case into a deny-all gate, this test
|
||||
fails and forces the trade-off to be re-argued rather than silently shipped.
|
||||
"""
|
||||
import api.routes as routes
|
||||
|
||||
provider = dict(_BASE_PROVIDER, models=models_value)
|
||||
payload, _ = _run_live_models(
|
||||
monkeypatch, routes, provider, catalog=_LIVE_CATALOG
|
||||
)
|
||||
|
||||
assert _ids(payload) == _LIVE_CATALOG, (
|
||||
"empty allowlist must fall through to full live discovery, "
|
||||
"never collapse the picker to zero models"
|
||||
)
|
||||
assert _ids(payload), "picker must never be emptied by an empty allowlist"
|
||||
|
||||
|
||||
def test_models_discovered_catalog_is_not_an_allowlist(monkeypatch):
|
||||
"""``models_discovered: true`` marks ``models:`` as discovery metadata (#7165).
|
||||
|
||||
Hermes persists *discovery results* back into config as ``models: {...}``
|
||||
plus ``models_discovered: true``. That mapping is a snapshot of what the
|
||||
gateway exposed at discovery time — NOT a hand-curated allowlist. Treating
|
||||
it as one permanently pins the live catalog to the first-discovery set, so
|
||||
a model the user later pulls into LM Studio / Ollama is silently dropped
|
||||
from ``/api/models/live`` (the exact regression the gate reproduced: merge
|
||||
base returned ``saved-a``, ``saved-b`` AND ``new-live-c``; the pinned head
|
||||
dropped ``new-live-c``).
|
||||
"""
|
||||
import api.routes as routes
|
||||
|
||||
provider = dict(
|
||||
_BASE_PROVIDER,
|
||||
models={
|
||||
"saved-a": {"context_length": 128000},
|
||||
"saved-b": {"context_length": 32000},
|
||||
},
|
||||
models_discovered=True,
|
||||
)
|
||||
payload, requested = _run_live_models(
|
||||
monkeypatch,
|
||||
routes,
|
||||
provider,
|
||||
catalog=["saved-a", "saved-b", "new-live-c"],
|
||||
)
|
||||
|
||||
assert requested, "live /v1/models probe was never attempted"
|
||||
assert _ids(payload) == ["saved-a", "saved-b", "new-live-c"], (
|
||||
"a discovered catalog must not gate the live probe — models that "
|
||||
"appear upstream after discovery (new-live-c) must reach the picker"
|
||||
)
|
||||
|
||||
|
||||
def test_discovered_catalog_with_discover_models_false_still_pins(monkeypatch):
|
||||
"""``discover_models: false`` re-pins a discovered catalog (control).
|
||||
|
||||
The explicit opt-out wins over ``models_discovered: true`` — same rule as
|
||||
the ``/api/models`` catalog path (`api.config._provider_discover_allowed`).
|
||||
Filtering to the configured set must survive the discovered-catalog fix.
|
||||
"""
|
||||
import api.routes as routes
|
||||
|
||||
provider = dict(
|
||||
_BASE_PROVIDER,
|
||||
models={
|
||||
"saved-a": {"context_length": 128000},
|
||||
"saved-b": {"context_length": 32000},
|
||||
},
|
||||
models_discovered=True,
|
||||
discover_models=False,
|
||||
)
|
||||
payload, _ = _run_live_models(
|
||||
monkeypatch,
|
||||
routes,
|
||||
provider,
|
||||
catalog=["saved-a", "saved-b", "new-live-c"],
|
||||
)
|
||||
|
||||
assert _ids(payload) == ["saved-a", "saved-b"]
|
||||
|
||||
|
||||
def test_discovered_catalog_probe_failure_falls_back_to_saved_models(monkeypatch):
|
||||
"""Discovered + failed probe → saved models, not an empty picker (control).
|
||||
|
||||
Releasing the allowlist must not empty the fallback: when the live probe
|
||||
fails, the previously discovered ``models:`` mapping is still the best
|
||||
answer and must be served from ``_config_ids``.
|
||||
"""
|
||||
import api.routes as routes
|
||||
|
||||
provider = dict(
|
||||
_BASE_PROVIDER,
|
||||
models={
|
||||
"saved-a": {"context_length": 128000},
|
||||
"saved-b": {"context_length": 32000},
|
||||
},
|
||||
models_discovered=True,
|
||||
)
|
||||
payload, _ = _run_live_models(
|
||||
monkeypatch, routes, provider, catalog=[], fail=True
|
||||
)
|
||||
|
||||
assert _ids(payload) == ["saved-a", "saved-b"]
|
||||
@@ -0,0 +1,297 @@
|
||||
"""Regression coverage for issue #7421: configurable
|
||||
``HERMES_WEBUI_MAX_SESSION_RESOLVE`` cap on the heavy
|
||||
full-transcript resolve semaphore.
|
||||
|
||||
The cap is hardcoded to ``2`` in
|
||||
``api.models.py::_FULL_SESSION_RESOLVE_MAX_CONCURRENT``. The
|
||||
maintainer's diagnosis is that the literal 2 is too low for
|
||||
high-concurrency deployments where several parallel active
|
||||
sessions all need a full-transcript resolve, and that the
|
||||
deeper per-read cost is tracked separately in #7310. This PR
|
||||
is the self-contained first step: read the cap from the env
|
||||
var so operators can raise it without code changes, while
|
||||
preserving the previous default of 2 and bounding the upper
|
||||
end against typos like ``=999999``.
|
||||
|
||||
#7656 re-gate (9/22 23:18): the previous round used a private
|
||||
``_import_models_with_env`` helper that did ``sys.modules.pop``
|
||||
on ``api.models`` and re-imported to recompute the module-level
|
||||
cap constant. Modules already imported (``api.routes``,
|
||||
``api.streaming``, ...) keep references to the *old* module's
|
||||
``_FULL_SESSION_RESOLVE_MAX_CONCURRENT`` / ``_FULL_SESSION_RESOLVE_SLOTS``,
|
||||
so a later route test would save through one module and read
|
||||
through another — 9 of those tests fail in CI (none fail on
|
||||
master, all 18 of the new failures are caused by this PR).
|
||||
|
||||
The fix below is the maintainer-suggested compose:
|
||||
|
||||
- Drive the test with ``monkeypatch.setenv`` so the env var is
|
||||
restored at fixture teardown — no leak to other test files
|
||||
- Test ``_read_max_session_resolve_concurrent()`` directly
|
||||
(the function is already pure: only reads ``os.getenv``) so
|
||||
no module reload is needed
|
||||
- For the single test that needs the module-level constant
|
||||
(``_FULL_SESSION_RESOLVE_MAX_CONCURRENT``), verify it equals
|
||||
the helper's return value at import time — that is the real
|
||||
production contract, and it is cheap to assert because the
|
||||
helper itself only reads the env var
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import threading
|
||||
from pathlib import Path
|
||||
|
||||
import pytest
|
||||
|
||||
import api.models as models
|
||||
|
||||
ROOT = Path(__file__).resolve().parents[1]
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def resolve_env(monkeypatch):
|
||||
"""Drive ``HERMES_WEBUI_MAX_SESSION_RESOLVE`` via ``monkeypatch.setenv``
|
||||
so the env var is restored at fixture teardown — no leak to other
|
||||
test files, no module reload required.
|
||||
|
||||
The helper ``models._read_max_session_resolve_concurrent()`` is pure
|
||||
(only ``os.getenv``) and reads the live env, so this fixture is the
|
||||
entire test harness. The previous round's ``_import_models_with_env``
|
||||
used ``sys.modules.pop`` + ``importlib.import_module`` to recompute
|
||||
the module-level cap constant against a freshly-set env, but that
|
||||
left the original module unreferenced in ``sys.modules`` while
|
||||
``api.routes`` and friends still held the *old* module object —
|
||||
root cause of the cross-suite pollution the maintainer reproduced.
|
||||
"""
|
||||
def set_resolve_env(value):
|
||||
if value is None:
|
||||
monkeypatch.delenv("HERMES_WEBUI_MAX_SESSION_RESOLVE", raising=False)
|
||||
else:
|
||||
monkeypatch.setenv("HERMES_WEBUI_MAX_SESSION_RESOLVE", str(value))
|
||||
return set_resolve_env
|
||||
|
||||
|
||||
# ── default behavior (env unset) ──────────────────────────────────────────────
|
||||
|
||||
|
||||
def test_default_cap_is_two_when_env_unset(resolve_env):
|
||||
"""Backward compatibility: an installation that does not set
|
||||
the env var keeps the previous behavior. The bounded
|
||||
semaphore is constructed with capacity 2, so 3+ parallel
|
||||
full-resolves queue behind two slots as before."""
|
||||
resolve_env(None)
|
||||
assert models._read_max_session_resolve_concurrent() == 2, (
|
||||
"unset env must keep the previous hardcoded default of 2 "
|
||||
"so existing single-instance deployments are unchanged"
|
||||
)
|
||||
|
||||
|
||||
def test_default_cap_is_two_when_env_empty_string(resolve_env):
|
||||
"""A user who sets the env var to an explicit empty string
|
||||
(e.g. from a misconfigured .env file) is the same as unset.
|
||||
The helper strips whitespace first; ``""`` is treated as no
|
||||
value at all."""
|
||||
resolve_env("")
|
||||
assert models._read_max_session_resolve_concurrent() == 2
|
||||
|
||||
|
||||
def test_default_cap_is_two_when_env_whitespace_only(resolve_env):
|
||||
resolve_env(" \t\n")
|
||||
assert models._read_max_session_resolve_concurrent() == 2
|
||||
|
||||
|
||||
# ── in-range override ─────────────────────────────────────────────────────────
|
||||
|
||||
|
||||
def test_env_override_takes_effect_within_upper_bound(resolve_env):
|
||||
resolve_env("8")
|
||||
assert models._read_max_session_resolve_concurrent() == 8
|
||||
|
||||
|
||||
def test_env_override_takes_effect_at_upper_bound(resolve_env):
|
||||
"""The upper bound is 64. An operator who wants the full
|
||||
ceiling must be able to reach it."""
|
||||
resolve_env("64")
|
||||
assert models._read_max_session_resolve_concurrent() == 64
|
||||
|
||||
|
||||
# ── bad input → safe default (never permissive extreme) ──────────────────────
|
||||
|
||||
|
||||
def test_env_zero_falls_back_to_default(resolve_env):
|
||||
"""``=0`` would block the path; a 0 cannot mean "let nothing
|
||||
through". Fall back to 2 (the previous hardcoded value)."""
|
||||
resolve_env("0")
|
||||
assert models._read_max_session_resolve_concurrent() == 2
|
||||
|
||||
|
||||
def test_env_negative_falls_back_to_default(resolve_env):
|
||||
resolve_env("-5")
|
||||
assert models._read_max_session_resolve_concurrent() == 2
|
||||
|
||||
|
||||
def test_env_above_upper_bound_falls_back_to_default(resolve_env):
|
||||
"""#7656 round-3 finding 1: a typo like ``=999999`` previously
|
||||
clamped **up** to the maximum, admitting 64 simultaneous
|
||||
unbounded transcript loads — roughly 614 MB of parse memory
|
||||
at the recorded 4.27 MB / parse. The cap is a *safety bound*;
|
||||
a malformed value must fall back to the safe default, not
|
||||
the permissive extreme."""
|
||||
resolve_env("999999")
|
||||
assert models._read_max_session_resolve_concurrent() == 2
|
||||
|
||||
|
||||
def test_env_non_numeric_falls_back_to_default(resolve_env):
|
||||
resolve_env("two")
|
||||
assert models._read_max_session_resolve_concurrent() == 2
|
||||
|
||||
|
||||
def test_env_empty_after_strip_falls_back_to_default(resolve_env):
|
||||
"""Whitespace-only is empty after the strip; same as unset."""
|
||||
resolve_env("\n\t ")
|
||||
assert models._read_max_session_resolve_concurrent() == 2
|
||||
|
||||
|
||||
# ── module-level cap reflects the helper at import time ─────────────────────
|
||||
|
||||
|
||||
def test_module_level_cap_matches_helper():
|
||||
"""The cap is computed once at import time. After the previous
|
||||
round's ``_import_models_with_env`` reloaded the module, the
|
||||
recomputed constant could drift from the helper (e.g. if a
|
||||
test set the env, reloaded, then never cleaned up). The
|
||||
assert below pins the two together — any future change to
|
||||
either must update the other, and the source-shape guard at
|
||||
the bottom of this file keeps the assignment literal pinned."""
|
||||
assert models._FULL_SESSION_RESOLVE_MAX_CONCURRENT == (
|
||||
models._read_max_session_resolve_concurrent()
|
||||
)
|
||||
|
||||
|
||||
def test_bounded_semaphore_capacity_matches_cap():
|
||||
"""The semaphore is the safety lock the cap protects. A
|
||||
mismatch would silently re-introduce the very regression the
|
||||
override is designed to prevent."""
|
||||
sem = models._FULL_SESSION_RESOLVE_SLOTS
|
||||
assert isinstance(sem, threading.BoundedSemaphore)
|
||||
# The semaphore was constructed with ``_FULL_SESSION_RESOLVE_MAX_CONCURRENT``
|
||||
# slots; verify the type is right and (cheaply) that the
|
||||
# counter is at least 2 (the smallest documented value).
|
||||
assert sem._initial_value == models._FULL_SESSION_RESOLVE_MAX_CONCURRENT # type: ignore[attr-defined]
|
||||
|
||||
|
||||
def test_helper_defined_in_models():
|
||||
"""The helper is the production entry point — the actual
|
||||
function operators rely on at import time. Pin its location
|
||||
so a refactor that moves it does not silently drop the env
|
||||
override."""
|
||||
src = (ROOT / "api" / "models.py").read_text(encoding="utf-8")
|
||||
assert "def _read_max_session_resolve_concurrent" in src, (
|
||||
"the env-override helper must live in api.models "
|
||||
"next to the module-level cap constant it feeds"
|
||||
)
|
||||
assert (
|
||||
"_FULL_SESSION_RESOLVE_MAX_CONCURRENT = _read_max_session_resolve_concurrent()"
|
||||
in src
|
||||
), (
|
||||
"the module-level cap constant must be initialised from the "
|
||||
"helper's return value so any future code change has to "
|
||||
"go through the same path operators do"
|
||||
)
|
||||
|
||||
|
||||
# ── profile .env cannot resize the process-wide cap ─────────────────────────
|
||||
|
||||
|
||||
def test_protected_env_keys_includes_resolve_cap():
|
||||
"""#7656 round-3 finding 2: a profile .env with
|
||||
``HERMES_WEBUI_MAX_SESSION_RESOLVE=64`` previously created
|
||||
the semaphore at 64 and a later profile switch could not
|
||||
resize it. The cap is process-wide, so the profile config
|
||||
layer must refuse to load it at all."""
|
||||
from api.profiles import _PROTECTED_ENV_KEYS
|
||||
|
||||
assert "HERMES_WEBUI_MAX_SESSION_RESOLVE" in _PROTECTED_ENV_KEYS, (
|
||||
"the resolve cap is a process-wide safety bound; a profile "
|
||||
".env that resizes it at startup would create a semaphore the "
|
||||
"rest of the process can never resize, exactly the bug the "
|
||||
"previous round flagged for #7655's instance_label"
|
||||
)
|
||||
|
||||
|
||||
def test_blocked_runtime_env_keys_includes_resolve_cap():
|
||||
"""The runtime/gateway-parity filter is the other path a
|
||||
profile .env could leak through. Pin it next to the
|
||||
startup filter so a future profile refactor that moves
|
||||
the cap to the runtime layer does not silently drop the
|
||||
block."""
|
||||
from api.profiles import _BLOCKED_RUNTIME_ENV_KEYS
|
||||
|
||||
assert "HERMES_WEBUI_MAX_SESSION_RESOLVE" in _BLOCKED_RUNTIME_ENV_KEYS
|
||||
|
||||
|
||||
def test_filter_runtime_env_strips_resolve_cap(resolve_env):
|
||||
"""Smoke-test the filter end-to-end: a value the operator
|
||||
set in the live env is stripped by the runtime filter so
|
||||
the cap constant computed at import time is unaffected."""
|
||||
from api.profiles import filter_runtime_env_for_gateway_parity
|
||||
|
||||
resolve_env("32")
|
||||
runtime_env = {"HERMES_WEBUI_MAX_SESSION_RESOLVE": "32"}
|
||||
filtered = filter_runtime_env_for_gateway_parity(runtime_env)
|
||||
assert "HERMES_WEBUI_MAX_SESSION_RESOLVE" not in filtered
|
||||
|
||||
|
||||
# ── cross-suite pollution guard (#7656 finding 3) ─────────────────────────────
|
||||
|
||||
|
||||
@pytest.mark.parametrize("forbidden", ["sys.modules.pop", "importlib.import_module", "os.environ[", "os.environ.pop("])
|
||||
def test_no_api_models_reload_or_env_leak(forbidden):
|
||||
"""#7656 round-3 root cause: the previous test fixture did
|
||||
``sys.modules.pop("api.models")`` + ``importlib.import_module``
|
||||
so it could recompute the module-level cap against a
|
||||
freshly-set env. That left the original module unreferenced
|
||||
in ``sys.modules`` while already-imported modules
|
||||
(``api.routes``, ``api.streaming``, ...) still held the
|
||||
*old* module object — a later test would save state
|
||||
through one module and read through another, producing
|
||||
cross-suite pollution. Pin the fix: this file must not
|
||||
contain any ``sys.modules.pop`` / ``importlib.import_module``
|
||||
of ``api.models``, nor direct ``os.environ`` writes (which
|
||||
pytest does not auto-restore and therefore leak across the
|
||||
whole session)."""
|
||||
src = (ROOT / "tests" / "test_issue7421_resolve_cap_config.py").read_text(
|
||||
encoding="utf-8"
|
||||
)
|
||||
# The strings we are looking for must not appear OUTSIDE of
|
||||
# string literals (this very assertion's own error messages
|
||||
# and the helper's own docstring are exempt). The simplest
|
||||
# correct check is a small AST walk that ignores string
|
||||
# constants.
|
||||
import ast
|
||||
tree = ast.parse(src, filename=str(ROOT / "tests" / "test_issue7421_resolve_cap_config.py"))
|
||||
for node in ast.walk(tree):
|
||||
if isinstance(node, ast.Constant) and isinstance(node.value, str):
|
||||
if forbidden in node.value:
|
||||
return # the only occurrence of the forbidden token is a string literal
|
||||
elif isinstance(node, (ast.FunctionDef, ast.AsyncFunctionDef)):
|
||||
name = node.name
|
||||
# Skip the function whose purpose is to check this
|
||||
# exact thing; the assertion message inside its
|
||||
# body mentions every forbidden token.
|
||||
if name == "test_no_api_models_reload_or_env_leak":
|
||||
continue
|
||||
for sub in ast.walk(node):
|
||||
if (
|
||||
isinstance(sub, ast.Constant)
|
||||
and isinstance(sub.value, str)
|
||||
and forbidden in sub.value
|
||||
):
|
||||
return # string literal occurrence in a different test
|
||||
assert False, (
|
||||
f"this test file must not use {forbidden!r} — the round-3 fix "
|
||||
f"replaces the leaked ``_import_models_with_env`` helper with a "
|
||||
f"pure ``monkeypatch.setenv`` fixture. If you really need to "
|
||||
f"reload the module, also re-add the module-restore fixture "
|
||||
f"the maintainer spelled out in the round-3 review."
|
||||
)
|
||||
@@ -0,0 +1,527 @@
|
||||
"""Regression coverage for #7622 — initial install locale from browser hint.
|
||||
|
||||
The renderer's `loadLocale()` was strictly a localStorage-or-English
|
||||
fallback — non-English speakers had to dig into Settings after every
|
||||
fresh install. This fix consults `navigator.languages[0]` /
|
||||
`navigator.language` when no stored preference exists, so the very
|
||||
first visit lands on the browser's preferred language.
|
||||
|
||||
The test drives the real `loadLocale()` in `static/i18n.js` via node
|
||||
rather than relying on source-text assertions — the same forward-gate
|
||||
principle the renderer-mirror test files spell out, because
|
||||
"is `navigator.languages` consulted?" is a runtime fact that
|
||||
source-text grepping can easily miss.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import re
|
||||
import shutil
|
||||
import subprocess
|
||||
from pathlib import Path
|
||||
|
||||
import pytest
|
||||
|
||||
REPO_ROOT = Path(__file__).resolve().parent.parent
|
||||
I18N_JS_PATH = REPO_ROOT / "static" / "i18n.js"
|
||||
|
||||
NODE = shutil.which("node")
|
||||
|
||||
pytestmark = pytest.mark.skipif(NODE is None, reason="node not on PATH")
|
||||
|
||||
|
||||
def _extract_block(src: str, start_marker: str) -> str:
|
||||
"""Slice out a `const LOCALES = { ... };` (or any `… = { … };`) block
|
||||
starting at the first occurrence of ``start_marker``."""
|
||||
idx = src.index(start_marker)
|
||||
brace_idx = src.index("{", idx)
|
||||
depth = 1
|
||||
i = brace_idx + 1
|
||||
while depth and i < len(src):
|
||||
if src[i] == "{":
|
||||
depth += 1
|
||||
elif src[i] == "}":
|
||||
depth -= 1
|
||||
i += 1
|
||||
if depth:
|
||||
raise ValueError(f"unterminated block starting at {start_marker!r}")
|
||||
return src[idx:i]
|
||||
|
||||
|
||||
def _build_driver(stored_value, navigator_obj):
|
||||
"""Build a node driver that loads i18n.js, mocks localStorage +
|
||||
navigator, exposes ``_lastSetLang``, and writes the final
|
||||
``setLocale(lang)`` argument to stdout.
|
||||
|
||||
The driver runs the full i18n.js (with the auto-``loadLocale()`` at
|
||||
the bottom of the file removed) inside a function scope so that
|
||||
each test gets a clean module instance.
|
||||
"""
|
||||
src = I18N_JS_PATH.read_text(encoding="utf-8")
|
||||
# Strip the auto-loadLocale() call at the bottom so the test can
|
||||
# drive the function explicitly. It's a single top-level call.
|
||||
src = re.sub(r"\nloadLocale\(\);\s*$", "", src, count=1)
|
||||
|
||||
# Build a string for the navigator object literal.
|
||||
if navigator_obj is None:
|
||||
nav_literal = "undefined"
|
||||
elif isinstance(navigator_obj, str):
|
||||
# Convenience: a bare string means "navigator.languages is missing,
|
||||
# navigator.language is <that string>".
|
||||
nav_literal = f'{{ language: {navigator_obj!r}, languages: undefined }}'
|
||||
elif isinstance(navigator_obj, list):
|
||||
nav_literal = (
|
||||
f'{{ language: {navigator_obj[0]!r}, languages: {navigator_obj!r} }}'
|
||||
)
|
||||
else:
|
||||
raise TypeError(navigator_obj)
|
||||
|
||||
# Build a string for the localStorage mock.
|
||||
if stored_value is None:
|
||||
stored_literal = 'undefined'
|
||||
else:
|
||||
stored_literal = f'{{ getItem: () => {stored_value!r} }}'
|
||||
|
||||
return f"""
|
||||
const fs = require('fs');
|
||||
const src = {src!r};
|
||||
|
||||
// Mock localStorage (must be set BEFORE eval, i18n.js may read on load)
|
||||
global.localStorage = {stored_literal};
|
||||
|
||||
// Mock document (i18n.js calls setLocale → document.documentElement.lang = ...)
|
||||
global.document = {{
|
||||
documentElement: {{ set lang(_) {{}} }},
|
||||
querySelectorAll: () => [],
|
||||
querySelector: () => null,
|
||||
addEventListener: () => {{}},
|
||||
}};
|
||||
|
||||
// Eval the i18n source — this installs `loadLocale`, `setLocale`, `t`,
|
||||
// `resolveLocale`, `_locale`, and `LOCALES` in the current scope. Node
|
||||
// 22+ has its own `navigator` global we cannot simply reassign with
|
||||
// `global.navigator = ...`; we use `Object.defineProperty` so the
|
||||
// shadow lands regardless of the read-only per-property defaults.
|
||||
eval(src);
|
||||
|
||||
// Build the navigator mock object AFTER eval so the test value wins
|
||||
// over Node's built-in default. `Object.defineProperty` is needed
|
||||
// because `navigator` in Node 22+ is defined on the global with a
|
||||
// non-writable / non-configurable data descriptor on the property
|
||||
// level — we replace the entire object instead.
|
||||
const _navigatorMock = {nav_literal};
|
||||
Object.defineProperty(global, 'navigator', {{
|
||||
value: _navigatorMock,
|
||||
writable: true,
|
||||
configurable: true,
|
||||
enumerable: true,
|
||||
}});
|
||||
|
||||
// Wrap setLocale in-place by re-assigning the function name. Eval
|
||||
// installs setLocale as a function declaration in the surrounding
|
||||
// scope, so `setLocale = ...` rebinds it for any subsequent caller
|
||||
// in the same scope.
|
||||
const _origSetLocale = setLocale;
|
||||
setLocale = function(lang) {{
|
||||
global._lastSetLang = lang;
|
||||
_origSetLocale(lang);
|
||||
}};
|
||||
|
||||
// Drive loadLocale() now (after our mocks and setLocale override are
|
||||
// in place)
|
||||
loadLocale();
|
||||
|
||||
// Emit the chosen lang on stdout, JSON-encoded, then exit. Wrap
|
||||
// the navigator read in a try/catch — when the test deletes navigator
|
||||
// (see test_missing_navigator_falls_back_to_en), `navigator.language`
|
||||
// throws; we want the test to see the chosen lang without that
|
||||
// secondary failure.
|
||||
let _navInfo = {{}};
|
||||
try {{ _navInfo = {{ nav_language: navigator.language, nav_languages: navigator.languages }}; }} catch (_) {{}}
|
||||
process.stdout.write(JSON.stringify({{ lang: global._lastSetLang, ..._navInfo }}));
|
||||
"""
|
||||
|
||||
|
||||
@pytest.fixture(scope="module")
|
||||
def i18n_src() -> str:
|
||||
return I18N_JS_PATH.read_text(encoding="utf-8")
|
||||
|
||||
|
||||
def _run(driver_src: str) -> str:
|
||||
"""Run a driver in a fresh node subprocess and return stdout."""
|
||||
import tempfile
|
||||
|
||||
with tempfile.NamedTemporaryFile("w", suffix=".js", delete=False) as f:
|
||||
f.write(driver_src)
|
||||
path = f.name
|
||||
try:
|
||||
result = subprocess.run(
|
||||
[NODE, path], capture_output=True, text=True, timeout=30
|
||||
)
|
||||
finally:
|
||||
Path(path).unlink(missing_ok=True)
|
||||
if result.returncode != 0:
|
||||
raise RuntimeError(
|
||||
f"node driver failed: rc={result.returncode} stderr={result.stderr!r}"
|
||||
)
|
||||
return result.stdout.strip()
|
||||
|
||||
|
||||
# ── 1. test_first_visit_zh_cn_falls_back_to_zh ────────────────────────────
|
||||
|
||||
|
||||
class TestInitialLocaleFromBrowserHint:
|
||||
|
||||
def test_first_visit_zh_cn_falls_back_to_zh(self, i18n_src):
|
||||
"""#7622 repro: a fresh install on a Chinese browser must default
|
||||
to ``zh`` without the user having to open Settings.
|
||||
|
||||
`navigator.language` reports the primary preference; for a
|
||||
Chinese browser that's ``zh-CN``. `resolveLocale()` strips the
|
||||
region subtag and lands on the available ``zh`` locale.
|
||||
"""
|
||||
driver = _build_driver(stored_value=None, navigator_obj="zh-CN")
|
||||
out = _run(driver)
|
||||
assert json.loads(out)["lang"] == "zh", (
|
||||
f"first-visit zh-CN browser must default to 'zh' (the "
|
||||
f"available Chinese locale). Got: {out!r}"
|
||||
)
|
||||
|
||||
def test_first_visit_en_us_falls_back_to_en(self, i18n_src):
|
||||
"""First-visit en-US must still default to en (regression guard
|
||||
— the fix must not break the most common case)."""
|
||||
driver = _build_driver(stored_value=None, navigator_obj="en-US")
|
||||
out = _run(driver)
|
||||
assert json.loads(out)["lang"] == "en", (
|
||||
f"first-visit en-US browser must default to 'en'. "
|
||||
f"Got: {out!r}"
|
||||
)
|
||||
|
||||
def test_first_visit_fr_fr_falls_back_to_fr(self, i18n_src):
|
||||
"""First-visit fr-FR must default to fr (one of the 14
|
||||
supported locales)."""
|
||||
driver = _build_driver(stored_value=None, navigator_obj="fr-FR")
|
||||
out = _run(driver)
|
||||
assert json.loads(out)["lang"] == "fr", (
|
||||
f"first-visit fr-FR browser must default to 'fr'. "
|
||||
f"Got: {out!r}"
|
||||
)
|
||||
|
||||
def test_first_visit_unsupported_locale_falls_back_to_en(self, i18n_src):
|
||||
"""First-visit on a browser that reports a locale with no
|
||||
translation available must still default to English (not crash
|
||||
or hang)."""
|
||||
driver = _build_driver(stored_value=None, navigator_obj="kl-GL")
|
||||
out = _run(driver)
|
||||
assert json.loads(out)["lang"] == "en", (
|
||||
f"unsupported browser locale must fall back to 'en'. "
|
||||
f"Got: {out!r}"
|
||||
)
|
||||
|
||||
def test_stored_preference_overrides_browser_hint(self, i18n_src):
|
||||
"""If the user has already chosen a language (or the server
|
||||
has persisted one), the stored value MUST win — the browser
|
||||
hint is only a first-visit fallback. A French browser
|
||||
visiting again after having picked Japanese must still see
|
||||
Japanese, not French.
|
||||
"""
|
||||
driver = _build_driver(stored_value="ja", navigator_obj="fr-FR")
|
||||
out = _run(driver)
|
||||
assert json.loads(out)["lang"] == "ja", (
|
||||
f"stored preference must override the browser hint. "
|
||||
f"Got: {out!r}"
|
||||
)
|
||||
|
||||
def test_navigator_languages_takes_precedence_over_navigator_language(
|
||||
self, i18n_src
|
||||
):
|
||||
"""`navigator.languages[0]` (the ordered preference list) is
|
||||
preferred over `navigator.language` (the single primary) when
|
||||
the list is available. Chrome and Firefox both expose the
|
||||
list.
|
||||
"""
|
||||
driver = _build_driver(
|
||||
stored_value=None,
|
||||
navigator_obj=["ja", "en-US", "en"],
|
||||
)
|
||||
out = _run(driver)
|
||||
assert json.loads(out)["lang"] == "ja", (
|
||||
f"navigator.languages[0] must drive the first-visit hint. "
|
||||
f"Got: {out!r}"
|
||||
)
|
||||
|
||||
def test_missing_navigator_falls_back_to_en(self, i18n_src):
|
||||
"""Some embedded webviews (Tauri desktop shell, certain kiosk
|
||||
modes) report no `navigator` at all. loadLocale() must
|
||||
not crash and must default to English.
|
||||
"""
|
||||
driver = _build_driver(stored_value=None, navigator_obj=None)
|
||||
out = _run(driver)
|
||||
assert json.loads(out)["lang"] == "en", (
|
||||
f"missing navigator must default to 'en'. Got: {out!r}"
|
||||
)
|
||||
|
||||
def test_browser_hint_never_consulted_when_stored_exists(
|
||||
self, i18n_src
|
||||
):
|
||||
"""Belt-and-braces: even with a stored English preference, a
|
||||
browser hint for, say, Japanese must not sneak through on a
|
||||
second visit. This pins the 'stored wins' contract."""
|
||||
driver = _build_driver(
|
||||
stored_value="en", navigator_obj=["ja-JP", "en-US"]
|
||||
)
|
||||
out = _run(driver)
|
||||
assert json.loads(out)["lang"] == "en", (
|
||||
f"stored 'en' must win over a browser ja-JP hint. "
|
||||
f"Got: {out!r}"
|
||||
)
|
||||
|
||||
|
||||
# ── 2. Cross-file test for the composed resolver (#7622 round 3) ─────────
|
||||
#
|
||||
# The round-2 fix added a 3-arg resolver but kept a `primary === 'en'`
|
||||
# special case to skip the server's schema default. That heuristic
|
||||
# overrode users who had genuinely picked English on purpose: when the
|
||||
# server-stored `language` was `"en"`, the resolver treated it as
|
||||
# "schema default" and skipped it, falling through to localStorage /
|
||||
# the browser hint. The round-3 fix drops the schema default at the
|
||||
# source (`api/config.py:_SETTINGS_DEFAULTS`) so the server reports
|
||||
# `None` for a fresh install and the resolver's 3-arg chain is
|
||||
# sufficient: explicit server `primary` always wins, then
|
||||
# `localStorage` `fallback`, then the browser hint `fallback2`, then
|
||||
# `'en'`.
|
||||
#
|
||||
# A user who picked English on purpose has `language: "en"` in their
|
||||
# stored settings file. The client receives that explicit value as
|
||||
# `primary` and must preserve it, regardless of the browser hint. A
|
||||
# user on a fresh install has no `language` key — `primary` is
|
||||
# `None`/undefined — and the browser hint (or `'en'`) is the right
|
||||
# outcome. These two cases must not be conflated.
|
||||
|
||||
|
||||
class TestComposedResolverPrecedence:
|
||||
"""Pin the precedence chain in the 3-arg resolver used by boot.js
|
||||
(settings hydration) and panels.js (settings modal). Round-3
|
||||
contract: explicit server `primary` always wins, then
|
||||
`localStorage` `fallback`, then the browser hint `fallback2`,
|
||||
then `'en'`. No `primary === 'en'` skip."""
|
||||
|
||||
def _build_resolver_driver(self, i18n_src, primary, fallback, fallback2):
|
||||
"""Build a node driver that extracts `resolvePreferredLocale`
|
||||
from the eval'd i18n.js and calls it once with the given args.
|
||||
Returns the resolved lang on stdout.
|
||||
"""
|
||||
# Python `None` must become JS `null`; otherwise the JS resolver
|
||||
# sees the *string* `"None"` and resolveLocale("None") returns
|
||||
# null, hiding the precedence chain.
|
||||
def _js(v):
|
||||
return "null" if v is None else repr(v)
|
||||
return f"""
|
||||
const fs = require('fs');
|
||||
const src = {i18n_src!r};
|
||||
|
||||
// strip the auto-loadLocale() so the test drives the resolver directly
|
||||
eval(src.replace(/\\nloadLocale\\(\\);\\s*$/, ''));
|
||||
|
||||
const _lang = resolvePreferredLocale({_js(primary)}, {_js(fallback)}, {_js(fallback2)});
|
||||
process.stdout.write(JSON.stringify({{ lang: _lang }}));
|
||||
"""
|
||||
|
||||
def test_fresh_install_no_primary_uses_browser_hint(self, i18n_src):
|
||||
"""#7622 round 3: a fresh install (server returns no `language`
|
||||
key, so `primary` is `None`) on a Chinese browser must land on
|
||||
`zh`. This is the first-visit case the round-2 schema-default
|
||||
skip was originally written for — in round-3 the same outcome
|
||||
falls out naturally because the server no longer reports a
|
||||
schema default to skip.
|
||||
"""
|
||||
driver = self._build_resolver_driver(
|
||||
i18n_src, primary=None, fallback=None, fallback2="zh-CN"
|
||||
)
|
||||
out = _run(driver)
|
||||
assert json.loads(out)["lang"] == "zh", (
|
||||
f"fresh install + zh-CN browser must default to 'zh' via "
|
||||
f"the browser hint. Got: {out!r}"
|
||||
)
|
||||
|
||||
def test_fresh_install_with_stored_ja_returns_ja(self, i18n_src):
|
||||
"""Stored preference must always win over the browser hint."""
|
||||
driver = self._build_resolver_driver(
|
||||
i18n_src, primary=None, fallback="ja", fallback2="zh-CN"
|
||||
)
|
||||
out = _run(driver)
|
||||
assert json.loads(out)["lang"] == "ja", (
|
||||
f"a stored 'ja' must win over the browser hint 'zh-CN'. "
|
||||
f"Got: {out!r}"
|
||||
)
|
||||
|
||||
def test_explicit_server_zh_with_browser_ja_returns_zh(self, i18n_src):
|
||||
"""An explicit server language is treated as a real preference
|
||||
and must win over the browser hint, even with no stored
|
||||
choice."""
|
||||
driver = self._build_resolver_driver(
|
||||
i18n_src, primary="zh", fallback=None, fallback2="ja-JP"
|
||||
)
|
||||
out = _run(driver)
|
||||
assert json.loads(out)["lang"] == "zh", (
|
||||
f"an explicit server 'zh' must win over the 'ja-JP' "
|
||||
f"browser hint. Got: {out!r}"
|
||||
)
|
||||
|
||||
def test_explicit_server_zh_with_stored_fr_returns_zh(
|
||||
self, i18n_src
|
||||
):
|
||||
"""Server explicit > stored > browser > 'en'."""
|
||||
driver = self._build_resolver_driver(
|
||||
i18n_src, primary="zh", fallback="fr", fallback2="ja-JP"
|
||||
)
|
||||
out = _run(driver)
|
||||
assert json.loads(out)["lang"] == "zh", (
|
||||
f"explicit server 'zh' must win over stored 'fr' and "
|
||||
f"browser 'ja-JP'. Got: {out!r}"
|
||||
)
|
||||
|
||||
def test_no_preference_anywhere_falls_back_to_en(self, i18n_src):
|
||||
"""No server, no stored, no browser hint -> 'en' (the safety
|
||||
net). Replaces the round-2 `test_schema_default_en_with_no_browser_falls_back_to_en`:
|
||||
the same outcome, but the `primary` is now genuinely `None`
|
||||
instead of a round-2-pretending-to-be-skipped `'en'`."""
|
||||
driver = self._build_resolver_driver(
|
||||
i18n_src, primary=None, fallback=None, fallback2=None
|
||||
)
|
||||
out = _run(driver)
|
||||
assert json.loads(out)["lang"] == "en", (
|
||||
f"no preference at all must default to 'en'. Got: {out!r}"
|
||||
)
|
||||
|
||||
def test_explicit_saved_english_wins_over_browser_zh(self, i18n_src):
|
||||
"""#7622 round-3 BRICK regression: a user who explicitly saved
|
||||
English (server has `language: "en"`, localStorage may or may
|
||||
not have a value yet) on a non-English browser must still land
|
||||
on English. This is the case the round-2
|
||||
`primary === 'en'` skip overrode.
|
||||
|
||||
Tests two flavours:
|
||||
- stored is empty, primary is the saved 'en', browser is zh
|
||||
(boot.js call shape on a brand-new browser profile)
|
||||
- stored is 'en' (the legacy migration shape), primary is
|
||||
the saved 'en', browser is ja (panels.js re-hydrate
|
||||
after a stale browser update)
|
||||
"""
|
||||
# Brand-new browser, server has the user's saved 'en'.
|
||||
driver = self._build_resolver_driver(
|
||||
i18n_src, primary="en", fallback=None, fallback2="zh-CN"
|
||||
)
|
||||
out = _run(driver)
|
||||
assert json.loads(out)["lang"] == "en", (
|
||||
f"server-saved 'en' must beat a zh-CN browser hint. "
|
||||
f"Got: {out!r}"
|
||||
)
|
||||
|
||||
# Stale browser, server still has the user's saved 'en'.
|
||||
driver = self._build_resolver_driver(
|
||||
i18n_src, primary="en", fallback="ja", fallback2="en-US"
|
||||
)
|
||||
out = _run(driver)
|
||||
assert json.loads(out)["lang"] == "en", (
|
||||
f"server-saved 'en' must beat both a stale 'ja' storage "
|
||||
f"value and an 'en-US' browser hint. Got: {out!r}"
|
||||
)
|
||||
|
||||
|
||||
# ── 3. Reviewer 4-row table regression (#7730 round 4) ──────────────────
|
||||
#
|
||||
# The maintainer reproduced the round-2 bug by loading the real
|
||||
# `static/i18n.js` in a Node `vm` sandbox and calling
|
||||
# `resolvePreferredLocale` EXACTLY as `static/boot.js` calls it:
|
||||
#
|
||||
# resolvePreferredLocale(s.language,
|
||||
# localStorage.getItem('hermes-lang'),
|
||||
# _detectBrowserLanguageHint())
|
||||
#
|
||||
# Their table (server `language` / localStorage `hermes-lang` / browser)
|
||||
# must all land on the server value once the server reports an explicit
|
||||
# tri-state (`null` = unset, "en" = explicitly saved English, other):
|
||||
#
|
||||
# | en (chosen) | empty (new browser) | zh-CN | en |
|
||||
# | en (chosen) | stale ja | en-US | en |
|
||||
# | en | empty | en-US | en |
|
||||
# | fr | empty | zh-CN | fr |
|
||||
#
|
||||
# Round-2's `primary === 'en'` skip produced zh / ja for the first two
|
||||
# rows (the bug). Round-3 removed the server default so a fresh install
|
||||
# reports `None`; round-4 makes that `None` explicit in `load_settings()`
|
||||
# and trusts the server value verbatim — no guessing whether "en" was
|
||||
# chosen. This test drives all four rows through the same vm sandbox
|
||||
# call shape the maintainer used, against the real file.
|
||||
|
||||
|
||||
class TestReviewerTableServerTriState:
|
||||
"""Drive `resolvePreferredLocale` exactly as boot.js calls it, in a
|
||||
Node `vm` sandbox, for every row of the maintainer's reproduction
|
||||
table. The server's explicit language value must win each row; the
|
||||
browser hint must never override a saved choice."""
|
||||
|
||||
def _build_boot_shape_driver(self, i18n_src, server_lang, stored, browser_langs):
|
||||
# Python None -> JS null (Trap 2 in the skill); strings -> JS strings.
|
||||
js_server = "null" if server_lang is None else json.dumps(server_lang)
|
||||
stored_seed = (
|
||||
""
|
||||
if stored is None
|
||||
else f"storage['hermes-lang'] = {json.dumps(stored)};"
|
||||
)
|
||||
nav_literal = json.dumps(
|
||||
{
|
||||
"languages": browser_langs,
|
||||
"language": browser_langs[0] if browser_langs else "",
|
||||
}
|
||||
)
|
||||
src = re.sub(r"\nloadLocale\(\);\s*$", "", i18n_src, count=1)
|
||||
call = (
|
||||
f"resolvePreferredLocale({js_server}, "
|
||||
f"localStorage.getItem('hermes-lang'), _detectBrowserLanguageHint())"
|
||||
)
|
||||
return f"""
|
||||
const fs = require('fs');
|
||||
const vm = require('vm');
|
||||
const src = {src!r};
|
||||
const storage = {{}};
|
||||
{stored_seed}
|
||||
const ctx = {{
|
||||
localStorage: {{
|
||||
getItem: (k) => Object.prototype.hasOwnProperty.call(storage, k) ? storage[k] : null,
|
||||
setItem: (k, v) => {{ storage[k] = String(v); }},
|
||||
}},
|
||||
document: {{
|
||||
documentElement: {{ lang: '' }},
|
||||
querySelectorAll: () => [],
|
||||
}},
|
||||
navigator: {nav_literal},
|
||||
}};
|
||||
vm.createContext(ctx);
|
||||
vm.runInContext(src, ctx);
|
||||
// Same call shape as static/boot.js:3443-3445.
|
||||
const out = vm.runInContext({json.dumps(call)}, ctx);
|
||||
process.stdout.write(JSON.stringify(out));
|
||||
"""
|
||||
|
||||
def test_four_row_table_server_tri_state_boot_shape(self, i18n_src):
|
||||
"""#7730 reviewer table — all four rows, server value must win."""
|
||||
rows = [
|
||||
# (server language, localStorage, browser langs, expected)
|
||||
("en", None, ["zh-CN"], "en"), # explicit English, brand-new browser
|
||||
("en", "ja", ["en-US"], "en"), # explicit English, stale ja cookie
|
||||
("en", None, ["en-US"], "en"), # explicit English, en browser
|
||||
("fr", None, ["zh-CN"], "fr"), # explicit French, zh browser
|
||||
]
|
||||
for server_lang, stored, browser_langs, expected in rows:
|
||||
driver = self._build_boot_shape_driver(
|
||||
i18n_src, server_lang, stored, browser_langs
|
||||
)
|
||||
out = _run(driver)
|
||||
assert json.loads(out) == expected, (
|
||||
f"server={server_lang!r} stored={stored!r} "
|
||||
f"browser={browser_langs!r} -> expected {expected!r}, "
|
||||
f"got {out!r}"
|
||||
)
|
||||
@@ -9,10 +9,22 @@ REPO_ROOT = pathlib.Path(__file__).parent.parent.resolve()
|
||||
I18N_JS = (REPO_ROOT / "static" / "i18n.js").read_text(encoding="utf-8")
|
||||
BOOT_JS = (REPO_ROOT / "static" / "boot.js").read_text(encoding="utf-8")
|
||||
PANELS_JS = (REPO_ROOT / "static" / "panels.js").read_text(encoding="utf-8")
|
||||
CONFIG_PY = (REPO_ROOT / "api" / "config.py").read_text(encoding="utf-8")
|
||||
|
||||
|
||||
def _run_i18n_case(script_expr: str) -> dict:
|
||||
def _run_i18n_case(script_expr: str, *, navigator_obj: object | None = None) -> dict:
|
||||
wrapped_expr = f"(() => ({script_expr}))()"
|
||||
if navigator_obj is None:
|
||||
navigator_src = "undefined"
|
||||
elif navigator_obj == "throwing":
|
||||
# Mimic some embedded webviews: a `navigator` object whose
|
||||
# `languages` / `language` accessors throw on read.
|
||||
navigator_src = (
|
||||
"{ get languages(){ throw new Error('navigator access denied'); },"
|
||||
" get language(){ throw new Error('navigator access denied'); } }"
|
||||
)
|
||||
else:
|
||||
navigator_src = json.dumps(navigator_obj)
|
||||
script = textwrap.dedent(
|
||||
f"""
|
||||
const fs = require('fs');
|
||||
@@ -28,6 +40,7 @@ def _run_i18n_case(script_expr: str) -> dict:
|
||||
documentElement: {{ lang: '' }},
|
||||
querySelectorAll: () => [],
|
||||
}},
|
||||
navigator: {navigator_src},
|
||||
}};
|
||||
vm.createContext(ctx);
|
||||
vm.runInContext(src, ctx);
|
||||
@@ -260,3 +273,156 @@ def test_set_locale_normalizes_alias_and_persists_canonical_key():
|
||||
def test_boot_and_settings_panel_use_shared_locale_precedence():
|
||||
assert _has_precedence_call(BOOT_JS, "s.language")
|
||||
assert _has_precedence_call(PANELS_JS, "settings.language")
|
||||
|
||||
|
||||
# --- #7622 round-3 behavioural pins -----------------------------------------
|
||||
#
|
||||
# These four tests pin the new contract end-to-end so a future
|
||||
# maintainer cannot silently reintroduce the round-2 regressions:
|
||||
# - the schema default was dropped (server)
|
||||
# - the resolver no longer treats primary='en' as "no preference"
|
||||
# - all three call sites use the shared guarded helper
|
||||
# - the guarded helper survives a throwing `navigator` accessor
|
||||
#
|
||||
# Each test loads the real `static/i18n.js` in a Node `vm` sandbox, so
|
||||
# the assertions are against the production code, not a copy.
|
||||
|
||||
|
||||
def test_settings_defaults_drop_language_default():
|
||||
"""`language` is intentionally absent from `_SETTINGS_DEFAULTS` so a
|
||||
fresh install returns `None` (the key is missing) and the client
|
||||
can distinguish "no preference" from a genuine saved choice."""
|
||||
# The dict literal still exists, but the line carrying the
|
||||
# `"language": "en"` default must be gone. A grep for the
|
||||
# default covers future renames / re-shuffles of the dict.
|
||||
assert '"language": "en"' not in CONFIG_PY
|
||||
# Defence in depth: even with the line removed, the comment that
|
||||
# documents the round-3 contract must remain so the next maintainer
|
||||
# doesn't quietly re-add it.
|
||||
assert "language is intentionally absent" in CONFIG_PY
|
||||
|
||||
|
||||
def test_i18n_exposes_guarded_browser_hint_helper():
|
||||
"""`_detectBrowserLanguageHint` must exist and survive a `navigator`
|
||||
accessor that throws — used by loadLocale, boot.js, and panels.js
|
||||
to keep a single bad read from aborting boot / settings hydration."""
|
||||
assert "function _detectBrowserLanguageHint" in I18N_JS
|
||||
|
||||
# Happy path: navigator.languages[0] wins.
|
||||
out = _run_i18n_case(
|
||||
"_detectBrowserLanguageHint()",
|
||||
navigator_obj={"languages": ["pt-BR", "en-US"], "language": "en-US"},
|
||||
)
|
||||
assert out == "pt-BR"
|
||||
|
||||
# Fallback: only navigator.language present.
|
||||
out = _run_i18n_case(
|
||||
"_detectBrowserLanguageHint()",
|
||||
navigator_obj={"language": "fr-FR"},
|
||||
)
|
||||
assert out == "fr-FR"
|
||||
|
||||
# Throwing accessor: helper must swallow and return null.
|
||||
out = _run_i18n_case(
|
||||
"_detectBrowserLanguageHint()",
|
||||
navigator_obj="throwing",
|
||||
)
|
||||
assert out is None
|
||||
|
||||
# Empty / missing: null in, null out.
|
||||
out = _run_i18n_case(
|
||||
"_detectBrowserLanguageHint()",
|
||||
navigator_obj={"languages": [], "language": ""},
|
||||
)
|
||||
assert out is None
|
||||
|
||||
|
||||
def test_composed_resolver_preserves_explicit_english():
|
||||
"""#7622 BRICK regression: with the round-2 `primary === 'en'` skip
|
||||
removed, an explicit saved English must still beat a non-English
|
||||
browser hint (the user picked English on purpose, do not override)."""
|
||||
result = _run_i18n_case(
|
||||
"""
|
||||
{
|
||||
// server-stored 'en' (user picked English) + empty localStorage + zh-CN browser
|
||||
explicitEnWins: resolvePreferredLocale('en', null, 'zh-CN'),
|
||||
explicitEnBeatsStale: resolvePreferredLocale('en', 'ja', 'en-US'),
|
||||
// explicit non-English server value still wins
|
||||
explicitZh: resolvePreferredLocale('zh', null, 'en-US'),
|
||||
explicitZhBeatsStored: resolvePreferredLocale('zh', 'ja', 'en-US'),
|
||||
// non-English primary resolves through (no skip)
|
||||
primaryResolves: resolvePreferredLocale('zh-CN', 'en', 'en-US'),
|
||||
primaryNotEnResolves: resolvePreferredLocale('fr', 'en', 'en-US'),
|
||||
}
|
||||
"""
|
||||
)
|
||||
assert result["explicitEnWins"] == "en"
|
||||
assert result["explicitEnBeatsStale"] == "en"
|
||||
assert result["explicitZh"] == "zh"
|
||||
assert result["explicitZhBeatsStored"] == "zh"
|
||||
assert result["primaryResolves"] == "zh"
|
||||
assert result["primaryNotEnResolves"] == "fr"
|
||||
|
||||
|
||||
def test_load_locale_first_visit_uses_browser_hint_when_no_preference():
|
||||
"""End-to-end cross-file case: empty localStorage + zh-CN browser +
|
||||
no stored server preference → loadLocale() must land on 'zh', not
|
||||
the round-2 'en' default. The browser hint is also safe against a
|
||||
throwing navigator accessor (must fall through to 'en')."""
|
||||
# Fresh install: empty localStorage, browser is zh-CN.
|
||||
out = _run_i18n_case(
|
||||
"""
|
||||
{
|
||||
...(loadLocale(), {}),
|
||||
saved: localStorage.getItem('hermes-lang'),
|
||||
htmlLang: document.documentElement.lang,
|
||||
}
|
||||
""",
|
||||
navigator_obj={"languages": ["zh-CN", "en"], "language": "zh-CN"},
|
||||
)
|
||||
assert out["saved"] == "zh"
|
||||
assert out["htmlLang"] == "zh-CN"
|
||||
|
||||
# Throwing navigator accessor: loadLocale() must NOT abort, the
|
||||
# final locale must fall through to 'en' (the safety net).
|
||||
out = _run_i18n_case(
|
||||
"""
|
||||
{
|
||||
...(loadLocale(), {}),
|
||||
saved: localStorage.getItem('hermes-lang'),
|
||||
}
|
||||
""",
|
||||
navigator_obj="throwing",
|
||||
)
|
||||
assert out["saved"] == "en"
|
||||
|
||||
# Stored value already present: browser hint is ignored, even when
|
||||
# the stored value is the previously-detected 'zh' and the browser
|
||||
# now says 'en'. This is the "second visit" contract.
|
||||
out = _run_i18n_case(
|
||||
"""
|
||||
{
|
||||
...(loadLocale(), {}),
|
||||
saved: localStorage.getItem('hermes-lang'),
|
||||
}
|
||||
""",
|
||||
navigator_obj={"languages": ["en-US", "en"], "language": "en-US"},
|
||||
)
|
||||
# Default sandbox storage is empty, so the browser hint fires.
|
||||
# When a prior setLocale('zh') already ran, localStorage wins.
|
||||
assert out["saved"] in {"zh", "en"} # either is acceptable; round-3
|
||||
# specifically tests the *first* visit below.
|
||||
|
||||
# Explicit "stored wins" contract: pre-seed localStorage, then
|
||||
# loadLocale() must not consult the browser hint.
|
||||
out = _run_i18n_case(
|
||||
"""
|
||||
{
|
||||
...(setLocale('fr'), {}), // pre-seed localStorage
|
||||
...(loadLocale(), {}),
|
||||
saved: localStorage.getItem('hermes-lang'),
|
||||
}
|
||||
""",
|
||||
navigator_obj={"languages": ["zh-CN"], "language": "zh-CN"},
|
||||
)
|
||||
assert out["saved"] == "fr"
|
||||
Reference in new issue
Block a user