feat(providers): add NVIDIA AI provider endpoint support (#3456)

* feat: add NVIDIA as an AI provider (integrate.api.nvidia.com)

* feat: add NVIDIA option to provider settings dropdown and aliases

* test: add NVIDIA provider detection and endpoint tests

* Add NVIDIA to _HOST_TO_CURATED and expand non-chat model filtering

- nvidia.com -> 'nvidia' curated key for proper provider routing
- _NON_CHAT_PREFIXES: bge, snowflake/arctic-embed, nvidia/nv-embed
- _NON_CHAT_CONTAINS: content-safety, -safety, -reward, nvclip,
  kosmos, fuyu, deplot, vila, neva, gliner, riva, -parse,
  -embedqa, -nemoretriever

* Expand non-chat model filtering for NVIDIA embedding/guard/video models

Add _NON_CHAT_PREFIXES: embed, recurrent
Add _NON_CHAT_CONTAINS: topic-control, guard, calibration,
  ai-synthetic-video, cosmos-reason2

Catches remaining unfiltered non-chat models from NVIDIA catalog:
embedding (llama-nemotron-embed, embed-qa), guard (llama-guard,
nemoguard-topic-control), calibration (ising-calibration),
video (ai-synthetic-video-detector, cosmos-reason2),
recurrent (recurrentgemma-2b)

* Filter non-chat models in _probe_endpoint via _is_chat_model()

Previously _is_chat_model() was only used in the per-model probe
and _first_chat_model(), so non-chat models still appeared in the
model picker even though they were filtered in those specific paths.
Applying the filter at _probe_endpoint() return ensures non-chat
models (embeddings, safety guards, reward, calibration, video
detectors, CLIP, VLM, translation, parsing, recurrent, etc.) never
enter cached_models and never appear in the picker.

* Fix _NON_CHAT_CONTAINS to catch org-prefixed embedding models

Prefix checks (mid.startswith) miss models with org prefixes like
baai/bge-m3, nvidia/embed-qa-4, google/recurrentgemma-2b, etc.
Adding the same terms to _NON_CHAT_CONTAINS ensures they are caught
regardless of the org prefix.

Adds: embed, bge, recurrent, starcoder, gemma-2b

* fix(model-routes): drop collision-prone substrings from global non-chat filter

The NVIDIA PR added several substrings to the shared _NON_CHAT_PREFIXES
and _NON_CHAT_CONTAINS tuples. These are intended to filter out
embedding, retrieval, safety, and vision models from NVIDIA's catalog
that are not chat-completions-capable. However, four of the added
substrings collide with legitimate chat models served by other providers:

  - gemma-2b  matches google/gemma-2b-it (instruct chat model)
  - starcoder matches bigcode/starcoder2-15b (code completion model)
  - recurrent matches google/recurrentgemma-2b (language model)
  - guard     matches meta-llama/Llama-Guard-3-8B (safety classifier)

Removing these four from the global tuples keeps the NVIDIA-specific
filtering intact (safety, embedding, retrieval, and vision models are
still caught by other tokens such as content-safety, -safety, -reward,
embed, bge, -embedqa, -nemoretriever, nvclip, deplot, etc.) while
preventing false negatives for instruct/code models on other providers.

Tests added for gemma-2b-it, google/gemma-2b-it, and
bigcode/starcoder2-15b-instruct asserting they are recognized as chat
models.

Co-authored-by: Kenny Van de Maele <kenny@kvandemaele.be>

* fix(nvidia): remove duplicate bge/embed tokens from _NON_CHAT_CONTAINS

Tokens already present in _NON_CHAT_PREFIXES, making the CONTAINS
entries redundant since the prefix check runs first.

Co-authored-by: Kenny Van de Maele <kenny@kvandemaele.be>

* fix(nvidia): move bge to CONTAINS, add llama-guard, remove stray blanks

Co-authored-by: Kenny Van de Maele <kenny@kvandemaele.be>

* style: fix indentation of groq and xai test cases in test_provider_endpoints.py

---------

Co-authored-by: Kenny Van de Maele <kenny@kvandemaele.be>

routes/model_routes.py

@@ -283,6 +283,7 @@ _HOST_TO_CURATED = (
     ("fireworks.ai", "fireworks"),
     ("googleapis.com", "google"),
     ("x.ai", "xai"),
+    ("nvidia.com", "nvidia"),
     ("openrouter.ai", "openrouter"),
     ("ollama.com", "ollama"),
 )
@@ -477,10 +478,17 @@ _NON_CHAT_PREFIXES = (
     "dall-e", "tts-", "whisper", "text-embedding", "embedding",
     "davinci", "babbage", "moderation", "omni-moderation",
     "sora", "gpt-image", "chatgpt-image",
+    # embedding / retrieval / non-chat models (common across providers)
+    "snowflake/arctic-embed", "nvidia/nv-embed", "embed",
 )
 _NON_CHAT_CONTAINS = (
     "-realtime", "-transcribe", "-tts", "-codex",
-    "codex-",
+    "codex-", "content-safety", "-safety", "-reward", "nvclip",
+    "kosmos", "fuyu", "deplot", "vila", "neva",
+    "gliner", "riva", "-parse", "-embedqa", "-nemoretriever",
+    "topic-control", "calibration",
+    "ai-synthetic-video", "cosmos-reason2",
+    "bge", "llama-guard",
 )
 _NON_CHAT_EXACT_PREFIXES = (
     "gpt-audio",  # gpt-audio, gpt-audio-mini etc. (not gpt-4o-audio-preview which is chat)
@@ -731,7 +739,7 @@ def _probe_endpoint(base_url: str, api_key: str = None, timeout: int = 5) -> Lis
                 for _e in _PROVIDER_CURATED.get(_ck, []):
                     if _e not in set(models) and not any(m.startswith(_e) for m in models):
                         models.append(_e)
-            return models
+            return [m for m in models if _is_chat_model(m)]
     except httpx.HTTPStatusError as e:
         if api_key:
             status = e.response.status_code if e.response is not None else "unknown"
@@ -755,7 +763,7 @@ def _probe_endpoint(base_url: str, api_key: str = None, timeout: int = 5) -> Lis
             data = r.json()
             models = [m.get("name") or m.get("model") for m in (data.get("models") or []) if m.get("name") or m.get("model")]
             if models:
-                return models
+                return [m for m in models if _is_chat_model(m)]
     except Exception as e:
         logger.debug(f"Ollama /api/tags probe failed for {base}: {e}")
     # Fall back to curated list if the provider has a URL-based match (e.g. z.ai has no /models endpoint)