fix(config): reasoning toggle for nested Gemini custom provider routes (#3431)

Version-gated the nested-gateway allow to 2.5-series/3-era (reviewer fix:
gemini-1.5/1.0 have no thinking controls -> selector would fail on send) +
pre-2.5 exclusion regression tests. Stamped v0.51.408 (Release NU).

Co-authored-by: b3nw <b3nw@users.noreply.github.com>

CHANGELOG.md

@@ -3,6 +3,12 @@
 
 ## [Unreleased]
 
+## [v0.51.408] — 2026-06-14 — Release NU (reasoning selector for nested Gemini custom-provider routes, #3431)
+
+### Fixed
+
+- **Custom provider model ids with nested Gemini gateway routes (e.g. `vertex/gemini-2.5-…`, `gemini_cli/gemini-2.5-…`) now expose the reasoning effort selector when the underlying model supports thinking.** Extends the heuristic fallback used for bare and dot-separated custom names; embedding and image-only Gemini routes stay excluded, and the allow is version-gated to the reasoning-capable families (Gemini 2.5 series and 3-era) so pre-2.5 routes like `vertex/gemini-1.5-pro` — which have no thinking controls — don't get a selector that would fail on send. OpenRouter-style `x-ai/…` ids continue to use the existing slash-prefix list. (#3431)
+
 ## [v0.51.407] — 2026-06-14 — Release NT (nest forked sessions under their parent in the sidebar, #3224)
 
 ### Added

api/config.py

@@ -2482,6 +2482,49 @@ def _candidate_supports_reasoning(candidate: str) -> bool:
     return False
 
 
+def _nested_route_reasoning_denied(model: str) -> bool:
+    """Hard deny for nested Gemini gateway routes that must never show a reasoning toggle."""
+    lower = str(model or "").strip().lower()
+    if not lower:
+        return False
+    for prefix in ("vertex/gemini-", "gemini_cli/gemini-"):
+        if lower.startswith(prefix):
+            tail = lower[len(prefix) :]
+            if tail.startswith("embedding") or "image" in tail or "imagine" in tail:
+                return True
+    return False
+
+
+def _nested_gateway_route_reasoning(model: str) -> bool:
+    """Recognize nested ``vertex/gemini-`` and ``gemini_cli/gemini-`` routes on custom providers.
+
+    The slash-prefix heuristic list includes ``google/gemini-2`` but not gateway-prefixed
+    Gemini ids, so capable models behind custom aggregators stayed hidden.
+    """
+    lower = str(model or "").strip().lower()
+    if not lower:
+        return False
+    for prefix in ("vertex/gemini-", "gemini_cli/gemini-"):
+        if lower.startswith(prefix):
+            tail = lower[len(prefix) :]
+            if tail.startswith("embedding") or "image" in tail or "imagine" in tail:
+                return False
+            # Gemini thinking/reasoning controls are documented for the 2.5
+            # series and 3-era models only — 1.5 (and earlier) have no thinking
+            # support, so a reasoning selector on e.g. ``vertex/gemini-1.5-pro``
+            # would let a user pick an effort that the route then rejects.
+            # Version-gate the allow to the reasoning-capable families.
+            if (
+                tail == "2.5"
+                or tail.startswith(("2.5-", "2.5.", "3-", "3."))
+                or "thinking" in tail
+                or "reasoning" in tail
+            ):
+                return True
+            return False
+    return False
+
+
 def _filter_reasoning_efforts_for_provider(
     efforts: list[str],
     model_id: str,
@@ -2535,6 +2578,8 @@ def _heuristic_reasoning_efforts(model_id: str, provider_id: str) -> list[str]:
     )
     if any(model.startswith(prefix) for prefix in prefixes):
         return list(VALID_REASONING_EFFORTS)
+    if _nested_gateway_route_reasoning(model):
+        return list(VALID_REASONING_EFFORTS)
     # Named custom providers often rewrite model ids with dots, underscores, or
     # extra vendor namespaces. Normalize those shapes before applying family-level
     # reasoning heuristics so "deepseek.v3.2", "deepseek_v4_flash", and
@@ -2602,6 +2647,9 @@ def resolve_model_reasoning_efforts(
 
     hinted_model = _strip_provider_hint_for_reasoning(model)
 
+    if _nested_route_reasoning_denied(hinted_model):
+        return []
+
     try:
         from hermes_cli.models import (
             github_model_reasoning_efforts,

tests/test_custom_provider_bare_model_reasoning.py

@@ -248,3 +248,58 @@ def test_deepseek_non_reasoning_variants_excluded(model_id):
     )
 
 
+# ── custom provider nested Gemini routes (vertex/, gemini_cli/) ───────────────
+
+
+@pytest.mark.parametrize(
+    "model_id",
+    [
+        "vertex/gemini-3.1-pro-preview",
+        "vertex/gemini-3-pro-preview",
+        "gemini_cli/gemini-3-pro-preview",
+    ],
+)
+def test_custom_nested_gemini_routes_expose_reasoning(model_id):
+    efforts = cfg.resolve_model_reasoning_efforts(
+        model_id,
+        provider_id="custom:newapi",
+    )
+    assert set(efforts) >= {"low", "medium", "high"}, (
+        f"{model_id} via custom:newapi should expose reasoning efforts"
+    )
+
+
+@pytest.mark.parametrize(
+    "model_id",
+    [
+        "vertex/gemini-embedding-001",
+        "vertex/gemini-3-pro-image-preview",
+    ],
+)
+def test_custom_nested_gemini_routes_exclude_non_reasoning(model_id):
+    assert cfg.resolve_model_reasoning_efforts(
+        model_id,
+        provider_id="custom:newapi",
+    ) == [], f"{model_id} must not expose reasoning efforts"
+
+
+@pytest.mark.parametrize(
+    "model_id",
+    [
+        "vertex/gemini-1.5-pro",
+        "vertex/gemini-1.5-flash",
+        "gemini_cli/gemini-1.5-pro",
+        "vertex/gemini-1.0-pro",
+    ],
+)
+def test_custom_nested_gemini_pre_2_5_routes_exclude_reasoning(model_id):
+    """Gemini thinking/reasoning controls are documented for the 2.5 series and
+    3-era models only — 1.5 (and earlier) have no thinking support, so the
+    nested-gateway detection must not expose a reasoning selector for them
+    (a user could otherwise pick an effort the route then rejects)."""
+    assert cfg.resolve_model_reasoning_efforts(
+        model_id,
+        provider_id="custom:newapi",
+    ) == [], f"{model_id} (pre-2.5 Gemini) must not expose reasoning efforts"
+
+