From 62ada5175c2ad6e4aa55986286ab8f06804cfabc Mon Sep 17 00:00:00 2001
From: Teknium <127238744+teknium1@users.noreply.github.com>
Date: Wed, 8 Jul 2026 12:30:47 -0700
Subject: [PATCH] feat(xai): add grok-4.5 (GA) to model catalog, context
 lengths, and reasoning-effort allowlist (#60887)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

* feat(xai): add grok-4.5 (early access) to catalog, context lengths, and reasoning-effort allowlist

- hermes_cli/models.py: grok-4.5 in _XAI_CURATED_EXTRAS (callable but absent
  from models.dev) and _XAI_STATIC_FALLBACK, so the /model picker and
  validation surface it on both xai and xai-oauth.
- agent/model_metadata.py: context lengths grok-4.5 -> 500K (per model card)
  and grok-build-latest -> 500K (alias); grok-4.5 added to
  _GROK_EFFORT_CAPABLE_PREFIXES.

Verified live against api.x.ai /v1/responses (2026-07-08): effort
low/medium/high accepted (server default: high), "none" rejected,
function calling works, full agent turn with terminal tool succeeded.

* feat(xai): grok-4.5 GA — add aggregator catalog entries, refresh comments

grok-4.5 is now GA: models.dev lists it (500K context, effort
low/medium/high) and both OpenRouter and Nous serve x-ai/grok-4.5.
Add it to the OpenRouter fallback snapshot and the Nous static list,
and update the early-access comments.

* chore: regenerate model-catalog.json for x-ai/grok-4.5
---
 agent/model_metadata.py               | 7 +++++++
 hermes_cli/models.py                  | 4 ++++
 website/static/api/model-catalog.json | 9 ++++++++-
 3 files changed, 19 insertions(+), 1 deletion(-)

diff --git a/agent/model_metadata.py b/agent/model_metadata.py
index c9a7d5771a8..88fab090251 100644
--- a/agent/model_metadata.py
+++ b/agent/model_metadata.py
@@ -289,11 +289,13 @@ DEFAULT_CONTEXT_LENGTHS = {
     # Premium+); /v1/responses additionally enforces a ~262144 input+output
     # budget, but the usable context (what we track here) is 200k.
     "grok-composer": 200000,    # grok-composer-2.5-fast (Grok Build CLI)
+    "grok-build-latest": 500000,  # alias of grok-4.5 (early access)
     "grok-build": 256000,       # grok-build-0.1
     "grok-code-fast": 256000,   # grok-code-fast-1
     "grok-2-vision": 8192,      # grok-2-vision, -1212, -latest
     "grok-4-fast": 2000000,     # grok-4-fast-(non-)reasoning, also matches -reasoning
     "grok-4.20": 2000000,       # grok-4.20-0309-(non-)reasoning, -multi-agent-0309
+    "grok-4.5": 500000,         # grok-4.5, grok-4.5-latest — 500K context per docs.x.ai
     "grok-4.3": 1000000,        # grok-4.3, grok-4.3-latest — 1M context per docs.x.ai
     "grok-4": 256000,           # grok-4, grok-4-0709
     "grok-3": 131072,           # grok-3, grok-3-mini, grok-3-fast, grok-3-mini-fast
@@ -347,6 +349,11 @@ _GROK_EFFORT_CAPABLE_PREFIXES = (
     "grok-3-mini",
     "grok-4.20-multi-agent",
     "grok-4.3",
+    # grok-4.5: verified live against /v1/responses 2026-07-08 — accepts
+    # effort low/medium/high (default: high when omitted) but REJECTS
+    # "none" ("This model does not support `reasoning_effort` value `none`"),
+    # unlike grok-4.3. models.dev agrees: effort values [low, medium, high].
+    "grok-4.5",
 )
 
 
diff --git a/hermes_cli/models.py b/hermes_cli/models.py
index e19b99d4b7c..a103be30ac5 100644
--- a/hermes_cli/models.py
+++ b/hermes_cli/models.py
@@ -48,6 +48,7 @@ OPENROUTER_MODELS: list[tuple[str, str]] = [
     ("google/gemini-3.1-pro-preview",          ""),
     ("google/gemini-3.5-flash",                ""),
     # xAI
+    ("x-ai/grok-4.5",                          ""),
     ("x-ai/grok-4.3",                          ""),
     # DeepSeek
     ("deepseek/deepseek-v4-pro",               ""),
@@ -113,6 +114,7 @@ def _codex_curated_models() -> list[str]:
 #  grok-4-1-fast{,-reasoning,-non-reasoning}, grok-code-fast-1 → grok-4.3).
 _XAI_STATIC_FALLBACK: list[str] = [
     "grok-build-0.1",
+    "grok-4.5",
     "grok-4.3",
     "grok-4.20-0309-reasoning",
     "grok-4.20-0309-non-reasoning",
@@ -121,6 +123,7 @@ _XAI_STATIC_FALLBACK: list[str] = [
 
 # Callable via xAI OAuth but omitted from models.dev and /v1/models listings.
 _XAI_CURATED_EXTRAS: list[str] = [
+    "grok-4.5",  # GA 2026-07 — kept until the models.dev disk cache refreshes
     "grok-composer-2.5-fast",
 ]
 
@@ -191,6 +194,7 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "google/gemini-3.1-pro-preview",
         "google/gemini-3.5-flash",
         # xAI
+        "x-ai/grok-4.5",
         "x-ai/grok-4.3",
         # DeepSeek
         "deepseek/deepseek-v4-pro",
diff --git a/website/static/api/model-catalog.json b/website/static/api/model-catalog.json
index d69dc3af4af..96009ade316 100644
--- a/website/static/api/model-catalog.json
+++ b/website/static/api/model-catalog.json
@@ -1,6 +1,6 @@
 {
   "version": 1,
-  "updated_at": "2026-07-08T13:38:17Z",
+  "updated_at": "2026-07-08T18:59:16Z",
   "metadata": {
     "source": "hermes-agent repo",
     "docs": "https://hermes-agent.nousresearch.com/docs/reference/model-catalog"
@@ -56,6 +56,10 @@
           "id": "google/gemini-3.5-flash",
           "description": ""
         },
+        {
+          "id": "x-ai/grok-4.5",
+          "description": ""
+        },
         {
           "id": "x-ai/grok-4.3",
           "description": ""
@@ -186,6 +190,9 @@
         {
           "id": "google/gemini-3.5-flash"
         },
+        {
+          "id": "x-ai/grok-4.5"
+        },
         {
           "id": "x-ai/grok-4.3"
         },