diff --git a/agent/model_metadata.py b/agent/model_metadata.py
index a8590b58384..653a90619a5 100644
--- a/agent/model_metadata.py
+++ b/agent/model_metadata.py
@@ -1108,6 +1108,11 @@ _CODEX_OAUTH_CONTEXT_FALLBACK: Dict[str, int] = {
     "gpt-5.1-codex-max": 272_000,
     "gpt-5.1-codex-mini": 272_000,
     "gpt-5.3-codex": 272_000,
+    # Spark runs on specialised low-latency hardware and exposes a smaller
+    # 128k window than other Codex OAuth slugs. Listed explicitly so the
+    # longest-key-first fallback resolves it correctly — substring match
+    # on "gpt-5.3-codex" otherwise wins and reports 272k. Availability is
+    # gated by ChatGPT Pro entitlement on the Codex backend.
     "gpt-5.3-codex-spark": 128_000,
     "gpt-5.2-codex": 272_000,
     "gpt-5.4-mini": 272_000,
diff --git a/hermes_cli/codex_models.py b/hermes_cli/codex_models.py
index 9e388ef0892..8e50004c2d6 100644
--- a/hermes_cli/codex_models.py
+++ b/hermes_cli/codex_models.py
@@ -16,6 +16,18 @@ DEFAULT_CODEX_MODELS: List[str] = [
     "gpt-5.4-mini",
     "gpt-5.4",
     "gpt-5.3-codex",
+    # gpt-5.3-codex-spark is in research preview and is exposed *only* via
+    # the Codex CLI / OAuth backend (chatgpt.com/backend-api/codex/models)
+    # for ChatGPT Pro subscribers. It is NOT available in the public OpenAI
+    # API, so it intentionally stays out of the "openai" provider catalog
+    # in hermes_cli/models.py — only the openai-codex (OAuth) provider
+    # surfaces it. The Codex backend reports ``supported_in_api: false`` for
+    # this slug; that flag describes API availability, not Codex backend
+    # availability, so the fetch/cache code paths below intentionally do
+    # not filter on it. PR #12994 removed this entry on the assumption it
+    # was unsupported — that was wrong; restored here. Keep it in the
+    # curated fallback so Pro users still see Spark in `/model` when live
+    # discovery is unavailable (offline first run, transient API failure).
     "gpt-5.3-codex-spark",
     "gpt-5.2-codex",
     "gpt-5.1-codex-max",
@@ -27,6 +39,10 @@ _FORWARD_COMPAT_TEMPLATE_MODELS: List[tuple[str, tuple[str, ...]]] = [
     ("gpt-5.4-mini", ("gpt-5.3-codex", "gpt-5.2-codex")),
     ("gpt-5.4", ("gpt-5.3-codex", "gpt-5.2-codex")),
     ("gpt-5.3-codex", ("gpt-5.2-codex",)),
+    # Surface Spark whenever any compatible Codex template is present so
+    # accounts hitting the live endpoint with an older lineup still see
+    # Spark in the picker. Backend gates real availability by ChatGPT Pro
+    # entitlement; Hermes does not.
     ("gpt-5.3-codex-spark", ("gpt-5.3-codex", "gpt-5.2-codex")),
 ]
 
diff --git a/hermes_cli/model_switch.py b/hermes_cli/model_switch.py
index 3a282425dc4..d75aca5cd08 100644
--- a/hermes_cli/model_switch.py
+++ b/hermes_cli/model_switch.py
@@ -1343,6 +1343,13 @@ def list_authenticated_providers(
             continue
 
         if hermes_slug in {"openai-codex", "copilot", "copilot-acp"}:
+            # Use live OAuth-backed discovery so the gateway /model picker
+            # matches what the user's authenticated Codex/Copilot backend
+            # actually serves — including ChatGPT-Pro-only Codex slugs
+            # (e.g. gpt-5.3-codex-spark) that aren't in the static curated
+            # catalog. ``provider_model_ids()`` falls back to the curated
+            # list when the live endpoint is unreachable, so this is safe
+            # for unauthenticated and offline cases too.
             model_ids = provider_model_ids(hermes_slug)
         # For aws_sdk providers (bedrock), use live discovery so the list
         # reflects the active region (eu.*, ap.*) not the static us.* list.