feat(openai): cover gpt-5.6 -pro variants (PR #61587 complement)

PR #61587 adds sol-pro/terra-pro/luna-pro to the aggregator lists.
Complete those on the native surfaces the same way this PR completes
the base tiers:

- hermes_cli/models.py: -pro variants in _PROVIDER_MODELS[openai-api].
- agent/usage_pricing.py: alias ("openai", "gpt-5.6-*-pro") onto the
  base-tier PricingEntry rows — the -pro high-effort modes bill at the
  SAME per-token rates (verified against OpenRouter live pricing
  2026-07-09: identical prompt/completion prices for base and -pro);
  they cost more per task by consuming more tokens, not a higher rate.
- Context lengths need no new entries: "gpt-5.6-sol" et al. are
  substrings of their -pro variants and both lookup tables match
  longest-key-first (verified: sol-pro -> 1.05M direct / 272K codex).
- model_switch sort: -pro variants parse as suffix "sol-pro" (rank 1),
  so /model gpt still defaults to base sol — pinned by test.
- Not added to DEFAULT_CODEX_MODELS: only confirmed routable via API/
  OpenRouter so far; codex live discovery will surface them if ChatGPT
  exposes them, same policy as other unconfirmed codex slugs.

Tests: invariant tests extended (pro aliases share base entries, base
sol outranks sol-pro); 191 targeted tests pass.

agent/usage_pricing.py

@@ -109,7 +109,11 @@ _OFFICIAL_DOCS_PRICING: Dict[tuple[str, str], PricingEntry] = {
     # writes are billed at 1.25x the uncached input rate; cache reads get the
     # standard 90% discount (0.10x input, confirmed: Sol $0.50/M cached).
     # Note: "Sol Fast mode" ($12.5/$75, up to 750 tok/s via Cerebras) is a
-    # separate serving tier, not covered by these entries.
+    # separate serving tier, not covered by these entries. The "-pro"
+    # variants (high-effort modes, GA alongside base tiers) bill at the
+    # SAME per-token rates and are aliased onto these entries below the
+    # dict (they cost more per task by consuming more tokens, not by a
+    # higher rate — verified against OpenRouter's live pricing 2026-07-09).
     # Source: https://openai.com/index/previewing-gpt-5-6-sol/
     (
         "openai",
@@ -607,6 +611,15 @@ _OFFICIAL_DOCS_PRICING: Dict[tuple[str, str], PricingEntry] = {
     ),
 }
 
+# GPT-5.6 "-pro" high-effort variants bill at the same per-token rates as
+# their base tiers (more tokens per task, not a higher rate). Alias them
+# onto the base entries so the snapshot stays single-source.
+for _base_56 in ("gpt-5.6-sol", "gpt-5.6-terra", "gpt-5.6-luna"):
+    _OFFICIAL_DOCS_PRICING[("openai", f"{_base_56}-pro")] = _OFFICIAL_DOCS_PRICING[
+        ("openai", _base_56)
+    ]
+del _base_56
+
 
 def _to_decimal(value: Any) -> Optional[Decimal]:
     if value is None: