feat(openai): complete gpt-5.6 registration — context, codex catalog, native picker, pricing

PR #61578 added the GPT-5.6 series (sol/terra/luna) to the two aggregator
surfaces (OPENROUTER_MODELS, _PROVIDER_MODELS[nous]). This completes the
registration on the remaining surfaces per the standard add-model checklist:

- agent/model_metadata.py: DEFAULT_CONTEXT_LENGTHS 1.05M (direct API, same
  as gpt-5.5; more-specific keys precede gpt-5.5 for longest-substring
  matching) + _CODEX_OAUTH_CONTEXT_FALLBACK 272K for all three slugs.
  Without these the direct-API fallback matched generic "gpt-5" = 400K.
- hermes_cli/codex_models.py: DEFAULT_CODEX_MODELS + forward-compat
  templates so ChatGPT-OAuth (openai-codex) pickers surface the series.
- hermes_cli/models.py: _PROVIDER_MODELS[openai-api] (native API picker).
- agent/usage_pricing.py: _OFFICIAL_DOCS_PRICING snapshot — sol 5/30,
  terra 2.50/15, luna 1/6 per 1M in/out; cache read 0.10x input, cache
  write 1.25x input (OpenAI billing change starting with the 5.6 series).
  GA 2026-07-09 at preview rates. Sol Fast mode (Cerebras tier) excluded.
- hermes_cli/model_switch.py: rank "sol" as a flagship suffix so
  /model gpt resolves to gpt-5.6-sol, not alphabetical-first luna.

Verified: registry E2E via real imports (both context tables, codex
forward-compat from a gpt-5.5 template, billing-route lookup for
openai/gpt-5.6-sol -> 5.00/M), alias resolution on openai-codex and
openai-api resolves to gpt-5.6-sol; 183 targeted tests pass
(model_metadata, usage_pricing, codex_models, model_catalog).

agent/model_metadata.py

@@ -229,6 +229,12 @@ DEFAULT_CONTEXT_LENGTHS = {
     # ChatGPT Codex OAuth caps it at 272K; both paths resolve via their own
     # provider-aware branches (_resolve_codex_oauth_context_length + models.dev).
     # This hardcoded value is only reached when every probe misses.
+    # GPT-5.6 series (Sol/Terra/Luna, GA 2026-07-09) — 1.05M on the direct
+    # OpenAI API (same as gpt-5.5). Codex OAuth caps these at 272K.
+    # More-specific keys precede "gpt-5.5" for longest-substring matching.
+    "gpt-5.6-luna": 1050000,
+    "gpt-5.6-terra": 1050000,
+    "gpt-5.6-sol": 1050000,
     "gpt-5.5": 1050000,
     "gpt-5.4-nano": 400000,           # 400k (not 1.05M like full 5.4)
     "gpt-5.4-mini": 400000,           # 400k (not 1.05M like full 5.4)
@@ -1837,6 +1843,9 @@ _CODEX_OAUTH_CONTEXT_FALLBACK: Dict[str, int] = {
     "gpt-5.3-codex-spark": 128_000,
     "gpt-5.2-codex": 272_000,
     "gpt-5.4-mini": 272_000,
+    "gpt-5.6-sol": 272_000,
+    "gpt-5.6-terra": 272_000,
+    "gpt-5.6-luna": 272_000,
     "gpt-5.5": 272_000,
     "gpt-5.4": 272_000,
     "gpt-5.2": 272_000,

agent/usage_pricing.py

@@ -103,6 +103,50 @@ _UTC_NOW = lambda: datetime.now(timezone.utc)
 # Official docs snapshot entries. Models whose published pricing and cache
 # semantics are stable enough to encode exactly.
 _OFFICIAL_DOCS_PRICING: Dict[tuple[str, str], PricingEntry] = {
+    # ── OpenAI GPT-5.6 series (Sol/Terra/Luna) ───────────────────────────
+    # Announced in limited preview 2026-06-26; GA 2026-07-09 at the same
+    # rates (Sol $5/$30, Terra $2.50/$15, Luna $1/$6 per 1M in/out). Cache
+    # 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.
+    # Source: https://openai.com/index/previewing-gpt-5-6-sol/
+    (
+        "openai",
+        "gpt-5.6-sol",
+    ): PricingEntry(
+        input_cost_per_million=Decimal("5.00"),
+        output_cost_per_million=Decimal("30.00"),
+        cache_read_cost_per_million=Decimal("0.50"),
+        cache_write_cost_per_million=Decimal("6.25"),
+        source="official_docs_snapshot",
+        source_url="https://openai.com/index/previewing-gpt-5-6-sol/",
+        pricing_version="openai-gpt-5.6-preview-2026-07",
+    ),
+    (
+        "openai",
+        "gpt-5.6-terra",
+    ): PricingEntry(
+        input_cost_per_million=Decimal("2.50"),
+        output_cost_per_million=Decimal("15.00"),
+        cache_read_cost_per_million=Decimal("0.25"),
+        cache_write_cost_per_million=Decimal("3.125"),
+        source="official_docs_snapshot",
+        source_url="https://openai.com/index/previewing-gpt-5-6-sol/",
+        pricing_version="openai-gpt-5.6-preview-2026-07",
+    ),
+    (
+        "openai",
+        "gpt-5.6-luna",
+    ): PricingEntry(
+        input_cost_per_million=Decimal("1.00"),
+        output_cost_per_million=Decimal("6.00"),
+        cache_read_cost_per_million=Decimal("0.10"),
+        cache_write_cost_per_million=Decimal("1.25"),
+        source="official_docs_snapshot",
+        source_url="https://openai.com/index/previewing-gpt-5-6-sol/",
+        pricing_version="openai-gpt-5.6-preview-2026-07",
+    ),
     # ── Anthropic Claude 4.8 ─────────────────────────────────────────────
     # Same $5/$25 base pricing as 4.6/4.7.  Fast-mode variant is a separate
     # model ID with 2x premium (vs the 6x premium on older Opus generations).

hermes_cli/codex_models.py

@@ -12,6 +12,10 @@ import os
 logger = logging.getLogger(__name__)
 
 DEFAULT_CODEX_MODELS: List[str] = [
+    # GPT-5.6 series (Sol/Terra/Luna) — GA 2026-07-09 (previewed 2026-06-26).
+    "gpt-5.6-sol",
+    "gpt-5.6-terra",
+    "gpt-5.6-luna",
     "gpt-5.5",
     "gpt-5.4-mini",
     "gpt-5.4",
@@ -44,6 +48,9 @@ DEFAULT_CODEX_MODELS: List[str] = [
 ]
 
 _FORWARD_COMPAT_TEMPLATE_MODELS: List[tuple[str, tuple[str, ...]]] = [
+    ("gpt-5.6-sol", ("gpt-5.5", "gpt-5.4")),
+    ("gpt-5.6-terra", ("gpt-5.5", "gpt-5.4")),
+    ("gpt-5.6-luna", ("gpt-5.5", "gpt-5.4")),
     ("gpt-5.5", ("gpt-5.4", "gpt-5.4-mini", "gpt-5.3-codex")),
     ("gpt-5.4-mini", ("gpt-5.3-codex",)),
     ("gpt-5.4", ("gpt-5.3-codex",)),

hermes_cli/model_switch.py

@@ -548,7 +548,10 @@ def _model_sort_key(model_id: str, prefix: str) -> tuple:
 
     # Suffix quality ranking: pro/max > (no suffix) > omni/flash/mini/lite
     # Lower number = preferred
-    _SUFFIX_RANK = {"pro": 0, "max": 0, "plus": 0, "turbo": 0}
+    # "sol" is the flagship tier of the GPT-5.6 series (sol > terra > luna);
+    # without it, alias resolution would tiebreak alphabetically and pick
+    # luna (the cheapest) for `/model gpt`.
+    _SUFFIX_RANK = {"pro": 0, "max": 0, "plus": 0, "turbo": 0, "sol": 0}
     suffix_rank = _SUFFIX_RANK.get(suffix, 1)
 
     return version_key + (suffix_rank, suffix)

hermes_cli/models.py

@@ -239,6 +239,9 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "gpt-4o-mini",
     ],
     "openai-api": [
+        "gpt-5.6-sol",
+        "gpt-5.6-terra",
+        "gpt-5.6-luna",
         "gpt-5.5",
         "gpt-5.5-pro",
         "gpt-5.4",