Add 5.6 pro variants by rob-maron · Pull Request #61587 · NousResearch/hermes-agent

rob-maron · 2026-07-09T17:42:28Z

No description provided.

Rerun scripts/build_model_catalog.py so the manifest is source-generated rather than hand-edited (the -pro rows from the cherry-picked NousResearch#61587 were already correct; only updated_at changes).

kshitijk4poor · 2026-07-09T19:04:44Z

Folded this into #61616, which completes the full GPT-5.6 family end-to-end (context lengths, native + codex catalogs, pricing snapshot, and the Codex 272K compaction auto-raise) on top of the aggregator lists this PR and #61578 added. Your commit is cherry-picked there with authorship preserved. Deferring to you on closing this one in favor of #61616.

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.

Rerun scripts/build_model_catalog.py so the manifest is source-generated rather than hand-edited (the -pro rows from the cherry-picked #61587 were already correct; only updated_at changes).

…lement) PR NousResearch#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.