feat: stealth/ox-alpha free model in the OpenRouter catalog

Adds OpenRouter's free "Ox Alpha" stealth reasoning model
(stealth/ox-alpha) to the OpenRouter fallback snapshot, plus the
provider-agnostic metadata it needs:

- OPENROUTER_MODELS: free-tier entry (1M ctx)
- DEFAULT_CONTEXT_LENGTHS: ox-alpha -> 1,048,576 (verified against
  OpenRouter live /api/v1/models; without this the slug fell through
  to no match)
- reasoning_timeouts.py: 300s stale floor for ox-alpha and the
  OpenCode Zen twin slug x-preview-f-free (reasoning model,
  long-horizon agentic work per its model card)
- model-catalog.json regenerated

Pricing snapshot skipped: openrouter bills via official_models_api
(live pricing; model is free anyway).
This commit is contained in:
Teknium
2026-08-20 20:52:53 -07:00
parent 1017a56274
commit c01cd26f95
4 changed files with 15 additions and 1 deletions
+3
View File
@@ -559,6 +559,9 @@ DEFAULT_CONTEXT_LENGTHS = {
# OpenCode Zen — "Ox Alpha" stealth model (x-preview-f-free). 1M context
# per OpenCode's launch announcement (2026-08-20); free, ZDR.
"x-preview-f": 1_048_576,
# OpenRouter — same "Ox Alpha" stealth model under its OpenRouter slug
# (stealth/ox-alpha). 1M context per OpenRouter live metadata (2026-08-20).
"ox-alpha": 1_048_576,
# Nemotron — NVIDIA's open-weights series (128K context across all sizes)
"nemotron": 131072,
# Arcee