common/hermes
2
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

fix(model_metadata): add xAI Grok context length fallbacks

Browse Source 
xAI /v1/models does not return context_length metadata, so Hermes
probes down to the 128k default whenever a user configures a custom
provider pointing at https://api.x.ai/v1. This forces every xAI user
to manually override model.context_length in config.yaml (2M for
Grok 4.20 / 4.1-fast / 4-fast) or lose most of the usable context
window.

Add DEFAULT_CONTEXT_LENGTHS entries for the Grok family so the
fallback lookup returns the correct value via substring matching.
Values sourced from models.dev (2026-04) and cross-checked against
the xAI /v1/models listing:

  - grok-4.20-*          2,000,000  (reasoning, non-reasoning, multi-agent)
  - grok-4-1-fast-*      2,000,000
  - grok-4-fast-*        2,000,000
  - grok-4 / grok-4-0709   256,000
  - grok-code-fast-1       256,000
  - grok-3*                131,072
  - grok-2 / latest        131,072
  - grok-2-vision*           8,192
  - grok (catch-all)       131,072

Keys are ordered longest-first so that specific variants match before
the catch-all, consistent with the existing Claude/Gemma/MiniMax entries.

Add TestDefaultContextLengths.test_grok_models_context_lengths and
test_grok_substring_matching to pin the values and verify the full
lookup path. All 77 tests in test_model_metadata.py pass.
This commit is contained in:
Julien Talbot
2026-04-10 12:08:16 +04:00
committed by Teknium
parent 5b22e61cfa
commit b577697189
2 changed files with 70 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
agent/model_metadata.py
View File

@@ -126,6 +126,21 @@ DEFAULT_CONTEXT_LENGTHS = {
"minimax": 1048576,
# GLM
"glm": 202752,
# xAI Grok — xAI /v1/models does not return context_length metadata,
# so these hardcoded fallbacks prevent Hermes from probing-down to
# the default 128k when the user points at https://api.x.ai/v1
# via a custom provider. Values sourced from models.dev (2026-04).
# Keys use substring matching (longest-first), so e.g. "grok-4.20"
# matches "grok-4.20-0309-reasoning" / "-non-reasoning" / "-multi-agent-0309".
"grok-code-fast": 256000, # grok-code-fast-1
"grok-4-1-fast": 2000000, # grok-4-1-fast-(non-)reasoning
"grok-2-vision": 8192, # grok-2-vision, -1212, -latest
"grok-4-fast": 2000000, # grok-4-fast-(non-)reasoning
"grok-4.20": 2000000, # grok-4.20-0309-(non-)reasoning, -multi-agent-0309
"grok-4": 256000, # grok-4, grok-4-0709
"grok-3": 131072, # grok-3, grok-3-mini, grok-3-fast, grok-3-mini-fast
"grok-2": 131072, # grok-2, grok-2-1212, grok-2-latest
"grok": 131072, # catch-all (grok-beta, unknown grok-*)
# Kimi
"kimi": 262144,
# Arcee