From bbc8f2f961f79f2c95c27f0c8ad4f9965daf89ee Mon Sep 17 00:00:00 2001 From: ronhi Date: Wed, 20 May 2026 17:15:51 -0500 Subject: [PATCH] chore(models): drop retired grok-4-1-fast from metadata, tests, docs xAI retired grok-4-1-fast. hermes_cli/models.py already removed it from the static fallback in an earlier commit, but the context-length metadata, the tests pinning those values, and the provider doc still referenced the retired ID. Clean those up so retired model names stop appearing in user-facing output. Co-Authored-By: Claude Opus 4.7 (1M context) --- agent/model_metadata.py | 3 +-- tests/agent/test_model_metadata.py | 3 --- website/docs/integrations/providers.md | 2 +- 3 files changed, 2 insertions(+), 6 deletions(-) diff --git a/agent/model_metadata.py b/agent/model_metadata.py index e9ec4bf03a7..2e0e3a65128 100644 --- a/agent/model_metadata.py +++ b/agent/model_metadata.py @@ -211,9 +211,8 @@ DEFAULT_CONTEXT_LENGTHS = { # matches "grok-4.20-0309-reasoning" / "-non-reasoning" / "-multi-agent-0309". "grok-build": 256000, # grok-build-0.1 "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-fast": 2000000, # grok-4-fast-(non-)reasoning, also matches -reasoning "grok-4.20": 2000000, # grok-4.20-0309-(non-)reasoning, -multi-agent-0309 "grok-4.3": 1000000, # grok-4.3, grok-4.3-latest — 1M context per docs.x.ai "grok-4": 256000, # grok-4, grok-4-0709 diff --git a/tests/agent/test_model_metadata.py b/tests/agent/test_model_metadata.py index e905c3e1f6b..e889f2e67bd 100644 --- a/tests/agent/test_model_metadata.py +++ b/tests/agent/test_model_metadata.py @@ -161,7 +161,6 @@ class TestDefaultContextLengths: # Values sourced from models.dev (2026-04). expected = { "grok-4.20": 2000000, - "grok-4-1-fast": 2000000, "grok-4-fast": 2000000, "grok-4": 256000, "grok-build": 256000, @@ -190,8 +189,6 @@ class TestDefaultContextLengths: ("grok-4.20-0309-reasoning", 2000000), ("grok-4.20-0309-non-reasoning", 2000000), ("grok-4.20-multi-agent-0309", 2000000), - ("grok-4-1-fast-reasoning", 2000000), - ("grok-4-1-fast-non-reasoning", 2000000), ("grok-4-fast-reasoning", 2000000), ("grok-4-fast-non-reasoning", 2000000), ("grok-4", 256000), diff --git a/website/docs/integrations/providers.md b/website/docs/integrations/providers.md index 9c51961c257..81dc3122d7c 100644 --- a/website/docs/integrations/providers.md +++ b/website/docs/integrations/providers.md @@ -264,7 +264,7 @@ When using the Z.AI / GLM provider, Hermes automatically probes multiple endpoin ### xAI (Grok) — Responses API + Prompt Caching -xAI is wired through the Responses API (`codex_responses` transport) for automatic reasoning support on Grok 4 models — no `reasoning_effort` parameter needed, the server reasons by default. Set `XAI_API_KEY` in `~/.hermes/.env` and pick xAI in `hermes model`, or drop `grok` as a shortcut into `/model grok-4-1-fast-reasoning`. +xAI is wired through the Responses API (`codex_responses` transport) for automatic reasoning support on Grok 4 models — no `reasoning_effort` parameter needed, the server reasons by default. Set `XAI_API_KEY` in `~/.hermes/.env` and pick xAI in `hermes model`, or drop `grok` as a shortcut into `/model grok-4-fast-reasoning`. SuperGrok and X Premium+ subscribers can sign in with browser OAuth instead of using an API key — pick **xAI Grok OAuth (SuperGrok / Premium+)** in `hermes model`, or run `hermes auth add xai-oauth`. The same OAuth bearer token is automatically reused by direct-to-xAI tools (TTS, image gen, video gen, transcription). See the [xAI Grok OAuth guide](../guides/xai-grok-oauth.md) for the full flow — and if Hermes runs on a remote host, also see [OAuth over SSH / Remote Hosts](../guides/oauth-over-ssh.md) for the required `ssh -L` tunnel.