From 4bb04bcc8d350cf17733f9a9754acd25354b1bfe Mon Sep 17 00:00:00 2001 From: 0xVox Date: Tue, 2 Jun 2026 23:58:33 -0700 Subject: [PATCH] fix: replace delisted x-ai/grok-4-fast default with the live openai/gpt-4.1-mini The shipped default LLM model id is delisted on OpenRouter, so a fresh setup (copy env.template, add a real OPENROUTER_API_KEY, run) fails on the first LLM call. x-ai/grok-4-fast is absent from the OpenRouter catalog and its endpoints list is empty (0 serving providers); llm_provider.py forwards LLM_MODEL verbatim, so the dead default reaches OpenRouter unchanged. Replace it with openai/gpt-4.1-mini, which is the code's own DEFAULT_LLM_MODEL (llm_provider.py:9) and is live on OpenRouter, in the three places the dead id is shipped: env.template (runtime default), docs/dev_docs/getting_started.md (setup example), and docs/usage/CONFIGURATION_GUIDE.md (cost-effective-model example). Template default now agrees with the code default. Leaves tests/test_llm_switching_e2e.py untouched: it uses x-ai/grok-4-fast on purpose as a disallowed model to assert white-list rejection, and a delisted id is still a valid "disallowed" example there. Co-Authored-By: Claude Opus 4.8 (1M context) --- methods/EverCore/docs/dev_docs/getting_started.md | 2 +- methods/EverCore/docs/usage/CONFIGURATION_GUIDE.md | 2 +- methods/EverCore/env.template | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/methods/EverCore/docs/dev_docs/getting_started.md b/methods/EverCore/docs/dev_docs/getting_started.md index 1df99d96..a6c0ed3e 100644 --- a/methods/EverCore/docs/dev_docs/getting_started.md +++ b/methods/EverCore/docs/dev_docs/getting_started.md @@ -76,7 +76,7 @@ Edit the `.env` file and fill in actual values for the following required items: ```bash # LLM provider and model LLM_PROVIDER=openrouter -LLM_MODEL=x-ai/grok-4-fast +LLM_MODEL=openai/gpt-4.1-mini LLM_TEMPERATURE=0.3 LLM_MAX_TOKENS=32768 diff --git a/methods/EverCore/docs/usage/CONFIGURATION_GUIDE.md b/methods/EverCore/docs/usage/CONFIGURATION_GUIDE.md index 2d5574f0..81a46f35 100644 --- a/methods/EverCore/docs/usage/CONFIGURATION_GUIDE.md +++ b/methods/EverCore/docs/usage/CONFIGURATION_GUIDE.md @@ -16,7 +16,7 @@ Provider selection is config-driven (e.g., `llm_config` in the app). When no sce | Variable | Required | Description | Example | |----------|----------|-------------|---------| | `LLM_PROVIDER` | No | Default provider type (used when scene config omits provider) | `openrouter` | -| `LLM_MODEL` | Yes | Model name. **Evaluation** recommends `gpt-4o-mini`, **Demo** can use cost-effective models like `x-ai/grok-4-fast` | `gpt-4o-mini` | +| `LLM_MODEL` | Yes | Model name. **Evaluation** recommends `gpt-4o-mini`, **Demo** can use cost-effective models like `openai/gpt-4.1-mini` | `gpt-4o-mini` | | `{PROVIDER}_API_KEY` | Yes* | Provider-specific API key (e.g., `OPENROUTER_API_KEY`, `OPENAI_API_KEY`) | `sk-or-v1-xxxx` | | `{PROVIDER}_BASE_URL` | No | Provider-specific base URL (e.g., `OPENROUTER_BASE_URL`, `OPENAI_BASE_URL`) | `https://openrouter.ai/api/v1` | | `LLM_API_KEY` | No | Fallback API key for default provider (legacy compatibility) | `sk-or-v1-xxxx` | diff --git a/methods/EverCore/env.template b/methods/EverCore/env.template index c9495b77..fc280e77 100755 --- a/methods/EverCore/env.template +++ b/methods/EverCore/env.template @@ -20,7 +20,7 @@ # LLM_PROVIDER controls the default provider (used when scene config omits provider) LLM_PROVIDER=openrouter -LLM_MODEL=x-ai/grok-4-fast +LLM_MODEL=openai/gpt-4.1-mini LLM_TEMPERATURE=0.3 LLM_MAX_TOKENS=32768 # Default provider fallback (legacy)