fix: replace delisted x-ai/grok-4-fast default with the live openai/gpt-4.1-mini

[Fearvox]

What

The out-of-box LLM model default is a delisted OpenRouter model, so a new
user who copies env.template, fills in a real OPENROUTER_API_KEY, and runs
EverCore fails on the first LLM call.

x-ai/grok-4-fast is no longer served on OpenRouter:

• It is absent from the OpenRouter model catalog (GET https://openrouter.ai/api/v1/models — 343 models; the only grok ids are
  x-ai/grok-build-0.1, x-ai/grok-4.3, x-ai/grok-4.20,
  x-ai/grok-4.20-multi-agent).
• GET …/models/x-ai/grok-4-fast/endpoints returns 0 serving endpoints, so
  a chat-completions request with it gets no providers and fails.

src/memory_layer/llm/llm_provider.py:45 forwards LLM_MODEL verbatim, so the
template value reaches OpenRouter unchanged.

This PR replaces the dead id with openai/gpt-4.1-mini — which is the code's
own hardcoded DEFAULT_LLM_MODEL (llm_provider.py:9) and has live OpenRouter
endpoints — in the three places the dead id is shipped:

• methods/EverCore/env.template (the runtime default)
• methods/EverCore/docs/dev_docs/getting_started.md (setup example)
• methods/EverCore/docs/usage/CONFIGURATION_GUIDE.md (the cost-effective-model example)

After this change the template default agrees with the code default, so a
fresh key-only setup works on the first call.

Why this id

openai/gpt-4.1-mini is already DEFAULT_LLM_MODEL in the code, is live on
OpenRouter, and is cost-effective — so template, docs, and code all agree.

Scope

Three files, one dead-id → live-id swap each. No code change. Intentionally
not touched: tests/test_llm_switching_e2e.py uses x-ai/grok-4-fast
deliberately as a disallowed model to assert white-list rejection — a delisted
id is still a valid "disallowed" example there, so its meaning is preserved.

Verification

OpenRouter catalog checked live (2026-06-02): x-ai/grok-4-fast not present;
openai/gpt-4.1-mini present. A running EverCore configured with
openai/gpt-4.1-mini serves normally.

Co-Authored-By: Claude Opus 4.8 (1M context) noreply@anthropic.com

🤖 Generated with Claude Code

[Copilot]

Copilot was unable to review this pull request because the user who requested the review has reached their quota limit.