claude-profile: remove provider-yaml system, embed model config in profiles

Provider selection phase removed; Anthropic driver→model_id is now
hardcoded in the script and non-Anthropic profiles supply provider.env
(MODEL_ID, ANTHROPIC_BASE_URL, ANTHROPIC_API_KEY_FILE).

Test suite baseline changes 58 → 41 assertions: the 17 dropped
assertions covered the removed provider-yaml selection phase, not
retained behaviour.

Includes refactor-derived memory: decisions (provider architecture,
driver enforcement via --model), bash gotchas (read -rp under set -e,
never eval user config), process lessons.

MEMORY.md

@@ -3,7 +3,8 @@
 <!-- Thin index only — one-line descriptions linking to memory/ topic files -->
 
 ## Gotchas
-- [Bash Gotchas](memory/gotchas-bash.md) — `set -e` silent failures, `((var++))` with zero, grep flag parsing, `local` scope, binary detection with `file` command, test harness `set -e` abort
+- [Bash Gotchas](memory/gotchas-bash.md) — `set -e` silent failures, `((var++))` with zero, grep flag parsing, `local` scope, binary detection with `file` command, test harness `set -e` abort, `read -rp` TTY exit, never eval user config
+- [Claude-Profile Gotchas](memory/gotchas-claude-profile.md) — context-loader path resolution, `--model` flag verification pattern
 - [Skills Gotchas](memory/gotchas-skills.md) — Non-ASCII frontmatter silently breaks loading, per-profile independent skills directories
 - [WezTerm Gotchas](memory/gotchas-wezterm.md) — Flatpak CLI not in PATH, proportional split math for equal panes