feat: drop reflection_prompt type and flag cached micro-learnings

Remove the reflection_prompt micro-learning format end-to-end: type
config, tool definition, container case, selector tile, and the
ReflectionPrompt component file. The format wasn't pulling its weight as
a learning surface.

Add a Beschikbaar badge to selector tiles whose topic already has a
published micro-learning of that type, so users know which formats open
instantly instead of triggering a fresh generation. Cached records are
fetched once per topic via the new getExistingTypesForTopic helper, and
re-fetched after a generation returns so newly-created formats light up
without a manual refresh.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

src/lib/llmTools.js

@@ -418,15 +418,3 @@ export const EMIT_FLASHCARD_SET_TOOL = {
   },
 };
 
-export const EMIT_REFLECTION_PROMPT_TOOL = {
-  name: 'emit_reflection_prompt',
-  description: 'Return an open-ended reflection question that asks the employee to connect the topic to their own professional experience, plus a model answer showing the expected depth and specificity.',
-  input_schema: {
-    type: 'object',
-    properties: {
-      prompt: { type: 'string', description: 'An open-ended question that cannot be answered with a fact. It must require the employee to think about their own context.' },
-      model_answer: { type: 'string', description: 'An example of a thoughtful, specific response (3–5 sentences). This is not a rubric — it illustrates depth.' },
-    },
-    required: ['prompt', 'model_answer'],
-  },
-};