Vision Lock v1: AI News Aggregator -> AI Enthusiast Daily (ADR-0007)

- docs/vision/VISION_LOCK_V1.md: permanent editorial mission, audience (builders/tinkerers/
  local-AI users/home-lab/agent devs), Editorial Test ('what would an enthusiast DO?'),
  architectual constraint (editorial vision is primary system), priority order.
- docs/vision/ADR-0007_EDITORIAL_PIVOT.md: accepted pivot record, before/after table,
  Sprint 1 evidence (high-signal = actionable, low-signal = spectator content).
- docs/vision/EDITORIAL_GUIDELINES.md: operating rules; score is draft, taste overrides;
  hand-before-machine; memory must store 'what can be done' not 'what happened'.
- docs/vision/SECTION_DEFINITIONS.md: 5 sections (What Shipped / Run It Locally /
  Benchmarks & Builds / Problem Solved / Worth Trying Tonight).
- docs/vision/SPRINT_1_FINDINGS.md: reference evidence, 45/200 UNCATEGORIZED taxonomy gap.
- Issue_001.md: handcrafted prototype edition from Sprint 1 stories; benchmark for all future automation.

This is the architectural directive. No scoring/narrative/memory work proceeds except in
service of the Vision Lock. Sprint 2 (Lens) stays blocked pending manual review tallies.

docs/vision/VISION_LOCK_V1.md

@@ -0,0 +1,63 @@
+# VISION LOCK V1
+
+**Status:** PERMANENT · LOCKED 2026-07-15
+**Authority:** Primary system constraint. No future scoring, narrative, memory, knowledge-graph, or editorial-automation work may contradict this document.
+
+---
+
+## Mission
+
+Find the **small number of developments that change what AI enthusiasts can DO today** — not what happened, but what became possible.
+
+## Audience
+
+NOT:
+- General readers
+- Investors
+- Executives
+- Policymakers
+
+IS:
+- **Builders** — people shipping things with AI
+- **Tinkerers** — people modifying, extending, breaking
+- **Local AI users** — people running models on their own hardware
+- **Home-lab operators** — people running inference, agents, pipelines at home
+- **Workflow creators** — people automating with agents
+- **Agent developers** — people building agent systems
+
+## Editorial Test
+
+For **every** story, ask one question:
+
+> **What would an AI enthusiast DO after reading this?**
+
+Acceptable answers:
+- `install it`
+- `benchmark it`
+- `run it`
+- `replicate it`
+- `learn from it`
+- `build with it`
+
+If the answer is:
+
+> **Nothing.**
+
+→ **Reject.**
+
+## Architectural Constraint
+
+The editorial vision is now the **primary system**.
+The architecture serves it. Not the other way around.
+
+Any future component — scorer, classifier, narrative engine, memory engine, knowledge graph, rendering layer, editorial automation — must be justified against the Editorial Test above. If a component optimizes for recency, volume, virality, or engagement instead of *actionability*, it contradicts the Lock and must be rejected or re-scoped.
+
+## Architectural Priority Order
+
+1. **Vision** — the Editorial Test wins all conflicts
+2. **Editorial Quality** — would we proudly publish this?
+3. **Reader Value** — can the reader DO something?
+4. **Automation** — only after 1–3 are proven by hand
+5. **Technical Elegance** — last. Never traded against 1–4.
+
+If any two levels conflict, the higher level wins.