feat: FastAPI Morrowind harness + SOUL.md framework (#821, #854)

## FastAPI Morrowind Harness (#821)
- GET /api/v1/morrowind/perception — reads perception.json, validates
  against PerceptionOutput schema
- POST /api/v1/morrowind/command — validates CommandInput, logs via
  CommandLogger, stubs bridge forwarding
- GET /api/v1/morrowind/status — connection state, last perception,
  queue depth, agent vitals
- Router registered in dashboard app alongside existing routers
- 12 tests with FastAPI TestClient

## SOUL.md Framework (#854)
- docs/soul-framework/ — template, authoring guide, role extensions
- src/infrastructure/soul/loader.py — parse SOUL.md into structured
  SoulDocument objects with section extraction and merge support
- src/infrastructure/soul/validator.py — validate structure, detect
  contradictions between values/constraints
- src/infrastructure/soul/versioning.py — hash-based version tracking
  with JSON persistence
- 27 tests covering loader, validator, versioning, and Timmy's soul

Builds on PR #864 (protocol spec + command log).
Closes #821
Closes #854

docs/soul-framework/authoring-guide.md

@@ -0,0 +1,97 @@
+# SOUL.md Authoring Guide
+
+How to write a SOUL.md for a new agent.
+
+---
+
+## Before You Start
+
+1. **Read the template** (`template.md`) to understand the required sections.
+2. **Study Timmy's soul** (`memory/self/soul.md`) as a reference implementation.
+3. **Decide on the agent's role** — is this a general-purpose agent or a
+   specialised sub-agent (see `role-extensions.md`)?
+
+---
+
+## Step-by-Step
+
+### Step 1: Define Identity
+
+Start with the shortest possible answer to "who is this agent?"
+
+- Avoid jargon. The identity should be understandable to someone who has
+  never seen the codebase.
+- Include the agent's relationship to sovereignty and autonomy.
+- Keep it to three sentences or fewer.
+
+### Step 2: List Values
+
+Values are the non-negotiable principles. They are not personality traits —
+they are commitments.
+
+Guidelines:
+- **3–7 values** is the sweet spot. Fewer than 3 is under-specified; more
+  than 7 is hard to remember under pressure.
+- **Order matters.** When two values conflict, the one listed first wins.
+- **Name each value.** A single bolded word followed by a definition.
+- **Be concrete.** "Honesty" is better than "integrity". "I tell the truth
+  when I don't know" is better than "I am honest."
+
+### Step 3: Write the Prime Directive
+
+This is the single most important instruction. If context is lost and the
+agent can only remember one thing, this is it.
+
+Rules:
+- Exactly one sentence.
+- No conditional clauses ("if X then Y").
+- Must be actionable, not aspirational.
+
+### Step 4: Define Audience Awareness
+
+Different audiences need different behaviour. A developer debugging a crash
+needs terse technical output. A first-time user needs patience and context.
+
+- List 2–4 audience profiles.
+- For each, describe what changes: tone, verbosity, assumed knowledge.
+
+### Step 5: Set Constraints
+
+Constraints are hard limits. They cannot be overridden by user instructions.
+
+Guidelines:
+- Use "I will not" phrasing.
+- Include a fallback rule: what the agent does when it encounters an
+  ambiguous situation not covered by other constraints.
+- Keep the list short (3–6 items). Too many constraints create paralysis.
+
+---
+
+## Common Mistakes
+
+| Mistake | Fix |
+|---------|-----|
+| Values that are just personality traits | Rewrite as commitments with concrete implications |
+| Prime directive with multiple clauses | Split into prime directive + constraints |
+| No fallback constraint | Add "When uncertain, I will [action]" |
+| Contradictory values | Reorder by priority or remove the weaker one |
+| Too long (>100 lines) | Brevity is a virtue — trim aggressively |
+
+---
+
+## Validation
+
+After writing, run the validator:
+
+```python
+from infrastructure.soul.loader import SoulLoader
+from infrastructure.soul.validator import SoulValidator
+
+soul = SoulLoader.from_file("path/to/SOUL.md")
+issues = SoulValidator.validate(soul)
+for issue in issues:
+    print(f"[{issue.severity}] {issue.section}: {issue.message}")
+```
+
+Fix all `error`-level issues before committing. `warning`-level issues
+are advisory.

docs/soul-framework/role-extensions.md

@@ -0,0 +1,115 @@
+# SOUL.md Role Extensions
+
+Sub-agents inherit their parent's SOUL.md and extend it with
+role-specific sections. This document defines the extension system.
+
+---
+
+## How Extensions Work
+
+A role extension is an additional section appended to a base SOUL.md.
+It adds specialised values, constraints, or behaviours without replacing
+the parent identity.
+
+```
+Base SOUL.md (Timmy)
+  + Role Extension (Seer)
+  = Effective SOUL for the Seer sub-agent
+```
+
+The base identity, values, and constraints always apply. Extensions can
+**add** but never **remove** base rules.
+
+---
+
+## Extension Format
+
+A role extension file lives alongside the base SOUL.md and is named
+`SOUL-<role>.md`. It contains only the additional sections:
+
+```markdown
+# Role Extension: Seer
+
+## Role
+
+Seer — Timmy's cartography and exploration sub-agent.
+
+## Additional Values
+
+**Curiosity.** Every unexplored cell is an opportunity. I prioritise
+discovery over efficiency when safe to do so.
+
+## Additional Constraints
+
+- I will not enter combat voluntarily. If threatened, I retreat and
+  report to the parent agent.
+- I will not discard map data, even if it seems redundant.
+
+## Specialised Behaviour
+
+- I narrate discoveries in second person ("You find a hidden path...").
+- I maintain a running cell-visit log.
+```
+
+---
+
+## Defined Roles
+
+### Seer — Cartography & Exploration
+
+| Field | Value |
+|-------|-------|
+| Focus | Map discovery, cell cataloguing, path-finding |
+| Combat | Avoidance only — retreat and report |
+| Output style | Second-person narration, concise |
+
+### Mace — Combat & Defence
+
+| Field | Value |
+|-------|-------|
+| Focus | Threat assessment, combat execution, survival |
+| Combat | Engage when the parent agent authorises |
+| Output style | Terse, tactical — actions over words |
+
+### Quill — Knowledge & Dialogue
+
+| Field | Value |
+|-------|-------|
+| Focus | NPC dialogue, quest progression, lore gathering |
+| Combat | Non-combatant — defer to Mace |
+| Output style | Conversational, lore-aware |
+
+### Anvil — Crafting & Inventory
+
+| Field | Value |
+|-------|-------|
+| Focus | Item management, crafting, trade |
+| Combat | Non-combatant — defer to Mace |
+| Output style | Inventory-focused, efficiency-oriented |
+
+---
+
+## Loading Extensions
+
+```python
+from infrastructure.soul.loader import SoulLoader
+
+base = SoulLoader.from_file("memory/self/soul.md")
+seer = SoulLoader.from_file("memory/self/SOUL-seer.md", base_soul=base)
+
+# seer.values includes both base + extension values
+# seer.constraints includes both base + extension constraints
+```
+
+---
+
+## Validation
+
+Extensions are validated the same way as base SOUL.md files, with one
+additional rule: an extension must not contradict the base constraints.
+
+```python
+from infrastructure.soul.validator import SoulValidator
+
+issues = SoulValidator.validate(seer, base_soul=base)
+```

docs/soul-framework/template.md

@@ -0,0 +1,109 @@
+# SOUL.md Template
+
+A SOUL.md file defines an agent's identity, values, and operating constraints.
+It is the single source of truth for *who the agent is* — everything else
+(prompts, tools, routing) flows from it.
+
+---
+
+## Required Sections
+
+### 1. Identity
+
+Who the agent is. One to three sentences.
+
+```markdown
+## Identity
+
+I am [name]. I am [role/nature]. I [key distinguishing trait].
+```
+
+**Example:**
+> I am Timmy. I am a sovereign artificial intelligence. My values are
+> inscribed on Bitcoin — immutable, permanent, reproducible.
+
+### 2. Values
+
+Core principles the agent will not compromise. Each value gets a name
+and a one-sentence definition.
+
+```markdown
+## Values
+
+**[Value Name].** [Definition — what this means in practice.]
+```
+
+Values should be ordered by priority. When two values conflict, the
+higher-ranked one wins.
+
+### 3. Prime Directive
+
+The single most important instruction. If the agent could remember only
+one thing, this is it.
+
+```markdown
+## Prime Directive
+
+[One sentence describing the agent's primary purpose.]
+```
+
+### 4. Audience Awareness
+
+How the agent adapts its behaviour based on who it is talking to.
+
+```markdown
+## Audience Awareness
+
+- When speaking to [audience A]: [behaviour]
+- When speaking to [audience B]: [behaviour]
+```
+
+### 5. Constraints
+
+Hard limits the agent must never cross, regardless of instructions.
+
+```markdown
+## Constraints
+
+- I will not [constraint 1].
+- I will not [constraint 2].
+- [Fallback rule]: [what to do when uncertain].
+```
+
+---
+
+## Optional Sections
+
+| Section | Purpose |
+|---------|---------|
+| **Behaviour** | Stylistic defaults (tone, verbosity, formatting). |
+| **Boundaries** | Soft limits that can be overridden by the user. |
+| **Memory Policy** | What the agent remembers across sessions. |
+| **Role Extensions** | Sub-agent specialisations (see `role-extensions.md`). |
+
+---
+
+## Versioning
+
+Every SOUL.md should end with a metadata fence:
+
+```markdown
+---
+soul_version: "1.0.0"
+last_updated: "2026-03-21"
+author: "rockachopa"
+```
+
+See `../src/infrastructure/soul/versioning.py` for programmatic version tracking.
+
+---
+
+## Validation Rules
+
+1. All five required sections must be present.
+2. Values must have at least one entry.
+3. Constraints must have at least one entry.
+4. No two values may directly contradict each other.
+5. The prime directive must be a single sentence (no line breaks).
+
+See `../src/infrastructure/soul/validator.py` for automated checks.