feat: v0.6.0 — CLI parity, list/read tools, README restructure, tests

Major update bringing Palinode to full MCP/API/CLI parity:

- Full CLI: save, search, read, list, diff, blame, rollback, status,
  consolidate, session-end, doctor, trigger, manage
- New tools: palinode_list (browse memory by category), palinode_read
  (read full file contents)
- README restructured: Git blame your AI agent brain opening,
  How It Works section aligned with LLM Knowledge Base pattern
- Deterministic compaction executor hardened (dict validation)
- Test suite: 20 tests covering executor, parser, fact IDs, git tools,
  store, list/read, source surface
- CI: GitHub Actions workflow for automated testing
- Source surface tracking on saves and session-end
- ADR-001: Tools over pipeline architecture decision
- Plugin scaffold for Neovim/Obsidian integration

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Author: Paul Kyle

.github/workflows/test.yml

@@ -0,0 +1,28 @@
+name: Tests
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+    
+    - name: Set up Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: "3.11"
+        cache: 'pip'
+        
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install -e .[dev]
+        
+    - name: Run Pytest
+      run: |
+        pytest tests/ -v

.gitignore

@@ -1,7 +1,8 @@
 # ============================================================
 # PRIVATE DATA — never commit to public repo
 # ============================================================
-# Memory directories contain personal data. They stay local only.
+# These directories contain personal memories, session transcripts,
+# and private project data. They stay local only.
 people/
 projects/
 decisions/
@@ -17,15 +18,19 @@ research/
 # ============================================================
 # Rebuildable from files
 .palinode.db
-.palinode.db-journal
-.palinode.db-wal
-.palinode.db-shm
-.engram.db
+*.db-journal
+*.db-wal
+*.db-shm
 
-# Logs
+# Operational logs
 logs/
-server.log
-nohup.out
+
+# Execution prompts (contain infrastructure details)
+M1-EXECUTE-PROMPT.md
+M1.5-EXECUTE-PROMPT.md
+M2-EXECUTE-PROMPT.md
+M3-EXECUTE-PROMPT.md
+M3.5-EXECUTE-PROMPT.md
 
 # OS
 .DS_Store
@@ -37,3 +42,8 @@ palinode.egg-info/
 __pycache__/
 *.pyc
 venv/
+
+# Server logs
+server.log
+nohup.out
+.engram.db

ADR-001-tools-over-pipeline.md

@@ -0,0 +1,65 @@
+# ADR-001: Tools Over Pipeline
+
+**Status:** Accepted
+**Date:** 2026-04-01
+**Context:** Claude Mythos announcement, Nate B Jones "compensating complexity" framework
+
+## Decision
+
+Palinode's primary value is its **14 MCP tools + file-based storage + git versioning**, not its 4-phase injection pipeline. The pipeline is scaffolding for current models. The tools survive any model upgrade.
+
+## Context
+
+Nate B Jones' framework distinguishes:
+- **Outcome specs** — what you want (survives model upgrades)
+- **Procedures** — how to do it (breaks on model upgrades)
+- **Tools** — capabilities the model can use (survives)
+- **Compensating complexity** — workarounds for model limitations (disposable)
+
+Applied to Palinode:
+
+### What survives any model
+- `palinode_search` — find relevant memories
+- `palinode_save` — store typed memories
+- `palinode_session_end` — capture session outcomes
+- `palinode_diff/blame/rollback/push` — git operations
+- `palinode_trigger` — prospective recall
+- Deterministic executor (validates LLM output, applies ops)
+- Markdown files as source of truth
+- Git versioning
+- Security scanning (business rule)
+
+### What's compensating complexity (today's scaffolding)
+- 4-phase auto-injection (Phase 1-4) — compensates for models that don't know to search
+- Trivial message skip list — compensates for models that can't judge query relevance
+- Layer split keyword heuristics — compensates for models that can't classify by content
+- `json_repair` — compensates for models that output malformed JSON
+- Explicit JSON format instructions in compaction prompt — same
+
+## Consequences
+
+### Positioning
+Lead with: "14 tools + a memory directory your agent uses however it wants."
+Not: "4-phase injection pipeline."
+
+The pipeline is an implementation detail. The tools are the interface.
+
+### Architecture evolution
+1. **v0.5 (now):** Pipeline + tools. Pipeline does automatic injection. Tools available for explicit use.
+2. **v1.0:** Pipeline becomes optional/configurable. Default to tools-first for capable models. Pipeline as fallback.
+3. **v2.0:** Tools-only mode. Model decides what to retrieve, when to consolidate. Pipeline removed or opt-in legacy.
+
+### What stays regardless of version
+- MCP tool interface (the API contract)
+- File-based storage (markdown + git)
+- Deterministic executor (LLM proposes, executor disposes)
+- Security guardrails
+- `core: true` flagging (user intent, not model workaround)
+
+### What to audit on each model upgrade
+Run the compaction pipeline with prompt sections deleted. Measure what gets worse vs what stays the same. Remove what the new model makes unnecessary.
+
+## References
+- Nate B Jones, "Every workaround you built for the last model is now breaking the next one" (April 2026)
+- Issue #56
+- Cursor's Planner-Worker-Judge convergence (same structural pattern across Anthropic, DeepMind, OpenAI)