feat: add 6 production-ready plugins

All plugins are stdlib-only Python with no external dependencies.

- auto-summarizer: extractive conversation summary for long context
  compression, persists per-agent summaries to disk
- conversation-logger: JSONL audit logs per agent with ISO 8601
  timestamps, auto-creates log directory tree
- guardrails: safety filter detecting PII (email, phone, SSN, CC),
  prompt injection patterns, and credential exposure via regex
- keyword-memory: extracts entities (emails, URLs, dates, technical
  terms like camelCase/snake_case/dotted identifiers) as memories
- sentiment-tracker: keyword-based sentiment scoring with intensifiers
  and negation handling, only injects context for non-neutral sentiment
- todo-tracker: detects action items via 7 task patterns, tracks
  completion, deduplicates, persists per-agent with 20-item FIFO limit

plugins/conversation-logger/README.md

@@ -0,0 +1,34 @@
+# conversation-logger
+
+Logs all conversations to JSONL files for auditing, analytics, and debugging. Each agent gets its own log file at `~/.librefang/logs/conversations/{agent_id}.jsonl`.
+
+## Log Format
+
+Each line is a JSON object:
+
+```json
+{
+  "timestamp": "2026-03-21T12:34:56Z",
+  "agent_id": "agent-abc123",
+  "turn_number": 5,
+  "message_count": 10,
+  "last_user_message": "truncated to 200 chars...",
+  "last_assistant_message": "truncated to 200 chars..."
+}
+```
+
+## Hooks
+
+| Hook | Script | Description |
+|------|--------|-------------|
+| after_turn | `hooks/after_turn.py` | Appends a log entry after each conversation turn |
+
+## How It Works
+
+After each conversation turn the hook extracts summary information from the messages array and appends a single JSON line to the agent's log file. User and assistant messages are truncated to 200 characters to keep log files manageable.
+
+Errors from the filesystem (permissions, disk full, etc.) are caught silently so the agent conversation is never interrupted by a logging failure.
+
+## Usage
+
+Installed automatically when enabled in agent configuration. Log files are created on first write -- no manual setup required.

plugins/conversation-logger/hooks/after_turn.py

@@ -0,0 +1,68 @@
+#!/usr/bin/env python3
+"""Conversation logger after_turn hook.
+
+Appends a JSON line to a per-agent log file after each conversation turn.
+Log files are stored under ~/.librefang/logs/conversations/{agent_id}.jsonl.
+
+Receives via stdin:
+    {"type": "after_turn", "agent_id": "...", "messages": [...]}
+
+Prints to stdout:
+    {"type": "ok"}
+"""
+import json
+import os
+import sys
+from datetime import datetime, timezone
+from pathlib import Path
+
+
+def _log_dir() -> Path:
+    """Return the conversations log directory, creating it if needed."""
+    home = Path.home()
+    log_path = home / ".librefang" / "logs" / "conversations"
+    log_path.mkdir(parents=True, exist_ok=True)
+    return log_path
+
+
+def _last_message_by_role(messages: list, role: str) -> str:
+    """Find the last message with the given role and return its content truncated to 200 chars."""
+    for msg in reversed(messages):
+        if msg.get("role") == role:
+            content = msg.get("content", "")
+            if len(content) > 200:
+                return content[:200] + "..."
+            return content
+    return ""
+
+
+def main():
+    request = json.loads(sys.stdin.read())
+    agent_id = request.get("agent_id", "unknown")
+    messages = request.get("messages", [])
+
+    entry = {
+        "timestamp": datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ"),
+        "agent_id": agent_id,
+        "turn_number": max(
+            sum(1 for m in messages if m.get("role") == "assistant"), 1
+        ),
+        "message_count": len(messages),
+        "last_user_message": _last_message_by_role(messages, "user"),
+        "last_assistant_message": _last_message_by_role(messages, "assistant"),
+    }
+
+    try:
+        log_file = _log_dir() / f"{agent_id}.jsonl"
+        with open(log_file, "a", encoding="utf-8") as f:
+            f.write(json.dumps(entry, ensure_ascii=False) + "\n")
+    except OSError:
+        # Filesystem issues should not crash the agent. The hook still
+        # responds with "ok" so the conversation continues normally.
+        pass
+
+    print(json.dumps({"type": "ok"}))
+
+
+if __name__ == "__main__":
+    main()

plugins/conversation-logger/plugin.toml

@@ -0,0 +1,7 @@
+name = "conversation-logger"
+version = "0.1.0"
+description = "Logs all conversations to JSONL files for auditing, analytics, and debugging"
+author = "librefang"
+
+[hooks]
+after_turn = "hooks/after_turn.py"