The Pirate — Phase 1.a: conversational read-only media agent

Ships a chat-based agent at /pirate that LLM-routes user questions to media-stack tools and returns natural-language answers grounded in real data. Foundation built on top of the existing API-tokens + dual-auth infrastructure so other apps (Open WebUI, HA voice, Synap) can consume the same Pirate API.

New subsystem (not the standard trigger/result pattern):
- pirate_conversations + pirate_messages tables
- service_configs table (admin-wide creds shared by media agents)
- /api/pirate/chat + /api/pirate/conversations/* (dual-auth: user session OR Bearer token scoped to user's pirate instance)
- /api/internal/pirate/* endpoints used by runtime subprocess
- /api/admin/services + Services tab in admin.html for cred management
- Auto-seeded service_configs on startup from Media Stack Reference defaults (never overwrite admin edits)
- Auto-seeded pirate catalog entry + per-user pirate instance on startup

Pirate package (agents/pirate/):
- prompts.py: system prompt, enforces read-only in Phase 1
- runtime.py: Anthropic-native tool-use loop (max 8 iterations, persists every turn)
- tools/_common.py: service_configs fetch + qBit session auth
- tools/sonarr.py: queue, upcoming, series_search, library_stats
- tools/radarr.py: queue, movie_search, library_stats
- tools/qbittorrent.py: torrents, transfer_stats, categories
- tools/storage.py: disk_space (via Sonarr diskspace API)
- Default model: claude-sonnet-4-5 (Haiku fumbles multi-step chains)

Dashboard:
- static/pirate.html — full chat UI with conversation sidebar, suggestion chips, inline tool-call visualization, 24h idle reset + New Chat button
- Pirate button added to main dashboard header

Wiki reorg: Agents / Developer Guides / Plans parent docs, per-agent reference docs, The Pirate doc. API Clients + Calling Agents docs moved under Developer Guides.

Working folder: PIRATE_PHASE_1A.md + NEXT_SESSION_PROMPT.md for fast bootstrap.

Smoke tested end-to-end: real tool calls against qBittorrent (13 active torrents correctly reported) and Sonarr disk-space; multi-turn conversation state preserved across follow-up questions.

On deck: Phase 1.b (Lidarr/Whisparr/Overseerr/Plex tools), then 1.d (OWUI pipeline), then 1.c (HA voice).

agents/pirate/tools/__init__.py

@@ -0,0 +1,25 @@
+"""Pirate tools — read-only functions the LLM can call.
+
+Each tool module exports a TOOLS list of dicts shaped for Anthropic tool use:
+    {"name": str, "description": str, "input_schema": {...}, "read_only": True, "fn": callable}
+
+The runtime loads all modules here and builds a combined catalog. The LLM picks
+which tool to call; the runtime executes it and returns the result as a tool message.
+"""
+
+from . import sonarr, radarr, qbittorrent, storage
+
+
+def build_catalog():
+    """Return a list of all available tools across all modules."""
+    catalog = []
+    for mod in (sonarr, radarr, qbittorrent, storage):
+        catalog.extend(getattr(mod, "TOOLS", []))
+    return catalog
+
+
+def find_tool(name):
+    for t in build_catalog():
+        if t["name"] == name:
+            return t
+    return None