feat: web_search + youtube_transcribe tools, shell interrupt backgrounding, fixes

- Add web_search tool (Firecrawl POST to /v1/search with query, limit, lang, country, scrapeOptions)
- Add youtube_transcribe tool (GET to transcriber service, handles completed/queued/failed statuses)
- Both tools registered for parent agents (always) and child agents (permission-gated)
- Added to summon enum, TOOL_DESCRIPTIONS, and core exports
- Shell interrupt: run_shell now races against user queue interrupt
  - When interrupted, command continues in background with run_shell_<uuid> job ID
  - BackgroundShellStore holds running processes, auto-cleans 10min after completion
  - retrieve tool extended to handle both agent IDs and shell job IDs
- Tool error detection: results starting with 'Error:' now marked isError in UI
- Fix TS error: cast unavailMatch[1] regex capture group to string
- Docker: network_mode host for Tailscale/LAN access to external services
- Bun.serve idleTimeout set to 60s (was default 10s)
- KeyUsage: clearer message when OpenCode usage data unavailable
- Firecrawl: only send scrapeOptions when scrape=true (avoid 400 on instances without scrape support)

1 files changed, 1 insertions, 0 deletions

diff --git a/packages/api/src/index.ts b/packages/api/src/index.ts
index b188e39..a0ad025 100644
--- a/packages/api/src/index.ts
+++ b/packages/api/src/index.ts
@@ -72,6 +72,7 @@ export { app };
 
 export default {
 	port: Number(process.env.PORT) || 3000,
+	idleTimeout: 60,
 	fetch: app.fetch,
 	websocket,
 };