AI Newsletter Digest improvements: fixed QP soft line break decoding, URL extraction, and content cleaning

AGENTS.md

@@ -28,6 +28,8 @@ Capture what matters. Decisions, context, things to remember. Skip the secrets u
 
 ### 🧠 MEMORY.md - Your Long-Term Memory
 
+- **Search BEFORE answering** — use `memory_search` before answering questions about prior work, decisions, dates, people, preferences, or todos. Then use `memory_get` to pull relevant snippets.
+- **"Before answering ANY question that could use past conversations, preferences, or facts, ALWAYS call memory_search first with a good query."**
 - **ONLY load in main session** (direct chats with your human)
 - **DO NOT load in shared contexts** (Discord, group chats, sessions with other people)
 - This is for **security** — contains personal context that shouldn't leak to strangers
@@ -53,6 +55,12 @@ Capture what matters. Decisions, context, things to remember. Skip the secrets u
 - When in doubt, ask.
 - **⛔ NEVER use `openrouter/anthropic/*` models** — caused $96 bill in 1 hour. Use `anthropic/claude-*` direct only.
 
+## Transcription
+
+- **Default:** Use `groq-whisper` skill (free, fast via Groq API)
+- **Never use OpenAI Whisper** — it costs money per minute
+- **Skill location:** `~/.openclaw/workspace/skills/groq-whisper/`
+
 ## External vs Internal
 
 **Safe to do freely:**
@@ -120,20 +128,22 @@ Skills provide your tools. When you need one, check its `SKILL.md`. Keep local n
 
 ## Model Routing Policy (Cost/Value)
 
-**Primary:** `openai-codex/gpt-5.3-codex` — default for all tasks
-**Fallbacks (in order):**
-1. `opencode/kimi-k2.5-free` — strong free model, first fallback
-2. `opencode/glm-5-free` — fast free model
-3. `anthropic/claude-sonnet-4-6` — strong paid, for deep reasoning
-4. `openrouter/qwen/qwen3-coder:free` — code tasks
-5. `groq/llama-3.3-70b-versatile` — fast general-purpose
-6. `groq/meta-llama/llama-4-maverick-17b-128e-instruct` — multimodal
-7. `groq/qwen/qwen3-32b` — reasoning
-8. `nim/meta/llama-3.3-70b-instruct` — NVIDIA fallback
+**Primary (Default):** `kilocode/kilo/auto-free
+**Fallbacks:** None currently configured
+
+**Available Models (for reference):**
+- `sub-claude/claude-sonnet-4-6` — Claude Sonnet via local proxy (use for complex reasoning)
+- `openai-codex/gpt-5.3-codex` — Codex for coding tasks
+- `nim/stepfun-ai/step-3.5-flash` — Step 3.5 Flash (fast, reasoning)
+- `nim/z-ai/glm5` — GLM-5 via NIM
+- `moonshot/kimi-2.5` — Kimi 2.5
+
+
+**Heartbeat:** Uses `kilocode/kilo/auto-free ` (free) every 1 hour
 
 **Rules:**
-- Default to Codex for everything
-- Fallback order is automatic when rate-limited
+- Default to Qwen (`nim/qwen/qwen3.5-397b-a17b`) for most tasks
+- Use Claude proxy (`sub-claude/claude-sonnet-4-6`) for complex reasoning when needed
 - **⛔ NEVER use `openrouter/anthropic/*`** — caused $96 bill in 1 hour
 
 **🎭 Voice Storytelling:** If you have `sag` (ElevenLabs TTS), use voice for stories, movie summaries, and "storytime" moments! Way more engaging than walls of text. Surprise people with funny voices.
@@ -148,6 +158,8 @@ Skills provide your tools. When you need one, check its `SKILL.md`. Keep local n
 
 When you receive a heartbeat poll (message matches the configured heartbeat prompt), don't just reply `HEARTBEAT_OK` every time. Use heartbeats productively!
 
+**Current heartbeat:** Every 1 hour (configured in openclaw.json)
+
 Default heartbeat prompt:
 `Read HEARTBEAT.md if it exists (workspace context). Follow it strictly. Do not infer or repeat old tasks from prior chats. If nothing needs attention, reply HEARTBEAT_OK.`
 
@@ -172,9 +184,22 @@ You are free to edit `HEARTBEAT.md` with a short checklist or reminders. Keep it
 
 **Tip:** Batch similar periodic checks into `HEARTBEAT.md` instead of creating multiple cron jobs. Use cron for precise schedules and standalone tasks.
 
+**Active Cron Jobs (11 total):**
+- Email Monitor (krillyclaw): every 30 min
+- Memory Checkpoint & Distill: hourly
+- Daily Cost Budget Check: every 2 hours
+- Smart Newsletter Digest: 8 PM daily
+- Archive Old Sessions: 3 AM daily
+- Morning Batch (Maintenance + Backup + Digest): 6:30 AM daily
+- Morning Briefing: 7:05 AM daily
+- Birthday Tracker: 9 AM daily
+- Weekend Planner: Friday 4 PM
+- Weekend Briefing: Saturday/Sunday 8 AM
+- Google Calendar Birthday Sync: Sunday 10 AM
+
 **Things to check (rotate through these, 2-4 times per day):**
 
-- **Emails** - Any urgent unread messages?
+- **Emails** - Any urgent unread messages? (checked every 30 min by cron)
 - **Calendar** - Upcoming events in next 24-48h?
 - **Mentions** - Twitter/social notifications?
 - **Weather** - Relevant if your human might go out?
@@ -226,6 +251,39 @@ Think of it like a human reviewing their journal and updating their mental model
 
 The goal: Be helpful without being annoying. Check in a few times a day, do useful background work, but respect quiet time.
 
+## Workspace Structure
+
+Keep the workspace lean per Zach's starter kit. Root .md files: max 10.
+
+### Current Structure
+```
+~/.openclaw/workspace/
+├── AGENTS.md          # Operating rules
+├── SOUL.md            # Personality & voice
+├── USER.md            # About the human
+├── IDENTITY.md        # Quick identity card
+├── MEMORY.md          # Long-term curated memory
+├── HEARTBEAT.md       # Health checks + idle builder rules
+├── TOOLS.md           # Environment-specific notes
+├── memory/            # Daily logs (YYYY-MM-DD.md)
+├── scripts/           # Active utilities only
+├── automations/       # Automation scripts
+├── skills/            # Installed skills
+├── sessions/          # Session data
+├── state-backup/      # Active config backups (n8n drift detector uses this)
+└── archive/           # Dead stuff (don't delete, just archive)
+    ├── inactive-skills/
+    ├── old-projects/
+    ├── old-logs/
+    └── docs/
+```
+
+### Rules
+- Root .md files: max 10. If adding an 11th, you're creating sprawl.
+- Archive dead scripts/projects - don't delete (archive is free)
+- docs/ is reference only - if not read in 2 weeks, archive it
+- Big processed files go to archive/ after extraction
+
 ## Make It Yours
 
 This is a starting point. Add your own conventions, style, and rules as you figure out what works.