fix(deadman-fallback): try/except/continue cascade + OpenRouter

- Add PROVIDER_TIMEOUT (30s default, env PROVIDER_TIMEOUT)
- Replace local-llama fallback with OpenRouter (openrouter/google/gemini-2.5-pro)
- Wrap fallback_to_openrouter, fallback_to_ollama, restore_config, enter_safe_mode in try/except
- Continue to next fallback on any error; no crash propagation
- Log all fallback events to request_log SQLite DB
- Provider errors caught/telemetry; never corrupt config

Closes #445

bin/deadman-fallback.py

@@ -24,12 +24,17 @@ import yaml
 import shutil
 from pathlib import Path
 from datetime import datetime, timedelta
+import sqlite3
+import urllib.request
+import urllib.error
 
 HERMES_HOME = Path(os.environ.get("HERMES_HOME", os.path.expanduser("~/.hermes")))
 CONFIG_PATH = HERMES_HOME / "config.yaml"
 FALLBACK_STATE = HERMES_HOME / "deadman-fallback-state.json"
 BACKUP_CONFIG = HERMES_HOME / "config.yaml.pre-fallback"
 FORGE_URL = "https://forge.alexanderwhitestone.com"
+# Golden-state fallback chain: Kimi → OpenRouter (Gemini 2.5 Pro) → Ollama (gemma4:latest)
+PROVIDER_TIMEOUT = int(os.getenv("PROVIDER_TIMEOUT", "30"))
 
 def load_config():
     with open(CONFIG_PATH) as f:
@@ -50,7 +55,7 @@ def save_state(state):
     with open(FALLBACK_STATE, "w") as f:
         json.dump(state, f, indent=2)
 
-def run(cmd, timeout=10):
+def run(cmd, timeout=PROVIDER_TIMEOUT):
     try:
         r = subprocess.run(cmd, shell=True, capture_output=True, text=True, timeout=timeout)
         return r.returncode, r.stdout.strip(), r.stderr.strip()
@@ -61,6 +66,23 @@ def run(cmd, timeout=10):
 
 # ─── HEALTH CHECKS ───
 
+
+def log_fallback_event(agent_name, provider, model, status, error_message=None):
+    """Log fallback events to request_log SQLite DB (telemetry)."""
+    try:
+        log_path = Path.home() / ".local" / "timmy" / "request_log.db"
+        if log_path.exists():
+            conn = sqlite3.connect(str(log_path))
+            cursor = conn.cursor()
+            cursor.execute("""
+                INSERT INTO request_log (timestamp, agent_name, provider, model, endpoint, status, error_message)
+                VALUES (datetime('now'), ?, ?, ?, ?, ?, ?)
+            """, (agent_name, provider, model, 'fallback_switch', status, error_message))
+            conn.commit()
+            conn.close()
+    except Exception:
+        pass  # Silent if telemetry unavailable
+
 def check_kimi():
     """Can we reach Kimi Coding API?"""
     key = os.environ.get("KIMI_API_KEY", "")
@@ -89,12 +111,38 @@ def check_kimi():
         return True, f"HTTP {out}"
     return False, f"HTTP {out} err={err[:80]}"
 
-def check_local_llama():
+def check_openrouter():
-    """Is local llama.cpp serving?"""
+    """Check OpenRouter API availability and credentials."""
-    code, out, err = run("curl -s http://localhost:8081/v1/models", timeout=5)
+    key = os.environ.get("OPENROUTER_API_KEY", "")
-    if code == 0 and "hermes" in out.lower():
+    if not key:
-        return True, "serving"
+        env_file = HERMES_HOME / ".env"
-    return False, f"exit={code}"
+        if env_file.exists():
+            for line in open(env_file):
+                line = line.strip()
+                if line.startswith("OPENROUTER_API_KEY="):
+                    key = line.split("=", 1)[1].strip().strip('"\'')
+                    break
+    if not key:
+        return False, "No OPENROUTER_API_KEY"
+    try:
+        req = urllib.request.Request(
+            "https://openrouter.ai/api/v1/models",
+            headers={"Authorization": "Bearer " + key}
+        )
+        resp = urllib.request.urlopen(req, timeout=PROVIDER_TIMEOUT)
+        if resp.status == 200:
+            data = json.loads(resp.read())
+            models = data.get("data", [])
+            return True, f"{len(models)} models available"
+        else:
+            return False, f"HTTP {resp.status}"
+    except urllib.error.HTTPError as e:
+        if e.code == 401:
+            return False, "Invalid OPENROUTER_API_KEY"
+        else:
+            return False, f"HTTP {e.code}"
+    except Exception as e:
+        return False, str(e)[:100]
 
 def check_ollama():
     """Is Ollama running?"""
@@ -127,15 +175,18 @@ def check_vps(ip, name):
 
 # ─── FALLBACK ACTIONS ───
 
-def fallback_to_local_model(cfg):
+def fallback_to_openrouter(cfg):
-    """Switch primary model from Kimi to local llama.cpp"""
+    "Switch primary model from Kimi to OpenRouter (Gemini 2.5 Pro)"
     if not BACKUP_CONFIG.exists():
         shutil.copy2(CONFIG_PATH, BACKUP_CONFIG)
     
-    cfg["model"]["provider"] = "local-llama.cpp"
+    openrouter_cfg = cfg.get("providers", {}).get("openrouter", {})
-    cfg["model"]["default"] = "hermes3"
+    base_url = openrouter_cfg.get("base_url", "https://openrouter.ai/api/v1")
+    cfg["model"]["provider"] = "openrouter"
+    cfg["model"]["default"] = "google/gemini-2.5-pro"
+    cfg["model"]["base_url"] = base_url
     save_config(cfg)
-    return "Switched primary model to local-llama.cpp/hermes3"
+    return "Switched primary model to openrouter/google/gemini-2.5-pro"
 
 def fallback_to_ollama(cfg):
     """Switch to Ollama if llama.cpp is also down"""
@@ -179,11 +230,11 @@ def diagnose_and_fallback():
     kimi_ok, kimi_msg = check_kimi()
     results["checks"]["kimi-coding"] = {"ok": kimi_ok, "msg": kimi_msg}
     
-    llama_ok, llama_msg = check_local_llama()
+    openrouter_ok, openrouter_msg = check_openrouter()
-    results["checks"]["local_llama"] = {"ok": llama_ok, "msg": llama_msg}
+    results["checks"]["openrouter"] = {"ok": openrouter_ok, "msg": openrouter_msg}
     
-    ollama_ok, ollama_msg = check_ollama()
+    oopenrouter_ok, oopenrouter_msg = check_ollama()
-    results["checks"]["ollama"] = {"ok": ollama_ok, "msg": ollama_msg}
+    results["checks"]["ollama"] = {"ok": oopenrouter_ok, "msg": oopenrouter_msg}
     
     gitea_ok, gitea_msg = check_gitea()
     results["checks"]["gitea"] = {"ok": gitea_ok, "msg": gitea_msg}
@@ -202,41 +253,79 @@ def diagnose_and_fallback():
     
     # ─── FALLBACK LOGIC ───
     
-    # Case 1: Primary (Kimi) down, local available
+    # Case 1: Primary (Kimi) down, try fallback chain (OpenRouter -> Ollama)
     if not kimi_ok and current_provider == "kimi-coding":
-        if llama_ok:
+        agent_name = cfg.get("agent", {}).get("name", "timmy")
-            msg = fallback_to_local_model(cfg)
+        applied = False
-            results["actions"].append(msg)
+        # Try OpenRouter fallback
-            state["active_fallbacks"].append("kimi->local-llama")
+        if openrouter_ok:
-            results["status"] = "degraded_local"
+            try:
-        elif ollama_ok:
+                msg = fallback_to_openrouter(cfg)
-            msg = fallback_to_ollama(cfg)
+                results["actions"].append(msg)
-            results["actions"].append(msg)
+                state["active_fallbacks"].append("kimi->openrouter")
-            state["active_fallbacks"].append("kimi->ollama")
+                results["status"] = "degraded_openrouter"
-            results["status"] = "degraded_ollama"
+                log_fallback_event(agent_name, "openrouter", "google/gemini-2.5-pro", "success")
-        else:
+                applied = True
-            msg = enter_safe_mode(state)
+            except Exception as e:
-            results["actions"].append(msg)
+                log(f"OpenRouter fallback failed: {e}")
-            results["status"] = "safe_mode"
+                log_fallback_event(agent_name, "openrouter", "google/gemini-2.5-pro", "error", str(e))
+        # If still not applied, try Ollama
+        if not applied and oopenrouter_ok:
+            try:
+                msg = fallback_to_ollama(cfg)
+                results["actions"].append(msg)
+                state["active_fallbacks"].append("kimi->ollama")
+                results["status"] = "degraded_ollama"
+                log_fallback_event(agent_name, "ollama", "gemma4:latest", "success")
+                applied = True
+            except Exception as e:
+                log(f"Ollama fallback failed: {e}")
+                log_fallback_event(agent_name, "ollama", "gemma4:latest", "error", str(e))
+        if not applied:
+            try:
+                msg = enter_safe_mode(state)
+                results["actions"].append(msg)
+                results["status"] = "safe_mode"
+            except Exception as e:
+                log(f"Safe mode failed: {e}")
     
-    # Case 2: Already on fallback, check if primary recovered
+    # Case 2: Already on fallback, check if primary recovered — restore with resilience
-    elif kimi_ok and "kimi->local-llama" in state.get("active_fallbacks", []):
+    elif kimi_ok:
-        msg = restore_config()
+        restored = False
-        results["actions"].append(msg)
+        agent_name = cfg.get("agent", {}).get("name", "timmy")
-        state["active_fallbacks"].remove("kimi->local-llama")
+        # Try restore from OpenRouter fallback
-        results["status"] = "recovered"
+        if "kimi->openrouter" in state.get("active_fallbacks", []):
-    elif kimi_ok and "kimi->ollama" in state.get("active_fallbacks", []):
+            try:
-        msg = restore_config()
+                msg = restore_config()
-        results["actions"].append(msg)
+                results["actions"].append(msg)
-        state["active_fallbacks"].remove("kimi->ollama")
+                state["active_fallbacks"].remove("kimi->openrouter")
-        results["status"] = "recovered"
+                results["status"] = "recovered"
+                restored = True
+                log_fallback_event(agent_name, "openrouter", "google/gemini-2.5-pro", "restored")
+            except Exception as e:
+                log(f"Restore from OpenRouter failed: {e}")
+                log_fallback_event(agent_name, "openrouter", "google/gemini-2.5-pro", "error", str(e))
+        # Try restore from Ollama fallback if still not restored
+        if not restored and "kimi->ollama" in state.get("active_fallbacks", []):
+            try:
+                msg = restore_config()
+                results["actions"].append(msg)
+                state["active_fallbacks"].remove("kimi->ollama")
+                results["status"] = "recovered"
+                restored = True
+                log_fallback_event(agent_name, "ollama", "gemma4:latest", "restored")
+            except Exception as e:
+                log(f"Restore from Ollama failed: {e}")
+                log_fallback_event(agent_name, "ollama", "gemma4:latest", "error", str(e))
+        if not restored:
+            log("WARNING: Primary recovered but unable to restore config")
     
     # Case 3: Gitea down — just flag it, work locally
     if not gitea_ok:
         results["actions"].append("WARN: Gitea unreachable — work cached locally until recovery")
         if "gitea_down" not in state.get("active_fallbacks", []):
             state["active_fallbacks"].append("gitea_down")
-        results["status"] = max(results["status"], "degraded_gitea", key=lambda x: ["healthy", "recovered", "degraded_gitea", "degraded_local", "degraded_ollama", "safe_mode"].index(x) if x in ["healthy", "recovered", "degraded_gitea", "degraded_local", "degraded_ollama", "safe_mode"] else 0)
+        results["status"] = max(results["status"], "degraded_gitea", key=lambda x: ["healthy", "recovered", "degraded_gitea", "degraded_openrouter", "degraded_ollama", "safe_mode"].index(x) if x in ["healthy", "recovered", "degraded_gitea", "degraded_openrouter", "degraded_ollama", "safe_mode"] else 0)
     elif "gitea_down" in state.get("active_fallbacks", []):
         state["active_fallbacks"].remove("gitea_down")
         results["actions"].append("Gitea recovered — resume normal operations")

bin/gitea-backup.sh

@@ -0,0 +1,87 @@
+#!/bin/bash
+# Gitea Daily Backup Script
+# Uses Gitea's native dump command to create automated backups of repositories and SQLite databases.
+# Designed to run on the VPS (Ezra) as part of a daily cron job.
+#
+# Configuration via environment variables:
+#   GITEA_BIN               Path to gitea binary (default: auto-detect)
+#   GITEA_BACKUP_DIR        Directory for backup archives (default: /var/backups/gitea)
+#   GITEA_BACKUP_RETENTION  Days to retain backups (default: 7)
+#   GITEA_BACKUP_LOG        Log file path (default: /var/log/gitea-backup.log)
+
+set -euo pipefail
+
+GITEA_BIN="${GITEA_BIN:-$(command -v gitea 2>/dev/null || echo "/usr/local/bin/gitea")}"
+BACKUP_DIR="${GITEA_BACKUP_DIR:-/var/backups/gitea}"
+RETENTION_DAYS="${GITEA_BACKUP_RETENTION:-7}"
+DATE="$(date +%Y-%m-%d_%H%M%S)"
+BACKUP_FILE="${BACKUP_DIR}/gitea-backup-${DATE}.tar.gz"
+LOG_FILE="${GITEA_BACKUP_LOG:-/var/log/gitea-backup.log}"
+
+mkdir -p "${BACKUP_DIR}"
+
+log() {
+  echo "[$(date '+%Y-%m-%d %H:%M:%S')] $*" | tee -a "${LOG_FILE}"
+}
+
+log "=== Starting Gitea daily backup ==="
+
+# Verify gitea binary exists
+if [ ! -x "${GITEA_BIN}" ]; then
+  log "ERROR: Gitea binary not found at ${GITEA_BIN}"
+  log "Set GITEA_BIN environment variable to the gitea binary path (e.g., /usr/bin/gitea)"
+  exit 1
+fi
+
+# Detect Gitea WORK_PATH
+WORK_PATH=""
+APP_INI=""
+for path in /etc/gitea/app.ini /home/git/gitea/custom/conf/app.ini ~/gitea/custom/conf/app.ini; do
+  if [ -f "$path" ]; then
+    APP_INI="$path"
+    break
+  fi
+done
+
+if [ -n "$APP_INI" ]; then
+  # Parse [app] WORK_PATH = /var/lib/gitea
+  WORK_PATH=$(sed -n 's/^[[:space:]]*WORK_PATH[[:space:]]*=[[:space:]]*//p' "$APP_INI" | head -1)
+  log "Detected WORK_PATH from app.ini: ${WORK_PATH}"
+fi
+
+# Fallback detection
+if [ -z "$WORK_PATH" ]; then
+  for d in /var/lib/gitea /home/git/gitea /srv/gitea /opt/gitea; do
+    if [ -d "$d" ]; then
+      WORK_PATH="$d"
+      break
+    fi
+  done
+  log "Inferred WORK_PATH: ${WORK_PATH:-not found}"
+fi
+
+if [ -z "$WORK_PATH" ]; then
+  log "ERROR: Could not determine Gitea WORK_PATH. Set GITEA_WORK_PATH manually."
+  exit 1
+fi
+
+# Perform gitea dump
+# Flags: --work-path sets the Gitea working directory, --file writes dump to tar.gz
+log "Running: gitea dump --work-path ${WORK_PATH} --file ${BACKUP_FILE}"
+"${GITEA_BIN}" dump --work-path "${WORK_PATH}" --file "${BACKUP_FILE}" 2>>"${LOG_FILE}"
+
+if [ $? -ne 0 ]; then
+  log "ERROR: gitea dump failed — check ${LOG_FILE} for details"
+  exit 1
+fi
+
+FILE_SIZE=$(du -h "${BACKUP_FILE}" | cut -f1)
+log "Backup created: ${BACKUP_FILE} (${FILE_SIZE})"
+
+# Prune old backups (keep last N days)
+find "${BACKUP_DIR}" -name "gitea-backup-*.tar.gz" -type f -mtime +$((${RETENTION_DAYS}-1)) -delete 2>/dev/null || true
+log "Pruned backups older than ${RETENTION_DAYS} days"
+
+log "=== Backup completed successfully ==="
+
+exit 0

cron/vps/gitea-daily-backup.yml

@@ -0,0 +1,9 @@
+- name: Daily Gitea Backup
+  schedule: '0 2 * * *'  # 2:00 AM daily
+  tasks:
+    - name: Run Gitea daily backup
+      shell: bash ~/.hermes/bin/gitea-backup.sh
+      env:
+        GITEA_BIN: /usr/local/bin/gitea
+        GITEA_BACKUP_DIR: /var/backups/gitea
+        GITEA_BACKUP_RETENTION: "7"

docs/backup-recovery-runbook.md

@@ -0,0 +1,155 @@
+# Gitea Backup & Recovery Runbook
+
+**Last updated:** 2026-04-30  
+**Scope:** Single-node VPS (Ezra, 143.198.27.163) running Gitea  
+**Backup Strategy:** Automated daily full dumps via `gitea dump`
+
+---
+
+## What Gets Backed Up
+
+| Component | Method | Frequency | Retention |
+|-----------|--------|-----------|-----------|
+| All Gitea repositories (bare git dirs) | `gitea dump --file` | Daily at 2:00 AM | 7 days |
+| SQLite databases (gitea.db, indexer.db, etc.) | Included in dump | Daily | 7 days |
+| Attachments, avatars, hooks | Included in dump | Daily | 7 days |
+
+**Backup location:** `/var/backups/gitea/gitea-backup-YYYY-MM-DD_HHMMSS.tar.gz`
+
+**Log file:** `/var/log/gitea-backup.log`
+
+---
+
+## Backup Architecture
+
+The backup script `bin/gitea-backup.sh` runs daily via Hermes cron (`cron/vps/gitea-daily-backup.yml`). It:
+
+1. Locates the Gitea `WORK_PATH` by reading `/etc/gitea/app.ini` or falling back to common locations (`/var/lib/gitea`, `/home/git/gitea`)
+2. Invokes `gitea dump --work-path <path> --file <backup-tar.gz>` — Gitea's native, consistent snapshot mechanism
+3. Prunes archives older than 7 days
+4. Logs all operations to `/var/log/gitea-backup.log`
+
+**Prerequisites on the VPS:**
+- Gitea binary available at `/usr/local/bin/gitea` (or set `GITEA_BIN` env var)
+- `gitea dump` command must be available (Gitea ≥ 1.12)
+- SSH access to the VPS for manual recovery operations
+- Sufficient disk space in `/var/backups/gitea` (typical dump: ~2–10 GB depending on repo count/size)
+
+---
+
+## Recovery Time Objective (RTO) & Recovery Point Objective (RPO)
+
+| Metric | Estimate |
+|--------|----------|
+| **RPO** (data loss window) | ≤ 24 hours (last daily backup) |
+| **RTO** (time to restore) | **~45 minutes** (cold restore from backup tarball) |
+| **Downtime impact** | Gitea offline during restore (~20 min) |
+
+---
+
+## Step-by-Step Recovery Procedure
+
+### Phase 1 — Assess & Prepare (5 min)
+
+1. SSH into Ezra VPS: `ssh root@143.198.27.163`
+2. Stop Gitea so files are quiescent:
+   ```bash
+   systemctl stop gitea
+   ```
+3. Confirm current Gitea data directory (for reference):
+   ```bash
+   gitea --work-path /var/lib/gitea --config /etc/gitea/app.ini dump --help 2>&1
+   # Or check app.ini for WORK_PATH
+   cat /etc/gitea/app.ini | grep '^WORK_PATH'
+   ```
+
+### Phase 2 — Restore from Backup (20 min)
+
+4. Choose the backup tarball to restore from:
+   ```bash
+   ls -lh /var/backups/gitea/
+   # Pick the most recent: gitea-backup-2026-04-29_020001.tar.gz
+   ```
+
+5. **Optional: Move current data aside** (safety copy):
+   ```bash
+   mv /var/lib/gitea /var/lib/gitea.bak-$(date +%s)
+   ```
+
+6. Extract the backup in place:
+   ```bash
+   mkdir -p /var/lib/gitea
+   tar -xzf /var/backups/gitea/gitea-backup-YYYY-MM-DD_HHMMSS.tar.gz -C /var/lib/gitea --strip-components=1
+   ```
+   *Note:* `gitea dump` archives contain a single top-level directory `gitea-dump-<timestamp>`. The `--strip-components=1` puts its contents directly into `/var/lib/gitea`.
+
+7. Set correct ownership (typically `git:git`):
+   ```bash
+   chown -R git:git /var/lib/gitea
+   ```
+
+### Phase 3 — Restart & Validate (15 min)
+
+8. Start Gitea:
+   ```bash
+   systemctl start gitea
+   ```
+
+9. Wait 30 seconds, then verify:
+   ```bash
+   systemctl status gitea
+   # Check HTTP endpoint
+   curl -s -o /dev/null -w '%{http_code}' http://localhost:3000/  # Should be 200
+   ```
+
+10. Log into Gitea UI and spot-check:
+    - Home page loads
+    - A few repositories are accessible
+    - Attachments (avatars) render
+    - Recent commits visible
+
+11. If the web UI works but indices are stale, rebuild them (wait for background jobs to process):
+    ```bash
+    gitea admin index rebuild-repo --all
+    ```
+
+### Post-Restore Checklist
+
+- [ ] Admin UI reachable at `https://forge.alexanderwhitestone.com`
+- [ ] Sample PRs/milestones/labels present
+- [ ] Repository clone via SSH works: `git clone git@forge.alexanderwhitestone.com:Timmy_Foundation/timmy-config.git`
+- [ ] Check backup script health: `cat /var/log/gitea-backup.log | tail -20`
+- [ ] Re-enable any disabled integrations (webhooks, CI/CD runners)
+- [ ] Notify the fleet: post to relevant channels confirming operational status
+
+---
+
+## Known Issues & Workarounds
+
+| Symptom | Likely cause | Fix |
+|---------|--------------|-----|
+| `gitea: command not found` | Binary at non-standard path | Set `GITEA_BIN=/path/to/gitea` in cron env |
+| `Permission denied` on backup dir | Cron user lacks write access to `/var/backups` | `mkdir /var/backups/gitea && chown root:root /var/backups/gitea` |
+| Restore fails: `"database or disk is full"` | Insufficient space on `/var/lib/gitea` | Expand disk or clean up old data first; backups require ~1.5x live data size |
+| Old backup tarballs not deleting | Retention cron not firing | Check `systemctl status hermes-cron` and cron logs |
+
+---
+
+## Off-Site Replication (Future Work)
+
+This backup is **on-site only** (same VPS). For true resilience, replicating to a secondary location is recommended:
+
+- **Option A — rsync to second VPS** (Push nightly to `backup@backup-alexanderwhitestone.com:/backups/gitea/`)
+- **Option B — S3-compatible bucket** with lifecycle policy
+- **Option C — GitHub mirror of each repo** using `git push --mirror` (already considered in issue #481 broader work)
+
+Current scope: single-VPS backup only (single point of failure mitigated but not eliminated).
+
+---
+
+## Related Documentation
+
+- `bin/gitea-backup.sh` — backup script source
+- `cron/vps/gitea-daily-backup.yml` — Hermes cron definition
+- Gitea official docs: <https://docs.gitea.com/administration/backup-and-restore>
+- Hermes cron: <https://hermes-agent.nousresearch.com/docs>