feat(openclaw): upgrade fleet to DeepSeek V4.1 Flash 1017 and harden operations
- Upgrade OpenClaw primary model from deepseek-v4.1-flash to deepseek-v4.1-flash-1017 across all interactive agents, heartbeats, compaction, and cron jobs. - Configure hardened OpenRouter provider routing for 1017 (deepinfra, inference-net, parasail, cloudflare) with strict fp8/bf16 quantization and tool_choice verification. - Retain deepseek-v4.1-flash (0910), z-ai/glm-5.3-flash, and qwen3.8-flash in the automated fallback chain. - Update ADR 0002 with 1017 economics (30% price reduction on prompt/cache, +60% intelligence benchmark increase) and a 7-point provider qualification playbook. - Add operational scripts and tooling for session compaction, subagent vector deduplication, gateway preflight, and triage diagnostics in k8s/openclaw. - Update DuckDB backend engine, git-sync logic, and test suites. - Enhance Mila tracking UI components and add container build configuration. - Sync Terraform infrastructure state for Authentik.
This commit is contained in:
Moritz Graf
@@ -1,97 +1,97 @@
|
||||
#!/usr/bin/env python3
|
||||
import json, os, subprocess, sys, time, urllib.request
|
||||
#!/usr/bin/env python3
|
||||
import json, os, subprocess, sys, time, urllib.request
|
||||
|
||||
INTERRUPTED_FILE = "/tmp/openclaw-interrupted-turns.json"
|
||||
INTERRUPTED_FILE = "/tmp/openclaw-interrupted-turns.json"
|
||||
|
||||
if not os.path.exists(INTERRUPTED_FILE):
|
||||
sys.exit(0)
|
||||
if not os.path.exists(INTERRUPTED_FILE):
|
||||
sys.exit(0)
|
||||
|
||||
try:
|
||||
with open(INTERRUPTED_FILE, "r") as f:
|
||||
turns = json.load(f)
|
||||
except Exception as e:
|
||||
print(f"[replay_interrupted_turns] Failed to read {INTERRUPTED_FILE}: {e}", file=sys.stderr)
|
||||
sys.exit(0)
|
||||
try:
|
||||
with open(INTERRUPTED_FILE, "r") as f:
|
||||
turns = json.load(f)
|
||||
except Exception as e:
|
||||
print(f"[replay_interrupted_turns] Failed to read {INTERRUPTED_FILE}: {e}", file=sys.stderr)
|
||||
sys.exit(0)
|
||||
|
||||
if not turns:
|
||||
sys.exit(0)
|
||||
if not turns:
|
||||
sys.exit(0)
|
||||
|
||||
print(f"[replay_interrupted_turns] Found {len(turns)} interrupted turn(s). Waiting for gateway /healthz...")
|
||||
print(f"[replay_interrupted_turns] Found {len(turns)} interrupted turn(s). Waiting for gateway /healthz...")
|
||||
|
||||
gateway_ready = False
|
||||
for _ in range(60):
|
||||
try:
|
||||
with urllib.request.urlopen("http://127.0.0.1:18790/healthz", timeout=3) as resp:
|
||||
if resp.status == 200:
|
||||
gateway_ready = True
|
||||
break
|
||||
except Exception:
|
||||
pass
|
||||
time.sleep(2)
|
||||
gateway_ready = False
|
||||
for _ in range(60):
|
||||
try:
|
||||
with urllib.request.urlopen("http://127.0.0.1:18790/healthz", timeout=3) as resp:
|
||||
if resp.status == 200:
|
||||
gateway_ready = True
|
||||
break
|
||||
except Exception:
|
||||
pass
|
||||
time.sleep(2)
|
||||
|
||||
if not gateway_ready:
|
||||
print("[replay_interrupted_turns] Gateway did not become healthy in 120s. Aborting.", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
if not gateway_ready:
|
||||
print("[replay_interrupted_turns] Gateway did not become healthy in 120s. Aborting.", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
# Allow 5s for Telegram ingress to bind
|
||||
time.sleep(5)
|
||||
# Allow 5s for Telegram ingress to bind
|
||||
time.sleep(5)
|
||||
|
||||
for turn in turns:
|
||||
sk = turn.get("session_key")
|
||||
sid = turn.get("session_id")
|
||||
agent_id = turn.get("agent")
|
||||
ctx = turn.get("context") or {}
|
||||
prompt = turn.get("prompt") or ""
|
||||
|
||||
channel = ctx.get("channel") or "telegram"
|
||||
to_target = ctx.get("to") or ""
|
||||
thread_id = ctx.get("threadId")
|
||||
|
||||
target = to_target
|
||||
if target.startswith("telegram:"):
|
||||
parts = target.split(":")
|
||||
target = parts[1] if len(parts) > 1 else target
|
||||
for turn in turns:
|
||||
sk = turn.get("session_key")
|
||||
sid = turn.get("session_id")
|
||||
agent_id = turn.get("agent")
|
||||
ctx = turn.get("context") or {}
|
||||
prompt = turn.get("prompt") or ""
|
||||
|
||||
print(f"[replay_interrupted_turns] Processing agent '{agent_id}' on session '{sk}' target='{target}' thread='{thread_id}'")
|
||||
|
||||
# 1. Send status notification to Telegram if target exists
|
||||
if target:
|
||||
notice = "⚠️ OpenClaw wurde während der Bearbeitung neu gestartet – deine Anfrage wird jetzt nachgeholt..."
|
||||
notify_cmd = [
|
||||
"openclaw", "message", "send",
|
||||
"--channel", channel,
|
||||
"--target", str(target),
|
||||
"-m", notice
|
||||
]
|
||||
if thread_id is not None:
|
||||
notify_cmd.extend(["--thread-id", str(thread_id)])
|
||||
try:
|
||||
subprocess.run(notify_cmd, check=False, timeout=30)
|
||||
print(f"[replay_interrupted_turns] Sent recovery notice to {target}")
|
||||
except Exception as e:
|
||||
print(f"[replay_interrupted_turns] Notice failed: {e}", file=sys.stderr)
|
||||
channel = ctx.get("channel") or "telegram"
|
||||
to_target = ctx.get("to") or ""
|
||||
thread_id = ctx.get("threadId")
|
||||
|
||||
# 2. Replay agent turn
|
||||
if sk and prompt:
|
||||
p_short = (prompt[:60] + "...") if len(prompt) > 60 else prompt
|
||||
print(f"[replay_interrupted_turns] Replaying agent turn: {p_short}")
|
||||
agent_cmd = [
|
||||
"openclaw", "agent",
|
||||
"--session-key", sk,
|
||||
"-m", prompt,
|
||||
"--deliver"
|
||||
]
|
||||
try:
|
||||
res = subprocess.run(agent_cmd, capture_output=True, text=True, timeout=300)
|
||||
if res.returncode == 0:
|
||||
print(f"[replay_interrupted_turns] Turn replay succeeded for {sk}")
|
||||
else:
|
||||
print(f"[replay_interrupted_turns] Turn replay exited with code {res.returncode}: {res.stderr[:200]}", file=sys.stderr)
|
||||
except Exception as e:
|
||||
print(f"[replay_interrupted_turns] Replay execution error: {e}", file=sys.stderr)
|
||||
target = to_target
|
||||
if target.startswith("telegram:"):
|
||||
parts = target.split(":")
|
||||
target = parts[1] if len(parts) > 1 else target
|
||||
|
||||
try:
|
||||
os.remove(INTERRUPTED_FILE)
|
||||
print(f"[replay_interrupted_turns] Cleaned up {INTERRUPTED_FILE}")
|
||||
except Exception:
|
||||
pass
|
||||
print(f"[replay_interrupted_turns] Processing agent '{agent_id}' on session '{sk}' target='{target}' thread='{thread_id}'")
|
||||
|
||||
# 1. Send status notification to Telegram if target exists
|
||||
if target:
|
||||
notice = "⚠️ OpenClaw wurde während der Bearbeitung neu gestartet – deine Anfrage wird jetzt nachgeholt..."
|
||||
notify_cmd = [
|
||||
"openclaw", "message", "send",
|
||||
"--channel", channel,
|
||||
"--target", str(target),
|
||||
"-m", notice
|
||||
]
|
||||
if thread_id is not None:
|
||||
notify_cmd.extend(["--thread-id", str(thread_id)])
|
||||
try:
|
||||
subprocess.run(notify_cmd, check=False, timeout=30)
|
||||
print(f"[replay_interrupted_turns] Sent recovery notice to {target}")
|
||||
except Exception as e:
|
||||
print(f"[replay_interrupted_turns] Notice failed: {e}", file=sys.stderr)
|
||||
|
||||
# 2. Replay agent turn
|
||||
if sk and prompt:
|
||||
p_short = (prompt[:60] + "...") if len(prompt) > 60 else prompt
|
||||
print(f"[replay_interrupted_turns] Replaying agent turn: {p_short}")
|
||||
agent_cmd = [
|
||||
"openclaw", "agent",
|
||||
"--session-key", sk,
|
||||
"-m", prompt,
|
||||
"--deliver"
|
||||
]
|
||||
try:
|
||||
res = subprocess.run(agent_cmd, capture_output=True, text=True, timeout=300)
|
||||
if res.returncode == 0:
|
||||
print(f"[replay_interrupted_turns] Turn replay succeeded for {sk}")
|
||||
else:
|
||||
print(f"[replay_interrupted_turns] Turn replay exited with code {res.returncode}: {res.stderr[:200]}", file=sys.stderr)
|
||||
except Exception as e:
|
||||
print(f"[replay_interrupted_turns] Replay execution error: {e}", file=sys.stderr)
|
||||
|
||||
try:
|
||||
os.remove(INTERRUPTED_FILE)
|
||||
print(f"[replay_interrupted_turns] Cleaned up {INTERRUPTED_FILE}")
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
Reference in New Issue
Block a user