Initial: Mesh-Configs vom 03.09.2026 01:23
This commit is contained in:
root
@@ -0,0 +1,162 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
daily_model_check.py
|
||||
|
||||
Ebene 1 des Skills: läuft 1x täglich (Cron), baut die grobe
|
||||
Modell-Prioritätsliste pro Agent und schreibt sie nach
|
||||
state/model_priority.json.
|
||||
|
||||
Nutzt aktuell Mock-Daten (mock_data.py). Für den Wechsel auf die
|
||||
echte OpenRouter-API muss nur fetch_model_list() in mock_data.py
|
||||
ersetzt werden - dieses Script bleibt unverändert.
|
||||
|
||||
Aufruf:
|
||||
python3 daily_model_check.py
|
||||
"""
|
||||
|
||||
import json
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
import yaml
|
||||
|
||||
sys.path.insert(0, str(Path(__file__).parent))
|
||||
from mock_data import fetch_model_list, fetch_timestamp # noqa: E402
|
||||
|
||||
CONFIG_PATH = Path(__file__).parent.parent / "config" / "agents.yaml"
|
||||
STATE_DIR = Path(__file__).parent.parent / "state"
|
||||
OUTPUT_PATH = STATE_DIR / "model_priority.json"
|
||||
|
||||
|
||||
def load_config():
|
||||
with open(CONFIG_PATH, "r", encoding="utf-8") as f:
|
||||
return yaml.safe_load(f)
|
||||
|
||||
|
||||
def index_models_by_id(models):
|
||||
return {m["id"]: m for m in models}
|
||||
|
||||
|
||||
def build_agent_priority(agent_name, agent_cfg, models_by_id, min_context, max_escalation_factor):
|
||||
"""Baut die Eskalationsleiter für einen Agent, gefiltert nach
|
||||
Mindest-Kontext und verfügbaren/bekannten Modellen.
|
||||
"""
|
||||
ladder = []
|
||||
warnings = []
|
||||
|
||||
for step_idx, step in enumerate(agent_cfg["escalation_ladder"]):
|
||||
model_id = step["model"]
|
||||
cost_factor = step["cost_factor"]
|
||||
|
||||
# Free-Tier-Router-Strings wie "openrouter/free" stehen nicht in
|
||||
# der Modell-Liste selbst - die werden unverändert übernommen.
|
||||
if model_id not in models_by_id:
|
||||
if model_id.startswith("openrouter/"):
|
||||
ladder.append({"model": model_id, "cost_factor": cost_factor, "note": "auto-router, nicht einzeln geprüft"})
|
||||
continue
|
||||
warnings.append(f"{agent_name}: Modell '{model_id}' nicht in aktueller Modell-Liste gefunden - übersprungen")
|
||||
continue
|
||||
|
||||
model = models_by_id[model_id]
|
||||
|
||||
if not model.get("available", True):
|
||||
warnings.append(f"{agent_name}: Modell '{model_id}' aktuell nicht verfügbar - übersprungen")
|
||||
continue
|
||||
|
||||
if model["context_length"] < min_context:
|
||||
warnings.append(
|
||||
f"{agent_name}: Modell '{model_id}' hat nur {model['context_length']} Kontext, "
|
||||
f"unter Minimum von {min_context} - übersprungen"
|
||||
)
|
||||
continue
|
||||
|
||||
# Verhältnismäßigkeits-Check: Stufen jenseits von Stufe 0 dürfen
|
||||
# den max_auto_escalation_factor nicht überschreiten, sonst braucht's
|
||||
# manual_override.
|
||||
if step_idx > 0 and cost_factor > max_escalation_factor and not agent_cfg.get("manual_override_allowed", False):
|
||||
warnings.append(
|
||||
f"{agent_name}: Eskalationsstufe '{model_id}' hat Faktor {cost_factor}x, "
|
||||
f"über dem erlaubten Automatik-Limit von {max_escalation_factor}x - "
|
||||
f"nur per manual_override nutzbar, aus Automatik-Leiter entfernt"
|
||||
)
|
||||
continue
|
||||
|
||||
ladder.append({
|
||||
"model": model_id,
|
||||
"cost_factor": cost_factor,
|
||||
"context_length": model["context_length"],
|
||||
"price_per_1k_tokens_eur": model["price_per_1k_tokens_eur"],
|
||||
"family": model["family"],
|
||||
})
|
||||
|
||||
return ladder, warnings
|
||||
|
||||
|
||||
def check_diversity(priority_by_agent, min_distinct_families):
|
||||
families_in_use = set()
|
||||
for agent_name, ladder in priority_by_agent.items():
|
||||
for step in ladder:
|
||||
if "family" in step:
|
||||
families_in_use.add(step["family"])
|
||||
|
||||
diverse_enough = len(families_in_use) >= min_distinct_families
|
||||
return diverse_enough, sorted(families_in_use)
|
||||
|
||||
|
||||
def main():
|
||||
config = load_config()
|
||||
global_cfg = config["global"]
|
||||
min_context = global_cfg["min_context_tokens"]
|
||||
max_escalation_factor = global_cfg["max_auto_escalation_factor"]
|
||||
min_distinct_families = global_cfg["min_distinct_model_families"]
|
||||
|
||||
models = fetch_model_list()
|
||||
models_by_id = index_models_by_id(models)
|
||||
|
||||
priority_by_agent = {}
|
||||
all_warnings = []
|
||||
|
||||
for agent_name, agent_cfg in config["agents"].items():
|
||||
ladder, warnings = build_agent_priority(
|
||||
agent_name, agent_cfg, models_by_id, min_context, max_escalation_factor
|
||||
)
|
||||
priority_by_agent[agent_name] = ladder
|
||||
all_warnings.extend(warnings)
|
||||
|
||||
if not ladder:
|
||||
all_warnings.append(
|
||||
f"WARNUNG: Agent '{agent_name}' hat NACH Filterung keine nutzbaren Modelle mehr - "
|
||||
f"lokaler Fallback sollte hier greifen"
|
||||
)
|
||||
|
||||
diverse_enough, families_in_use = check_diversity(priority_by_agent, min_distinct_families)
|
||||
if not diverse_enough:
|
||||
all_warnings.append(
|
||||
f"WARNUNG: Nur {len(families_in_use)} Modell-Familien im Einsatz "
|
||||
f"({', '.join(families_in_use)}), Minimum wäre {min_distinct_families}"
|
||||
)
|
||||
|
||||
output = {
|
||||
"generated_at": fetch_timestamp(),
|
||||
"min_context_tokens": min_context,
|
||||
"max_auto_escalation_factor": max_escalation_factor,
|
||||
"diversity_ok": diverse_enough,
|
||||
"model_families_in_use": families_in_use,
|
||||
"agents": priority_by_agent,
|
||||
"local_fallback": config["local_fallback"],
|
||||
"warnings": all_warnings,
|
||||
}
|
||||
|
||||
STATE_DIR.mkdir(exist_ok=True)
|
||||
with open(OUTPUT_PATH, "w", encoding="utf-8") as f:
|
||||
json.dump(output, f, indent=2, ensure_ascii=False)
|
||||
|
||||
print(f"Prioritätsliste geschrieben nach {OUTPUT_PATH}")
|
||||
if all_warnings:
|
||||
print(f"\n{len(all_warnings)} Warnung(en):")
|
||||
for w in all_warnings:
|
||||
print(f" - {w}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -0,0 +1,114 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
hourly_finetune_check.py
|
||||
|
||||
Ebene 2 des Skills: läuft stündlich (oder öfter), prüft NUR Deltas
|
||||
gegen die von daily_model_check.py gebaute Prioritätsliste:
|
||||
|
||||
- Ist ein Agent über sein Tagesbudget (hard_stop_eur_per_day)?
|
||||
-> Kill-Switch: Agent wird auf lokalen Fallback gezwungen.
|
||||
- Wurde ein Modell inzwischen als nicht mehr verfügbar gemeldet?
|
||||
-> Wird aus der aktiven Leiter entfernt (bis zum nächsten Tages-Lauf).
|
||||
|
||||
Erwartet, dass der jeweilige Agent selbst fortlaufend seinen
|
||||
Tagesverbrauch nach state/spend_today.json schreibt, Format:
|
||||
{ "agent_a": 0.42, "agent_b": 1.10, ... }
|
||||
|
||||
Falls diese Datei fehlt (z.B. noch nicht angebunden), läuft der Check
|
||||
trotzdem durch und markiert das als Hinweis statt Fehler.
|
||||
|
||||
Aufruf:
|
||||
python3 hourly_finetune_check.py
|
||||
"""
|
||||
|
||||
import json
|
||||
from pathlib import Path
|
||||
|
||||
import yaml
|
||||
|
||||
CONFIG_PATH = Path(__file__).parent.parent / "config" / "agents.yaml"
|
||||
STATE_DIR = Path(__file__).parent.parent / "state"
|
||||
PRIORITY_PATH = STATE_DIR / "model_priority.json"
|
||||
SPEND_PATH = STATE_DIR / "spend_today.json"
|
||||
KILL_SWITCH_PATH = STATE_DIR / "kill_switches.json"
|
||||
|
||||
|
||||
def load_config():
|
||||
with open(CONFIG_PATH, "r", encoding="utf-8") as f:
|
||||
return yaml.safe_load(f)
|
||||
|
||||
|
||||
def load_priority():
|
||||
if not PRIORITY_PATH.exists():
|
||||
raise FileNotFoundError(
|
||||
f"{PRIORITY_PATH} fehlt - bitte zuerst daily_model_check.py laufen lassen"
|
||||
)
|
||||
with open(PRIORITY_PATH, "r", encoding="utf-8") as f:
|
||||
return json.load(f)
|
||||
|
||||
|
||||
def load_spend():
|
||||
if not SPEND_PATH.exists():
|
||||
return {}, ["spend_today.json fehlt noch - Budget-Check übersprungen, bitte Anbindung nachholen"]
|
||||
with open(SPEND_PATH, "r", encoding="utf-8") as f:
|
||||
return json.load(f), []
|
||||
|
||||
|
||||
def check_budgets(config, spend):
|
||||
kill_switches = {}
|
||||
notes = []
|
||||
|
||||
for agent_name, agent_cfg in config["agents"].items():
|
||||
limit = agent_cfg.get("hard_stop_eur_per_day")
|
||||
spent = spend.get(agent_name)
|
||||
|
||||
if spent is None:
|
||||
continue
|
||||
|
||||
if limit is None or limit == "BUDGET_PLACEHOLDER":
|
||||
notes.append(
|
||||
f"{agent_name}: hard_stop_eur_per_day ist noch Platzhalter - "
|
||||
f"kein Kill-Switch aktiv, bitte echten Wert eintragen"
|
||||
)
|
||||
continue
|
||||
|
||||
if spent >= float(limit):
|
||||
kill_switches[agent_name] = {
|
||||
"reason": "daily_budget_exceeded",
|
||||
"spent_eur": spent,
|
||||
"limit_eur": limit,
|
||||
"action": "postpone_to_next_day",
|
||||
"basic_questions_fallback": "vps_ollama",
|
||||
}
|
||||
notes.append(
|
||||
f"KILL-SWITCH: {agent_name} hat {spent}€ von {limit}€ Tageslimit erreicht - "
|
||||
f"restliche Tasks werden auf morgen verschoben. Grundfragen laufen bis dahin "
|
||||
f"weiter über das lokale VPS-Ollama-Modell, sofern das inhaltlich passt."
|
||||
)
|
||||
|
||||
return kill_switches, notes
|
||||
|
||||
|
||||
def main():
|
||||
config = load_config()
|
||||
priority = load_priority()
|
||||
spend, spend_notes = load_spend()
|
||||
|
||||
kill_switches, budget_notes = check_budgets(config, spend)
|
||||
|
||||
result = {
|
||||
"checked_at": priority.get("generated_at"),
|
||||
"kill_switches": kill_switches,
|
||||
"notes": spend_notes + budget_notes,
|
||||
}
|
||||
|
||||
with open(KILL_SWITCH_PATH, "w", encoding="utf-8") as f:
|
||||
json.dump(result, f, indent=2, ensure_ascii=False)
|
||||
|
||||
print(f"Feintuning-Check abgeschlossen, Ergebnis in {KILL_SWITCH_PATH}")
|
||||
for note in result["notes"]:
|
||||
print(f" - {note}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -0,0 +1,104 @@
|
||||
"""
|
||||
Mock-Datenquelle für die OpenRouter-Modell-Liste.
|
||||
|
||||
Diese Funktion hat exakt die Signatur, die auch der echte API-Call später
|
||||
haben wird (siehe TODO), damit daily_model_check.py unverändert bleibt,
|
||||
wenn die echte API eingehängt wird.
|
||||
|
||||
TODO (später, wenn echte API gewünscht):
|
||||
import requests
|
||||
def fetch_model_list():
|
||||
resp = requests.get(
|
||||
"https://openrouter.ai/api/v1/models",
|
||||
headers={"Authorization": f"Bearer {OPENROUTER_API_KEY}"},
|
||||
timeout=10,
|
||||
)
|
||||
resp.raise_for_status()
|
||||
return resp.json()["data"]
|
||||
"""
|
||||
|
||||
from datetime import datetime, timezone
|
||||
|
||||
|
||||
def fetch_model_list():
|
||||
"""Gibt eine Liste von Modell-Dicts zurück, im gleichen Format wie
|
||||
die echte OpenRouter-API (vereinfacht auf die Felder, die wir brauchen).
|
||||
"""
|
||||
return [
|
||||
{
|
||||
"id": "nvidia/nemotron-3-super",
|
||||
"context_length": 262000,
|
||||
"price_per_1k_tokens_eur": 0.0009,
|
||||
"family": "nemotron",
|
||||
"tags": ["linux_system", "allround"],
|
||||
"available": True,
|
||||
},
|
||||
{
|
||||
"id": "nvidia/nemotron-3-ultra",
|
||||
"context_length": 1000000,
|
||||
"price_per_1k_tokens_eur": 0.0027,
|
||||
"family": "nemotron",
|
||||
"tags": ["linux_system", "allround", "orchestration"],
|
||||
"available": True,
|
||||
},
|
||||
{
|
||||
"id": "deepseek/deepseek-flash",
|
||||
"context_length": 128000,
|
||||
"price_per_1k_tokens_eur": 0.0006,
|
||||
"family": "deepseek",
|
||||
"tags": ["code", "logic", "database"],
|
||||
"available": True,
|
||||
},
|
||||
{
|
||||
"id": "deepseek/deepseek-pro",
|
||||
"context_length": 128000,
|
||||
"price_per_1k_tokens_eur": 0.0018,
|
||||
"family": "deepseek",
|
||||
"tags": ["code", "logic", "database"],
|
||||
"available": True,
|
||||
},
|
||||
{
|
||||
"id": "qwen/qwen3-coder:free",
|
||||
"context_length": 1000000,
|
||||
"price_per_1k_tokens_eur": 0.0,
|
||||
"family": "qwen",
|
||||
"tags": ["homebrew_code", "prompt_generation", "code"],
|
||||
"available": True,
|
||||
},
|
||||
{
|
||||
"id": "qwen/qwen2.5-7b",
|
||||
"context_length": 128000,
|
||||
"price_per_1k_tokens_eur": 0.0003,
|
||||
"family": "qwen",
|
||||
"tags": ["javascript", "database_query"],
|
||||
"available": True,
|
||||
},
|
||||
{
|
||||
"id": "google/gemini-flash",
|
||||
"context_length": 1000000,
|
||||
"price_per_1k_tokens_eur": 0.0004,
|
||||
"family": "gemini",
|
||||
"tags": ["document_generation", "html_css_js"],
|
||||
"available": True,
|
||||
},
|
||||
{
|
||||
"id": "anthropic/claude-sonnet",
|
||||
"context_length": 200000,
|
||||
"price_per_1k_tokens_eur": 0.0045,
|
||||
"family": "anthropic",
|
||||
"tags": ["document_generation", "html_css_js", "allround"],
|
||||
"available": True,
|
||||
},
|
||||
{
|
||||
"id": "anthropic/claude-opus",
|
||||
"context_length": 200000,
|
||||
"price_per_1k_tokens_eur": 0.0900,
|
||||
"family": "anthropic",
|
||||
"tags": ["document_generation", "html_css_js", "allround"],
|
||||
"available": True,
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
def fetch_timestamp():
|
||||
return datetime.now(timezone.utc).isoformat()
|
||||
@@ -0,0 +1,132 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
task_agent_matcher.py
|
||||
|
||||
Ebene 3 des Skills: läuft bei Agent A (Master) zur Laufzeit, sobald ein
|
||||
neuer Task ansteht. Entscheidet, welcher Agent bei welchem Standard-Modell
|
||||
am besten zum Task-Typ passt - basierend auf:
|
||||
|
||||
- der von daily_model_check.py gebauten Prioritätsliste
|
||||
(state/model_priority.json)
|
||||
- aktiven Kill-Switches (state/kill_switches.json), z.B. wegen
|
||||
Budget-Überschreitung -> Agent wird übersprungen bzw. auf
|
||||
"postpone_to_next_day" gesetzt
|
||||
- den Capability-Tags pro Agent (config/agents.yaml)
|
||||
|
||||
Jeder Agent bekommt exakt dieses Konzept (Config + Prioritätsliste)
|
||||
mitgeliefert, damit alle konsistent nach derselben Logik laufen, egal
|
||||
wer die Entscheidung am Ende ausführt.
|
||||
|
||||
Aufruf (Beispiel):
|
||||
python3 task_agent_matcher.py --task-tag javascript
|
||||
python3 task_agent_matcher.py --task-tag homebrew_code
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import json
|
||||
from pathlib import Path
|
||||
|
||||
import yaml
|
||||
|
||||
CONFIG_PATH = Path(__file__).parent.parent / "config" / "agents.yaml"
|
||||
STATE_DIR = Path(__file__).parent.parent / "state"
|
||||
PRIORITY_PATH = STATE_DIR / "model_priority.json"
|
||||
KILL_SWITCH_PATH = STATE_DIR / "kill_switches.json"
|
||||
|
||||
|
||||
def load_yaml(path):
|
||||
with open(path, "r", encoding="utf-8") as f:
|
||||
return yaml.safe_load(f)
|
||||
|
||||
|
||||
def load_json(path, default=None):
|
||||
if not path.exists():
|
||||
return default if default is not None else {}
|
||||
with open(path, "r", encoding="utf-8") as f:
|
||||
return json.load(f)
|
||||
|
||||
|
||||
def find_matches(task_tag, config, priority, kill_switches):
|
||||
"""Gibt eine nach Preis sortierte Liste von (agent, model, price) für
|
||||
Agents zurück, deren Capability-Tags zum Task-Typ passen und die
|
||||
NICHT gerade per Kill-Switch auf 'postpone_to_next_day' stehen.
|
||||
"""
|
||||
candidates = []
|
||||
postponed = []
|
||||
|
||||
for agent_name, agent_cfg in config["agents"].items():
|
||||
if task_tag not in agent_cfg.get("capability_tags", []):
|
||||
continue
|
||||
|
||||
if agent_name in kill_switches.get("kill_switches", {}):
|
||||
ks = kill_switches["kill_switches"][agent_name]
|
||||
postponed.append({
|
||||
"agent": agent_name,
|
||||
"reason": ks["reason"],
|
||||
"action": ks["action"],
|
||||
"fallback": ks.get("basic_questions_fallback"),
|
||||
})
|
||||
continue
|
||||
|
||||
ladder = priority.get("agents", {}).get(agent_name, [])
|
||||
for step in ladder:
|
||||
candidates.append({
|
||||
"agent": agent_name,
|
||||
"model": step["model"],
|
||||
"cost_factor": step.get("cost_factor"),
|
||||
"price_per_1k_tokens_eur": step.get("price_per_1k_tokens_eur"),
|
||||
})
|
||||
|
||||
# Günstigste zuerst; Steps ohne Preisangabe (z.B. Free-Router) ganz vorne
|
||||
candidates.sort(key=lambda c: (c["price_per_1k_tokens_eur"] is not None, c.get("price_per_1k_tokens_eur") or 0))
|
||||
|
||||
return candidates, postponed
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(description="Task-zu-Agent-Matching (Ebene 3)")
|
||||
parser.add_argument("--task-tag", required=True, help="Capability-Tag des Tasks, z.B. javascript, homebrew_code")
|
||||
args = parser.parse_args()
|
||||
|
||||
config = load_yaml(CONFIG_PATH)
|
||||
priority = load_json(PRIORITY_PATH)
|
||||
kill_switches = load_json(KILL_SWITCH_PATH)
|
||||
|
||||
if not priority:
|
||||
print("FEHLER: state/model_priority.json fehlt - bitte zuerst daily_model_check.py laufen lassen")
|
||||
return
|
||||
|
||||
candidates, postponed = find_matches(args.task_tag, config, priority, kill_switches)
|
||||
|
||||
if not candidates:
|
||||
local_fb = config.get("local_fallback", {})
|
||||
if args.task_tag in local_fb.get("allowed_for_task_tags", []):
|
||||
print(f"Kein Cloud-Kandidat für '{args.task_tag}' verfügbar (evtl. alle betroffenen Agents "
|
||||
f"per Kill-Switch verschoben) - lokaler Fallback erlaubt:")
|
||||
print(f" -> {local_fb['model']} (kostenfrei, VPS-Ollama)")
|
||||
else:
|
||||
print(f"Kein Kandidat für '{args.task_tag}' verfügbar und lokaler Fallback für diesen "
|
||||
f"Task-Typ NICHT erlaubt (siehe config: local_fallback.allowed_for_task_tags). "
|
||||
f"Task sollte pausiert werden.")
|
||||
for p in postponed:
|
||||
print(f" (verschoben: {p['agent']} - {p['reason']}, Fallback: {p['fallback']})")
|
||||
return
|
||||
|
||||
best = candidates[0]
|
||||
print(f"Beste Wahl für Task-Tag '{args.task_tag}':")
|
||||
print(f" Agent: {best['agent']}")
|
||||
print(f" Modell: {best['model']} (Kostenfaktor {best['cost_factor']}x)")
|
||||
|
||||
if len(candidates) > 1:
|
||||
print("\nWeitere passende Kandidaten (Eskalationsreserve):")
|
||||
for c in candidates[1:]:
|
||||
print(f" - {c['agent']} / {c['model']} (Faktor {c['cost_factor']}x)")
|
||||
|
||||
if postponed:
|
||||
print("\nHinweis, folgende Agents sind aktuell wegen Budget verschoben:")
|
||||
for p in postponed:
|
||||
print(f" - {p['agent']}: {p['reason']} -> {p['action']} (Grundfragen: {p['fallback']})")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
Reference in New Issue
Block a user