Compare commits
13 Commits
feat/601-m
...
fix/690
| Author | SHA1 | Date | |
|---|---|---|---|
| fdacbf5e78 | |||
| 60c3838c2b | |||
| 9251ffc4b5 | |||
| d120526244 | |||
| 8596ff761b | |||
| 7553fd4f3e | |||
| 71082fe06f | |||
| 6d678e938e | |||
| ad751a6de6 | |||
| 130fa40f0c | |||
| 82f9810081 | |||
| 2548277137 | |||
| 2b234fde79 |
@@ -1,3 +1,4 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Full Nostr agent-to-agent communication demo - FINAL WORKING
|
||||
"""
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Soul Eval Gate — The Conscience of the Training Pipeline
|
||||
|
||||
|
||||
83
bin/validate_config.py
Normal file
83
bin/validate_config.py
Normal file
@@ -0,0 +1,83 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Config Validator -- pre-deploy YAML validation for timmy-config sidecar.
|
||||
|
||||
Validates YAML syntax, required keys (model.default, model.provider,
|
||||
toolsets), and provider names before deploy.sh writes to ~/.hermes/.
|
||||
|
||||
Usage:
|
||||
python3 bin/validate_config.py [path/to/config.yaml]
|
||||
python3 bin/validate_config.py --strict (fail on warnings too)
|
||||
"""
|
||||
import json, os, sys, yaml
|
||||
from pathlib import Path
|
||||
|
||||
REQUIRED = {
|
||||
"model": {"type": dict, "keys": {"default": str, "provider": str}},
|
||||
"toolsets": {"type": list},
|
||||
}
|
||||
ALLOWED_PROVIDERS = [
|
||||
"anthropic", "openai", "nous", "ollama", "openrouter", "openai-codex"
|
||||
]
|
||||
|
||||
def validate(path):
|
||||
errors = []
|
||||
try:
|
||||
with open(path) as f:
|
||||
data = yaml.safe_load(f)
|
||||
except Exception as e:
|
||||
return [f"YAML parse error: {e}"]
|
||||
if not isinstance(data, dict):
|
||||
return [f"Expected mapping, got {type(data).__name__}"]
|
||||
|
||||
for key, spec in REQUIRED.items():
|
||||
if key not in data:
|
||||
errors.append(f"Required key missing: {key}")
|
||||
continue
|
||||
if spec["type"] == dict and not isinstance(data[key], dict):
|
||||
errors.append(f"{key}: expected dict")
|
||||
continue
|
||||
if spec["type"] == list and not isinstance(data[key], list):
|
||||
errors.append(f"{key}: expected list")
|
||||
continue
|
||||
if "keys" in spec:
|
||||
for sub, sub_type in spec["keys"].items():
|
||||
if sub not in data[key]:
|
||||
errors.append(f"{key}.{sub}: required")
|
||||
elif not isinstance(data[key][sub], sub_type):
|
||||
errors.append(f"{key}.{sub}: expected {sub_type.__name__}")
|
||||
|
||||
provider = data.get("model", {}).get("provider")
|
||||
if provider and provider not in ALLOWED_PROVIDERS:
|
||||
errors.append(f"model.provider: unknown provider '{provider}'")
|
||||
|
||||
# Check JSON files
|
||||
for jf in ["channel_directory.json"]:
|
||||
jp = Path(path).parent / jf
|
||||
if jp.exists():
|
||||
try:
|
||||
json.loads(jp.read_text())
|
||||
except Exception as e:
|
||||
errors.append(f"{jf}: invalid JSON: {e}")
|
||||
|
||||
return errors
|
||||
|
||||
def main():
|
||||
strict = "--strict" in sys.argv
|
||||
args = [a for a in sys.argv[1:] if not a.startswith("--")]
|
||||
path = args[0] if args else str(Path(__file__).parent.parent / "config.yaml")
|
||||
|
||||
if not os.path.exists(path):
|
||||
print(f"ERROR: {path} not found")
|
||||
sys.exit(1)
|
||||
|
||||
errs = validate(path)
|
||||
if errs:
|
||||
for e in errs:
|
||||
print(f"ERROR: {e}")
|
||||
print(f"Validation FAILED: {len(errs)} issue(s)")
|
||||
sys.exit(1)
|
||||
print(f"OK: {path} is valid")
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
9
cron/pipeline-scheduler.yml
Normal file
9
cron/pipeline-scheduler.yml
Normal file
@@ -0,0 +1,9 @@
|
||||
- name: Nightly Pipeline Scheduler
|
||||
schedule: '*/30 18-23,0-8 * * *' # Every 30 min, off-peak hours only
|
||||
tasks:
|
||||
- name: Check and start pipelines
|
||||
shell: "bash scripts/nightly-pipeline-scheduler.sh"
|
||||
env:
|
||||
PIPELINE_TOKEN_LIMIT: "500000"
|
||||
PIPELINE_PEAK_START: "9"
|
||||
PIPELINE_PEAK_END: "18"
|
||||
@@ -1,3 +1,4 @@
|
||||
#!/usr/bin/env python3
|
||||
import json
|
||||
from hermes_tools import browser_navigate, browser_vision
|
||||
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
#!/usr/bin/env python3
|
||||
import json
|
||||
from hermes_tools import browser_navigate, browser_vision
|
||||
|
||||
|
||||
50
scripts/nightly-pipeline-scheduler.md
Normal file
50
scripts/nightly-pipeline-scheduler.md
Normal file
@@ -0,0 +1,50 @@
|
||||
# Nightly Pipeline Scheduler
|
||||
|
||||
Auto-starts batch pipelines when inference is available.
|
||||
|
||||
## What It Does
|
||||
|
||||
1. Checks inference provider health (OpenRouter, Ollama, RunPod)
|
||||
2. Checks if it's off-peak hours (configurable, default: after 6PM)
|
||||
3. Checks interactive session load (don't fight with live users)
|
||||
4. Checks daily token budget (configurable limit)
|
||||
5. Starts the highest-priority incomplete pipeline
|
||||
|
||||
## Pipeline Priority Order
|
||||
|
||||
| Priority | Pipeline | Deps | Max Tokens |
|
||||
|----------|----------|------|------------|
|
||||
| 1 | playground-factory | none | 100,000 |
|
||||
| 2 | training-factory | none | 150,000 |
|
||||
| 3 | knowledge-mine | training-factory running | 80,000 |
|
||||
| 4 | adversary | knowledge-mine running | 50,000 |
|
||||
| 5 | codebase-genome | none | 120,000 |
|
||||
|
||||
## Usage
|
||||
|
||||
```bash
|
||||
# Normal run (used by cron)
|
||||
./scripts/nightly-pipeline-scheduler.sh
|
||||
|
||||
# Dry run (show what would start)
|
||||
./scripts/nightly-pipeline-scheduler.sh --dry-run
|
||||
|
||||
# Status report
|
||||
./scripts/nightly-pipeline-scheduler.sh --status
|
||||
|
||||
# Force start during peak hours
|
||||
./scripts/nightly-pipeline-scheduler.sh --force
|
||||
```
|
||||
|
||||
## Configuration
|
||||
|
||||
Set via environment variables:
|
||||
- `PIPELINE_TOKEN_LIMIT`: Daily token budget (default: 500,000)
|
||||
- `PIPELINE_PEAK_START`: Peak hours start (default: 9)
|
||||
- `PIPELINE_PEAK_END`: Peak hours end (default: 18)
|
||||
- `HERMES_HOME`: Hermes home directory (default: ~/.hermes)
|
||||
|
||||
## Cron
|
||||
|
||||
Runs every 30 minutes. Off-peak only (unless --force).
|
||||
See `cron/pipeline-scheduler.yml`.
|
||||
383
scripts/nightly-pipeline-scheduler.sh
Normal file
383
scripts/nightly-pipeline-scheduler.sh
Normal file
@@ -0,0 +1,383 @@
|
||||
#!/usr/bin/env bash
|
||||
# nightly-pipeline-scheduler.sh — Auto-start batch pipelines when inference is available.
|
||||
#
|
||||
# Checks provider health, pipeline progress, token budget, and interactive load.
|
||||
# Starts the highest-priority incomplete pipeline that can run.
|
||||
#
|
||||
# Usage:
|
||||
# ./scripts/nightly-pipeline-scheduler.sh # Normal run
|
||||
# ./scripts/nightly-pipeline-scheduler.sh --dry-run # Show what would start
|
||||
# ./scripts/nightly-pipeline-scheduler.sh --status # Pipeline status report
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
# --- Configuration ---
|
||||
HERMES_HOME="${HERMES_HOME:-$HOME/.hermes}"
|
||||
BUDGET_FILE="${HERMES_HOME}/pipeline_budget.json"
|
||||
STATE_FILE="${HERMES_HOME}/pipeline_state.json"
|
||||
LOG_FILE="${HERMES_HOME}/logs/pipeline-scheduler.log"
|
||||
TOKEN_DAILY_LIMIT="${PIPELINE_TOKEN_LIMIT:-500000}"
|
||||
PEAK_HOURS_START="${PIPELINE_PEAK_START:-9}"
|
||||
PEAK_HOURS_END="${PIPELINE_PEAK_END:-18}"
|
||||
|
||||
# Pipeline definitions (priority order)
|
||||
# Each pipeline: name, script, max_tokens, dependencies
|
||||
PIPELINES=(
|
||||
"playground-factory|scripts/pipeline_playground_factory.sh|100000|none"
|
||||
"training-factory|scripts/pipeline_training_factory.sh|150000|none"
|
||||
"knowledge-mine|scripts/pipeline_knowledge_mine.sh|80000|training-factory"
|
||||
"adversary|scripts/pipeline_adversary.sh|50000|knowledge-mine"
|
||||
"codebase-genome|scripts/pipeline_codebase_genome.sh|120000|none"
|
||||
)
|
||||
|
||||
# --- Colors ---
|
||||
RED='\033[0;31m'
|
||||
GREEN='\033[0;32m'
|
||||
YELLOW='\033[0;33m'
|
||||
CYAN='\033[0;36m'
|
||||
NC='\033[0m'
|
||||
|
||||
# --- Helpers ---
|
||||
now_hour() { date +%-H; }
|
||||
is_peak_hours() {
|
||||
local h=$(now_hour)
|
||||
[[ $h -ge $PEAK_HOURS_START && $h -lt $PEAK_HOURS_END ]]
|
||||
}
|
||||
|
||||
ensure_dirs() {
|
||||
mkdir -p "$(dirname "$LOG_FILE")" "$(dirname "$BUDGET_FILE")" "$(dirname "$STATE_FILE")"
|
||||
}
|
||||
|
||||
log() { echo "[$(date '+%Y-%m-%d %H:%M:%S')] $*" | tee -a "$LOG_FILE"; }
|
||||
|
||||
get_budget_used_today() {
|
||||
if [[ -f "$BUDGET_FILE" ]]; then
|
||||
local today=$(date +%Y-%m-%d)
|
||||
python3 -c "
|
||||
import json, sys
|
||||
with open('$BUDGET_FILE') as f:
|
||||
d = json.load(f)
|
||||
print(d.get('daily', {}).get('$today', {}).get('tokens_used', 0))
|
||||
" 2>/dev/null || echo 0
|
||||
else
|
||||
echo 0
|
||||
fi
|
||||
}
|
||||
|
||||
get_budget_remaining() {
|
||||
local used=$(get_budget_used_today)
|
||||
echo $((TOKEN_DAILY_LIMIT - used))
|
||||
}
|
||||
|
||||
update_budget() {
|
||||
local pipeline="$1"
|
||||
local tokens="$2"
|
||||
local today=$(date +%Y-%m-%d)
|
||||
python3 -c "
|
||||
import json, os
|
||||
path = '$BUDGET_FILE'
|
||||
d = {}
|
||||
if os.path.exists(path):
|
||||
with open(path) as f:
|
||||
d = json.load(f)
|
||||
daily = d.setdefault('daily', {})
|
||||
day = daily.setdefault('$today', {'tokens_used': 0, 'pipelines': {}})
|
||||
day['tokens_used'] = day.get('tokens_used', 0) + $tokens
|
||||
day['pipelines']['$pipeline'] = day['pipelines'].get('$pipeline', 0) + $tokens
|
||||
with open(path, 'w') as f:
|
||||
json.dump(d, f, indent=2)
|
||||
"
|
||||
}
|
||||
|
||||
get_pipeline_state() {
|
||||
if [[ -f "$STATE_FILE" ]]; then
|
||||
cat "$STATE_FILE"
|
||||
else
|
||||
echo "{}"
|
||||
fi
|
||||
}
|
||||
|
||||
set_pipeline_state() {
|
||||
local pipeline="$1"
|
||||
local state="$2" # running, complete, failed, skipped
|
||||
python3 -c "
|
||||
import json, os
|
||||
path = '$STATE_FILE'
|
||||
d = {}
|
||||
if os.path.exists(path):
|
||||
with open(path) as f:
|
||||
d = json.load(f)
|
||||
d['$pipeline'] = {'state': '$state', 'updated': '$(date -Iseconds)'}
|
||||
with open(path, 'w') as f:
|
||||
json.dump(d, f, indent=2)
|
||||
"
|
||||
}
|
||||
|
||||
is_pipeline_complete() {
|
||||
local pipeline="$1"
|
||||
python3 -c "
|
||||
import json, os
|
||||
path = '$STATE_FILE'
|
||||
if not os.path.exists(path):
|
||||
print('false')
|
||||
else:
|
||||
with open(path) as f:
|
||||
d = json.load(f)
|
||||
state = d.get('$pipeline', {}).get('state', 'not_started')
|
||||
print('true' if state == 'complete' else 'false')
|
||||
" 2>/dev/null || echo false
|
||||
}
|
||||
|
||||
is_pipeline_running() {
|
||||
local pipeline="$1"
|
||||
python3 -c "
|
||||
import json, os
|
||||
path = '$STATE_FILE'
|
||||
if not os.path.exists(path):
|
||||
print('false')
|
||||
else:
|
||||
with open(path) as f:
|
||||
d = json.load(f)
|
||||
state = d.get('$pipeline', {}).get('state', 'not_started')
|
||||
print('true' if state == 'running' else 'false')
|
||||
" 2>/dev/null || echo false
|
||||
}
|
||||
|
||||
check_dependency() {
|
||||
local dep="$1"
|
||||
if [[ "$dep" == "none" ]]; then
|
||||
return 0
|
||||
fi
|
||||
# For knowledge-mine: training-factory must be running or complete
|
||||
if [[ "$dep" == "training-factory" ]]; then
|
||||
local state=$(python3 -c "
|
||||
import json, os
|
||||
path = '$STATE_FILE'
|
||||
if not os.path.exists(path):
|
||||
print('not_started')
|
||||
else:
|
||||
with open(path) as f:
|
||||
d = json.load(f)
|
||||
print(d.get('training-factory', {}).get('state', 'not_started'))
|
||||
" 2>/dev/null || echo "not_started")
|
||||
[[ "$state" == "running" || "$state" == "complete" ]]
|
||||
return $?
|
||||
fi
|
||||
# For adversary: knowledge-mine must be at least 50% done
|
||||
# Simplified: check if it's running (we'd need progress tracking for 50%)
|
||||
if [[ "$dep" == "knowledge-mine" ]]; then
|
||||
local state=$(python3 -c "
|
||||
import json, os
|
||||
path = '$STATE_FILE'
|
||||
if not os.path.exists(path):
|
||||
print('not_started')
|
||||
else:
|
||||
with open(path) as f:
|
||||
d = json.load(f)
|
||||
print(d.get('knowledge-mine', {}).get('state', 'not_started'))
|
||||
" 2>/dev/null || echo "not_started")
|
||||
[[ "$state" == "running" || "$state" == "complete" ]]
|
||||
return $?
|
||||
fi
|
||||
return 0
|
||||
}
|
||||
|
||||
check_inference_available() {
|
||||
# Check if any inference provider is responding
|
||||
# 1. Check OpenRouter
|
||||
local or_ok=$(curl -s -o /dev/null -w "%{http_code}" \
|
||||
--connect-timeout 5 "https://openrouter.ai/api/v1/models" 2>/dev/null || echo "000")
|
||||
|
||||
# 2. Check local Ollama
|
||||
local ollama_ok=$(curl -s -o /dev/null -w "%{http_code}" \
|
||||
--connect-timeout 5 "http://localhost:11434/api/tags" 2>/dev/null || echo "000")
|
||||
|
||||
# 3. Check RunPod (if configured)
|
||||
local runpod_ok="000"
|
||||
if [[ -n "${RUNPOD_ENDPOINT:-}" ]]; then
|
||||
runpod_ok=$(curl -s -o /dev/null -w "%{http_code}" \
|
||||
--connect-timeout 5 "$RUNPOD_ENDPOINT/health" 2>/dev/null || echo "000")
|
||||
fi
|
||||
|
||||
if [[ "$or_ok" == "200" || "$ollama_ok" == "200" || "$runpod_ok" == "200" ]]; then
|
||||
return 0
|
||||
fi
|
||||
return 1
|
||||
}
|
||||
|
||||
check_interactive_load() {
|
||||
# Check if there are active interactive sessions (don't fight with live users)
|
||||
# Look for tmux panes with active hermes sessions
|
||||
local active=$(tmux list-panes -a -F '#{pane_pid} #{pane_current_command}' 2>/dev/null \
|
||||
| grep -c "hermes\|python3" || echo 0)
|
||||
|
||||
# If more than 3 interactive sessions, skip pipeline start
|
||||
if [[ $active -gt 3 ]]; then
|
||||
return 1
|
||||
fi
|
||||
return 0
|
||||
}
|
||||
|
||||
start_pipeline() {
|
||||
local name="$1"
|
||||
local script="$2"
|
||||
local max_tokens="$3"
|
||||
local budget_remaining="$4"
|
||||
local mode="${5:-run}"
|
||||
|
||||
if [[ "$budget_remaining" -lt "$max_tokens" ]]; then
|
||||
log "SKIP $name: insufficient budget ($budget_remaining < $max_tokens tokens)"
|
||||
return 1
|
||||
fi
|
||||
|
||||
if [[ ! -f "$script" ]]; then
|
||||
log "SKIP $name: script not found ($script)"
|
||||
return 1
|
||||
fi
|
||||
|
||||
if [[ "$mode" == "dry-run" ]]; then
|
||||
log "DRY-RUN: Would start $name (budget: $budget_remaining, needs: $max_tokens)"
|
||||
return 0
|
||||
fi
|
||||
|
||||
log "START $name (budget: $budget_remaining, max_tokens: $max_tokens)"
|
||||
set_pipeline_state "$name" "running"
|
||||
|
||||
# Run in background, capture output
|
||||
local log_path="${HERMES_HOME}/logs/pipeline-${name}.log"
|
||||
bash "$script" --max-tokens "$max_tokens" >> "$log_path" 2>&1 &
|
||||
local pid=$!
|
||||
|
||||
# Wait a moment to check if it started OK
|
||||
sleep 2
|
||||
if kill -0 $pid 2>/dev/null; then
|
||||
log "RUNNING $name (PID: $pid, log: $log_path)"
|
||||
# Record the PID
|
||||
python3 -c "
|
||||
import json, os
|
||||
path = '$STATE_FILE'
|
||||
d = {}
|
||||
if os.path.exists(path):
|
||||
with open(path) as f:
|
||||
d = json.load(f)
|
||||
d['$name']['pid'] = $pid
|
||||
with open(path, 'w') as f:
|
||||
json.dump(d, f, indent=2)
|
||||
"
|
||||
return 0
|
||||
else
|
||||
log "FAIL $name: script exited immediately"
|
||||
set_pipeline_state "$name" "failed"
|
||||
return 1
|
||||
fi
|
||||
}
|
||||
|
||||
# --- Main ---
|
||||
main() {
|
||||
local mode="${1:-run}"
|
||||
ensure_dirs
|
||||
|
||||
log "=== Pipeline Scheduler ($mode) ==="
|
||||
|
||||
# Check 1: Is inference available?
|
||||
if ! check_inference_available; then
|
||||
log "No inference provider available. Skipping all pipelines."
|
||||
exit 0
|
||||
fi
|
||||
log "Inference: AVAILABLE"
|
||||
|
||||
# Check 2: Is it peak hours?
|
||||
if is_peak_hours && [[ "$mode" != "--force" ]]; then
|
||||
local h=$(now_hour)
|
||||
log "Peak hours ($h:00). Skipping pipeline start. Use --force to override."
|
||||
exit 0
|
||||
fi
|
||||
log "Off-peak: OK"
|
||||
|
||||
# Check 3: Interactive load
|
||||
if ! check_interactive_load && [[ "$mode" != "--force" ]]; then
|
||||
log "High interactive load. Skipping pipeline start."
|
||||
exit 0
|
||||
fi
|
||||
log "Interactive load: OK"
|
||||
|
||||
# Check 4: Token budget
|
||||
local budget=$(get_budget_remaining)
|
||||
log "Token budget remaining: $budget / $TOKEN_DAILY_LIMIT"
|
||||
|
||||
if [[ $budget -le 0 ]]; then
|
||||
log "Daily token budget exhausted. Stopping."
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# Check 5: Pipeline status
|
||||
if [[ "$mode" == "--status" ]]; then
|
||||
echo -e "${CYAN}Pipeline Status:${NC}"
|
||||
echo "────────────────────────────────────────────────────"
|
||||
for entry in "${PIPELINES[@]}"; do
|
||||
IFS='|' read -r name script max_tokens dep <<< "$entry"
|
||||
local state=$(python3 -c "
|
||||
import json, os
|
||||
path = '$STATE_FILE'
|
||||
if not os.path.exists(path):
|
||||
print('not_started')
|
||||
else:
|
||||
with open(path) as f:
|
||||
d = json.load(f)
|
||||
print(d.get('$name', {}).get('state', 'not_started'))
|
||||
" 2>/dev/null || echo "not_started")
|
||||
|
||||
local color=$NC
|
||||
case "$state" in
|
||||
running) color=$YELLOW ;;
|
||||
complete) color=$GREEN ;;
|
||||
failed) color=$RED ;;
|
||||
esac
|
||||
printf " %-25s %b%s%b (max: %s tokens, dep: %s)\n" "$name" "$color" "$state" "$NC" "$max_tokens" "$dep"
|
||||
done
|
||||
echo "────────────────────────────────────────────────────"
|
||||
echo " Budget: $budget / $TOKEN_DAILY_LIMIT tokens remaining"
|
||||
echo " Peak hours: $PEAK_HOURS_START:00 - $PEAK_HOURS_END:00"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# Find and start the highest-priority incomplete pipeline
|
||||
local started=0
|
||||
for entry in "${PIPELINES[@]}"; do
|
||||
IFS='|' read -r name script max_tokens dep <<< "$entry"
|
||||
|
||||
# Skip if already running or complete
|
||||
if [[ "$(is_pipeline_running $name)" == "true" ]]; then
|
||||
log "SKIP $name: already running"
|
||||
continue
|
||||
fi
|
||||
if [[ "$(is_pipeline_complete $name)" == "true" ]]; then
|
||||
log "SKIP $name: already complete"
|
||||
continue
|
||||
fi
|
||||
|
||||
# Check dependency
|
||||
if ! check_dependency "$dep"; then
|
||||
log "SKIP $name: dependency $dep not met"
|
||||
continue
|
||||
fi
|
||||
|
||||
# Try to start
|
||||
if start_pipeline "$name" "$script" "$max_tokens" "$budget" "$mode"; then
|
||||
started=1
|
||||
# Only start one pipeline per run (let it claim tokens before next check)
|
||||
# Exception: playground-factory and training-factory can run in parallel
|
||||
if [[ "$name" != "playground-factory" && "$name" != "training-factory" ]]; then
|
||||
break
|
||||
fi
|
||||
fi
|
||||
done
|
||||
|
||||
if [[ $started -eq 0 ]]; then
|
||||
log "No pipelines to start (all complete, running, or blocked)."
|
||||
fi
|
||||
|
||||
log "=== Pipeline Scheduler done ==="
|
||||
}
|
||||
|
||||
main "$@"
|
||||
207
scripts/validate-sidecar-config.py
Normal file
207
scripts/validate-sidecar-config.py
Normal file
@@ -0,0 +1,207 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
validate-sidecar-config.py — Pre-deploy validation for timmy-config sidecar.
|
||||
|
||||
Validates YAML syntax, required keys, value types before deploy.
|
||||
Rejects bad config with clear errors.
|
||||
|
||||
Usage:
|
||||
python3 scripts/validate-sidecar-config.py ~/.timmy/config.yaml
|
||||
python3 scripts/validate-sidecar-config.py --all # Validate all config files
|
||||
python3 scripts/validate-sidecar-config.py --schema # Print expected schema
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
try:
|
||||
import yaml
|
||||
HAS_YAML = True
|
||||
except ImportError:
|
||||
HAS_YAML = False
|
||||
|
||||
# Expected schema: field -> type
|
||||
REQUIRED_SCHEMA = {
|
||||
"model": str,
|
||||
"provider": str,
|
||||
}
|
||||
|
||||
OPTIONAL_SCHEMA = {
|
||||
"api_base": str,
|
||||
"max_tokens": int,
|
||||
"temperature": (int, float),
|
||||
"system_prompt": str,
|
||||
"tools": list,
|
||||
"memory_enabled": bool,
|
||||
"session_timeout": int,
|
||||
"log_level": str,
|
||||
}
|
||||
|
||||
CONFIG_DIRS = [
|
||||
Path.home() / ".timmy",
|
||||
Path.home() / ".hermes",
|
||||
]
|
||||
|
||||
|
||||
def validate_yaml_syntax(filepath: Path) -> list[str]:
|
||||
"""Validate YAML can be parsed."""
|
||||
errors = []
|
||||
try:
|
||||
content = filepath.read_text(errors="ignore")
|
||||
if HAS_YAML:
|
||||
yaml.safe_load(content)
|
||||
else:
|
||||
# Fallback: check for basic JSON-in-YAML
|
||||
json.loads(content)
|
||||
except (yaml.YAMLError if HAS_YAML else Exception, json.JSONDecodeError) as e:
|
||||
errors.append(f"YAML syntax error: {e}")
|
||||
except OSError as e:
|
||||
errors.append(f"Cannot read file: {e}")
|
||||
return errors
|
||||
|
||||
|
||||
def validate_schema(filepath: Path) -> list[str]:
|
||||
"""Validate config against expected schema."""
|
||||
errors = []
|
||||
try:
|
||||
content = filepath.read_text(errors="ignore")
|
||||
if HAS_YAML:
|
||||
config = yaml.safe_load(content) or {}
|
||||
else:
|
||||
config = json.loads(content)
|
||||
except Exception as e:
|
||||
return [f"Cannot parse: {e}"]
|
||||
|
||||
if not isinstance(config, dict):
|
||||
return ["Config must be a YAML/JSON object (dict)"]
|
||||
|
||||
# Check required keys
|
||||
for key, expected_type in REQUIRED_SCHEMA.items():
|
||||
if key not in config:
|
||||
errors.append(f"Missing required key: '{key}' (expected {expected_type.__name__})")
|
||||
elif not isinstance(config[key], expected_type):
|
||||
errors.append(f"Wrong type for '{key}': expected {expected_type.__name__}, got {type(config[key]).__name__}")
|
||||
|
||||
# Check optional keys types
|
||||
for key, expected_type in OPTIONAL_SCHEMA.items():
|
||||
if key in config:
|
||||
if isinstance(expected_type, tuple):
|
||||
if not isinstance(config[key], expected_type):
|
||||
type_names = " or ".join(t.__name__ for t in expected_type)
|
||||
errors.append(f"Wrong type for '{key}': expected {type_names}, got {type(config[key]).__name__}")
|
||||
else:
|
||||
if not isinstance(config[key], expected_type):
|
||||
errors.append(f"Wrong type for '{key}': expected {expected_type.__name__}, got {type(config[key]).__name__}")
|
||||
|
||||
# Check for common mistakes
|
||||
if "model" in config and isinstance(config["model"], str):
|
||||
if config["model"].startswith("http"):
|
||||
errors.append("'model' looks like a URL — did you mean 'api_base'?")
|
||||
|
||||
if "api_base" in config and isinstance(config["api_base"], str):
|
||||
if not config["api_base"].startswith("http"):
|
||||
errors.append("'api_base' should start with http:// or https://")
|
||||
|
||||
return errors
|
||||
|
||||
|
||||
def validate_file(filepath: Path) -> tuple[bool, list[str]]:
|
||||
"""Full validation of a config file. Returns (valid, errors)."""
|
||||
errors = []
|
||||
errors.extend(validate_yaml_syntax(filepath))
|
||||
if not errors:
|
||||
errors.extend(validate_schema(filepath))
|
||||
return len(errors) == 0, errors
|
||||
|
||||
|
||||
def find_config_files() -> list[Path]:
|
||||
"""Find config files in standard locations."""
|
||||
configs = []
|
||||
for d in CONFIG_DIRS:
|
||||
if not d.exists():
|
||||
continue
|
||||
for f in d.rglob("*.yaml"):
|
||||
if f.name in ("config.yaml", "settings.yaml", "env.yaml", "config.yml"):
|
||||
configs.append(f)
|
||||
for f in d.rglob("*.yml"):
|
||||
if "config" in f.name.lower():
|
||||
configs.append(f)
|
||||
for f in d.rglob("*.json"):
|
||||
if f.name in ("config.json", "settings.json"):
|
||||
configs.append(f)
|
||||
return sorted(set(configs))
|
||||
|
||||
|
||||
def cmd_validate(filepath: str) -> bool:
|
||||
path = Path(filepath)
|
||||
if not path.exists():
|
||||
print(f"ERROR: {path} not found")
|
||||
return False
|
||||
|
||||
valid, errors = validate_file(path)
|
||||
if valid:
|
||||
print(f"OK: {path}")
|
||||
else:
|
||||
print(f"FAIL: {path}")
|
||||
for e in errors:
|
||||
print(f" - {e}")
|
||||
return valid
|
||||
|
||||
|
||||
def cmd_validate_all() -> bool:
|
||||
configs = find_config_files()
|
||||
if not configs:
|
||||
print("No config files found in standard locations.")
|
||||
return True
|
||||
|
||||
all_valid = True
|
||||
for config in configs:
|
||||
valid, errors = validate_file(config)
|
||||
if valid:
|
||||
print(f"OK: {config}")
|
||||
else:
|
||||
all_valid = False
|
||||
print(f"FAIL: {config}")
|
||||
for e in errors:
|
||||
print(f" - {e}")
|
||||
|
||||
print(f"\n{'All configs valid.' if all_valid else 'Validation failures found.'}")
|
||||
return all_valid
|
||||
|
||||
|
||||
def cmd_schema():
|
||||
print("Required keys:")
|
||||
for key, typ in REQUIRED_SCHEMA.items():
|
||||
print(f" {key}: {typ.__name__}")
|
||||
print("\nOptional keys:")
|
||||
for key, typ in OPTIONAL_SCHEMA.items():
|
||||
if isinstance(typ, tuple):
|
||||
print(f" {key}: {'|'.join(t.__name__ for t in typ)}")
|
||||
else:
|
||||
print(f" {key}: {typ.__name__}")
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(description="Validate sidecar config files")
|
||||
parser.add_argument("file", nargs="?", help="Config file to validate")
|
||||
parser.add_argument("--all", action="store_true", help="Validate all config files")
|
||||
parser.add_argument("--schema", action="store_true", help="Print expected schema")
|
||||
args = parser.parse_args()
|
||||
|
||||
if args.schema:
|
||||
cmd_schema()
|
||||
elif args.all:
|
||||
ok = cmd_validate_all()
|
||||
sys.exit(0 if ok else 1)
|
||||
elif args.file:
|
||||
ok = cmd_validate(args.file)
|
||||
sys.exit(0 if ok else 1)
|
||||
else:
|
||||
parser.print_help()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,3 +1,4 @@
|
||||
#!/usr/bin/env python3
|
||||
import json
|
||||
from hermes_tools import browser_navigate, browser_vision
|
||||
|
||||
|
||||
Reference in New Issue
Block a user