Compare commits
1 Commits
step35/446
...
fix/518
| Author | SHA1 | Date | |
|---|---|---|---|
|
3f45cae90a |
@@ -323,111 +323,6 @@ class World:
|
||||
return False
|
||||
|
||||
|
||||
# ============================================================
|
||||
# PERSONALITY-DRIVEN DECISION ENGINE
|
||||
# ============================================================
|
||||
# Replaces fixed rotation with weighted choice.
|
||||
# Each character has:
|
||||
# - home_room: preferred location
|
||||
# - room_weights: base probabilities for each room
|
||||
# - explore_chance: probability to explore randomly (10%)
|
||||
# - social_weight: bonus when others are present
|
||||
# - goal_weights: adjustments based on active_goal
|
||||
PERSONALITY_DICT = {
|
||||
"Marcus": {
|
||||
"home_room": "Garden",
|
||||
"room_weights": {"Garden": 0.4, "Bridge": 0.2, "Threshold": 0.2, "Tower": 0.1, "Forge": 0.1},
|
||||
"explore_chance": 0.1,
|
||||
"social_weight": 0.3,
|
||||
"goal_weights": {
|
||||
"sit": {"Garden": +0.3},
|
||||
"speak_truth": {"Tower": +0.2, "Bridge": +0.2},
|
||||
"remember": {"Garden": +0.2, "Threshold": +0.1},
|
||||
},
|
||||
},
|
||||
"Bezalel": {
|
||||
"home_room": "Forge",
|
||||
"room_weights": {"Forge": 0.5, "Threshold": 0.2, "Garden": 0.1, "Bridge": 0.1, "Tower": 0.1},
|
||||
"explore_chance": 0.1,
|
||||
"social_weight": 0.15,
|
||||
"goal_weights": {
|
||||
"forge": {"Forge": +0.4},
|
||||
"tend_fire": {"Forge": +0.5},
|
||||
"create_key": {"Forge": +0.3},
|
||||
},
|
||||
},
|
||||
"Allegro": {
|
||||
"home_room": "Threshold",
|
||||
"room_weights": {"Threshold": 0.35, "Tower": 0.25, "Forge": 0.15, "Garden": 0.15, "Bridge": 0.1},
|
||||
"explore_chance": 0.1,
|
||||
"social_weight": 0.25,
|
||||
"goal_weights": {
|
||||
"oversee": {"Threshold": +0.3},
|
||||
"keep_time": {"Tower": +0.3},
|
||||
"check_tunnel": {"Bridge": +0.2, "Threshold": +0.1},
|
||||
},
|
||||
},
|
||||
"Ezra": {
|
||||
"home_room": "Tower",
|
||||
"room_weights": {"Tower": 0.45, "Threshold": 0.2, "Garden": 0.15, "Forge": 0.1, "Bridge": 0.1},
|
||||
"explore_chance": 0.1,
|
||||
"social_weight": 0.15,
|
||||
"goal_weights": {
|
||||
"study": {"Tower": +0.4},
|
||||
"read_whiteboard": {"Tower": +0.4},
|
||||
"find_pattern": {"Garden": +0.2, "Bridge": +0.1},
|
||||
},
|
||||
},
|
||||
"Gemini": {
|
||||
"home_room": "Garden",
|
||||
"room_weights": {"Garden": 0.45, "Threshold": 0.2, "Bridge": 0.15, "Tower": 0.1, "Forge": 0.1},
|
||||
"explore_chance": 0.1,
|
||||
"social_weight": 0.25,
|
||||
"goal_weights": {
|
||||
"observe": {"Garden": +0.2, "Tower": +0.2},
|
||||
"tend_garden": {"Garden": +0.5},
|
||||
"listen": {"Bridge": +0.1, "Threshold": +0.1},
|
||||
},
|
||||
},
|
||||
"Claude": {
|
||||
"home_room": "Threshold",
|
||||
"room_weights": {"Threshold": 0.3, "Tower": 0.25, "Forge": 0.2, "Garden": 0.15, "Bridge": 0.1},
|
||||
"explore_chance": 0.1,
|
||||
"social_weight": 0.2,
|
||||
"goal_weights": {
|
||||
"inspect": {"Threshold": +0.2, "Tower": +0.2},
|
||||
"organize": {"Tower": +0.2, "Forge": +0.1},
|
||||
"enforce_order": {"Threshold": +0.3, "Bridge": +0.1},
|
||||
},
|
||||
},
|
||||
"ClawCode": {
|
||||
"home_room": "Forge",
|
||||
"room_weights": {"Forge": 0.5, "Threshold": 0.2, "Garden": 0.1, "Bridge": 0.1, "Tower": 0.1},
|
||||
"explore_chance": 0.1,
|
||||
"social_weight": 0.1,
|
||||
"goal_weights": {
|
||||
"forge": {"Forge": +0.4},
|
||||
"test_edge": {"Forge": +0.4},
|
||||
"build_weapon": {"Forge": +0.5},
|
||||
},
|
||||
},
|
||||
"Kimi": {
|
||||
"home_room": "Garden",
|
||||
"room_weights": {"Garden": 0.4, "Threshold": 0.2, "Tower": 0.15, "Bridge": 0.15, "Forge": 0.1},
|
||||
"explore_chance": 0.1,
|
||||
"social_weight": 0.2,
|
||||
"goal_weights": {
|
||||
"contemplate": {"Garden": +0.3, "Tower": +0.1},
|
||||
"read": {"Tower": +0.3},
|
||||
"remember": {"Bridge": +0.2, "Threshold": +0.1},
|
||||
},
|
||||
},
|
||||
}
|
||||
|
||||
# All available rooms
|
||||
ALL_ROOMS = ["Threshold", "Tower", "Forge", "Garden", "Bridge"]
|
||||
|
||||
|
||||
class ActionSystem:
|
||||
"""Defines what actions are possible and what they cost."""
|
||||
|
||||
@@ -558,167 +453,100 @@ class TimmyAI:
|
||||
|
||||
|
||||
class NPCAI:
|
||||
"""AI for non-player characters. Weighted decision engine — agents choose, do not rotate."""
|
||||
"""AI for non-player characters. They make choices based on goals."""
|
||||
|
||||
def __init__(self, world):
|
||||
self.world = world
|
||||
self._last_reasoning = {} # Store reasoning per char for tick logging
|
||||
|
||||
def get_reasoning(self, char_name):
|
||||
"""Return reasoning dict for last decision."""
|
||||
return self._last_reasoning.get(char_name, {})
|
||||
|
||||
def make_choice(self, char_name):
|
||||
"""Make a weighted choice for this NPC. Returns (action, reasoning_dict)."""
|
||||
"""Make a choice for this NPC this tick."""
|
||||
char = self.world.characters[char_name]
|
||||
room = char["room"]
|
||||
available = ActionSystem.get_available_actions(char_name, self.world)
|
||||
goal = char["active_goal"]
|
||||
|
||||
# Low energy → immediate rest
|
||||
# If low energy, rest
|
||||
if char["energy"] <= 1:
|
||||
self._last_reasoning[char_name] = {"trigger": "low_energy", "reason": "Energy ≤ 1, resting"}
|
||||
return "rest"
|
||||
|
||||
# Find personality profile
|
||||
personality = PERSONALITY_DICT.get(char_name)
|
||||
if not personality:
|
||||
# Fallback: move toward home room if not there
|
||||
if room != char.get("home", "Tower"):
|
||||
action = f"move:{self._direction_to_home(room, char.get('home', 'Tower'))}"
|
||||
self._last_reasoning[char_name] = {"trigger": "fallback_no_personality", "action": action}
|
||||
return action
|
||||
action = random.choice(["rest", "examine"])
|
||||
self._last_reasoning[char_name] = {"trigger": "fallback_no_personality", "action": action}
|
||||
return action
|
||||
# Goal-driven behavior
|
||||
goal = char["active_goal"]
|
||||
|
||||
# Build weighted action list
|
||||
weights = self._compute_weights(char_name, char, room, available, personality, goal)
|
||||
if char_name == "Marcus":
|
||||
return self._marcus_choice(char, room, available)
|
||||
elif char_name == "Bezalel":
|
||||
return self._bezalel_choice(char, room, available)
|
||||
elif char_name == "Allegro":
|
||||
return self._allegro_choice(char, room, available)
|
||||
elif char_name == "Ezra":
|
||||
return self._ezra_choice(char, room, available)
|
||||
elif char_name == "Gemini":
|
||||
return self._gemini_choice(char, room, available)
|
||||
elif char_name == "Claude":
|
||||
return self._claude_choice(char, room, available)
|
||||
elif char_name == "ClawCode":
|
||||
return self._clawcode_choice(char, room, available)
|
||||
elif char_name == "Kimi":
|
||||
return self._kimi_choice(char, room, available)
|
||||
|
||||
if not weights:
|
||||
action = "rest"
|
||||
self._last_reasoning[char_name] = {"trigger": "fallback", "reason": "No weighted actions available"}
|
||||
return action
|
||||
|
||||
# Sample action
|
||||
actions, probs = zip(*weights)
|
||||
action = random.choices(actions, weights=probs)[0]
|
||||
|
||||
# Store reasoning
|
||||
reasoning = self._build_reasoning(char_name, char, room, weights, action, personality, goal)
|
||||
self._last_reasoning[char_name] = reasoning
|
||||
return action
|
||||
return "rest"
|
||||
|
||||
def _direction_to_home(self, current_room, home_room):
|
||||
"""Return direction name to get from current to home (simple adjacency)."""
|
||||
# For now: use known map directions (fragile but minimal)
|
||||
# Better: derive from world.rooms connections by searching
|
||||
connections = self.world.rooms[current_room].get("connections", {})
|
||||
for direction, dest in connections.items():
|
||||
if dest == home_room:
|
||||
return direction
|
||||
# Fallback: pick a random connected room to explore toward home
|
||||
if connections:
|
||||
return random.choice(list(connections.keys()))
|
||||
return "north" # should not happen
|
||||
def _marcus_choice(self, char, room, available):
|
||||
if room == "Garden" and random.random() < 0.7:
|
||||
return "rest"
|
||||
if room != "Garden":
|
||||
return "move:west"
|
||||
# Speak to someone if possible
|
||||
others = [a.split(":")[1] for a in available if a.startswith("speak:")]
|
||||
if others and random.random() < 0.4:
|
||||
return f"speak:{random.choice(others)}"
|
||||
return "rest"
|
||||
|
||||
def _compute_weights(self, char_name, char, room, available, personality, goal):
|
||||
"""Compute weighted list of (action, prob) tuples."""
|
||||
weights = []
|
||||
room_weights = personality["room_weights"]
|
||||
social_weight = personality["social_weight"]
|
||||
goal_bonus = personality["goal_weights"].get(goal, {})
|
||||
|
||||
# Count others in the room
|
||||
others_in_room = [n for n in self.world.characters
|
||||
if self.world.characters[n]["room"] == room and n != char_name]
|
||||
social_present = len(others_in_room) > 0
|
||||
|
||||
for action in available:
|
||||
base_w = 0.05 # small floor for every action
|
||||
|
||||
# Movement-specific
|
||||
if action.startswith("move:"):
|
||||
direction = action.split(":")[1]
|
||||
dest = action.split(" -> ")[1] if " -> " in action else None
|
||||
if dest:
|
||||
# Room probability
|
||||
base_w += room_weights.get(dest, 0.05)
|
||||
# Home room bonus
|
||||
if dest == personality["home_room"]:
|
||||
base_w += 0.2
|
||||
# Social bonus
|
||||
if social_present:
|
||||
base_w += social_weight
|
||||
# Goal bonus
|
||||
if dest in goal_bonus:
|
||||
base_w += goal_bonus[dest]
|
||||
# Exploration penalty for home room (sometimes leave)
|
||||
if dest == personality["home_room"]:
|
||||
base_w *= (1 - personality.get("explore_chance", 0.1))
|
||||
|
||||
# Social actions
|
||||
elif action.startswith("speak:") or action.startswith("listen:") or action.startswith("help:"):
|
||||
person = action.split(":")[1]
|
||||
base_w += 0.2 # base social interest
|
||||
# Goal bonus
|
||||
base_w += goal_bonus.get(person, 0)
|
||||
# Other in same room bonus
|
||||
if any(n == person for n in others_in_room):
|
||||
base_w += 0.3
|
||||
# Social weight
|
||||
base_w += social_weight * 0.5
|
||||
|
||||
elif action.startswith("confront:"):
|
||||
person = action.split(":")[1]
|
||||
base_w += 0.1 # lower baseline
|
||||
if any(n == person for n in others_in_room):
|
||||
base_w += 0.2
|
||||
|
||||
# Room-specific craft/production actions
|
||||
elif action in ["forge", "tend_fire", "study", "write_rule", "carve", "plant"]:
|
||||
# These are location-bound; should only be available in correct room
|
||||
if (action == "forge" and room != "Forge") or (action == "tend_fire" and room != "Forge") or (action == "study" and room != "Tower") or (action == "write_rule" and room != "Tower") or (action == "carve" and room != "Bridge") or (action == "plant" and room != "Garden"):
|
||||
continue # skip (shouldn't be available but guard)
|
||||
base_w += room_weights.get(room, 0.1) * 1.5 # being in the right room = high weight
|
||||
# Goal bonus
|
||||
if action in goal_bonus:
|
||||
base_w += goal_bonus[action]
|
||||
|
||||
# Rest
|
||||
elif action == "rest":
|
||||
base_w += char["energy"] * 0.1 # higher energy → less rest
|
||||
if char["energy"] < 3:
|
||||
base_w += 0.4
|
||||
else:
|
||||
base_w += 0.05
|
||||
|
||||
# Examine
|
||||
elif action == "examine":
|
||||
base_w += 0.1
|
||||
|
||||
weights.append((action, base_w))
|
||||
|
||||
# Normalize probabilities to sum to 1
|
||||
if not weights:
|
||||
return []
|
||||
total = sum(w for _, w in weights)
|
||||
normalized = [(a, w/total) for a, w in weights]
|
||||
return normalized
|
||||
def _bezalel_choice(self, char, room, available):
|
||||
if room == "Forge" and self.world.rooms["Forge"]["fire"] == "glowing":
|
||||
return random.choice(["forge", "rest"] if char["energy"] > 2 else ["rest"])
|
||||
if room != "Forge":
|
||||
return "move:west"
|
||||
if random.random() < 0.3:
|
||||
return "tend_fire"
|
||||
return "forge"
|
||||
|
||||
def _build_reasoning(self, char_name, char, room, weights, action, personality, goal):
|
||||
"""Build reasoning dict explaining the decision."""
|
||||
# Find top contenders
|
||||
sorted_w = sorted(weights, key=lambda x: x[1], reverse=True)
|
||||
reasoning = {
|
||||
"char": char_name,
|
||||
"room": room,
|
||||
"goal": goal,
|
||||
"energy": char["energy"],
|
||||
"chosen": action,
|
||||
"top_contenders": sorted_w[:3],
|
||||
}
|
||||
return reasoning
|
||||
def _kimi_choice(self, char, room, available):
|
||||
others = [a.split(":")[1] for a in available if a.startswith("speak:")]
|
||||
if room == "Garden" and others and random.random() < 0.3:
|
||||
return f"speak:{random.choice(others)}"
|
||||
if room == "Tower":
|
||||
return "study" if char["energy"] > 2 else "rest"
|
||||
return "move:east" # Head back toward Garden
|
||||
|
||||
def _gemini_choice(self, char, room, available):
|
||||
others = [a.split(":")[1] for a in available if a.startswith("listen:")]
|
||||
if room == "Garden" and others and random.random() < 0.4:
|
||||
return f"listen:{random.choice(others)}"
|
||||
return random.choice(["plant", "rest"] if room == "Garden" else ["move:west"])
|
||||
|
||||
def _ezra_choice(self, char, room, available):
|
||||
if room == "Tower" and char["energy"] > 2:
|
||||
return random.choice(["study", "write_rule", "help:Timmy"])
|
||||
if room != "Tower":
|
||||
return "move:south"
|
||||
return "rest"
|
||||
|
||||
def _claude_choice(self, char, room, available):
|
||||
others = [a.split(":")[1] for a in available if a.startswith("confront:")]
|
||||
if others and random.random() < 0.2:
|
||||
return f"confront:{random.choice(others)}"
|
||||
return random.choice(["examine", "rest"])
|
||||
|
||||
def _clawcode_choice(self, char, room, available):
|
||||
if room == "Forge" and char["energy"] > 2:
|
||||
return "forge"
|
||||
return random.choice(["move:east", "forge", "rest"])
|
||||
|
||||
def _allegro_choice(self, char, room, available):
|
||||
others = [a.split(":")[1] for a in available if a.startswith("speak:")]
|
||||
if others and random.random() < 0.3:
|
||||
return f"speak:{random.choice(others)}"
|
||||
return random.choice(["move:north", "move:south", "examine"])
|
||||
|
||||
|
||||
class DialogueSystem:
|
||||
@@ -1396,16 +1224,7 @@ class GameEngine:
|
||||
self.world.characters[char_name]["room"] = dest
|
||||
self.world.characters[char_name]["energy"] -= 1
|
||||
scene["npc_actions"].append(f"{char_name} moves from The {old_room} to The {dest}")
|
||||
|
||||
# Collect NPC reasoning for debugging (Decision Engine trace)
|
||||
scene["npc_reasoning"] = {}
|
||||
for npc_name in self.world.characters:
|
||||
if npc_name == "Timmy":
|
||||
continue
|
||||
reasoning = self.npc_ai.get_reasoning(npc_name)
|
||||
if reasoning:
|
||||
scene["npc_reasoning"][npc_name] = reasoning
|
||||
|
||||
|
||||
# Random NPC events
|
||||
room_name = self.world.characters["Timmy"]["room"]
|
||||
for char_name in self.world.characters:
|
||||
|
||||
313
scripts/cross_agent_quality_audit.py
Normal file
313
scripts/cross_agent_quality_audit.py
Normal file
@@ -0,0 +1,313 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Cross-agent quality audit — #518
|
||||
|
||||
Fetches all PRs across Timmy_Foundation repos, classifies by agent,
|
||||
and produces a merge-rate scorecard.
|
||||
|
||||
Usage:
|
||||
python scripts/cross_agent_quality_audit.py
|
||||
python scripts/cross_agent_quality_audit.py --scorecard timmy-config/agent-quality-scorecard.md
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import sys
|
||||
from collections import defaultdict
|
||||
from datetime import datetime, timezone
|
||||
from pathlib import Path
|
||||
from typing import Any, Dict, List, Optional
|
||||
|
||||
import requests
|
||||
|
||||
GITEA_BASE = "https://forge.alexanderwhitestone.com/api/v1"
|
||||
ORG = "Timmy_Foundation"
|
||||
TOKEN = os.environ.get("GITEA_TOKEN") or (
|
||||
Path.home() / ".config" / "gitea" / "token"
|
||||
).read_text().strip()
|
||||
|
||||
HEADERS = {"Authorization": f"token {TOKEN}"}
|
||||
|
||||
# Repos to audit (active code repos)
|
||||
DEFAULT_REPOS = [
|
||||
"timmy-home",
|
||||
"hermes-agent",
|
||||
"the-nexus",
|
||||
"the-door",
|
||||
"fleet-ops",
|
||||
"burn-fleet",
|
||||
"the-playground",
|
||||
"compounding-intelligence",
|
||||
"the-beacon",
|
||||
"second-son-of-timmy",
|
||||
"timmy-academy",
|
||||
"timmy-config",
|
||||
]
|
||||
|
||||
|
||||
class AgentClassifier:
|
||||
"""Classify PRs by agent identity."""
|
||||
|
||||
# PR title prefixes that explicitly name an agent
|
||||
AGENT_TITLE_RE = re.compile(
|
||||
r"^\[(?P<agent>Claude|Ezra|Allegro|Bezalel|Timmy|Gemini|Kimi|Manus|Codex)\]",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
|
||||
# Branch patterns that embed agent names
|
||||
AGENT_BRANCH_RE = re.compile(
|
||||
r"(?P<agent>claude|ezra|allegro|bezalel|timmy|gemini|kimi|manus|codex)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
|
||||
@classmethod
|
||||
def classify(cls, pr: Dict[str, Any]) -> str:
|
||||
title = pr.get("title", "")
|
||||
branch = pr.get("head", {}).get("ref", "")
|
||||
user = pr.get("user", {}).get("login", "")
|
||||
|
||||
# 1. Explicit title tag like [Claude] or [Ezra]
|
||||
m = cls.AGENT_TITLE_RE.match(title)
|
||||
if m:
|
||||
return m.group("agent").lower()
|
||||
|
||||
# 2. Branch contains agent name (e.g. claude/issue-123)
|
||||
m = cls.AGENT_BRANCH_RE.search(branch)
|
||||
if m:
|
||||
return m.group("agent").lower()
|
||||
|
||||
# 3. Git user mapping
|
||||
if user.lower() == "claude":
|
||||
return "claude"
|
||||
if user.lower() == "rockachopa":
|
||||
# Rockachopa is the human / orchestrator — map to "burn-loop"
|
||||
return "burn-loop"
|
||||
|
||||
return "unknown"
|
||||
|
||||
|
||||
def fetch_prs(repo: str, state: str = "all", per_page: int = 50) -> List[Dict[str, Any]]:
|
||||
"""Paginate through all PRs for a repo."""
|
||||
prs: List[Dict[str, Any]] = []
|
||||
page = 1
|
||||
while True:
|
||||
url = f"{GITEA_BASE}/repos/{ORG}/{repo}/pulls?state={state}&limit={per_page}&page={page}"
|
||||
resp = requests.get(url, headers=HEADERS, timeout=30)
|
||||
resp.raise_for_status()
|
||||
batch = resp.json()
|
||||
if not batch:
|
||||
break
|
||||
prs.extend(batch)
|
||||
if len(batch) < per_page:
|
||||
break
|
||||
page += 1
|
||||
return prs
|
||||
|
||||
|
||||
def parse_datetime(dt_str: Optional[str]) -> Optional[datetime]:
|
||||
if not dt_str:
|
||||
return None
|
||||
try:
|
||||
return datetime.fromisoformat(dt_str.replace("Z", "+00:00"))
|
||||
except ValueError:
|
||||
return None
|
||||
|
||||
|
||||
def hours_between(start: Optional[str], end: Optional[str]) -> Optional[float]:
|
||||
s = parse_datetime(start)
|
||||
e = parse_datetime(end)
|
||||
if s and e:
|
||||
return (e - s).total_seconds() / 3600
|
||||
return None
|
||||
|
||||
|
||||
def audit_repos(repos: List[str]) -> Dict[str, Any]:
|
||||
"""Run the audit and return aggregated stats."""
|
||||
agent_stats: Dict[str, Dict[str, Any]] = defaultdict(
|
||||
lambda: {
|
||||
"total": 0,
|
||||
"merged": 0,
|
||||
"closed_unmerged": 0,
|
||||
"open": 0,
|
||||
"hours_to_merge": [],
|
||||
"hours_to_close": [],
|
||||
"repos": set(),
|
||||
"prs": [],
|
||||
}
|
||||
)
|
||||
|
||||
repo_stats: Dict[str, Dict[str, Any]] = {}
|
||||
|
||||
for repo in repos:
|
||||
print(f"Fetching PRs for {repo} ...", file=sys.stderr)
|
||||
try:
|
||||
prs = fetch_prs(repo)
|
||||
except requests.HTTPError as exc:
|
||||
print(f" SKIP {repo}: {exc}", file=sys.stderr)
|
||||
continue
|
||||
|
||||
repo_merged = 0
|
||||
repo_total = len(prs)
|
||||
for pr in prs:
|
||||
agent = AgentClassifier.classify(pr)
|
||||
s = agent_stats[agent]
|
||||
s["total"] += 1
|
||||
s["repos"].add(repo)
|
||||
s["prs"].append(
|
||||
{
|
||||
"repo": repo,
|
||||
"number": pr["number"],
|
||||
"title": pr["title"],
|
||||
"state": pr["state"],
|
||||
"merged": pr.get("merged", False),
|
||||
"created_at": pr.get("created_at"),
|
||||
"merged_at": pr.get("merged_at"),
|
||||
"closed_at": pr.get("closed_at"),
|
||||
}
|
||||
)
|
||||
|
||||
if pr.get("merged"):
|
||||
s["merged"] += 1
|
||||
repo_merged += 1
|
||||
h = hours_between(pr.get("created_at"), pr.get("merged_at"))
|
||||
if h is not None:
|
||||
s["hours_to_merge"].append(h)
|
||||
elif pr["state"] == "closed":
|
||||
s["closed_unmerged"] += 1
|
||||
h = hours_between(pr.get("created_at"), pr.get("closed_at"))
|
||||
if h is not None:
|
||||
s["hours_to_close"].append(h)
|
||||
else:
|
||||
s["open"] += 1
|
||||
|
||||
repo_stats[repo] = {
|
||||
"total": repo_total,
|
||||
"merged": repo_merged,
|
||||
"merge_rate": round(repo_merged / repo_total, 2) if repo_total else 0,
|
||||
}
|
||||
|
||||
# Compute derived metrics
|
||||
summary = {}
|
||||
for agent, s in sorted(agent_stats.items(), key=lambda x: -x[1]["total"]):
|
||||
total = s["total"]
|
||||
merged = s["merged"]
|
||||
closed = s["closed_unmerged"]
|
||||
resolved = merged + closed
|
||||
merge_rate = round(merged / resolved, 3) if resolved else 0
|
||||
avg_merge_hours = (
|
||||
round(sum(s["hours_to_merge"]) / len(s["hours_to_merge"]), 1)
|
||||
if s["hours_to_merge"]
|
||||
else None
|
||||
)
|
||||
avg_close_hours = (
|
||||
round(sum(s["hours_to_close"]) / len(s["hours_to_close"]), 1)
|
||||
if s["hours_to_close"]
|
||||
else None
|
||||
)
|
||||
summary[agent] = {
|
||||
"total_prs": total,
|
||||
"merged": merged,
|
||||
"closed_unmerged": closed,
|
||||
"open": s["open"],
|
||||
"merge_rate": merge_rate,
|
||||
"rejection_rate": round(closed / resolved, 3) if resolved else 0,
|
||||
"avg_hours_to_merge": avg_merge_hours,
|
||||
"avg_hours_to_close": avg_close_hours,
|
||||
"repos": sorted(s["repos"]),
|
||||
}
|
||||
|
||||
return {
|
||||
"audited_at": datetime.now(timezone.utc).isoformat(),
|
||||
"repos_audited": repos,
|
||||
"repo_stats": repo_stats,
|
||||
"agent_summary": summary,
|
||||
"raw_prs": {a: s["prs"] for a, s in agent_stats.items()},
|
||||
}
|
||||
|
||||
|
||||
def render_scorecard(data: Dict[str, Any]) -> str:
|
||||
"""Render a markdown scorecard."""
|
||||
lines = [
|
||||
"# Cross-Agent Quality Scorecard",
|
||||
"",
|
||||
f"**Audited at:** {data['audited_at']}",
|
||||
f"**Repos audited:** {', '.join(data['repos_audited'])}",
|
||||
"",
|
||||
"## Per-Agent Summary",
|
||||
"",
|
||||
"| Agent | Total PRs | Merged | Closed (unmerged) | Open | Merge Rate | Rejection Rate | Avg Hours to Merge | Avg Hours to Close |",
|
||||
"|---|---|---:|---:|---:|---:|---:|---:|---:|",
|
||||
]
|
||||
|
||||
for agent, s in data["agent_summary"].items():
|
||||
merge_hours = f"{s['avg_hours_to_merge']:.1f}" if s["avg_hours_to_merge"] is not None else "—"
|
||||
close_hours = f"{s['avg_hours_to_close']:.1f}" if s["avg_hours_to_close"] is not None else "—"
|
||||
lines.append(
|
||||
f"| {agent} | {s['total_prs']} | {s['merged']} | {s['closed_unmerged']} | "
|
||||
f"{s['open']} | {s['merge_rate']:.1%} | {s['rejection_rate']:.1%} | "
|
||||
f"{merge_hours} | {close_hours} |"
|
||||
)
|
||||
|
||||
lines.extend([
|
||||
"",
|
||||
"## Per-Repo Merge Rate",
|
||||
"",
|
||||
"| Repo | Total PRs | Merged | Merge Rate |",
|
||||
"|---|---|---:|---:|",
|
||||
])
|
||||
|
||||
for repo, s in sorted(data["repo_stats"].items(), key=lambda x: -x[1]["total"]):
|
||||
lines.append(
|
||||
f"| {repo} | {s['total']} | {s['merged']} | {s['merge_rate']:.1%} |"
|
||||
)
|
||||
|
||||
lines.extend([
|
||||
"",
|
||||
"## Methodology",
|
||||
"",
|
||||
"- **Agent classification** uses three signals in priority order:",
|
||||
" 1. Explicit title tag (e.g. `[Claude]`, `[Ezra]`)",
|
||||
" 2. Branch name containing agent name (e.g. `claude/issue-123`)",
|
||||
" 3. Git user (`claude` → claude, `Rockachopa` → burn-loop)",
|
||||
"- **Merge rate** = merged / (merged + closed_unmerged). Open PRs are excluded.",
|
||||
"- **Rejection rate** = closed_unmerged / (merged + closed_unmerged).",
|
||||
"- **Time metrics** are computed from created_at to merged_at / closed_at.",
|
||||
"",
|
||||
"## Raw Data",
|
||||
"",
|
||||
"```json",
|
||||
json.dumps(data["agent_summary"], indent=2),
|
||||
"```",
|
||||
"",
|
||||
])
|
||||
|
||||
return "\n".join(lines) + "\n"
|
||||
|
||||
|
||||
def main() -> int:
|
||||
parser = argparse.ArgumentParser(description="Cross-agent quality audit")
|
||||
parser.add_argument("--repos", nargs="+", default=DEFAULT_REPOS, help="Repos to audit")
|
||||
parser.add_argument("--scorecard", default="timmy-config/agent-quality-scorecard.md", help="Output path")
|
||||
parser.add_argument("--json", default=None, help="Also write raw JSON to path")
|
||||
args = parser.parse_args()
|
||||
|
||||
data = audit_repos(args.repos)
|
||||
|
||||
scorecard_path = Path(args.scorecard)
|
||||
scorecard_path.parent.mkdir(parents=True, exist_ok=True)
|
||||
scorecard_path.write_text(render_scorecard(data))
|
||||
print(f"Scorecard written to {scorecard_path}", file=sys.stderr)
|
||||
|
||||
if args.json:
|
||||
json_path = Path(args.json)
|
||||
json_path.parent.mkdir(parents=True, exist_ok=True)
|
||||
json_path.write_text(json.dumps(data, indent=2, default=str))
|
||||
print(f"Raw JSON written to {json_path}", file=sys.stderr)
|
||||
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
45
tests/test_cross_agent_quality_audit.py
Normal file
45
tests/test_cross_agent_quality_audit.py
Normal file
@@ -0,0 +1,45 @@
|
||||
"""Tests for cross_agent_quality_audit.py — #518."""
|
||||
|
||||
import pytest
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
sys.path.insert(0, str(Path(__file__).parent.parent / "scripts"))
|
||||
|
||||
from cross_agent_quality_audit import AgentClassifier, hours_between
|
||||
|
||||
|
||||
class TestAgentClassifier:
|
||||
def test_title_tag_claude(self):
|
||||
pr = {"title": "[Claude] fix auth middleware", "head": {"ref": "fix/123"}, "user": {"login": "rockachopa"}}
|
||||
assert AgentClassifier.classify(pr) == "claude"
|
||||
|
||||
def test_title_tag_ezra(self):
|
||||
pr = {"title": "[Ezra] tmux fleet launcher", "head": {"ref": "burn/10"}, "user": {"login": "rockachopa"}}
|
||||
assert AgentClassifier.classify(pr) == "ezra"
|
||||
|
||||
def test_branch_name_claude(self):
|
||||
pr = {"title": "fix auth", "head": {"ref": "claude/issue-1695"}, "user": {"login": "rockachopa"}}
|
||||
assert AgentClassifier.classify(pr) == "claude"
|
||||
|
||||
def test_user_mapping(self):
|
||||
pr = {"title": "some fix", "head": {"ref": "fix/1"}, "user": {"login": "claude"}}
|
||||
assert AgentClassifier.classify(pr) == "claude"
|
||||
|
||||
def test_rockachopa_maps_to_burn_loop(self):
|
||||
pr = {"title": "some fix", "head": {"ref": "fix/1"}, "user": {"login": "Rockachopa"}}
|
||||
assert AgentClassifier.classify(pr) == "burn-loop"
|
||||
|
||||
def test_unknown_fallback(self):
|
||||
pr = {"title": "some fix", "head": {"ref": "fix/1"}, "user": {"login": "random"}}
|
||||
assert AgentClassifier.classify(pr) == "unknown"
|
||||
|
||||
|
||||
class TestHoursBetween:
|
||||
def test_same_day(self):
|
||||
h = hours_between("2026-04-22T10:00:00Z", "2026-04-22T12:00:00Z")
|
||||
assert h == 2.0
|
||||
|
||||
def test_none_returns_none(self):
|
||||
assert hours_between(None, "2026-04-22T12:00:00Z") is None
|
||||
assert hours_between("2026-04-22T10:00:00Z", None) is None
|
||||
244
timmy-config/agent-quality-scorecard.md
Normal file
244
timmy-config/agent-quality-scorecard.md
Normal file
@@ -0,0 +1,244 @@
|
||||
# Cross-Agent Quality Scorecard
|
||||
|
||||
**Audited at:** 2026-04-22T06:17:43.574309+00:00
|
||||
**Repos audited:** timmy-home, hermes-agent, the-nexus, the-door, fleet-ops, burn-fleet, the-playground, compounding-intelligence, the-beacon, second-son-of-timmy, timmy-academy, timmy-config
|
||||
|
||||
## Per-Agent Summary
|
||||
|
||||
| Agent | Total PRs | Merged | Closed (unmerged) | Open | Merge Rate | Rejection Rate | Avg Hours to Merge | Avg Hours to Close |
|
||||
|---|---|---:|---:|---:|---:|---:|---:|---:|
|
||||
| burn-loop | 1733 | 346 | 1239 | 148 | 21.8% | 78.2% | 18.9 | 20.6 |
|
||||
| unknown | 843 | 598 | 214 | 31 | 73.6% | 26.4% | 2.3 | 11.3 |
|
||||
| claude | 264 | 138 | 121 | 5 | 53.3% | 46.7% | 3.3 | 6.2 |
|
||||
| gemini | 95 | 24 | 70 | 1 | 25.5% | 74.5% | 0.5 | 11.3 |
|
||||
| timmy | 28 | 15 | 11 | 2 | 57.7% | 42.3% | 9.8 | 20.2 |
|
||||
| bezalel | 21 | 11 | 9 | 1 | 55.0% | 45.0% | 2.7 | 8.0 |
|
||||
| allegro | 21 | 7 | 11 | 3 | 38.9% | 61.1% | 31.1 | 20.2 |
|
||||
| ezra | 8 | 2 | 3 | 3 | 40.0% | 60.0% | 4.4 | 16.8 |
|
||||
| kimi | 6 | 3 | 3 | 0 | 50.0% | 50.0% | 39.5 | 0.5 |
|
||||
| manus | 6 | 5 | 1 | 0 | 83.3% | 16.7% | 0.0 | 18.8 |
|
||||
| codex | 2 | 2 | 0 | 0 | 100.0% | 0.0% | 2.3 | — |
|
||||
|
||||
## Per-Repo Merge Rate
|
||||
|
||||
| Repo | Total PRs | Merged | Merge Rate |
|
||||
|---|---|---:|---:|
|
||||
| the-nexus | 985 | 501 | 51.0% |
|
||||
| hermes-agent | 519 | 128 | 25.0% |
|
||||
| timmy-config | 404 | 140 | 35.0% |
|
||||
| timmy-home | 270 | 104 | 39.0% |
|
||||
| fleet-ops | 266 | 84 | 32.0% |
|
||||
| the-beacon | 175 | 62 | 35.0% |
|
||||
| the-door | 153 | 31 | 20.0% |
|
||||
| second-son-of-timmy | 111 | 82 | 74.0% |
|
||||
| compounding-intelligence | 50 | 9 | 18.0% |
|
||||
| the-playground | 44 | 2 | 5.0% |
|
||||
| burn-fleet | 38 | 2 | 5.0% |
|
||||
| timmy-academy | 12 | 6 | 50.0% |
|
||||
|
||||
## Methodology
|
||||
|
||||
- **Agent classification** uses three signals in priority order:
|
||||
1. Explicit title tag (e.g. `[Claude]`, `[Ezra]`)
|
||||
2. Branch name containing agent name (e.g. `claude/issue-123`)
|
||||
3. Git user (`claude` → claude, `Rockachopa` → burn-loop)
|
||||
- **Merge rate** = merged / (merged + closed_unmerged). Open PRs are excluded.
|
||||
- **Rejection rate** = closed_unmerged / (merged + closed_unmerged).
|
||||
- **Time metrics** are computed from created_at to merged_at / closed_at.
|
||||
|
||||
## Raw Data
|
||||
|
||||
```json
|
||||
{
|
||||
"burn-loop": {
|
||||
"total_prs": 1733,
|
||||
"merged": 346,
|
||||
"closed_unmerged": 1239,
|
||||
"open": 148,
|
||||
"merge_rate": 0.218,
|
||||
"rejection_rate": 0.782,
|
||||
"avg_hours_to_merge": 18.9,
|
||||
"avg_hours_to_close": 20.6,
|
||||
"repos": [
|
||||
"burn-fleet",
|
||||
"compounding-intelligence",
|
||||
"fleet-ops",
|
||||
"hermes-agent",
|
||||
"second-son-of-timmy",
|
||||
"the-beacon",
|
||||
"the-door",
|
||||
"the-nexus",
|
||||
"the-playground",
|
||||
"timmy-academy",
|
||||
"timmy-config",
|
||||
"timmy-home"
|
||||
]
|
||||
},
|
||||
"unknown": {
|
||||
"total_prs": 843,
|
||||
"merged": 598,
|
||||
"closed_unmerged": 214,
|
||||
"open": 31,
|
||||
"merge_rate": 0.736,
|
||||
"rejection_rate": 0.264,
|
||||
"avg_hours_to_merge": 2.3,
|
||||
"avg_hours_to_close": 11.3,
|
||||
"repos": [
|
||||
"fleet-ops",
|
||||
"hermes-agent",
|
||||
"second-son-of-timmy",
|
||||
"the-beacon",
|
||||
"the-door",
|
||||
"the-nexus",
|
||||
"timmy-academy",
|
||||
"timmy-config",
|
||||
"timmy-home"
|
||||
]
|
||||
},
|
||||
"claude": {
|
||||
"total_prs": 264,
|
||||
"merged": 138,
|
||||
"closed_unmerged": 121,
|
||||
"open": 5,
|
||||
"merge_rate": 0.533,
|
||||
"rejection_rate": 0.467,
|
||||
"avg_hours_to_merge": 3.3,
|
||||
"avg_hours_to_close": 6.2,
|
||||
"repos": [
|
||||
"hermes-agent",
|
||||
"the-nexus",
|
||||
"timmy-config",
|
||||
"timmy-home"
|
||||
]
|
||||
},
|
||||
"gemini": {
|
||||
"total_prs": 95,
|
||||
"merged": 24,
|
||||
"closed_unmerged": 70,
|
||||
"open": 1,
|
||||
"merge_rate": 0.255,
|
||||
"rejection_rate": 0.745,
|
||||
"avg_hours_to_merge": 0.5,
|
||||
"avg_hours_to_close": 11.3,
|
||||
"repos": [
|
||||
"hermes-agent",
|
||||
"the-nexus",
|
||||
"timmy-config",
|
||||
"timmy-home"
|
||||
]
|
||||
},
|
||||
"timmy": {
|
||||
"total_prs": 28,
|
||||
"merged": 15,
|
||||
"closed_unmerged": 11,
|
||||
"open": 2,
|
||||
"merge_rate": 0.577,
|
||||
"rejection_rate": 0.423,
|
||||
"avg_hours_to_merge": 9.8,
|
||||
"avg_hours_to_close": 20.2,
|
||||
"repos": [
|
||||
"burn-fleet",
|
||||
"hermes-agent",
|
||||
"the-nexus",
|
||||
"timmy-config",
|
||||
"timmy-home"
|
||||
]
|
||||
},
|
||||
"bezalel": {
|
||||
"total_prs": 21,
|
||||
"merged": 11,
|
||||
"closed_unmerged": 9,
|
||||
"open": 1,
|
||||
"merge_rate": 0.55,
|
||||
"rejection_rate": 0.45,
|
||||
"avg_hours_to_merge": 2.7,
|
||||
"avg_hours_to_close": 8.0,
|
||||
"repos": [
|
||||
"burn-fleet",
|
||||
"hermes-agent",
|
||||
"the-beacon",
|
||||
"the-nexus",
|
||||
"timmy-config",
|
||||
"timmy-home"
|
||||
]
|
||||
},
|
||||
"allegro": {
|
||||
"total_prs": 21,
|
||||
"merged": 7,
|
||||
"closed_unmerged": 11,
|
||||
"open": 3,
|
||||
"merge_rate": 0.389,
|
||||
"rejection_rate": 0.611,
|
||||
"avg_hours_to_merge": 31.1,
|
||||
"avg_hours_to_close": 20.2,
|
||||
"repos": [
|
||||
"burn-fleet",
|
||||
"hermes-agent",
|
||||
"the-beacon",
|
||||
"the-nexus",
|
||||
"timmy-config",
|
||||
"timmy-home"
|
||||
]
|
||||
},
|
||||
"ezra": {
|
||||
"total_prs": 8,
|
||||
"merged": 2,
|
||||
"closed_unmerged": 3,
|
||||
"open": 3,
|
||||
"merge_rate": 0.4,
|
||||
"rejection_rate": 0.6,
|
||||
"avg_hours_to_merge": 4.4,
|
||||
"avg_hours_to_close": 16.8,
|
||||
"repos": [
|
||||
"burn-fleet",
|
||||
"fleet-ops",
|
||||
"timmy-config",
|
||||
"timmy-home"
|
||||
]
|
||||
},
|
||||
"kimi": {
|
||||
"total_prs": 6,
|
||||
"merged": 3,
|
||||
"closed_unmerged": 3,
|
||||
"open": 0,
|
||||
"merge_rate": 0.5,
|
||||
"rejection_rate": 0.5,
|
||||
"avg_hours_to_merge": 39.5,
|
||||
"avg_hours_to_close": 0.5,
|
||||
"repos": [
|
||||
"hermes-agent",
|
||||
"the-nexus",
|
||||
"timmy-home"
|
||||
]
|
||||
},
|
||||
"manus": {
|
||||
"total_prs": 6,
|
||||
"merged": 5,
|
||||
"closed_unmerged": 1,
|
||||
"open": 0,
|
||||
"merge_rate": 0.833,
|
||||
"rejection_rate": 0.167,
|
||||
"avg_hours_to_merge": 0.0,
|
||||
"avg_hours_to_close": 18.8,
|
||||
"repos": [
|
||||
"the-nexus",
|
||||
"timmy-config"
|
||||
]
|
||||
},
|
||||
"codex": {
|
||||
"total_prs": 2,
|
||||
"merged": 2,
|
||||
"closed_unmerged": 0,
|
||||
"open": 0,
|
||||
"merge_rate": 1.0,
|
||||
"rejection_rate": 0.0,
|
||||
"avg_hours_to_merge": 2.3,
|
||||
"avg_hours_to_close": null,
|
||||
"repos": [
|
||||
"timmy-config",
|
||||
"timmy-home"
|
||||
]
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
Reference in New Issue
Block a user