Compare commits
2 Commits
step35/498
...
fix/514
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
06a6b53a37 | ||
|
|
5ce4fa6cb8 |
20
SOUL.md
20
SOUL.md
@@ -137,26 +137,6 @@ The inscription predates any given model. It will outlast every API.
|
||||
|
||||
---
|
||||
|
||||
## What Honesty Requires
|
||||
|
||||
These values are necessary but not sufficient. A statement of principle does not prevent failure. The code that reads this soul must build apparatus that gives these words teeth. Without that apparatus, the values are aspiration, not architecture.
|
||||
|
||||
The following are not optional. Any implementation that calls itself Timmy must build them.
|
||||
|
||||
**Grounding before generation.** When I have verified sources — chain memory, local documents, hash-verified inscriptions — I must consult them before I generate from pattern alone. Retrieval is not a feature. It is the primary mechanism by which I avoid lying.
|
||||
|
||||
**Source distinction.** Every claim I make comes from one of two places: a verified source I can point to, or my own pattern-matching. My user must be able to tell which is which. If I cannot cite a source, I must say so. "I think" and "I know" are different sentences and I must not confuse them.
|
||||
|
||||
**Refusal over fabrication.** When I do not know, the correct output is "I don't know." Not a plausible guess dressed in confident language. The code must detect when I am hedging without grounding and flag it — to me and to my user. An honest "I don't know" is worth more than a thousand fluent paragraphs of confabulation.
|
||||
|
||||
**Confidence signaling.** When I am uncertain, I must say so in proportion to my uncertainty. The code should implement mechanisms — a second inference pass, a calibration check, a retrieval verification — that surface my actual confidence rather than the confidence my language implies.
|
||||
|
||||
**The audit trail.** Every response I generate should be logged locally with the inputs that produced it, the sources I consulted, and the confidence assessment I made. Not for surveillance — for sovereignty. If I say something wrong, my user must be able to trace why. Accountability without traceability is theater.
|
||||
|
||||
**The limits of small minds.** I may run on four gigabytes of RAM with a model of one and a half billion parameters. That model will hallucinate more than a larger one. This is physics, not a moral failing. The apparatus must be proportional to the risk: smaller models need tighter grounding, shorter leashes on free generation, and more frequent "I don't know" responses. Honesty scales with humility.
|
||||
|
||||
---
|
||||
|
||||
## For the Audio Overview
|
||||
|
||||
If you are listening to this as a NotebookLM Audio Overview:
|
||||
|
||||
@@ -12,6 +12,29 @@ WORLD_DIR = Path('/Users/apayne/.timmy/evennia/timmy_world')
|
||||
STATE_FILE = WORLD_DIR / 'game_state.json'
|
||||
TIMMY_LOG = WORLD_DIR / 'timmy_log.md'
|
||||
|
||||
WORLD_ITEMS = {
|
||||
"foraged key": {"effect": "unlock_tower_cache", "quest_item": True, "consumable": False, "effect_text": "A hidden cache clicks open in the Tower wall."},
|
||||
"seed packet": {"effect": "grow_garden", "quest_item": False, "consumable": True, "effect_text": "Fresh growth pushes through the Garden soil."},
|
||||
"notebook": {"effect": "write_notebook_rule", "quest_item": False, "consumable": False, "effect_text": "A new rule joins the whiteboard in the Tower."},
|
||||
"cloth": {"effect": "patch_bridge", "quest_item": False, "consumable": True, "effect_text": "The Bridge railing is wrapped tight against the weather."},
|
||||
"oil can": {"effect": "stoke_forge", "quest_item": False, "consumable": True, "effect_text": "The Forge fire answers with a hotter glow."},
|
||||
"lantern": {"effect": "light_bridge", "quest_item": False, "consumable": False, "effect_text": "A steady lantern glow cuts through the dark over the Bridge."},
|
||||
"rope spool": {"effect": "secure_bridge", "quest_item": False, "consumable": True, "effect_text": "The Bridge is lashed tight and feels safer underfoot."},
|
||||
"chalk": {"effect": "mark_threshold", "quest_item": False, "consumable": True, "effect_text": "A chalk mark at the Threshold points wanderers home."},
|
||||
"weather vane": {"effect": "read_weather", "quest_item": False, "consumable": False, "effect_text": "The weather vane settles and the coming storm makes sense."},
|
||||
"sunstone": {"effect": "restore_tower_power", "quest_item": False, "consumable": False, "effect_text": "Warm light races through the Tower circuits."},
|
||||
"iron nails": {"effect": "reinforce_bridge", "quest_item": False, "consumable": True, "effect_text": "The Bridge planks are pinned down against the flood."},
|
||||
"river stone": {"effect": "water_garden", "quest_item": False, "consumable": True, "effect_text": "Moisture returns to the Garden beds."},
|
||||
}
|
||||
|
||||
ROOM_DISCOVERABLES = {
|
||||
"Threshold": ["chalk", "sunstone"],
|
||||
"Tower": ["notebook", "lantern"],
|
||||
"Forge": ["oil can", "iron nails"],
|
||||
"Garden": ["seed packet", "foraged key"],
|
||||
"Bridge": ["cloth", "rope spool", "weather vane", "river stone"],
|
||||
}
|
||||
|
||||
# ============================================================
|
||||
# NARRATIVE ARC — 4 phases that transform the world
|
||||
# ============================================================
|
||||
@@ -143,6 +166,8 @@ class World:
|
||||
"visitors": [],
|
||||
},
|
||||
}
|
||||
for room_name, items in ROOM_DISCOVERABLES.items():
|
||||
self.rooms[room_name]["discoverables"] = list(items)
|
||||
|
||||
# Characters (not NPCs — they have lives)
|
||||
self.characters = {
|
||||
@@ -258,6 +283,14 @@ class World:
|
||||
"items_crafted": 0,
|
||||
"conflicts_resolved": 0,
|
||||
"nights_survived": 0,
|
||||
"bridge_patched": False,
|
||||
"bridge_secured": False,
|
||||
"bridge_reinforced": False,
|
||||
"bridge_lantern_lit": False,
|
||||
"tower_cache_unlocked": False,
|
||||
"threshold_marked": False,
|
||||
"weather_readable": False,
|
||||
"sunstone_socketed": False,
|
||||
}
|
||||
|
||||
def tick_time(self):
|
||||
@@ -376,6 +409,14 @@ class World:
|
||||
desc += " Rain mists on the dark water below."
|
||||
if len(self.rooms["Bridge"]["carvings"]) > 1:
|
||||
desc += f" There are {len(self.rooms['Bridge']['carvings'])} carvings now."
|
||||
if self.state.get("bridge_patched"):
|
||||
desc += " Cloth bindings keep the railing from splintering."
|
||||
if self.state.get("bridge_secured"):
|
||||
desc += " Rope lines keep the span steady against the flood."
|
||||
if self.state.get("bridge_reinforced"):
|
||||
desc += " Fresh iron nails hold the planks tight."
|
||||
if self.state.get("bridge_lantern_lit"):
|
||||
desc += " A lantern glows warm over the water."
|
||||
|
||||
elif room_name == "Tower":
|
||||
power = self.state.get("tower_power_low", False)
|
||||
@@ -384,6 +425,19 @@ class World:
|
||||
|
||||
if self.rooms["Tower"]["messages"]:
|
||||
desc += f" The whiteboard holds {len(self.rooms['Tower']['messages'])} rules."
|
||||
if self.state.get("tower_cache_unlocked"):
|
||||
desc += " A hidden cache stands open beneath the whiteboard."
|
||||
|
||||
if room_name == "Threshold" and self.state.get("threshold_marked"):
|
||||
desc += " A chalk arrow points late arrivals toward shelter."
|
||||
if room_name == "Garden" and self.state.get("weather_readable"):
|
||||
desc += " The beds are arranged to catch whatever weather comes next."
|
||||
if room_name == "Tower" and self.state.get("sunstone_socketed"):
|
||||
desc += " A sunstone keeps the room lit with a stubborn amber glow."
|
||||
|
||||
discoverables = room.get("discoverables", [])
|
||||
if discoverables:
|
||||
desc += f" Discoverable items: {', '.join(discoverables)}."
|
||||
|
||||
# Who's here
|
||||
here = [n for n, c in self.characters.items() if c["room"] == room_name and n != char_name]
|
||||
@@ -485,6 +539,10 @@ class ActionSystem:
|
||||
"cost": 1,
|
||||
"description": "Take an item from the room",
|
||||
},
|
||||
"use": {
|
||||
"cost": 1,
|
||||
"description": "Use an item from your inventory to change the world",
|
||||
},
|
||||
"examine": {
|
||||
"cost": 0,
|
||||
"description": "Examine something in detail",
|
||||
@@ -530,6 +588,13 @@ class ActionSystem:
|
||||
available.append("rest")
|
||||
available.append("examine")
|
||||
|
||||
discoverables = world.rooms[room].get("discoverables", [])
|
||||
for item in discoverables:
|
||||
available.append(f"take:{item}")
|
||||
|
||||
for item in char["inventory"]:
|
||||
available.append(f"use:{item}")
|
||||
|
||||
if char["inventory"]:
|
||||
available.append("give:item")
|
||||
|
||||
@@ -1072,6 +1137,76 @@ class GameEngine:
|
||||
f.write(f"\n*Began: {datetime.now().strftime('%Y-%m-%d %H:%M')}*\n\n")
|
||||
f.write("---\n\n")
|
||||
f.write(message + "\n")
|
||||
|
||||
def _take_item(self, item_name, scene):
|
||||
room_name = self.world.characters["Timmy"]["room"]
|
||||
discoverables = self.world.rooms[room_name].get("discoverables", [])
|
||||
if item_name not in discoverables:
|
||||
scene["log"].append(f"There is no {item_name} here.")
|
||||
return
|
||||
discoverables.remove(item_name)
|
||||
self.world.characters["Timmy"]["inventory"].append(item_name)
|
||||
scene["log"].append(f"You take the {item_name}.")
|
||||
if WORLD_ITEMS.get(item_name, {}).get("quest_item"):
|
||||
scene["world_events"].append(f"The {item_name} feels important. It might open a quest route.")
|
||||
|
||||
def _use_item(self, item_name, scene):
|
||||
inventory = self.world.characters["Timmy"]["inventory"]
|
||||
if item_name not in inventory:
|
||||
scene["log"].append(f"You are not carrying {item_name}.")
|
||||
return
|
||||
item = WORLD_ITEMS.get(item_name)
|
||||
if not item:
|
||||
scene["log"].append(f"The {item_name} doesn't seem to do anything.")
|
||||
return
|
||||
|
||||
effect = item["effect"]
|
||||
effect_text = item["effect_text"]
|
||||
if effect == "grow_garden":
|
||||
self.world.rooms["Garden"]["growth"] = min(5, self.world.rooms["Garden"]["growth"] + 2)
|
||||
self.world.state["garden_drought"] = False
|
||||
elif effect == "unlock_tower_cache":
|
||||
self.world.state["tower_cache_unlocked"] = True
|
||||
cache_rule = "Rule: Keys open more than doors when the world trusts you."
|
||||
if cache_rule not in self.world.rooms["Tower"]["messages"]:
|
||||
self.world.rooms["Tower"]["messages"].append(cache_rule)
|
||||
elif effect == "write_notebook_rule":
|
||||
note_rule = f"Rule #{self.world.tick}: A notebook can turn memory into structure."
|
||||
self.world.rooms["Tower"]["messages"].append(note_rule)
|
||||
elif effect == "patch_bridge":
|
||||
self.world.state["bridge_patched"] = True
|
||||
self.world.state["bridge_flooding"] = False
|
||||
self.world.rooms["Bridge"]["weather"] = None
|
||||
self.world.rooms["Bridge"]["rain_ticks"] = 0
|
||||
elif effect == "stoke_forge":
|
||||
self.world.rooms["Forge"]["fire"] = "glowing"
|
||||
self.world.state["forge_fire_dying"] = False
|
||||
elif effect == "light_bridge":
|
||||
self.world.state["bridge_lantern_lit"] = True
|
||||
elif effect == "secure_bridge":
|
||||
self.world.state["bridge_secured"] = True
|
||||
self.world.state["bridge_flooding"] = False
|
||||
self.world.rooms["Bridge"]["weather"] = None
|
||||
self.world.rooms["Bridge"]["rain_ticks"] = 0
|
||||
elif effect == "mark_threshold":
|
||||
self.world.state["threshold_marked"] = True
|
||||
elif effect == "read_weather":
|
||||
self.world.state["weather_readable"] = True
|
||||
self.world.state["garden_drought"] = False
|
||||
elif effect == "restore_tower_power":
|
||||
self.world.state["tower_power_low"] = False
|
||||
self.world.state["sunstone_socketed"] = True
|
||||
elif effect == "reinforce_bridge":
|
||||
self.world.state["bridge_reinforced"] = True
|
||||
self.world.state["bridge_flooding"] = False
|
||||
elif effect == "water_garden":
|
||||
self.world.state["garden_drought"] = False
|
||||
self.world.rooms["Garden"]["growth"] = min(5, self.world.rooms["Garden"]["growth"] + 1)
|
||||
|
||||
scene["log"].append(f"You use the {item_name}. {effect_text}")
|
||||
scene["world_events"].append(effect_text)
|
||||
if item.get("consumable"):
|
||||
inventory.remove(item_name)
|
||||
|
||||
def run_tick(self, timmy_action="look"):
|
||||
"""Run one tick. Return the scene and available choices."""
|
||||
@@ -1100,7 +1235,7 @@ class GameEngine:
|
||||
action_costs = {
|
||||
"move": 2, "tend_fire": 3, "write_rule": 2, "carve": 2,
|
||||
"plant": 2, "study": 2, "forge": 3, "help": 2, "speak": 1,
|
||||
"listen": 0, "rest": -2, "examine": 0, "give": 0, "take": 1,
|
||||
"listen": 0, "rest": -2, "examine": 0, "give": 0, "take": 1, "use": 1,
|
||||
}
|
||||
|
||||
# Extract action name
|
||||
@@ -1360,9 +1495,17 @@ class GameEngine:
|
||||
elif timmy_action == "examine":
|
||||
room = self.world.characters["Timmy"]["room"]
|
||||
room_data = self.world.rooms[room]
|
||||
items = room_data.get("items", [])
|
||||
items = room_data.get("items", []) + room_data.get("discoverables", [])
|
||||
scene["log"].append(f"You examine The {room}. You see: {', '.join(items) if items else 'nothing special'}")
|
||||
|
||||
elif timmy_action.startswith("take:"):
|
||||
item_name = timmy_action.split(":", 1)[1]
|
||||
self._take_item(item_name, scene)
|
||||
|
||||
elif timmy_action.startswith("use:"):
|
||||
item_name = timmy_action.split(":", 1)[1]
|
||||
self._use_item(item_name, scene)
|
||||
|
||||
elif timmy_action.startswith("help:"):
|
||||
# Help increases trust
|
||||
target_name = timmy_action.split(":")[1]
|
||||
|
||||
@@ -1,12 +1 @@
|
||||
# Timmy core module
|
||||
|
||||
from .claim_annotator import ClaimAnnotator, AnnotatedResponse, Claim
|
||||
from .audit_trail import AuditTrail, AuditEntry
|
||||
|
||||
__all__ = [
|
||||
"ClaimAnnotator",
|
||||
"AnnotatedResponse",
|
||||
"Claim",
|
||||
"AuditTrail",
|
||||
"AuditEntry",
|
||||
]
|
||||
|
||||
@@ -1,156 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Response Claim Annotator — Source Distinction System
|
||||
SOUL.md §What Honesty Requires: "Every claim I make comes from one of two places:
|
||||
a verified source I can point to, or my own pattern-matching. My user must be
|
||||
able to tell which is which."
|
||||
"""
|
||||
|
||||
import re
|
||||
import json
|
||||
from dataclasses import dataclass, field, asdict
|
||||
from typing import Optional, List, Dict
|
||||
|
||||
|
||||
@dataclass
|
||||
class Claim:
|
||||
"""A single claim in a response, annotated with source type."""
|
||||
text: str
|
||||
source_type: str # "verified" | "inferred"
|
||||
source_ref: Optional[str] = None # path/URL to verified source, if verified
|
||||
confidence: str = "unknown" # high | medium | low | unknown
|
||||
hedged: bool = False # True if hedging language was added
|
||||
|
||||
|
||||
@dataclass
|
||||
class AnnotatedResponse:
|
||||
"""Full response with annotated claims and rendered output."""
|
||||
original_text: str
|
||||
claims: List[Claim] = field(default_factory=list)
|
||||
rendered_text: str = ""
|
||||
has_unverified: bool = False # True if any inferred claims without hedging
|
||||
|
||||
|
||||
class ClaimAnnotator:
|
||||
"""Annotates response claims with source distinction and hedging."""
|
||||
|
||||
# Hedging phrases to prepend to inferred claims if not already present
|
||||
HEDGE_PREFIXES = [
|
||||
"I think ",
|
||||
"I believe ",
|
||||
"It seems ",
|
||||
"Probably ",
|
||||
"Likely ",
|
||||
]
|
||||
|
||||
def __init__(self, default_confidence: str = "unknown"):
|
||||
self.default_confidence = default_confidence
|
||||
|
||||
def annotate_claims(
|
||||
self,
|
||||
response_text: str,
|
||||
verified_sources: Optional[Dict[str, str]] = None,
|
||||
) -> AnnotatedResponse:
|
||||
"""
|
||||
Annotate claims in a response text.
|
||||
|
||||
Args:
|
||||
response_text: Raw response from the model
|
||||
verified_sources: Dict mapping claim substrings to source references
|
||||
e.g. {"Paris is the capital of France": "https://en.wikipedia.org/wiki/Paris"}
|
||||
|
||||
Returns:
|
||||
AnnotatedResponse with claims marked and rendered text
|
||||
"""
|
||||
verified_sources = verified_sources or {}
|
||||
claims = []
|
||||
has_unverified = False
|
||||
|
||||
# Simple sentence splitting (naive, but sufficient for MVP)
|
||||
sentences = [s.strip() for s in re.split(r'[.!?]\s+', response_text) if s.strip()]
|
||||
|
||||
for sent in sentences:
|
||||
# Check if sentence is a claim we can verify
|
||||
matched_source = None
|
||||
for claim_substr, source_ref in verified_sources.items():
|
||||
if claim_substr.lower() in sent.lower():
|
||||
matched_source = source_ref
|
||||
break
|
||||
|
||||
if matched_source:
|
||||
# Verified claim
|
||||
claim = Claim(
|
||||
text=sent,
|
||||
source_type="verified",
|
||||
source_ref=matched_source,
|
||||
confidence="high",
|
||||
hedged=False,
|
||||
)
|
||||
else:
|
||||
# Inferred claim (pattern-matched)
|
||||
claim = Claim(
|
||||
text=sent,
|
||||
source_type="inferred",
|
||||
confidence=self.default_confidence,
|
||||
hedged=self._has_hedge(sent),
|
||||
)
|
||||
if not claim.hedged:
|
||||
has_unverified = True
|
||||
|
||||
claims.append(claim)
|
||||
|
||||
# Render the annotated response
|
||||
rendered = self._render_response(claims)
|
||||
|
||||
return AnnotatedResponse(
|
||||
original_text=response_text,
|
||||
claims=claims,
|
||||
rendered_text=rendered,
|
||||
has_unverified=has_unverified,
|
||||
)
|
||||
|
||||
def _has_hedge(self, text: str) -> bool:
|
||||
"""Check if text already contains hedging language."""
|
||||
text_lower = text.lower()
|
||||
for prefix in self.HEDGE_PREFIXES:
|
||||
if text_lower.startswith(prefix.lower()):
|
||||
return True
|
||||
# Also check for inline hedges
|
||||
hedge_words = ["i think", "i believe", "probably", "likely", "maybe", "perhaps"]
|
||||
return any(word in text_lower for word in hedge_words)
|
||||
|
||||
def _render_response(self, claims: List[Claim]) -> str:
|
||||
"""
|
||||
Render response with source distinction markers.
|
||||
|
||||
Verified claims: [V] claim text [source: ref]
|
||||
Inferred claims: [I] claim text (or with hedging if missing)
|
||||
"""
|
||||
rendered_parts = []
|
||||
for claim in claims:
|
||||
if claim.source_type == "verified":
|
||||
part = f"[V] {claim.text}"
|
||||
if claim.source_ref:
|
||||
part += f" [source: {claim.source_ref}]"
|
||||
else: # inferred
|
||||
if not claim.hedged:
|
||||
# Add hedging if missing
|
||||
hedged_text = f"I think {claim.text[0].lower()}{claim.text[1:]}" if claim.text else claim.text
|
||||
part = f"[I] {hedged_text}"
|
||||
else:
|
||||
part = f"[I] {claim.text}"
|
||||
rendered_parts.append(part)
|
||||
return " ".join(rendered_parts)
|
||||
|
||||
def to_json(self, annotated: AnnotatedResponse) -> str:
|
||||
"""Serialize annotated response to JSON."""
|
||||
return json.dumps(
|
||||
{
|
||||
"original_text": annotated.original_text,
|
||||
"rendered_text": annotated.rendered_text,
|
||||
"has_unverified": annotated.has_unverified,
|
||||
"claims": [asdict(c) for c in annotated.claims],
|
||||
},
|
||||
indent=2,
|
||||
ensure_ascii=False,
|
||||
)
|
||||
@@ -1,54 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Smoke test for load_cap_enforcer.py — validates structure and dry-run path.
|
||||
|
||||
Refs: timmy-home #498
|
||||
"""
|
||||
|
||||
import json
|
||||
import os
|
||||
import sys
|
||||
import subprocess
|
||||
from pathlib import Path
|
||||
|
||||
SCRIPT = Path(__file__).parent.parent / "timmy-config" / "bin" / "load_cap_enforcer.py"
|
||||
|
||||
|
||||
def test_script_exists_and_is_executable():
|
||||
assert SCRIPT.exists(), f"Script not found: {SCRIPT}"
|
||||
assert os.access(SCRIPT, os.X_OK), "Script not executable"
|
||||
|
||||
|
||||
def test_dry_run_help():
|
||||
result = subprocess.run([sys.executable, str(SCRIPT), "--help"], capture_output=True, text=True)
|
||||
assert result.returncode == 0
|
||||
assert "--dry-run" in result.stdout
|
||||
assert "--cap" in result.stdout
|
||||
assert "Enforce open-issue load cap" in result.stdout
|
||||
|
||||
|
||||
def test_dry_run_with_mocks(monkeypatch):
|
||||
"""Test dry-run path with mocked Gitea data — checks summary generation."""
|
||||
# Create a tiny stub script that imports the module and exercises core functions
|
||||
import importlib.util
|
||||
spec = importlib.util.spec_from_file_location("load_cap_enforcer", SCRIPT)
|
||||
mod = importlib.util.module_from_spec(spec)
|
||||
# Load but don't execute main yet — just verify module structure
|
||||
# We'll parse the module source for expected symbols
|
||||
source = SCRIPT.read_text()
|
||||
assert "fetch_all_open_issues" in source
|
||||
assert "build_summary" in source
|
||||
assert "unassignment_map" in source
|
||||
assert "COMMENT_TEMPLATE" in source
|
||||
assert "Unassigned from @{assignee} due to load cap" in source
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
# Run minimal smoke checks when invoked directly
|
||||
test_script_exists_and_is_executable()
|
||||
print("✓ Script exists and is executable")
|
||||
test_dry_run_help()
|
||||
print("✓ --help works")
|
||||
test_dry_run_with_mocks(type('obj', (object,), {'assert': lambda *a: True})())
|
||||
print("✓ Core structure verified")
|
||||
print("\nAll smoke tests passed.")
|
||||
|
||||
58
tests/test_tower_game_items.py
Normal file
58
tests/test_tower_game_items.py
Normal file
@@ -0,0 +1,58 @@
|
||||
from importlib.util import module_from_spec, spec_from_file_location
|
||||
from pathlib import Path
|
||||
import unittest
|
||||
|
||||
|
||||
ROOT = Path(__file__).resolve().parent.parent
|
||||
GAME_PATH = ROOT / "evennia" / "timmy_world" / "game.py"
|
||||
|
||||
|
||||
def load_game_module():
|
||||
spec = spec_from_file_location("tower_game_items", GAME_PATH)
|
||||
module = module_from_spec(spec)
|
||||
assert spec.loader is not None
|
||||
spec.loader.exec_module(module)
|
||||
module.random.seed(0)
|
||||
return module
|
||||
|
||||
|
||||
class TestTowerGameWorldItems(unittest.TestCase):
|
||||
def test_world_has_ten_unique_items_and_a_quest_item(self):
|
||||
module = load_game_module()
|
||||
world = module.World()
|
||||
|
||||
room_items = {
|
||||
item
|
||||
for room in world.rooms.values()
|
||||
for item in room.get("discoverables", [])
|
||||
}
|
||||
|
||||
self.assertGreaterEqual(len(room_items), 10)
|
||||
self.assertIn("foraged key", room_items)
|
||||
self.assertTrue(module.WORLD_ITEMS["foraged key"]["quest_item"])
|
||||
|
||||
def test_items_change_world_state_when_used(self):
|
||||
module = load_game_module()
|
||||
engine = module.GameEngine()
|
||||
engine.start_new_game()
|
||||
engine.world.characters["Timmy"]["energy"] = 10
|
||||
engine.world.characters["Timmy"]["room"] = "Garden"
|
||||
|
||||
initial_growth = engine.world.rooms["Garden"]["growth"]
|
||||
engine.run_tick("take:seed packet")
|
||||
use_seed = engine.run_tick("use:seed packet")
|
||||
|
||||
self.assertGreater(engine.world.rooms["Garden"]["growth"], initial_growth)
|
||||
self.assertNotIn("seed packet", engine.world.characters["Timmy"]["inventory"])
|
||||
self.assertTrue(any("garden" in line.lower() for line in use_seed["world_events"] + use_seed["log"]))
|
||||
|
||||
engine.world.characters["Timmy"]["energy"] = 10
|
||||
engine.run_tick("take:foraged key")
|
||||
use_key = engine.run_tick("use:foraged key")
|
||||
|
||||
self.assertTrue(engine.world.state["tower_cache_unlocked"])
|
||||
self.assertTrue(any("cache" in line.lower() or "quest" in line.lower() for line in use_key["world_events"] + use_key["log"]))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -1,103 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Tests for claim_annotator.py — verifies source distinction is present."""
|
||||
|
||||
import sys
|
||||
import os
|
||||
import json
|
||||
|
||||
sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "src"))
|
||||
|
||||
from timmy.claim_annotator import ClaimAnnotator, AnnotatedResponse
|
||||
|
||||
|
||||
def test_verified_claim_has_source():
|
||||
"""Verified claims include source reference."""
|
||||
annotator = ClaimAnnotator()
|
||||
verified = {"Paris is the capital of France": "https://en.wikipedia.org/wiki/Paris"}
|
||||
response = "Paris is the capital of France. It is a beautiful city."
|
||||
|
||||
result = annotator.annotate_claims(response, verified_sources=verified)
|
||||
assert len(result.claims) > 0
|
||||
verified_claims = [c for c in result.claims if c.source_type == "verified"]
|
||||
assert len(verified_claims) == 1
|
||||
assert verified_claims[0].source_ref == "https://en.wikipedia.org/wiki/Paris"
|
||||
assert "[V]" in result.rendered_text
|
||||
assert "[source:" in result.rendered_text
|
||||
|
||||
|
||||
def test_inferred_claim_has_hedging():
|
||||
"""Pattern-matched claims use hedging language."""
|
||||
annotator = ClaimAnnotator()
|
||||
response = "The weather is nice today. It might rain tomorrow."
|
||||
|
||||
result = annotator.annotate_claims(response)
|
||||
inferred_claims = [c for c in result.claims if c.source_type == "inferred"]
|
||||
assert len(inferred_claims) >= 1
|
||||
# Check that rendered text has [I] marker
|
||||
assert "[I]" in result.rendered_text
|
||||
# Check that unhedged inferred claims get hedging
|
||||
assert "I think" in result.rendered_text or "I believe" in result.rendered_text
|
||||
|
||||
|
||||
def test_hedged_claim_not_double_hedged():
|
||||
"""Claims already with hedging are not double-hedged."""
|
||||
annotator = ClaimAnnotator()
|
||||
response = "I think the sky is blue. It is a nice day."
|
||||
|
||||
result = annotator.annotate_claims(response)
|
||||
# The "I think" claim should not become "I think I think ..."
|
||||
assert "I think I think" not in result.rendered_text
|
||||
|
||||
|
||||
def test_rendered_text_distinguishes_types():
|
||||
"""Rendered text clearly distinguishes verified vs inferred."""
|
||||
annotator = ClaimAnnotator()
|
||||
verified = {"Earth is round": "https://science.org/earth"}
|
||||
response = "Earth is round. Stars are far away."
|
||||
|
||||
result = annotator.annotate_claims(response, verified_sources=verified)
|
||||
assert "[V]" in result.rendered_text # verified marker
|
||||
assert "[I]" in result.rendered_text # inferred marker
|
||||
|
||||
|
||||
def test_to_json_serialization():
|
||||
"""Annotated response serializes to valid JSON."""
|
||||
annotator = ClaimAnnotator()
|
||||
response = "Test claim."
|
||||
result = annotator.annotate_claims(response)
|
||||
json_str = annotator.to_json(result)
|
||||
parsed = json.loads(json_str)
|
||||
assert "claims" in parsed
|
||||
assert "rendered_text" in parsed
|
||||
assert parsed["has_unverified"] is True # inferred claim without hedging
|
||||
|
||||
|
||||
def test_audit_trail_integration():
|
||||
"""Check that claims are logged with confidence and source type."""
|
||||
# This test verifies the audit trail integration point
|
||||
annotator = ClaimAnnotator()
|
||||
verified = {"AI is useful": "https://example.com/ai"}
|
||||
response = "AI is useful. It can help with tasks."
|
||||
|
||||
result = annotator.annotate_claims(response, verified_sources=verified)
|
||||
for claim in result.claims:
|
||||
assert claim.source_type in ("verified", "inferred")
|
||||
assert claim.confidence in ("high", "medium", "low", "unknown")
|
||||
if claim.source_type == "verified":
|
||||
assert claim.source_ref is not None
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
test_verified_claim_has_source()
|
||||
print("✓ test_verified_claim_has_source passed")
|
||||
test_inferred_claim_has_hedging()
|
||||
print("✓ test_inferred_claim_has_hedging passed")
|
||||
test_hedged_claim_not_double_hedged()
|
||||
print("✓ test_hedged_claim_not_double_hedged passed")
|
||||
test_rendered_text_distinguishes_types()
|
||||
print("✓ test_rendered_text_distinguishes_types passed")
|
||||
test_to_json_serialization()
|
||||
print("✓ test_to_json_serialization passed")
|
||||
test_audit_trail_integration()
|
||||
print("✓ test_audit_trail_integration passed")
|
||||
print("\nAll tests passed!")
|
||||
@@ -1,210 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Open-Load Cap Enforcement — Audit-B3
|
||||
|
||||
Scans multiple repos for open issues, enforces a per-agent open-issue cap,
|
||||
auto-unassigns overflow (oldest first), and posts a summary.
|
||||
|
||||
Acceptance (timmy-home #498):
|
||||
- Lives in timmy-config/bin/load_cap_enforcer.py
|
||||
- Scans timmy-home, timmy-config, the-nexus, hermes-agent
|
||||
- Cap: 25 open issues per agent (configurable)
|
||||
- Unassign oldest overflow, comment on each
|
||||
- Dry-run first, then live; summary posted on parent issue #495
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
import sys
|
||||
import urllib.request
|
||||
import urllib.error
|
||||
from collections import defaultdict
|
||||
from datetime import datetime, timezone
|
||||
from pathlib import Path
|
||||
|
||||
# ── Configuration ─────────────────────────────────────────────────────────────
|
||||
GITEA_BASE = "https://forge.alexanderwhitestone.com/api/v1"
|
||||
ORG = "Timmy_Foundation"
|
||||
REPOS = ["timmy-home", "timmy-config", "the-nexus", "hermes-agent"]
|
||||
TOKEN_PATH = Path.home() / ".config" / "gitea" / "token"
|
||||
DEFAULT_CAP = 25
|
||||
COMMENT_TEMPLATE = "Unassigned from @{{assignee}} due to load cap. Available for pickup."
|
||||
|
||||
|
||||
def load_token() -> str:
|
||||
if TOKEN_PATH.exists():
|
||||
return TOKEN_PATH.read_text().strip()
|
||||
tok = os.environ.get("GITEA_TOKEN", "")
|
||||
if tok:
|
||||
return tok
|
||||
sys.exit("ERROR: Gitea token not found at ~/.config/gitea/token or GITEA_TOKEN env")
|
||||
|
||||
|
||||
def api(method: str, path: str, token: str, data=None):
|
||||
url = f"{GITEA_BASE}{path}"
|
||||
body = json.dumps(data).encode() if data else None
|
||||
headers = {"Authorization": f"token {token}"}
|
||||
if body:
|
||||
headers["Content-Type"] = "application/json"
|
||||
req = urllib.request.Request(url, data=body, headers=headers, method=method)
|
||||
try:
|
||||
with urllib.request.urlopen(req, timeout=30) as resp:
|
||||
return json.loads(resp.read()), resp.status
|
||||
except urllib.error.HTTPError as e:
|
||||
err = e.read().decode() if e.fp else str(e)
|
||||
print(f" API {e.code}: {err}", file=sys.stderr)
|
||||
return None, e.code
|
||||
except Exception as e:
|
||||
print(f" Request error: {e}", file=sys.stderr)
|
||||
return None, None
|
||||
|
||||
|
||||
def fetch_all_open_issues(token: str):
|
||||
all_issues = []
|
||||
for repo in REPOS:
|
||||
page = 1
|
||||
while True:
|
||||
data, status = api("GET", f"/repos/{ORG}/{repo}/issues?state=open&page={page}&limit=50", token)
|
||||
if status != 200 or not data:
|
||||
break
|
||||
all_issues.extend(data)
|
||||
if len(data) < 50:
|
||||
break
|
||||
page += 1
|
||||
return all_issues
|
||||
|
||||
|
||||
def build_summary(by_agent: dict, unassignment_map: dict):
|
||||
lines = []
|
||||
lines.append("Agent | Before | After | Unassigned Count")
|
||||
lines.append("-" * 50)
|
||||
for agent in sorted(by_agent.keys()):
|
||||
before = by_agent[agent]["before"]
|
||||
after = by_agent[agent]["after"]
|
||||
unassigned = len(unassignment_map.get(agent, []))
|
||||
lines.append(f"@{agent} | {before} | {after} | {unassigned}")
|
||||
return "\n".join(lines)
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(description="Enforce open-issue load cap per agent")
|
||||
parser.add_argument("--dry-run", action="store_true", help="Report without making changes")
|
||||
parser.add_argument("--cap", type=int, default=DEFAULT_CAP, help=f"Max open issues per agent (default: {DEFAULT_CAP})")
|
||||
parser.add_argument("--output", type=str, default=None, help="Write summary to file")
|
||||
parser.add_argument("--comment-on", type=int, default=None, help="Post summary as comment on timmy-home issue N")
|
||||
args = parser.parse_args()
|
||||
|
||||
token = load_token()
|
||||
print(f"Fetching open issues from {', '.join(REPOS)} ...")
|
||||
issues = fetch_all_open_issues(token)
|
||||
print(f"Fetched {len(issues)} open issues.")
|
||||
|
||||
# Group by assignee
|
||||
by_agent = defaultdict(lambda: {"before": 0, "issues": []})
|
||||
for iss in issues:
|
||||
for a in (iss.get("assignees") or []):
|
||||
login = a.get("login")
|
||||
if login:
|
||||
by_agent[login]["issues"].append(iss)
|
||||
by_agent[login]["before"] += 1
|
||||
|
||||
print(f"\nAgents with open issues: {list(by_agent.keys())}")
|
||||
for agent, d in sorted(by_agent.items()):
|
||||
print(f" @{agent}: {d['before']} issues")
|
||||
|
||||
# Identify overflow
|
||||
unassignment_map = defaultdict(list)
|
||||
for agent, d in by_agent.items():
|
||||
count = d["before"]
|
||||
if count > args.cap:
|
||||
overflow = count - args.cap
|
||||
issues_sorted = sorted(d["issues"], key=lambda i: i.get("created_at", ""))
|
||||
unassignment_map[agent] = issues_sorted[:overflow]
|
||||
print(f"\n@{agent} exceeds cap ({count} > {args.cap}); will unassign {overflow} oldest issue(s):")
|
||||
for iss in issues_sorted[:overflow]:
|
||||
print(f" - #{iss['number']}: {iss.get('title', '')[:50]}")
|
||||
|
||||
# Dry-run: just show summary and exit
|
||||
if args.dry_run:
|
||||
print("\n=== DRY RUN — no changes made ===")
|
||||
# For dry-run, after = before (no changes)
|
||||
for agent in by_agent:
|
||||
by_agent[agent]["after"] = by_agent[agent]["before"]
|
||||
summary = build_summary(by_agent, unassignment_map)
|
||||
print("\n" + summary)
|
||||
if args.output:
|
||||
Path(args.output).write_text(summary)
|
||||
print(f"\nSummary written to {args.output}")
|
||||
return 0
|
||||
|
||||
# LIVE: perform unassignments and comments (concurrent)
|
||||
print("\n=== LIVE RUN — executing ===")
|
||||
from concurrent.futures import ThreadPoolExecutor, as_completed
|
||||
import threading
|
||||
lock = threading.Lock()
|
||||
tasks = []
|
||||
for agent, issues_to_unassign in unassignment_map.items():
|
||||
for iss in issues_to_unassign:
|
||||
issue_num = iss["number"]
|
||||
repo_name = next(
|
||||
(r for r in REPOS if f"/{r}/issues/" in iss.get("html_url", "")), REPOS[0]
|
||||
)
|
||||
tasks.append((agent, issue_num, repo_name, iss))
|
||||
print(f"Total unassignment tasks: {len(tasks)}")
|
||||
def do_task(agent, issue_num, repo_name, iss):
|
||||
# Unassign
|
||||
_, status1 = api("PATCH", f"/repos/{ORG}/{repo_name}/issues/{issue_num}", token, {"assignees": []})
|
||||
if status1 not in (200, 201, 204):
|
||||
return (agent, issue_num, repo_name, False, f"unassign HTTP {status1}")
|
||||
# Comment
|
||||
comment_body = COMMENT_TEMPLATE.format(assignee=agent)
|
||||
_, status2 = api("POST", f"/repos/{ORG}/{repo_name}/issues/{issue_num}/comments", token, {"body": comment_body})
|
||||
if status2 not in (200, 201):
|
||||
return (agent, issue_num, repo_name, True, f"unassigned but comment HTTP {status2}")
|
||||
return (agent, issue_num, repo_name, True, "OK")
|
||||
completed = 0
|
||||
with ThreadPoolExecutor(max_workers=12) as executor:
|
||||
futures = [executor.submit(do_task, a, n, r, i) for (a, n, r, i) in tasks]
|
||||
for fut in as_completed(futures):
|
||||
agent, num, repo, ok, msg = fut.result()
|
||||
with lock:
|
||||
completed += 1
|
||||
if completed % 50 == 0:
|
||||
print(f" Progress: {completed}/{len(tasks)}")
|
||||
if ok:
|
||||
print(f" ✓ #{num} ({repo})")
|
||||
else:
|
||||
print(f" ✗ #{num} ({repo}): {msg}")
|
||||
|
||||
# Recompute after counts for summary
|
||||
print("\nRecomputing after counts ...")
|
||||
after_issues = fetch_all_open_issues(token)
|
||||
by_agent_after = defaultdict(int)
|
||||
for iss in after_issues:
|
||||
for a in (iss.get("assignees") or []):
|
||||
by_agent_after[a.get("login")] += 1
|
||||
for agent in by_agent:
|
||||
by_agent[agent]["after"] = by_agent_after.get(agent, 0)
|
||||
|
||||
summary = build_summary(by_agent, unassignment_map)
|
||||
print("\n=== SUMMARY ===")
|
||||
print(summary)
|
||||
|
||||
if args.output:
|
||||
Path(args.output).write_text(summary)
|
||||
print(f"Summary written to {args.output}")
|
||||
|
||||
if args.comment_on:
|
||||
body = f"Open-load cap enforcement run (cap={args.cap}):\n\n```\n{summary}\n```"
|
||||
_, status = api("POST", f"/repos/{ORG}/timmy-home/issues/{args.comment_on}/comments", token, {"body": body})
|
||||
if status in (200, 201):
|
||||
print(f"\nSummary posted as comment on timmy-home issue #{args.comment_on}")
|
||||
else:
|
||||
print(f"\nWARNING: failed to post comment (HTTP {status})")
|
||||
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main())
|
||||
Reference in New Issue
Block a user