Compare commits
2 Commits
step35/969
...
fix/515
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
f68f110d0e | ||
|
|
289f0410aa |
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 +12,27 @@ WORLD_DIR = Path('/Users/apayne/.timmy/evennia/timmy_world')
|
||||
STATE_FILE = WORLD_DIR / 'game_state.json'
|
||||
TIMMY_LOG = WORLD_DIR / 'timmy_log.md'
|
||||
|
||||
FRIENDSHIP_THRESHOLD = 0.5
|
||||
TENSION_THRESHOLD = -0.5
|
||||
NPC_RELATIONSHIP_SEEDS = {
|
||||
("Kimi", "Marcus"): {
|
||||
"values": {"Kimi": 0.45, "Marcus": 0.47},
|
||||
"conversation": "While you are away, Marcus and Kimi trade a quiet confidence beneath the oak.",
|
||||
"milestone": "A friendship starts to take root between Marcus and Kimi.",
|
||||
"hint": "Marcus and Kimi move with the easy familiarity of old friends.",
|
||||
"delta": 0.08,
|
||||
"kind": "friendship",
|
||||
},
|
||||
("Bezalel", "ClawCode"): {
|
||||
"values": {"Bezalel": -0.46, "ClawCode": -0.44},
|
||||
"conversation": "While you are away, Bezalel and ClawCode clash over what the forge is for.",
|
||||
"milestone": "Tension hardens between Bezalel and ClawCode at the anvil.",
|
||||
"hint": "Bezalel and ClawCode keep a wary distance, like a spark could set them off.",
|
||||
"delta": -0.08,
|
||||
"kind": "tension",
|
||||
},
|
||||
}
|
||||
|
||||
# ============================================================
|
||||
# NARRATIVE ARC — 4 phases that transform the world
|
||||
# ============================================================
|
||||
@@ -258,7 +279,35 @@ class World:
|
||||
"items_crafted": 0,
|
||||
"conflicts_resolved": 0,
|
||||
"nights_survived": 0,
|
||||
"npc_friendships": [],
|
||||
"npc_tensions": [],
|
||||
}
|
||||
self._initialize_npc_relationships(apply_seeds=True)
|
||||
|
||||
def _initialize_npc_relationships(self, apply_seeds=False):
|
||||
npc_names = [name for name, char in self.characters.items() if not char.get("is_player", False)]
|
||||
for npc_name in npc_names:
|
||||
trust_map = self.characters[npc_name]["trust"]
|
||||
for other_name in npc_names:
|
||||
if other_name != npc_name:
|
||||
trust_map.setdefault(other_name, 0.0)
|
||||
if apply_seeds:
|
||||
for pair, seed in NPC_RELATIONSHIP_SEEDS.items():
|
||||
left, right = pair
|
||||
self.characters[left]["trust"][right] = seed["values"][left]
|
||||
self.characters[right]["trust"][left] = seed["values"][right]
|
||||
self.state.setdefault("npc_friendships", [])
|
||||
self.state.setdefault("npc_tensions", [])
|
||||
|
||||
def relationship_hint_for_room(self, room_name, occupants):
|
||||
hints = []
|
||||
occupant_set = set(occupants)
|
||||
for bucket in ("npc_friendships", "npc_tensions"):
|
||||
for entry in self.state.get(bucket, []):
|
||||
pair = set(entry.get("pair", []))
|
||||
if entry.get("room") == room_name and pair.issubset(occupant_set):
|
||||
hints.append(entry.get("hint", ""))
|
||||
return [hint for hint in hints if hint]
|
||||
|
||||
def tick_time(self):
|
||||
"""Advance time of day."""
|
||||
@@ -389,6 +438,8 @@ class World:
|
||||
here = [n for n, c in self.characters.items() if c["room"] == room_name and n != char_name]
|
||||
if here:
|
||||
desc += f"\n Here: {', '.join(here)}"
|
||||
for hint in self.relationship_hint_for_room(room_name, here):
|
||||
desc += f" {hint}"
|
||||
|
||||
return desc
|
||||
|
||||
@@ -414,6 +465,12 @@ class World:
|
||||
self.rooms = data.get("rooms", self.rooms)
|
||||
self.characters = data.get("characters", self.characters)
|
||||
self.state = data.get("state", self.state)
|
||||
needs_seed = not any(
|
||||
any(other != "Timmy" for other in char.get("trust", {}))
|
||||
for name, char in self.characters.items()
|
||||
if not char.get("is_player", False)
|
||||
)
|
||||
self._initialize_npc_relationships(apply_seeds=needs_seed)
|
||||
return True
|
||||
return False
|
||||
|
||||
@@ -427,20 +484,6 @@ class ActionSystem:
|
||||
"description": "Move to an adjacent room",
|
||||
"target": "room",
|
||||
},
|
||||
"run": {
|
||||
"cost": 3,
|
||||
"description": "Run to an adjacent room (faster but more tiring)",
|
||||
"target": "room",
|
||||
},
|
||||
"jump": {
|
||||
"cost": 1,
|
||||
"description": "Jump in place (brief energy surge)",
|
||||
},
|
||||
"gallop": {
|
||||
"cost": 4,
|
||||
"description": "Gallop across open ground (requires Threshold or Bridge)",
|
||||
"target": "room",
|
||||
},
|
||||
"speak": {
|
||||
"cost": 1,
|
||||
"description": "Say something to someone in the room",
|
||||
@@ -516,13 +559,6 @@ class ActionSystem:
|
||||
connections = world.rooms[room].get("connections", {})
|
||||
for direction, dest in connections.items():
|
||||
available.append(f"move:{direction} -> {dest}")
|
||||
available.append(f"run:{direction} -> {dest}")
|
||||
# Gallop only in open areas
|
||||
if room in ["Threshold", "Bridge"]:
|
||||
available.append(f"gallop:{direction} -> {dest}")
|
||||
|
||||
# Jump always available
|
||||
available.append("jump")
|
||||
|
||||
# Speaking (if others are here)
|
||||
here = [n for n in world.characters if world.characters[n]["room"] == room and n != char_name]
|
||||
@@ -1093,6 +1129,69 @@ 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 _adjust_mutual_trust(self, left, right, delta):
|
||||
for speaker, listener in ((left, right), (right, left)):
|
||||
trust_map = self.world.characters[speaker]["trust"]
|
||||
trust_map[listener] = max(-1.0, min(1.0, trust_map.get(listener, 0.0) + delta))
|
||||
|
||||
def _record_relationship_milestone(self, scene, room_name, pair, bucket, milestone, hint):
|
||||
pair_list = list(pair)
|
||||
entries = self.world.state.setdefault(bucket, [])
|
||||
if any(entry.get("pair") == pair_list for entry in entries):
|
||||
return
|
||||
entries.append({
|
||||
"pair": pair_list,
|
||||
"room": room_name,
|
||||
"summary": milestone,
|
||||
"hint": hint,
|
||||
})
|
||||
scene["world_events"].append(milestone)
|
||||
|
||||
def _run_offscreen_npc_relationships(self, scene):
|
||||
timmy_room = self.world.characters["Timmy"]["room"]
|
||||
rooms = {}
|
||||
for char_name, char in self.world.characters.items():
|
||||
if char.get("is_player", False):
|
||||
continue
|
||||
rooms.setdefault(char["room"], []).append(char_name)
|
||||
|
||||
for room_name, occupants in rooms.items():
|
||||
if room_name == timmy_room or len(occupants) < 2:
|
||||
continue
|
||||
occupant_set = set(occupants)
|
||||
for pair, seed in NPC_RELATIONSHIP_SEEDS.items():
|
||||
if not set(pair).issubset(occupant_set):
|
||||
continue
|
||||
left, right = pair
|
||||
self._adjust_mutual_trust(left, right, seed["delta"])
|
||||
scene["npc_actions"].append(f"{left} and {right} speak in The {room_name} while you are away.")
|
||||
scene["world_events"].append(seed["conversation"])
|
||||
self.world.characters[left]["spoken"].append(seed["conversation"])
|
||||
self.world.characters[right]["spoken"].append(seed["conversation"])
|
||||
self.world.characters[left]["memories"].append(seed["conversation"])
|
||||
self.world.characters[right]["memories"].append(seed["conversation"])
|
||||
|
||||
left_trust = self.world.characters[left]["trust"][right]
|
||||
right_trust = self.world.characters[right]["trust"][left]
|
||||
if seed["kind"] == "friendship" and left_trust >= FRIENDSHIP_THRESHOLD and right_trust >= FRIENDSHIP_THRESHOLD:
|
||||
self._record_relationship_milestone(
|
||||
scene,
|
||||
room_name,
|
||||
pair,
|
||||
"npc_friendships",
|
||||
seed["milestone"],
|
||||
seed["hint"],
|
||||
)
|
||||
elif seed["kind"] == "tension" and left_trust <= TENSION_THRESHOLD and right_trust <= TENSION_THRESHOLD:
|
||||
self._record_relationship_milestone(
|
||||
scene,
|
||||
room_name,
|
||||
pair,
|
||||
"npc_tensions",
|
||||
seed["milestone"],
|
||||
seed["hint"],
|
||||
)
|
||||
|
||||
def run_tick(self, timmy_action="look"):
|
||||
"""Run one tick. Return the scene and available choices."""
|
||||
@@ -1112,16 +1211,14 @@ class GameEngine:
|
||||
"npc_actions": [],
|
||||
"choices": [],
|
||||
"log": [],
|
||||
"particles": [],
|
||||
}
|
||||
|
||||
# Process Timmy's action
|
||||
timmy_energy = self.world.characters["Timmy"]["energy"]
|
||||
room_name = self.world.characters["Timmy"]["room"] # current room for early exit messages
|
||||
|
||||
# Energy constraint checks
|
||||
action_costs = {
|
||||
"move": 2, "run": 3, "jump": 1, "gallop": 4, "tend_fire": 3, "write_rule": 2, "carve": 2,
|
||||
"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,
|
||||
}
|
||||
@@ -1182,10 +1279,6 @@ class GameEngine:
|
||||
self.world.characters["Timmy"]["room"] = dest
|
||||
self.world.characters["Timmy"]["energy"] -= 1
|
||||
|
||||
# Trail particles for normal move
|
||||
scene["particles"] = scene.get("particles", [])
|
||||
scene["particles"].append("✨ dust sparkles in your wake")
|
||||
|
||||
scene["log"].append(f"You move {direction} to The {dest}.")
|
||||
scene["timmy_room"] = dest
|
||||
|
||||
@@ -1196,7 +1289,7 @@ class GameEngine:
|
||||
# Check trust changes for arrival
|
||||
here = [n for n in self.world.characters if self.world.characters[n]["room"] == dest and n != "Timmy"]
|
||||
if here:
|
||||
scene["log"].append(f"{repr(', ').join(here)} {('are' if len(here)>1 else 'is')} already here.")
|
||||
scene["log"].append(f"{', '.join(here)} {'are' if len(here)>1 else 'is'} already here.")
|
||||
for person in here:
|
||||
self.world.characters[person]["trust"]["Timmy"] = min(1.0,
|
||||
self.world.characters[person]["trust"].get("Timmy", 0) + 0.05)
|
||||
@@ -1241,55 +1334,6 @@ class GameEngine:
|
||||
else:
|
||||
scene["log"].append("You can't go that way.")
|
||||
|
||||
elif timmy_action.startswith("run:"):
|
||||
direction = timmy_action.split(":")[1]
|
||||
current_room = self.world.characters["Timmy"]["room"]
|
||||
connections = self.world.rooms[current_room].get("connections", {})
|
||||
|
||||
if direction in connections:
|
||||
dest = connections[direction]
|
||||
self.world.characters["Timmy"]["room"] = dest
|
||||
self.world.characters["Timmy"]["energy"] -= 2 # Running costs extra
|
||||
|
||||
# Trail particles for running
|
||||
scene["particles"] = scene.get("particles", [])
|
||||
scene["particles"].append("💨 sprinting dust trail")
|
||||
scene["particles"].append("✨ sparkles streaking")
|
||||
|
||||
scene["log"].append(f"You sprint {direction} to The {dest}.")
|
||||
else:
|
||||
scene["log"].append("You can't go that way.")
|
||||
|
||||
elif timmy_action == "jump":
|
||||
# Jump in place - energizing
|
||||
self.world.characters["Timmy"]["energy"] = min(10, self.world.characters["Timmy"]["energy"] + 0.5)
|
||||
scene["particles"] = scene.get("particles", [])
|
||||
scene["particles"].append("⭐ jump sparkle burst")
|
||||
scene["log"].append("You jump! A burst of energy lifts you.")
|
||||
|
||||
elif timmy_action.startswith("gallop:"):
|
||||
direction = timmy_action.split(":")[1]
|
||||
current_room = self.world.characters["Timmy"]["room"]
|
||||
connections = self.world.rooms[current_room].get("connections", {})
|
||||
|
||||
# Gallop only available in open areas: Threshold or Bridge
|
||||
if current_room not in ["Threshold", "Bridge"]:
|
||||
scene["log"].append("You need open ground to gallop. Find the Threshold or Bridge.")
|
||||
elif direction in connections:
|
||||
dest = connections[direction]
|
||||
self.world.characters["Timmy"]["room"] = dest
|
||||
self.world.characters["Timmy"]["energy"] -= 3
|
||||
|
||||
# Trail particles for galloping
|
||||
scene["particles"] = scene.get("particles", [])
|
||||
scene["particles"].append("🌟 galloping star dust")
|
||||
scene["particles"].append("✨ running sparkles")
|
||||
scene["particles"].append("💨 wind trail")
|
||||
|
||||
scene["log"].append(f"You gallop {direction} to The {dest}. Hooves thunder.")
|
||||
else:
|
||||
scene["log"].append("You can't gallop that way.")
|
||||
|
||||
elif timmy_action.startswith("speak:"):
|
||||
target = timmy_action.split(":")[1]
|
||||
if self.world.characters[target]["room"] == self.world.characters["Timmy"]["room"]:
|
||||
@@ -1473,6 +1517,8 @@ 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}")
|
||||
|
||||
self._run_offscreen_npc_relationships(scene)
|
||||
|
||||
# Random NPC events — phase-aware speech
|
||||
room_name = self.world.characters["Timmy"]["room"]
|
||||
|
||||
@@ -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,
|
||||
)
|
||||
52
tests/test_tower_game_npc_relationships.py
Normal file
52
tests/test_tower_game_npc_relationships.py
Normal file
@@ -0,0 +1,52 @@
|
||||
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_relationships", 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 TestTowerGameNpcRelationships(unittest.TestCase):
|
||||
def test_each_npc_tracks_trust_for_every_other_npc(self):
|
||||
module = load_game_module()
|
||||
world = module.World()
|
||||
npc_names = [name for name, char in world.characters.items() if not char.get("is_player", False)]
|
||||
|
||||
for npc_name in npc_names:
|
||||
with self.subTest(npc=npc_name):
|
||||
trust_map = world.characters[npc_name]["trust"]
|
||||
expected = set(npc_names) - {npc_name}
|
||||
self.assertTrue(expected.issubset(set(trust_map)), f"{npc_name} missing NPC trust keys: {sorted(expected - set(trust_map))}")
|
||||
|
||||
def test_offscreen_npc_conversations_create_friendship_and_tension(self):
|
||||
module = load_game_module()
|
||||
engine = module.GameEngine()
|
||||
engine.start_new_game()
|
||||
|
||||
result = engine.run_tick("look")
|
||||
|
||||
friendships = {tuple(rel["pair"]) for rel in engine.world.state["npc_friendships"]}
|
||||
tensions = {tuple(rel["pair"]) for rel in engine.world.state["npc_tensions"]}
|
||||
|
||||
self.assertIn(("Kimi", "Marcus"), friendships)
|
||||
self.assertIn(("Bezalel", "ClawCode"), tensions)
|
||||
self.assertTrue(any("while you are away" in line.lower() for line in result["world_events"]))
|
||||
|
||||
garden_desc = engine.world.get_room_desc("Garden", "Timmy")
|
||||
forge_desc = engine.world.get_room_desc("Forge", "Timmy")
|
||||
self.assertIn("Marcus and Kimi", garden_desc)
|
||||
self.assertIn("Bezalel and ClawCode", forge_desc)
|
||||
|
||||
|
||||
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!")
|
||||
Reference in New Issue
Block a user