Compare commits

..

3 Commits

Author SHA1 Message Date
Oleksandr Kozachuk e7e51e4230 img-17: cache image-only posts; news pipeline notes 2026-07-13 16:50:58 +02:00
Oleksandr Kozachuk 5a3623f813 strengthen picture_edit hint: model must use edit for previously shared images 2026-07-13 16:45:15 +02:00
Oleksandr Kozachuk e21c262299 image input pipeline: content-hash cache, data-url vision, picture_edit real 2026-07-13 16:33:48 +02:00
8 changed files with 544 additions and 15 deletions
+4
View File
@@ -55,3 +55,7 @@ enable-game-info = true
# image-model = "gpt-image-2" # default; dall-e-3 gets clamped to n=1 # image-model = "gpt-image-2" # default; dall-e-3 gets clamped to n=1
# image-size = "1024x1024" # image-size = "1024x1024"
# image-quality = "medium" # passed through only when set # image-quality = "medium" # passed through only when set
# Image input pipeline (SPEC-004, FDB-010) — active with history-directory:
# image-cache-mb = 500 # LRU cap (ggg: consider 2000 — screenshots)
# image-cache-ttl-days = 90
# image-max-bytes = 8388608 # 8 MB upload cap
+22 -6
View File
@@ -12,6 +12,7 @@ from pathlib import Path
from pprint import pformat from pprint import pformat
from typing import Any, Dict, List, Optional, Tuple, Union from typing import Any, Dict, List, Optional, Tuple, Union
from .images import ImageCache
from .memory import MemoryManager from .memory import MemoryManager
from .persistence import PersistentStore from .persistence import PersistentStore
@@ -153,17 +154,16 @@ class AIResponder(AIResponderBase):
if stored_memory is not None: if stored_memory is not None:
self.memory = stored_memory self.memory = stored_memory
self.memory_manager = MemoryManager(self.store, lambda: self.config, self.consolidate, self.channel) self.memory_manager = MemoryManager(self.store, lambda: self.config, self.consolidate, self.channel)
self.image_cache: Optional[ImageCache] = None
if self.store is not None:
self.image_cache = ImageCache(self.store, Path(self.config["history-directory"]).expanduser() / "images", lambda: self.config)
logging.info(f"memmory:\n{self.memory}") logging.info(f"memmory:\n{self.memory}")
# Dynamic values move to a context suffix so the persona prefix # Dynamic values move to a context suffix so the persona prefix
# stays byte-stable for the prompt cache (ENV-20) # stays byte-stable for the prompt cache (ENV-20)
DYNAMIC_PLACEHOLDERS = ("{date}", "{time}", "{news}", "{memory}") DYNAMIC_PLACEHOLDERS = ("{date}", "{time}", "{news}", "{memory}")
def message(self, message: AIMessage, limit: Optional[int] = None) -> List[Dict[str, Any]]: def _context_lines(self, message: AIMessage) -> List[str]:
messages = []
persona = self.config.get(self.channel, self.config["system"])
for placeholder in self.DYNAMIC_PLACEHOLDERS:
persona = persona.replace(placeholder, "")
context = [f"date: {time.strftime('%Y-%m-%d')} ({time.strftime('%A')})", f"time: {time.strftime('%H:%M:%S')}"] context = [f"date: {time.strftime('%Y-%m-%d')} ({time.strftime('%A')})", f"time: {time.strftime('%H:%M:%S')}"]
news_feed = self.config.get("news") news_feed = self.config.get("news")
if news_feed and os.path.exists(news_feed): if news_feed and os.path.exists(news_feed):
@@ -173,7 +173,23 @@ class AIResponder(AIResponderBase):
memory_block = self.memory_manager.memory_block(participants, self.memory) memory_block = self.memory_manager.memory_block(participants, self.memory)
if memory_block: if memory_block:
context.append("memory:\n" + memory_block) context.append("memory:\n" + memory_block)
system = persona.rstrip() + "\n\n## Context\n" + "\n".join(context) if self.image_cache is not None:
recent_images = self.image_cache.recent(message.channel, 4)
if recent_images:
# the model cannot use picture_edit unless told images exist (IMG-16)
context.append(
f"recent images in this channel: {len(recent_images)}. When the user asks to modify, reuse, combine or"
" include a previously shared image, you MUST set picture_edit=true — text-to-image cannot see earlier"
" images; only picture_edit passes them to the image model."
)
return context
def message(self, message: AIMessage, limit: Optional[int] = None) -> List[Dict[str, Any]]:
messages = []
persona = self.config.get(self.channel, self.config["system"])
for placeholder in self.DYNAMIC_PLACEHOLDERS:
persona = persona.replace(placeholder, "")
system = persona.rstrip() + "\n\n## Context\n" + "\n".join(self._context_lines(message))
messages.append({"role": "system", "content": system}) messages.append({"role": "system", "content": system})
if limit is not None: if limit is not None:
while len(self.history) > limit: while len(self.history) > limit:
+43 -8
View File
@@ -197,6 +197,8 @@ class FjerkroaBot(commands.Bot):
removed += self.airesponder.store.delete_history_of_user(user) removed += self.airesponder.store.delete_history_of_user(user)
# facts + observations + episode traces (MEM-09) # facts + observations + episode traces (MEM-09)
removed += self.airesponder.store.purge_user_memory(user) removed += self.airesponder.store.purge_user_memory(user)
if self.airesponder.image_cache is not None:
removed += self.airesponder.image_cache.purge_user(user) # IMG-14
logging.info(f"forgetme: removed {removed} entries for {user}") logging.info(f"forgetme: removed {removed} entries for {user}")
await message.channel.send( await message.channel.send(
f"Removed your messages, facts and memory traces ({removed} entries).", f"Removed your messages, facts and memory traces ({removed} entries).",
@@ -337,6 +339,8 @@ class FjerkroaBot(commands.Bot):
async def on_message_delete(self, message): async def on_message_delete(self, message):
airesponder = self.get_ai_responder(self.get_channel_name(message.channel)) airesponder = self.get_ai_responder(self.get_channel_name(message.channel))
if airesponder.image_cache is not None:
airesponder.image_cache.purge_message(str(message.id)) # IMG-14
await airesponder.observe_event(message.author.name, "delete", f"deleted: {message.content}") await airesponder.observe_event(message.author.name, "delete", f"deleted: {message.content}")
def on_config_file_modified(self, event): def on_config_file_modified(self, event):
@@ -397,27 +401,46 @@ class FjerkroaBot(commands.Bot):
def get_ai_responder(self, channel_name): def get_ai_responder(self, channel_name):
return self.aichannels[channel_name] if channel_name in self.aichannels else self.airesponder return self.aichannels[channel_name] if channel_name in self.aichannels else self.airesponder
async def _ingest_attachments(self, message, channel_name: str, airesponder) -> list:
"""Cache-first attachment handling; CDN URLs never travel further (IMG-10/11)."""
urls = []
for attachment in message.attachments:
if airesponder.image_cache is None:
urls.append(attachment.url)
continue
sha = await airesponder.image_cache.ingest_url(attachment.url, channel_name, message.author.name, str(message.id))
if sha is not None:
recent = airesponder.image_cache.recent(channel_name, 8)
ext = next((row["ext"] for row in recent if row["sha256"] == sha), "png")
data_url = airesponder.image_cache.data_url(sha, ext)
if data_url:
urls.append(data_url)
return urls
async def handle_message_through_responder(self, message): async def handle_message_through_responder(self, message):
"""Handle a message through the AI responder""" """Handle a message through the AI responder"""
message_content = str(message.content).strip() message_content = str(message.content).strip()
if message.reference and message.reference.resolved and isinstance(message.reference.resolved.content, str): if message.reference and message.reference.resolved and isinstance(message.reference.resolved.content, str):
reference_content = str(message.reference.resolved.content).replace("\n", "> \n") reference_content = str(message.reference.resolved.content).replace("\n", "> \n")
message_content = f"> {reference_content}\n\n{message_content}" message_content = f"> {reference_content}\n\n{message_content}"
channel_name = self.get_channel_name(message.channel)
airesponder = self.get_ai_responder(channel_name)
attachment_urls = []
if message.attachments:
attachment_urls = await self._ingest_attachments(message, channel_name, airesponder)
if len(message_content) < 1: if len(message_content) < 1:
# image-only posts: cached + observed, no reply (IMG-17)
if attachment_urls:
await airesponder.observe_event(message.author.name, "image", f"posted {len(attachment_urls)} image(s)")
return return
message_content = self._resolve_mentions(message_content) message_content = self._resolve_mentions(message_content)
channel_name = self.get_channel_name(message.channel)
msg = AIMessage( msg = AIMessage(
message.author.name, message_content, channel_name, self.user in message.mentions or isinstance(message.channel, DMChannel) message.author.name, message_content, channel_name, self.user in message.mentions or isinstance(message.channel, DMChannel)
) )
if message.attachments: if attachment_urls:
for attachment in message.attachments: msg.urls = attachment_urls
if not msg.urls:
msg.urls = []
msg.urls.append(attachment.url)
# Reply/ignore classifier gate — direct messages bypass (BEH-01/02/03/07) # Reply/ignore classifier gate — direct messages bypass (BEH-01/02/03/07)
airesponder = self.get_ai_responder(channel_name)
handled, factual = await self._classifier_gate(message, msg, airesponder, channel_name) handled, factual = await self._classifier_gate(message, msg, airesponder, channel_name)
if handled: if handled:
return return
@@ -462,7 +485,19 @@ class FjerkroaBot(commands.Bot):
"""Send the answer paced, split and with images on the last part (BEH-04/05/06)""" """Send the answer paced, split and with images on the last part (BEH-04/05/06)"""
files = None files = None
if response.picture is not None: if response.picture is not None:
buffers = await airesponder.draw(response.picture, getattr(response, "picture_count", 1)) count = getattr(response, "picture_count", 1)
channel_name = self.get_channel_name(answer_channel)
buffers = None
if getattr(response, "picture_edit", False) and airesponder.image_cache is not None:
sources = airesponder.image_cache.recent_paths(channel_name, 4)
if sources:
buffers = await airesponder.edit_openai(response.picture, sources, count)
if buffers is None:
# empty cache or no edit request: plain generation (IMG-13 fallback)
buffers = await airesponder.draw(response.picture, count)
if airesponder.image_cache is not None:
for buffer in buffers:
airesponder.image_cache.ingest_bytes(buffer.getvalue(), channel_name, "assistant", None) # IMG-15
files = [discord.File(fp=buffer, filename=f"image-{index}.png") for index, buffer in enumerate(buffers)] files = [discord.File(fp=buffer, filename=f"image-{index}.png") for index, buffer in enumerate(buffers)]
parts = split_answer(response.answer, int(self.config.get("split-threshold", 1200)), int(self.config.get("split-max-parts", 3))) parts = split_answer(response.answer, int(self.config.get("split-threshold", 1200)), int(self.config.get("split-max-parts", 3)))
pace = float(self.config.get("typing-chars-per-second", 0) or 0) pace = float(self.config.get("typing-chars-per-second", 0) or 0)
+124
View File
@@ -0,0 +1,124 @@
"""Content-hash image cache (SPEC-004, FDB-010).
Attachments are downloaded once, sniffed, stored under their sha256
and served to vision as data: URLs — Discord's expiring CDN links
never travel further (IMG-10/11). LRU + TTL keep the cache bounded
(IMG-12); deletions and !forgetme propagate here (IMG-14).
"""
import base64
import hashlib
import logging
from pathlib import Path
from typing import Any, Callable, Dict, List, Optional
import aiohttp
from .persistence import PersistentStore
DEFAULT_CACHE_MB = 500
DEFAULT_TTL_DAYS = 90
DEFAULT_MAX_BYTES = 8 * 1024 * 1024
DOWNLOAD_TIMEOUT_S = 20
MAGIC = [
(b"\x89PNG", "png"),
(b"\xff\xd8\xff", "jpg"),
(b"GIF87a", "gif"),
(b"GIF89a", "gif"),
]
def sniff_ext(data: bytes) -> Optional[str]:
"""Extension from magic bytes only — names and headers lie (IMG-10)."""
for magic, ext in MAGIC:
if data.startswith(magic):
return ext
if data[:4] == b"RIFF" and data[8:12] == b"WEBP":
return "webp"
return None
class ImageCache:
def __init__(self, store: PersistentStore, root: Path, config_getter: Callable[[], Dict[str, Any]]) -> None:
self.store = store
self.root = Path(root)
self._config = config_getter
self.root.mkdir(parents=True, exist_ok=True)
def _path(self, sha256: str, ext: str) -> Path:
return self.root / f"{sha256}.{ext}"
def ingest_bytes(self, data: bytes, channel: str, user: str, message_id: Optional[str]) -> Optional[str]:
ext = sniff_ext(data)
if ext is None:
logging.warning(f"image cache: rejected non-image bytes from {user} (IMG-10)")
return None
if len(data) > int(self._config().get("image-max-bytes", DEFAULT_MAX_BYTES)):
logging.warning(f"image cache: rejected oversized upload from {user} ({len(data)} bytes)")
return None
sha256 = hashlib.sha256(data).hexdigest()
path = self._path(sha256, ext)
if not path.exists():
path.write_bytes(data)
self.store.image_add(sha256, channel, user, message_id, ext, len(data))
self.evict()
return sha256
async def ingest_url(self, url: str, channel: str, user: str, message_id: Optional[str]) -> Optional[str]:
try:
data = await self._download(url)
except Exception as err:
logging.warning(f"image cache: download failed for {user}: {repr(err)}")
return None
return self.ingest_bytes(data, channel, user, message_id)
async def _download(self, url: str) -> bytes:
limit = int(self._config().get("image-max-bytes", DEFAULT_MAX_BYTES))
timeout = aiohttp.ClientTimeout(total=DOWNLOAD_TIMEOUT_S)
async with aiohttp.ClientSession(timeout=timeout) as session:
async with session.get(url) as response:
response.raise_for_status()
return await response.content.read(limit + 1)
def data_url(self, sha256: str, ext: str) -> Optional[str]:
path = self._path(sha256, ext)
if not path.exists():
return None
mime = "jpeg" if ext == "jpg" else ext
return f"data:image/{mime};base64," + base64.b64encode(path.read_bytes()).decode()
def recent(self, channel: str, count: int) -> List[Dict[str, Any]]:
return self.store.images_recent(channel, count)
def recent_paths(self, channel: str, count: int) -> List[Path]:
paths = [self._path(row["sha256"], row["ext"]) for row in self.recent(channel, count)]
return [path for path in paths if path.exists()]
def _remove(self, sha256: str, ext: str) -> None:
self._path(sha256, ext).unlink(missing_ok=True)
self.store.images_delete(sha256)
def evict(self) -> None:
"""TTL first, then LRU down to the byte cap (IMG-12)."""
config = self._config()
for row in self.store.images_expired(int(config.get("image-cache-ttl-days", DEFAULT_TTL_DAYS))):
self._remove(row["sha256"], row["ext"])
cap = int(config.get("image-cache-mb", DEFAULT_CACHE_MB)) * 1024 * 1024
while self.store.images_total_bytes() > cap:
victims = self.store.images_oldest(1)
if not victims:
break
self._remove(victims[0]["sha256"], victims[0]["ext"])
def purge_user(self, user: str) -> int:
rows = self.store.images_for_user(user)
for row in rows:
self._remove(row["sha256"], row["ext"])
return len(rows)
def purge_message(self, message_id: str) -> int:
rows = self.store.images_for_message(message_id)
for row in rows:
self._remove(row["sha256"], row["ext"])
return len(rows)
+27
View File
@@ -96,6 +96,10 @@ async def openai_image(client, *args, **kwargs):
return await client.images.generate(*args, **kwargs) return await client.images.generate(*args, **kwargs)
async def openai_image_edit(client, *args, **kwargs):
return await client.images.edit(*args, **kwargs)
class OpenAIResponder(AIResponder, LeonardoAIDrawMixIn): class OpenAIResponder(AIResponder, LeonardoAIDrawMixIn):
def __init__(self, config: Dict[str, Any], channel: Optional[str] = None) -> None: def __init__(self, config: Dict[str, Any], channel: Optional[str] = None) -> None:
super().__init__(config, channel) super().__init__(config, channel)
@@ -354,6 +358,29 @@ class OpenAIResponder(AIResponder, LeonardoAIDrawMixIn):
logging.debug(f"Full traceback: {traceback.format_exc()}") logging.debug(f"Full traceback: {traceback.format_exc()}")
return None, limit return None, limit
async def edit_openai(self, description: str, paths: List[Any], count: int = 1) -> List[BytesIO]:
"""Edit/remix from cached inputs, ≤4 files (IMG-13)."""
if not self.ledger.budget_ok():
raise RuntimeError("daily budget exhausted - refusing image edit")
model = self.config.get("image-model", "gpt-image-2")
handles = [open(path, "rb") for path in paths[:4]]
try:
response = await openai_image_edit(
self.client,
model=model,
image=handles if len(handles) > 1 else handles[0],
prompt=description,
n=max(1, min(int(count), 4)),
size=self.config.get("image-size", "1024x1024"),
)
finally:
for handle in handles:
handle.close()
buffers = [BytesIO(base64.b64decode(item.b64_json)) for item in response.data]
self.ledger.add_images(len(buffers))
logging.info(f"edited {len(buffers)} image(s) on {model} from {len(handles)} input(s)")
return buffers
async def classify(self, message: Any, history_tail: List[Dict[str, Any]]) -> Optional[Dict[str, Any]]: async def classify(self, message: Any, history_tail: List[Dict[str, Any]]) -> Optional[Dict[str, Any]]:
"""~100-token reply/factual/emoji verdict on classifier-model (BEH-01/03).""" """~100-token reply/factual/emoji verdict on classifier-model (BEH-01/03)."""
if "classifier-model" not in self.config or not self.ledger.budget_ok(): if "classifier-model" not in self.config or not self.ledger.budget_ok():
+54 -1
View File
@@ -13,7 +13,7 @@ from contextlib import closing
from pathlib import Path from pathlib import Path
from typing import Any, Dict, List, Optional from typing import Any, Dict, List, Optional
SCHEMA_VERSION = 3 SCHEMA_VERSION = 4
class PersistentStore: class PersistentStore:
@@ -60,6 +60,12 @@ class PersistentStore:
) )
# Legacy single-string memories carry over as one episode each (MEM-08) # Legacy single-string memories carry over as one episode each (MEM-08)
conn.execute("INSERT INTO episodes (channel, summary) SELECT channel, content FROM memory") conn.execute("INSERT INTO episodes (channel, summary) SELECT channel, content FROM memory")
if version < 4:
conn.execute(
"CREATE TABLE IF NOT EXISTS images (id INTEGER PRIMARY KEY, sha256 TEXT UNIQUE NOT NULL, channel TEXT NOT NULL,"
" user TEXT NOT NULL, message_id TEXT, ext TEXT NOT NULL, bytes INTEGER NOT NULL,"
" created_at TEXT NOT NULL DEFAULT (datetime('now')))"
)
if version < SCHEMA_VERSION: if version < SCHEMA_VERSION:
conn.execute(f"PRAGMA user_version = {SCHEMA_VERSION}") conn.execute(f"PRAGMA user_version = {SCHEMA_VERSION}")
os.chmod(self.db_path, 0o600) # conversation data (PER-04) os.chmod(self.db_path, 0o600) # conversation data (PER-04)
@@ -189,6 +195,53 @@ class PersistentStore:
) )
return cursor.rowcount return cursor.rowcount
# --- image cache index (SPEC-004, FDB-010) ---
def image_add(self, sha256: str, channel: str, user: str, message_id: Optional[str], ext: str, nbytes: int) -> None:
with closing(self._connect()) as conn, conn:
conn.execute(
"INSERT OR IGNORE INTO images (sha256, channel, user, message_id, ext, bytes) VALUES (?, ?, ?, ?, ?, ?)",
(sha256, channel, user, message_id, ext, nbytes),
)
def images_recent(self, channel: str, count: int) -> List[Dict[str, Any]]:
with closing(self._connect()) as conn:
rows = conn.execute(
"SELECT sha256, user, ext FROM images WHERE channel = ? ORDER BY id DESC LIMIT ?", (channel, count)
).fetchall()
return [{"sha256": row[0], "user": row[1], "ext": row[2]} for row in rows]
def images_total_bytes(self) -> int:
with closing(self._connect()) as conn:
row = conn.execute("SELECT COALESCE(SUM(bytes), 0) FROM images").fetchone()
return int(row[0])
def images_oldest(self, count: int) -> List[Dict[str, Any]]:
with closing(self._connect()) as conn:
rows = conn.execute("SELECT sha256, ext, bytes FROM images ORDER BY id LIMIT ?", (count,)).fetchall()
return [{"sha256": row[0], "ext": row[1], "bytes": row[2]} for row in rows]
def images_expired(self, ttl_days: int) -> List[Dict[str, Any]]:
with closing(self._connect()) as conn:
rows = conn.execute(
"SELECT sha256, ext FROM images WHERE created_at < datetime('now', ?)", (f"-{int(ttl_days)} days",)
).fetchall()
return [{"sha256": row[0], "ext": row[1]} for row in rows]
def images_delete(self, sha256: str) -> None:
with closing(self._connect()) as conn, conn:
conn.execute("DELETE FROM images WHERE sha256 = ?", (sha256,))
def images_for_user(self, user: str) -> List[Dict[str, Any]]:
with closing(self._connect()) as conn:
rows = conn.execute("SELECT sha256, ext FROM images WHERE user = ?", (user,)).fetchall()
return [{"sha256": row[0], "ext": row[1]} for row in rows]
def images_for_message(self, message_id: str) -> List[Dict[str, Any]]:
with closing(self._connect()) as conn:
rows = conn.execute("SELECT sha256, ext FROM images WHERE message_id = ?", (message_id,)).fetchall()
return [{"sha256": row[0], "ext": row[1]} for row in rows]
def purge_user_memory(self, user: str) -> int: def purge_user_memory(self, user: str) -> int:
"""Facts, observations and episode traces of one user (MEM-09).""" """Facts, observations and episode traces of one user (MEM-09)."""
removed = 0 removed = 0
+58
View File
@@ -37,3 +37,61 @@ The translate-before-draw step is deleted: the model's picture prompt
reaches the image API verbatim (current image models handle reaches the image API verbatim (current image models handle
Norwegian/German natively). The `translate()` method and its Norwegian/German natively). The `translate()` method and its
`fix-model` dependency are gone (closes D-009). `fix-model` dependency are gone (closes D-009).
## Input pipeline (FDB-010)
Attachments live in a content-hash cache
(`<history-directory>/images/<sha256>.<ext>`, index in the store,
schema v4). Active only with a store; without one the legacy CDN-URL
path remains.
### IMG-10 — Attachments are ingested at message time (coverage: test)
Every image attachment is downloaded immediately (timeout, size cap
`image-max-bytes` default 8 MB) and stored under its content hash.
Only sniffed png/jpeg/gif/webp bytes are accepted — extension and
declared MIME are ignored (attacker-controlled). Rejected content is
dropped and logged (D11 root fix + cache-abuse hardening).
### IMG-11 — Vision reads from the cache, never CDN URLs (coverage: test)
Vision parts are `data:` URLs built from cached bytes. Discord's
signed, expiring CDN URLs never reach the model or the history.
### IMG-12 — The cache is capped and aged (coverage: test)
`image-cache-mb` (default 500) LRU-evicts oldest-first;
`image-cache-ttl-days` (default 90) ages entries out. Eviction always
removes file and index row together.
### IMG-13 — picture_edit edits the newest channel images (coverage: test)
`picture_edit=true` calls `images.edit` with up to the 4 newest
cached images of the answer channel as inputs (API max is 16; 4 keeps
prompts sane). An empty cache falls back to plain generation — the
flag alone must never fail a reply.
### IMG-14 — Deletion propagates to the cache (coverage: test)
Deleting a Discord message purges its cached images; `!forgetme`
purges all of the user's images — files and rows (extends
SAF-08/MEM-09).
### IMG-15 — Generated images join the cache (coverage: test)
Bot-generated images are ingested like uploads (user `assistant`), so
"make a variant of that" remix chains work on the bot's own output.
### IMG-17 — Image-only messages are cached (coverage: test)
A message consisting only of attachments (no text) is ingested into
the cache and recorded as an observation, even though no reply is
produced — the image must be available for later `picture_edit` and
vision follow-ups. (Previously the empty-text early-return dropped
such posts entirely.)
### IMG-16 — The prompt announces editable images (coverage: test)
When the answer channel has cached images, the context suffix states
how many and that `picture_edit=true` edits the newest — the model
cannot use a capability it does not know about.
+212
View File
@@ -0,0 +1,212 @@
"""Unit coverage for SPEC-004 input pipeline (IMG-10..16)."""
import base64
import sqlite3
import tempfile
import unittest
from pathlib import Path
from unittest.mock import AsyncMock, MagicMock, Mock, patch
from fjerkroa_bot.ai_responder import AIMessage, AIResponse
from fjerkroa_bot.images import ImageCache, sniff_ext
from fjerkroa_bot.openai_responder import OpenAIResponder
from fjerkroa_bot.persistence import PersistentStore
from .test_bdd_envelope import FakeModelResponder
from .test_spec_ops import OpsBase
PNG = b"\x89PNG\r\n\x1a\n" + b"x" * 64
def make_cache(tmp, config=None):
store = PersistentStore(Path(tmp) / "bot.db")
cache = ImageCache(store, Path(tmp) / "images", lambda: config or {})
return store, cache
class TestIngest(unittest.TestCase):
def test_sniffed_types_only(self):
"""IMG-10: magic bytes decide; garbage and foreign types are rejected."""
self.assertEqual(sniff_ext(PNG), "png")
self.assertEqual(sniff_ext(b"\xff\xd8\xff\xe0rest"), "jpg")
self.assertIsNone(sniff_ext(b"MZ\x90\x00 definitely-an-exe"))
with tempfile.TemporaryDirectory() as tmp:
store, cache = make_cache(tmp)
self.assertIsNone(cache.ingest_bytes(b"not an image", "chat", "alice", "1"))
sha = cache.ingest_bytes(PNG, "chat", "alice", "1")
self.assertIsNotNone(sha)
self.assertTrue((Path(tmp) / "images" / f"{sha}.png").exists())
self.assertEqual(store.images_recent("chat", 5)[0]["sha256"], sha)
def test_size_cap(self):
"""IMG-10: oversized uploads are dropped."""
with tempfile.TemporaryDirectory() as tmp:
_, cache = make_cache(tmp, {"image-max-bytes": 32})
self.assertIsNone(cache.ingest_bytes(PNG, "chat", "alice", "1"))
class TestVisionDataUrls(OpsBase):
async def test_attachment_becomes_data_url(self):
"""IMG-11: the model sees a data: URL, never the CDN link."""
with tempfile.TemporaryDirectory() as tmp:
_, cache = make_cache(tmp)
self.bot.airesponder.image_cache = cache
self.bot.respond = AsyncMock()
message = self.public_msg("look at this")
attachment = Mock()
attachment.url = "https://cdn.discordapp.com/attachments/1/2/cat.png?ex=deadbeef"
message.attachments = [attachment]
message.id = 42
with patch.object(ImageCache, "_download", new_callable=AsyncMock, return_value=PNG):
await self.bot.on_message(message)
sent_msg = self.bot.respond.await_args.args[0]
self.assertTrue(sent_msg.urls[0].startswith("data:image/png;base64,"))
self.assertNotIn("cdn.discordapp.com", sent_msg.urls[0])
class TestEviction(unittest.TestCase):
def test_lru_cap(self):
"""IMG-12: byte cap evicts oldest first, file + row together."""
big = b"\x89PNG\r\n\x1a\n" + b"a" * (700 * 1024)
big2 = b"\x89PNG\r\n\x1a\n" + b"b" * (700 * 1024)
with tempfile.TemporaryDirectory() as tmp:
store, cache = make_cache(tmp, {"image-cache-mb": 1})
first = cache.ingest_bytes(big, "chat", "alice", "1")
second = cache.ingest_bytes(big2, "chat", "alice", "2")
shas = [row["sha256"] for row in store.images_recent("chat", 5)]
self.assertNotIn(first, shas)
self.assertIn(second, shas)
self.assertFalse((Path(tmp) / "images" / f"{first}.png").exists())
def test_ttl(self):
"""IMG-12: entries past image-cache-ttl-days age out."""
with tempfile.TemporaryDirectory() as tmp:
store, cache = make_cache(tmp, {"image-cache-ttl-days": 30})
sha = cache.ingest_bytes(PNG, "chat", "alice", "1")
with sqlite3.connect(store.db_path) as conn:
conn.execute("UPDATE images SET created_at = datetime('now', '-60 days') WHERE sha256 = ?", (sha,))
cache.evict()
self.assertEqual(store.images_recent("chat", 5), [])
self.assertFalse((Path(tmp) / "images" / f"{sha}.png").exists())
class TestEditPath(OpsBase):
async def prepare(self, with_images):
self.tmp = tempfile.TemporaryDirectory()
self.addCleanup(self.tmp.cleanup)
_, cache = make_cache(self.tmp.name)
self.bot.airesponder.image_cache = cache
if with_images:
cache.ingest_bytes(PNG, "chat", "alice", "1")
self.bot.airesponder.edit_openai = AsyncMock(return_value=[__import__("io").BytesIO(PNG)])
self.bot.airesponder.draw = AsyncMock(return_value=[__import__("io").BytesIO(PNG)])
response = AIResponse("her", True, "chat", None, "als wikinger", True, False)
channel = MagicMock()
channel.name = "chat"
channel.send = AsyncMock()
channel.typing = MagicMock(return_value=AsyncMock(__aenter__=AsyncMock(), __aexit__=AsyncMock()))
await self.bot.send_answer_with_typing(response, channel, self.bot.airesponder, factual=True)
async def test_edit_uses_cached_sources(self):
"""IMG-13: picture_edit + cached images -> images.edit path."""
await self.prepare(with_images=True)
self.bot.airesponder.edit_openai.assert_awaited_once()
self.bot.airesponder.draw.assert_not_awaited()
async def test_empty_cache_falls_back_to_generate(self):
"""IMG-13: empty cache -> plain generation, the flag never fails a reply."""
await self.prepare(with_images=False)
self.bot.airesponder.edit_openai.assert_not_awaited()
self.bot.airesponder.draw.assert_awaited_once()
class TestPurges(OpsBase):
async def test_message_delete_and_forgetme_purge_images(self):
"""IMG-14: message deletion and !forgetme remove files + rows."""
with tempfile.TemporaryDirectory() as tmp:
store, cache = make_cache(tmp)
self.bot.airesponder.image_cache = cache
cache.ingest_bytes(PNG, "chat", "alice", "99")
deleted = MagicMock()
deleted.id = 99
deleted.content = "pic"
deleted.author.name = "alice"
deleted.channel = MagicMock()
await self.bot.on_message_delete(deleted)
self.assertEqual(store.images_recent("chat", 5), [])
cache.ingest_bytes(b"\x89PNG\r\n\x1a\n" + b"z" * 32, "chat", "alice", "100")
message = self.public_msg("!forgetme")
message.author.name = "alice"
await self.bot.on_message(message)
self.assertEqual(store.images_recent("chat", 5), [])
class TestGeneratedImagesCached(OpsBase):
async def test_bot_output_joins_cache(self):
"""IMG-15: generated images are ingested as user 'assistant'."""
with tempfile.TemporaryDirectory() as tmp:
store, cache = make_cache(tmp)
self.bot.airesponder.image_cache = cache
self.bot.airesponder.draw = AsyncMock(return_value=[__import__("io").BytesIO(PNG)])
response = AIResponse("her", True, "chat", None, "en katt", False, False)
channel = MagicMock()
channel.name = "chat"
channel.send = AsyncMock()
await self.bot.send_answer_with_typing(response, channel, self.bot.airesponder, factual=True)
rows = store.images_recent("chat", 5)
self.assertEqual(len(rows), 1)
self.assertEqual(rows[0]["user"], "assistant")
class TestImageOnlyMessages(OpsBase):
async def test_image_only_post_cached_no_reply(self):
"""IMG-17: attachment without text -> cached + observed, no reply."""
with tempfile.TemporaryDirectory() as tmp:
store, cache = make_cache(tmp)
self.bot.airesponder.image_cache = cache
self.bot.airesponder.observe_event = AsyncMock()
self.bot.respond = AsyncMock()
message = self.public_msg("")
message.content = ""
message.channel.name = "chat"
attachment = Mock()
attachment.url = "https://cdn.discordapp.com/attachments/1/2/silent.png"
message.attachments = [attachment]
message.id = 77
with patch.object(ImageCache, "_download", new_callable=AsyncMock, return_value=PNG):
await self.bot.on_message(message)
self.assertEqual(len(store.images_recent("chat", 5)), 1)
self.bot.airesponder.observe_event.assert_awaited_once()
self.bot.respond.assert_not_awaited()
class TestContextAnnouncesImages(unittest.IsolatedAsyncioTestCase):
def test_suffix_mentions_picture_edit(self):
"""IMG-16: cached channel images are announced in the context suffix."""
with tempfile.TemporaryDirectory() as tmp:
config = {"system": "s", "history-limit": 5, "history-directory": tmp}
responder = FakeModelResponder(config, "chat")
responder.image_cache.ingest_bytes(PNG, "chat", "alice", "1")
system = responder.message(AIMessage("alice", "hei", "chat"))[0]["content"]
self.assertIn("picture_edit", system)
self.assertIn("recent images in this channel: 1", system)
class TestEditOpenai(unittest.IsolatedAsyncioTestCase):
async def test_edit_call_shape_and_metering(self):
"""IMG-13: images.edit gets the file handles, n clamped, ledger counts."""
responder = OpenAIResponder({"openai-token": "t", "model": "m", "system": "s", "history-limit": 5}, "chat")
with tempfile.TemporaryDirectory() as tmp:
paths = []
for index in range(2):
path = Path(tmp) / f"in{index}.png"
path.write_bytes(PNG)
paths.append(path)
api_result = Mock(data=[Mock(b64_json=base64.b64encode(b"out").decode())])
with patch("fjerkroa_bot.openai_responder.openai_image_edit", new_callable=AsyncMock) as edit_mock:
edit_mock.return_value = api_result
buffers = await responder.edit_openai("wikinger", paths, 9)
self.assertEqual(buffers[0].read(), b"out")
self.assertEqual(edit_mock.await_args.kwargs["n"], 4)
self.assertEqual(len(edit_mock.await_args.kwargs["image"]), 2)
self.assertEqual(responder.ledger.images_today(), 1)