Vito
6c82098207
* feat(images): link summary on workspace image items
* fix(images): carry title source and cut first-line titles like the Library
Summaries gain title_source (stored or text). The inspector always shows a
stored title and confirms only a first-line title against the file, so a
stored title equal to the first line is no longer withheld. A link-title read
failure no longer marks a readable link unavailable. First-line titles over
80 characters end with an ellipsis, as the Library's title() does. The card
gate for unconfirmed first-line titles is pinned as an expected failure for B2.
* feat(images): unambiguous seed on workspace items
Workspace items gain `seed`, read with the shared generation-parameter
parser from the prompt/workflow records the header open already loaded
(each at most 2 MiB; no extra file reads, videos give None). A
placeholder or non-integer seed gives None. JSON integers beyond 2**53
are recovered exactly, so the card prints the digits the inspector shows.
The same parse confirms first-line card titles: a `text` title shows only
when the file's parsed positive gives the same title. One helper applies
that rule on the card and in the inspector, which now reads the positive
from its own inspection records with the same parser.
* fix(images): a deeply nested record no longer fails the workspace listing
The Python parser recurses over nested arrays where JavaScript String()
does not, so a crafted 2 KB PNG turned every workspace page holding it
(and its inspect route) into a 500. Card facts now treat RecursionError
like any record the parser cannot use: no seed and no confirmed title.
Also: Library previews skip the card parse they never show; the parse
runs after the file handle closes; the exact-seed read uses the one JSON
reader (parse_js_json(..., exact_integers=True)) and the public
number_string; record size is decided from the text length unless only
the UTF-8 byte count can tell.
* feat(images): search and filter workspace images by linked prompts
The workspace listing now takes category (exact), tags (comma list, all
required) and sort=rating, and q also matches the linked positive's text,
Library title, pair title and tag names. One bounded, parameterized SELECT
(get_image_link_matches / get_image_paths_matching) returns normalized
paths of unambiguously linked images; the listing is intersected with it.
Unlinked and ambiguous files are excluded by a category or tag filter and
sort last by rating, with a newest-first tie-break. The cursor scope covers
the new filters and sort; unknown values are still rejected.
The derived listing values and sort orders are cached per gallery scan so a
50,000-file listing with 20,000 links pages well under 150 ms at p95.
* test(images): count the filter budget everywhere, time it in one job
The 150 ms wall-clock budget failed under the CI coverage tracer, so it
is split. test_filter_work_is_bounded runs on every job and under
coverage: one filter SELECT per request, the ambiguity probe is an index
search (EXPLAIN QUERY PLAN), the per-scan values are built on the cold
request only, and a cursor page calls the sort key at most
ceil(log2 n)+3 times. test_filter_budget runs only with
PROMPTMANAGER_PERF_BUDGET=1 and no tracer, asserts the best of three
rounds' p95, and has its own non-required "perf budget" job. TESTING.md
records the convention.
* fix(images): rating sort works however many link rows the database holds
The filter SELECT counted every generated_images row against a 500,000
row cap and materialized all of them first, so a large history made
sort=rating answer 400 with nothing to narrow. The rows are now streamed
and only paths in the listing's normalized set are kept, so memory is
bounded by the listing; the cap and LinkFilterTooBroad are gone.
* fix(images): rebuild workspace listing values only where the scan changed
A TTL rescan that finds the same files reuses the previous values and
sort orders; one that finds a few changes rebuilds only those files.
Gallery invalidation and a gallery-roots change drop the derived values,
so old roots no longer hold memory. category is trimmed like tags.
* fix(images): a monitor invalidation rebuilds only the new files' values
The image monitor invalidates the gallery whenever it sees a new file,
and that dropped every derived workspace value, so the next request paid
a full cold build. Invalidation now keeps the per-file values and drops
only the sort orders; the rescan reuses every unchanged file and builds
only new or changed ones. A gallery-roots change still drops everything.
* feat(library): expose run count, last use and variant totals
* fix(library): an out-of-range last use reads as unknown, not a failed list
* perf(images): read positive counts only on a plain listing's first page
* feat(images): persist image favorites
Favorites are stored in image_favorites keyed by the gallery root label
and the relative path, set and cleared through PUT/DELETE
/prompt_manager/images/favorite with a {root_index, path} body validated
against the rooted listing. Workspace image cards carry favorite: bool.
The table is created by migration, travels with backups, is optional in
old backups and required after a restore's migration.
* fix(images): key favorites by the real root and case-normalized path
Folder names are not unique across gallery roots, so two roots shown as
"output" shared each other's stars. Favorites are now keyed by the
root's real, case-normalized path (server-side only) and a
case-normalized relative path, so a Windows case-only rename keeps its
star while distinct Linux files stay distinct. Toggles look the file up
in a per-scan dictionary instead of walking the listing.
* fix(images): favorites lookup follows monitor invalidation and the stored key bound
A monitor invalidation now also drops the favorites lookup, which held the
previous scan list until the next toggle. PUT refuses a favorite whose root
or relative key would exceed the schema's 4096-character bound, so the live
database keeps passing startup and restore validation.
* docs(testing): workspace data fields for the concept pages
* fix(images): card facts read the inspector's projected graphs
The inspector hands its browser parser only graphs the inspection
projection parsed (strict JSON, depth 64, node ceiling); a deeper record
is "limited" there, so the legacy fill never runs and no seed shows. The
card parsed the raw records instead and showed a seed the inspector did
not, e.g. for a 900-deep class_type beside a normal sampler.
project_graph() is now the one projection step, used by the inspection
response and by the card. The card runs the shared parser on the
projected graphs, the same values the browser receives: big integers
arrive as their exact digits, so the separate exact-integer re-parse and
the parse_js_json flag it needed are gone.
* fix(images): send the card seed as a decimal string
JSON.parse rounds a number past 2**53, so a listing seed such as
9223372036854788153 reached the page as 9223372036854788000 while the
inspector showed the file's digits. Every non-null card seed is now its
decimal string.
The Node parity harness now JSON.parses the real listing response and
compares String(seed) with the seed the inspector shows, including a
seed past 2**53. TESTING.md describes the string contract and drops the
removed exact re-read.
* fix(images): bound digit-string seeds and isolate each card's parse
A seed recorded as a 5000-digit string reached int(), which raises
ValueError past Python's integer string limit, and the listing answered
500. A digit-string seed now has at most 20 digits (2**64 fits), and the
conversion falls back to no seed on ValueError.
Each card's parse is also guarded in the page builder: an unexpected
error in one file's records logs a warning and gives that card no seed
and no first-line title, and the rest of the page still lists.
* fix(images): filename search survives a failed prompt-link read
On main a workspace q matched only file paths, so search worked with a
broken database. Since search also matches linked prompts, any q turned
a failed link read into a 500. A q without category, tags or the rating
sort now falls back to filename matches with a null positive_count and
logs the failure with its traceback; those linked filters still fail.
* fix(images): card reads PNG records with the inspector's reader
The card read PNG text through Pillow's header info, where a later
duplicate prompt chunk silently wins and text after IDAT is missed. The
inspector's bounded reader refuses conflicting duplicates and reads text
after IDAT, so a file with two different prompt chunks showed a card
seed the inspector refused.
PNG cards now read their records with read_inspection_file, the reader
the inspector uses. When it refuses a file the card keeps its
dimensions from Pillow and shows no seed. Other formats still use
Pillow's header info, as the inspector's header read does.
* perf(images): read each card's header facts once per gallery scan
Every page parsed each card's prompt and workflow records again, about
3.4 ms per 50 KB record set and 25 ms per 400 KB workflow, inside
ComfyUI's server process, on every scroll-back and refresh.
Dimensions, the seed and the parsed positive's display title are now
cached per root by (path, mtime), beside the scan's per-file values and
invalidated the same way: a rescan keeps unchanged files and prunes the
rest, a roots change drops them all, and only files of the current scan
are stored. An unreadable header is not stored. Links and favorites
are still read on every page.
* ci: run the perf budget on main pushes and on demand only
The wall-clock budget has under 2x margin on shared ubuntu runners, and
a red exact-head check blocks a merge that must never be rerun to green.
The job now runs on each push to main and on workflow_dispatch, not on
pull requests. TESTING.md says a red run on main means fix the code.
* fix(library): cut display titles at 80 UTF-16 units, never inside a pair
The server counted code points while the Library's JavaScript counts UTF-16
units, so a first line of emoji kept 80 emoji on cards but showed 40 in the
Library. Both now cut at 80 UTF-16 units and drop a character that would
straddle the limit instead of leaving half a surrogate pair.
1181 lines
48 KiB
Python
1181 lines
48 KiB
Python
"""
|
|
Database schema and models for KikoTextEncode prompt storage.
|
|
"""
|
|
|
|
import contextlib
|
|
import datetime
|
|
import json
|
|
import math
|
|
import sqlite3
|
|
import os
|
|
import threading
|
|
import tempfile
|
|
import weakref
|
|
from contextlib import closing
|
|
from pathlib import Path
|
|
from typing import Optional, Set, Tuple
|
|
|
|
from .library_schema import library_schema_error, migrate_library_state
|
|
from .image_favorites import image_favorites_schema_error, migrate_image_favorites
|
|
from .execution_history_schema import (
|
|
history_schema_error,
|
|
migrate_execution_history,
|
|
rotate_history_epoch,
|
|
)
|
|
|
|
# Import logging system
|
|
try:
|
|
from ..utils.logging_config import get_logger
|
|
except ImportError:
|
|
import sys
|
|
|
|
current_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
|
|
sys.path.insert(0, current_dir)
|
|
from utils.logging_config import get_logger
|
|
|
|
# last_used_at is UTC ISO text so ORDER BY can compare it as text. The backfill
|
|
# writes milliseconds (SQLite's %f); live writes use microseconds so runs in the
|
|
# same millisecond still order correctly. Both forms sort correctly together.
|
|
ISO_TIMESTAMP_FORMAT = "%Y-%m-%dT%H:%M:%f+00:00"
|
|
|
|
|
|
MAX_PAIR_PROVENANCE_LENGTH = 4_000_000
|
|
MAX_PAIR_PROVENANCE_DEPTH = 64
|
|
|
|
|
|
def pair_provenance_error(encoded: object) -> Optional[str]:
|
|
"""Validate the same bounded JSON object for live writes and restores."""
|
|
if not isinstance(encoded, str):
|
|
return "Pair provenance must be JSON text"
|
|
if len(encoded) > MAX_PAIR_PROVENANCE_LENGTH:
|
|
return "Pair provenance exceeds the size limit"
|
|
try:
|
|
value = json.loads(encoded)
|
|
except (ValueError, TypeError, RecursionError):
|
|
return "Pair provenance is not readable JSON"
|
|
if not isinstance(value, dict):
|
|
return "Pair provenance must be a JSON object"
|
|
pending = [(iter((value,)), 0)]
|
|
while pending:
|
|
children, depth = pending[-1]
|
|
try:
|
|
item = next(children)
|
|
except StopIteration:
|
|
pending.pop()
|
|
continue
|
|
if depth > MAX_PAIR_PROVENANCE_DEPTH:
|
|
return "Pair provenance exceeds the nesting limit"
|
|
if isinstance(item, float) and not math.isfinite(item):
|
|
return "Pair provenance contains nonfinite numbers"
|
|
if isinstance(item, dict):
|
|
pending.append((iter(item.values()), depth + 1))
|
|
elif isinstance(item, list):
|
|
pending.append((iter(item), depth + 1))
|
|
return None
|
|
|
|
|
|
def utc_now_iso() -> str:
|
|
"""Current UTC time as ISO text with microseconds.
|
|
|
|
Example: 2026-10-07T18:39:06.758123+00:00
|
|
"""
|
|
return datetime.datetime.now(datetime.timezone.utc).isoformat(
|
|
timespec="microseconds"
|
|
)
|
|
|
|
|
|
def normalize_image_path(path: str) -> str:
|
|
"""Canonical form of an image path for generated_images.file_path.
|
|
|
|
Absolute, with '..' and '.' collapsed and the platform's case folding
|
|
applied, so two spellings of one file (or the same basename in two date
|
|
folders) compare the way the filesystem would.
|
|
"""
|
|
return os.path.normcase(os.path.normpath(os.path.abspath(path)))
|
|
|
|
|
|
# How long a connection waits for a locked database before giving up. Thirty
|
|
# seconds covers a scan or a thumbnail run writing while ComfyUI saves images,
|
|
# and the slow disks of CI runners.
|
|
BUSY_TIMEOUT_SECONDS = 30
|
|
SQLITE_HEADER = b"SQLite format 3\x00"
|
|
REQUIRED_PROMPT_COLUMNS = ("id", "text", "created_at")
|
|
|
|
|
|
def configure_connection(conn: sqlite3.Connection) -> None:
|
|
"""Apply the locking and durability settings every managed connection shares.
|
|
|
|
WAL lets readers run beside the single writer. In WAL mode
|
|
``synchronous=NORMAL`` keeps the database consistent after an application
|
|
or ComfyUI crash and flushes only at checkpoints, so a commit no longer
|
|
holds SQLite's write lock across a disk flush. Under ``FULL`` a slow flush
|
|
(common on Windows) let other writers' polling busy handlers starve past
|
|
BUSY_TIMEOUT_SECONDS and fail with "database is locked" (#242). Without
|
|
WAL (for example an in-memory database) SQLite's FULL default is kept.
|
|
"""
|
|
journal_mode = conn.execute("PRAGMA journal_mode = WAL").fetchone()[0]
|
|
conn.execute("PRAGMA foreign_keys = ON")
|
|
conn.execute(f"PRAGMA busy_timeout = {BUSY_TIMEOUT_SECONDS * 1000}")
|
|
if str(journal_mode).lower() == "wal":
|
|
conn.execute("PRAGMA synchronous = NORMAL")
|
|
|
|
|
|
class PromptModel:
|
|
"""Database model for prompt storage and schema management."""
|
|
|
|
# Paths (normalised, see _schema_key) whose schema has been created and
|
|
# migrated in this process. Many PromptDatabase instances point at the
|
|
# same file; only the first one pays for the schema check.
|
|
_initialized_paths: Set[str] = set()
|
|
_init_lock = threading.Lock()
|
|
# Every live model, so a shutdown or a test teardown can close them all
|
|
# before the database file is deleted (Windows refuses otherwise).
|
|
_instances: "weakref.WeakSet[PromptModel]" = weakref.WeakSet()
|
|
_instances_lock = threading.Lock()
|
|
|
|
def __init__(self, db_path: str):
|
|
"""
|
|
Initialize the database model.
|
|
|
|
Args:
|
|
db_path: Absolute path to the SQLite database file
|
|
"""
|
|
self.logger = get_logger("prompt_manager.database.models")
|
|
self.logger.debug(f"Initializing database model with path: {db_path}")
|
|
self.db_path = db_path
|
|
# One connection per thread (see get_connection); every open connection
|
|
# is also tracked here so close_all can clean up across threads.
|
|
self._local = threading.local()
|
|
self._connections: Set[sqlite3.Connection] = set()
|
|
self._conn_lock = threading.Lock()
|
|
# Bumped by _close_all_connections so threads holding a closed
|
|
# connection reopen on their next get_connection().
|
|
self._generation = 0
|
|
with PromptModel._instances_lock:
|
|
PromptModel._instances.add(self)
|
|
self._ensure_database_exists()
|
|
|
|
def _ensure_database_exists(self) -> None:
|
|
"""
|
|
Create database and tables if they don't exist.
|
|
|
|
Sets up the database schema including tables for prompts and generated images,
|
|
creates necessary indexes, and applies any pending migrations.
|
|
|
|
Raises:
|
|
Exception: If database creation fails
|
|
"""
|
|
key = self._schema_key()
|
|
with PromptModel._init_lock:
|
|
if key in PromptModel._initialized_paths and os.path.exists(self.db_path):
|
|
return
|
|
try:
|
|
conn = sqlite3.connect(self.db_path, timeout=BUSY_TIMEOUT_SECONDS)
|
|
try:
|
|
configure_connection(conn)
|
|
self._create_tables(conn)
|
|
self._create_indexes(conn)
|
|
conn.commit()
|
|
finally:
|
|
conn.close()
|
|
except Exception as e:
|
|
self.logger.error(f"Error creating database: {e}")
|
|
raise
|
|
PromptModel._initialized_paths.add(key)
|
|
|
|
def _schema_key(self) -> str:
|
|
"""Normalised identity of db_path for the once-per-process schema cache."""
|
|
return os.path.normcase(os.path.realpath(self.db_path))
|
|
|
|
@classmethod
|
|
def reset_schema_cache(cls) -> None:
|
|
"""Forget which databases were initialised (tests and restores)."""
|
|
with cls._init_lock:
|
|
cls._initialized_paths.clear()
|
|
|
|
@contextlib.contextmanager
|
|
def _table_rebuild(self, conn: sqlite3.Connection):
|
|
"""Run a copy-and-swap table rebuild with foreign keys disabled.
|
|
|
|
DROP TABLE on a parent table with foreign_keys ON performs an implicit
|
|
DELETE that cascades into child rows (generated_images, prompt_tags),
|
|
so the rebuild runs with the pragma off. The pragma is a no-op inside
|
|
a transaction, hence the commits around it. Errors roll back and
|
|
propagate after the pragma is restored.
|
|
"""
|
|
conn.commit()
|
|
conn.execute("PRAGMA foreign_keys = OFF")
|
|
# Explicit BEGIN: in sqlite3's legacy transaction mode DDL autocommits,
|
|
# so without it a failed copy would leave the *_new table behind.
|
|
conn.execute("BEGIN")
|
|
try:
|
|
yield
|
|
conn.commit()
|
|
except BaseException:
|
|
conn.rollback()
|
|
raise
|
|
finally:
|
|
conn.execute("PRAGMA foreign_keys = ON")
|
|
|
|
def _create_tables(self, conn: sqlite3.Connection) -> None:
|
|
"""
|
|
Create the prompts and generated_images tables with all required columns.
|
|
|
|
Args:
|
|
conn: Active database connection
|
|
|
|
Creates:
|
|
- prompts table: Stores prompt text and metadata
|
|
- generated_images table: Links generated images to their source prompts
|
|
"""
|
|
conn.execute("""
|
|
CREATE TABLE IF NOT EXISTS prompts (
|
|
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
|
text TEXT NOT NULL,
|
|
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
|
|
updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
|
|
category TEXT,
|
|
tags TEXT,
|
|
rating INTEGER CHECK(rating >= 1 AND rating <= 5),
|
|
notes TEXT,
|
|
hash TEXT UNIQUE,
|
|
last_used_at TIMESTAMP,
|
|
run_count INTEGER NOT NULL DEFAULT 0
|
|
)
|
|
""")
|
|
|
|
# Create images table for gallery functionality
|
|
conn.execute("""
|
|
CREATE TABLE IF NOT EXISTS generated_images (
|
|
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
|
prompt_id INTEGER NOT NULL,
|
|
image_path TEXT NOT NULL,
|
|
filename TEXT NOT NULL,
|
|
generation_time TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
|
|
file_size INTEGER,
|
|
width INTEGER,
|
|
height INTEGER,
|
|
format TEXT,
|
|
workflow_data TEXT,
|
|
prompt_metadata TEXT,
|
|
parameters TEXT,
|
|
file_path TEXT,
|
|
FOREIGN KEY (prompt_id) REFERENCES prompts(id) ON DELETE CASCADE,
|
|
UNIQUE(prompt_id, file_path)
|
|
)
|
|
""")
|
|
|
|
# Create normalized tag tables (junction table pattern)
|
|
conn.execute("""
|
|
CREATE TABLE IF NOT EXISTS tags (
|
|
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
|
name TEXT NOT NULL UNIQUE
|
|
)
|
|
""")
|
|
conn.execute("""
|
|
CREATE TABLE IF NOT EXISTS prompt_tags (
|
|
prompt_id INTEGER NOT NULL,
|
|
tag_id INTEGER NOT NULL,
|
|
PRIMARY KEY (prompt_id, tag_id),
|
|
FOREIGN KEY (prompt_id) REFERENCES prompts(id) ON DELETE CASCADE,
|
|
FOREIGN KEY (tag_id) REFERENCES tags(id) ON DELETE CASCADE
|
|
)
|
|
""")
|
|
|
|
# Check if we need to migrate from old schema with workflow_name
|
|
self._migrate_workflow_name_removal(conn)
|
|
|
|
# Fix foreign key data type mismatch
|
|
self._migrate_foreign_key_types(conn)
|
|
|
|
# Migrate JSON tags to normalized junction tables
|
|
self._migrate_json_tags_to_junction(conn)
|
|
|
|
# Usage tracking columns (after any migration that rebuilds prompts)
|
|
self._migrate_add_usage_columns(conn)
|
|
|
|
# Image uniqueness by full path instead of basename (3.2.4)
|
|
self._migrate_image_uniqueness_by_path(conn)
|
|
self._migrate_prompt_pairs(conn)
|
|
migrate_execution_history(conn)
|
|
migrate_library_state(conn)
|
|
migrate_image_favorites(conn)
|
|
|
|
def _migrate_prompt_pairs(self, conn: sqlite3.Connection) -> None:
|
|
conn.execute("SAVEPOINT prompt_pair_schema")
|
|
try:
|
|
conn.execute("""
|
|
CREATE TABLE IF NOT EXISTS prompt_pairs (
|
|
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
|
positive_prompt_id INTEGER NOT NULL,
|
|
negative_prompt_id INTEGER,
|
|
title TEXT,
|
|
category TEXT,
|
|
rating INTEGER CHECK(rating BETWEEN 1 AND 5),
|
|
notes TEXT,
|
|
created_at TEXT NOT NULL DEFAULT CURRENT_TIMESTAMP,
|
|
updated_at TEXT NOT NULL DEFAULT CURRENT_TIMESTAMP,
|
|
last_used_at TEXT,
|
|
run_count INTEGER NOT NULL DEFAULT 0,
|
|
archived INTEGER NOT NULL DEFAULT 0 CHECK(archived IN (0, 1)),
|
|
FOREIGN KEY(positive_prompt_id)
|
|
REFERENCES prompts(id) ON DELETE RESTRICT,
|
|
FOREIGN KEY(negative_prompt_id)
|
|
REFERENCES prompts(id) ON DELETE RESTRICT,
|
|
UNIQUE(positive_prompt_id, negative_prompt_id)
|
|
)
|
|
""")
|
|
conn.execute("""
|
|
CREATE TABLE IF NOT EXISTS prompt_pair_tags (
|
|
pair_id INTEGER NOT NULL,
|
|
tag_id INTEGER NOT NULL,
|
|
PRIMARY KEY(pair_id, tag_id),
|
|
FOREIGN KEY(pair_id) REFERENCES prompt_pairs(id) ON DELETE CASCADE,
|
|
FOREIGN KEY(tag_id) REFERENCES tags(id) ON DELETE CASCADE
|
|
)
|
|
""")
|
|
conn.execute("""
|
|
CREATE TABLE IF NOT EXISTS image_prompt_pairs (
|
|
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
|
image_id INTEGER NOT NULL,
|
|
pair_id INTEGER NOT NULL,
|
|
provenance TEXT NOT NULL,
|
|
created_at TEXT NOT NULL DEFAULT CURRENT_TIMESTAMP,
|
|
FOREIGN KEY(image_id)
|
|
REFERENCES generated_images(id) ON DELETE CASCADE,
|
|
FOREIGN KEY(pair_id) REFERENCES prompt_pairs(id) ON DELETE RESTRICT,
|
|
UNIQUE(pair_id, image_id, provenance)
|
|
)
|
|
""")
|
|
self._create_pair_indexes(conn)
|
|
error = self._pair_schema_error(conn)
|
|
if error:
|
|
raise sqlite3.DatabaseError(error)
|
|
conn.execute("RELEASE prompt_pair_schema")
|
|
except BaseException:
|
|
conn.execute("ROLLBACK TO prompt_pair_schema")
|
|
conn.execute("RELEASE prompt_pair_schema")
|
|
raise
|
|
|
|
@staticmethod
|
|
def _create_pair_indexes(conn: sqlite3.Connection) -> None:
|
|
conn.execute(
|
|
"CREATE UNIQUE INDEX IF NOT EXISTS idx_prompt_pairs_positive_only "
|
|
"ON prompt_pairs(positive_prompt_id) WHERE negative_prompt_id IS NULL"
|
|
)
|
|
for name, target in (
|
|
("idx_prompt_pairs_negative", "prompt_pairs(negative_prompt_id)"),
|
|
("idx_prompt_pair_tags_tag", "prompt_pair_tags(tag_id)"),
|
|
("idx_image_prompt_pairs_image", "image_prompt_pairs(image_id)"),
|
|
):
|
|
conn.execute(f"CREATE INDEX IF NOT EXISTS {name} ON {target}")
|
|
|
|
@staticmethod
|
|
def _pair_schema_error(conn: sqlite3.Connection) -> Optional[str]:
|
|
required = {
|
|
"prompt_pairs": {
|
|
"id",
|
|
"positive_prompt_id",
|
|
"negative_prompt_id",
|
|
"title",
|
|
"category",
|
|
"rating",
|
|
"notes",
|
|
"created_at",
|
|
"updated_at",
|
|
"last_used_at",
|
|
"run_count",
|
|
"archived",
|
|
},
|
|
"prompt_pair_tags": {"pair_id", "tag_id"},
|
|
"image_prompt_pairs": {
|
|
"id",
|
|
"image_id",
|
|
"pair_id",
|
|
"provenance",
|
|
"created_at",
|
|
},
|
|
}
|
|
present = {
|
|
row[0]
|
|
for row in conn.execute("SELECT name FROM sqlite_master WHERE type='table'")
|
|
}
|
|
if not present.intersection(required):
|
|
return None
|
|
if not set(required).issubset(present):
|
|
return "Incomplete prompt pair schema"
|
|
foreign_keys = {
|
|
"prompt_pairs": {
|
|
("positive_prompt_id", "prompts", "id", "RESTRICT"),
|
|
("negative_prompt_id", "prompts", "id", "RESTRICT"),
|
|
},
|
|
"prompt_pair_tags": {
|
|
("pair_id", "prompt_pairs", "id", "CASCADE"),
|
|
("tag_id", "tags", "id", "CASCADE"),
|
|
},
|
|
"image_prompt_pairs": {
|
|
("pair_id", "prompt_pairs", "id", "RESTRICT"),
|
|
("image_id", "generated_images", "id", "CASCADE"),
|
|
},
|
|
}
|
|
unique = {
|
|
"prompt_pairs": ("positive_prompt_id", "negative_prompt_id"),
|
|
"prompt_pair_tags": ("pair_id", "tag_id"),
|
|
"image_prompt_pairs": ("pair_id", "image_id", "provenance"),
|
|
}
|
|
non_null = {
|
|
"prompt_pairs": {
|
|
"positive_prompt_id",
|
|
"created_at",
|
|
"updated_at",
|
|
"run_count",
|
|
"archived",
|
|
},
|
|
"prompt_pair_tags": {"pair_id", "tag_id"},
|
|
"image_prompt_pairs": {"pair_id", "image_id", "provenance", "created_at"},
|
|
}
|
|
integer_columns = {
|
|
"id",
|
|
"positive_prompt_id",
|
|
"negative_prompt_id",
|
|
"pair_id",
|
|
"tag_id",
|
|
"image_id",
|
|
"rating",
|
|
"run_count",
|
|
"archived",
|
|
}
|
|
for table, columns in required.items():
|
|
info = {row[1]: row for row in conn.execute(f"PRAGMA table_info({table})")}
|
|
if not columns.issubset(info):
|
|
return f"{table} is missing required pair columns"
|
|
if any(not info[name][3] for name in non_null[table]):
|
|
return f"{table} has nullable required pair columns"
|
|
if any(
|
|
info[name][2].upper()
|
|
!= ("INTEGER" if name in integer_columns else "TEXT")
|
|
for name in columns
|
|
):
|
|
return f"{table} has invalid pair column types"
|
|
primary = tuple(
|
|
name
|
|
for name in sorted(info, key=lambda name: info[name][5])
|
|
if info[name][5]
|
|
)
|
|
if primary != (
|
|
("pair_id", "tag_id") if table == "prompt_pair_tags" else ("id",)
|
|
):
|
|
return f"{table} has an invalid pair primary key"
|
|
actual_fks = {
|
|
(row[3], row[2], row[4], row[6])
|
|
for row in conn.execute(f"PRAGMA foreign_key_list({table})")
|
|
}
|
|
if actual_fks != foreign_keys[table]:
|
|
return f"{table} has invalid pair foreign key definitions"
|
|
if conn.execute(f"PRAGMA foreign_key_check({table})").fetchone():
|
|
return f"{table} contains foreign key violations"
|
|
indexes = list(conn.execute(f"PRAGMA index_list({table})"))
|
|
index_columns = {}
|
|
for row in indexes:
|
|
name = row[1].replace('"', '""')
|
|
index_columns[row[1]] = tuple(
|
|
item[2] for item in conn.execute(f'PRAGMA index_info("{name}")')
|
|
)
|
|
if not any(
|
|
row[2] and not row[4] and index_columns[row[1]] == unique[table]
|
|
for row in indexes
|
|
):
|
|
return f"{table} is missing pair uniqueness constraints"
|
|
if table == "prompt_pairs":
|
|
null_unique = False
|
|
for row in indexes:
|
|
if (
|
|
row[2]
|
|
and row[4]
|
|
and index_columns[row[1]] == ("positive_prompt_id",)
|
|
):
|
|
sql = conn.execute(
|
|
"SELECT sql FROM sqlite_master WHERE type='index' AND name"
|
|
"=?",
|
|
(row[1],),
|
|
).fetchone()[0]
|
|
if " ".join(sql.lower().split()).endswith(
|
|
"where negative_prompt_id is null"
|
|
):
|
|
null_unique = True
|
|
if not null_unique:
|
|
return "prompt_pairs is missing empty-negative pair uniqueness"
|
|
if conn.execute(
|
|
"SELECT 1 FROM image_prompt_pairs ip "
|
|
"JOIN prompt_pairs pp ON pp.id=ip.pair_id "
|
|
"JOIN generated_images gi ON gi.id=ip.image_id "
|
|
"WHERE pp.positive_prompt_id IS NOT gi.prompt_id LIMIT 1"
|
|
).fetchone():
|
|
return "Image pair association has a different positive prompt owner"
|
|
for row in conn.execute("SELECT provenance FROM image_prompt_pairs"):
|
|
error = pair_provenance_error(row[0])
|
|
if error:
|
|
return error
|
|
return None
|
|
|
|
def _create_indexes(self, conn: sqlite3.Connection) -> None:
|
|
"""
|
|
Create indexes for better query performance.
|
|
|
|
Args:
|
|
conn: Active database connection
|
|
|
|
Creates indexes on:
|
|
- Text content for search operations
|
|
- Categories and tags for filtering
|
|
- Timestamps for sorting
|
|
- Hash values for duplicate detection
|
|
"""
|
|
indexes = [
|
|
("idx_prompts_text", "prompts(text)"),
|
|
("idx_prompts_category", "prompts(category)"),
|
|
("idx_prompts_created_at", "prompts(created_at)"),
|
|
("idx_prompts_hash", "prompts(hash)"),
|
|
("idx_prompts_rating", "prompts(rating)"),
|
|
("idx_prompts_last_used", "prompts(last_used_at)"),
|
|
("idx_prompts_run_count", "prompts(run_count)"),
|
|
("idx_prompt_images", "generated_images(prompt_id)"),
|
|
("idx_image_path", "generated_images(image_path)"),
|
|
("idx_image_file_path", "generated_images(file_path)"),
|
|
("idx_generation_time", "generated_images(generation_time)"),
|
|
("idx_prompt_tags_tag", "prompt_tags(tag_id)"),
|
|
("idx_tags_name", "tags(name)"),
|
|
]
|
|
|
|
for name, target in indexes:
|
|
conn.execute(f"CREATE INDEX IF NOT EXISTS {name} ON {target}")
|
|
|
|
def get_connection(self) -> sqlite3.Connection:
|
|
"""
|
|
Get the calling thread's database connection.
|
|
|
|
Each thread gets its own ``sqlite3.Connection`` (kept in
|
|
``threading.local``), created on first use and reused by that thread
|
|
thereafter. Every connection gets ``row_factory = sqlite3.Row`` and the
|
|
shared settings of ``configure_connection``: WAL journaling with
|
|
``synchronous=NORMAL``, ``PRAGMA foreign_keys = ON`` and a
|
|
``busy_timeout`` of BUSY_TIMEOUT_SECONDS so concurrent writers wait
|
|
instead of failing. Callers use it as a context manager
|
|
(``with conn:``), which commits or rolls back that thread's transaction
|
|
and leaves the connection open. No lock is held while a connection is in use.
|
|
|
|
Returns:
|
|
sqlite3.Connection: The current thread's configured connection
|
|
"""
|
|
conn = getattr(self._local, "conn", None)
|
|
if conn is not None and self._local.generation == self._generation:
|
|
return conn
|
|
|
|
# check_same_thread=False only so close_all can clean up other
|
|
# threads' connections; each connection is still used by one thread.
|
|
conn = sqlite3.connect(
|
|
self.db_path, check_same_thread=False, timeout=BUSY_TIMEOUT_SECONDS
|
|
)
|
|
conn.row_factory = sqlite3.Row
|
|
configure_connection(conn)
|
|
self._local.conn = conn
|
|
self._local.generation = self._generation
|
|
with self._conn_lock:
|
|
self._connections.add(conn)
|
|
return conn
|
|
|
|
@classmethod
|
|
def close_all_instances(cls) -> None:
|
|
"""Close every connection of every live model in this process."""
|
|
with cls._instances_lock:
|
|
models = list(cls._instances)
|
|
for model in models:
|
|
model.close_all()
|
|
|
|
def close_all(self) -> None:
|
|
"""Close every thread's connection; they reopen lazily on next use.
|
|
|
|
Needed before deleting the database file (Windows keeps open files
|
|
locked) and by tests that ran queries through executor threads.
|
|
"""
|
|
with self._conn_lock:
|
|
connections = list(self._connections)
|
|
self._connections.clear()
|
|
self._generation += 1
|
|
self._local.conn = None
|
|
for conn in connections:
|
|
try:
|
|
conn.close()
|
|
except sqlite3.Error as e:
|
|
self.logger.warning(f"Error closing database connection: {e}")
|
|
|
|
def close(self) -> None:
|
|
"""Close the calling thread's connection, if it has one.
|
|
|
|
Other threads keep their connections. Call this before deleting or
|
|
replacing the database file: Windows refuses to delete an open file.
|
|
"""
|
|
conn = getattr(self._local, "conn", None)
|
|
if conn is None:
|
|
return
|
|
self._local.conn = None
|
|
with self._conn_lock:
|
|
self._connections.discard(conn)
|
|
try:
|
|
conn.close()
|
|
except sqlite3.Error as e:
|
|
self.logger.warning(f"Error closing database connection: {e}")
|
|
|
|
def _migrate_workflow_name_removal(self, conn: sqlite3.Connection) -> None:
|
|
"""
|
|
Remove workflow_name column if it exists in existing database.
|
|
|
|
Args:
|
|
conn: Active database connection
|
|
|
|
This migration handles legacy schema updates by removing the deprecated
|
|
workflow_name column while preserving all other data.
|
|
|
|
Raises:
|
|
sqlite3.Error: If the rebuild fails (logged, nothing half-applied)
|
|
"""
|
|
try:
|
|
cursor = conn.execute("PRAGMA table_info(prompts)")
|
|
columns = [column[1] for column in cursor.fetchall()]
|
|
if "workflow_name" not in columns:
|
|
return
|
|
|
|
self.logger.info("Migrating database: removing workflow_name column")
|
|
with self._table_rebuild(conn):
|
|
# A previous attempt may have died between CREATE and RENAME
|
|
conn.execute("DROP TABLE IF EXISTS prompts_new")
|
|
conn.execute("""
|
|
CREATE TABLE prompts_new (
|
|
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
|
text TEXT NOT NULL,
|
|
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
|
|
updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
|
|
category TEXT,
|
|
tags TEXT,
|
|
rating INTEGER CHECK(rating >= 1 AND rating <= 5),
|
|
notes TEXT,
|
|
hash TEXT UNIQUE
|
|
)
|
|
""")
|
|
conn.execute("""
|
|
INSERT INTO prompts_new (id, text, created_at, updated_at,
|
|
category, tags, rating, notes, hash)
|
|
SELECT id, text, created_at, updated_at, category, tags, rating,
|
|
notes, hash
|
|
FROM prompts
|
|
""")
|
|
conn.execute("DROP TABLE prompts")
|
|
conn.execute("ALTER TABLE prompts_new RENAME TO prompts")
|
|
self.logger.info("Database migration completed")
|
|
|
|
except sqlite3.Error as e:
|
|
self.logger.error(f"Migration error (workflow_name removal): {e}")
|
|
raise
|
|
|
|
def _migrate_foreign_key_types(self, conn: sqlite3.Connection) -> None:
|
|
"""
|
|
Fix foreign key data type mismatch in generated_images table.
|
|
|
|
Args:
|
|
conn: Active database connection
|
|
|
|
Converts prompt_id from TEXT to INTEGER type to match the prompts table's
|
|
primary key type, ensuring referential integrity.
|
|
|
|
Raises:
|
|
sqlite3.Error: If the rebuild fails (logged, nothing half-applied)
|
|
"""
|
|
try:
|
|
cursor = conn.execute("PRAGMA table_info(generated_images)")
|
|
columns = {column[1]: column[2] for column in cursor.fetchall()}
|
|
if columns.get("prompt_id") != "TEXT":
|
|
return
|
|
|
|
self.logger.info("Migrating foreign key types: prompt_id TEXT -> INTEGER")
|
|
with self._table_rebuild(conn):
|
|
conn.execute("DROP TABLE IF EXISTS generated_images_new")
|
|
conn.execute("""
|
|
CREATE TABLE generated_images_new (
|
|
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
|
prompt_id INTEGER NOT NULL,
|
|
image_path TEXT NOT NULL,
|
|
filename TEXT NOT NULL,
|
|
generation_time TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
|
|
file_size INTEGER,
|
|
width INTEGER,
|
|
height INTEGER,
|
|
format TEXT,
|
|
workflow_data TEXT,
|
|
prompt_metadata TEXT,
|
|
parameters TEXT,
|
|
FOREIGN KEY (prompt_id) REFERENCES prompts(id) ON DELETE CASCADE
|
|
)
|
|
""")
|
|
conn.execute("""
|
|
INSERT INTO generated_images_new
|
|
(id, prompt_id, image_path, filename, generation_time, file_size,
|
|
width, height, format, workflow_data, prompt_metadata, parameters)
|
|
SELECT id, CAST(prompt_id AS INTEGER), image_path, filename,
|
|
generation_time,
|
|
file_size, width, height, format, workflow_data,
|
|
prompt_metadata, parameters
|
|
FROM generated_images
|
|
WHERE prompt_id != '' AND prompt_id IS NOT NULL
|
|
AND CAST(prompt_id AS INTEGER) IN (SELECT id FROM prompts)
|
|
""")
|
|
conn.execute("DROP TABLE generated_images")
|
|
conn.execute(
|
|
"ALTER TABLE generated_images_new RENAME TO generated_images"
|
|
)
|
|
self.logger.info("Foreign key migration completed")
|
|
|
|
except sqlite3.Error as e:
|
|
self.logger.error(f"Migration error (foreign key types): {e}")
|
|
raise
|
|
|
|
def _migrate_json_tags_to_junction(self, conn: sqlite3.Connection) -> None:
|
|
"""
|
|
Populate tags and prompt_tags tables from legacy JSON tags column.
|
|
|
|
Runs once: skips if the tags table already has data. Uses json_each()
|
|
to extract tag names from the JSON arrays stored in prompts.tags.
|
|
|
|
Raises:
|
|
sqlite3.Error: If the migration fails (logged)
|
|
"""
|
|
try:
|
|
cursor = conn.execute("SELECT COUNT(*) FROM tags")
|
|
if cursor.fetchone()[0] > 0:
|
|
return # Already migrated
|
|
|
|
cursor = conn.execute(
|
|
"SELECT COUNT(*) FROM prompts "
|
|
"WHERE tags IS NOT NULL AND tags != '' AND tags != '[]'"
|
|
)
|
|
if cursor.fetchone()[0] == 0:
|
|
return # No tags to migrate
|
|
|
|
self.logger.info("Migrating JSON tags to normalized junction tables")
|
|
|
|
# Insert all unique tag names
|
|
conn.execute(
|
|
"INSERT OR IGNORE INTO tags (name) "
|
|
"SELECT DISTINCT je.value FROM prompts, json_each(prompts.tags) AS je "
|
|
"WHERE prompts.tags IS NOT NULL AND prompts.tags != '' AND "
|
|
"prompts.tags != '[]'"
|
|
)
|
|
|
|
# Populate junction table
|
|
conn.execute(
|
|
"INSERT OR IGNORE INTO prompt_tags (prompt_id, tag_id) "
|
|
"SELECT p.id, t.id "
|
|
"FROM prompts p, json_each(p.tags) AS je "
|
|
"JOIN tags t ON t.name = je.value "
|
|
"WHERE p.tags IS NOT NULL AND p.tags != '' AND p.tags != '[]'"
|
|
)
|
|
|
|
tag_count = conn.execute("SELECT COUNT(*) FROM tags").fetchone()[0]
|
|
link_count = conn.execute("SELECT COUNT(*) FROM prompt_tags").fetchone()[0]
|
|
self.logger.info(
|
|
f"Tag migration complete: {tag_count} unique tags, {link_count} "
|
|
"prompt-tag links"
|
|
)
|
|
|
|
except sqlite3.Error as e:
|
|
self.logger.error(f"Migration error (tag junction): {e}")
|
|
raise
|
|
|
|
def _migrate_add_usage_columns(self, conn: sqlite3.Connection) -> None:
|
|
"""
|
|
Add last_used_at and run_count (3.2.4) and estimate usage for existing rows.
|
|
|
|
The backfill runs only when the columns are added, i.e. on the upgrade
|
|
from a version without usage tracking. Afterwards a NULL last_used_at
|
|
means "never run": saving a prompt does not stamp it, only
|
|
record_prompt_use does, and "Recently Used" relies on that.
|
|
|
|
The estimate comes from linked images: run_count is the image count (at
|
|
least 1) and last_used_at the newest image time, falling back to created_at.
|
|
Timestamps are compared with julianday() because prompts use ISO 'T'
|
|
timestamps while generated_images uses SQLite's CURRENT_TIMESTAMP format.
|
|
"""
|
|
try:
|
|
columns = {row[1] for row in conn.execute("PRAGMA table_info(prompts)")}
|
|
added = False
|
|
if "last_used_at" not in columns:
|
|
self.logger.info("Adding prompt usage column last_used_at")
|
|
conn.execute("ALTER TABLE prompts ADD COLUMN last_used_at TIMESTAMP")
|
|
added = True
|
|
if "run_count" not in columns:
|
|
self.logger.info("Adding prompt usage column run_count")
|
|
conn.execute(
|
|
"ALTER TABLE prompts ADD COLUMN run_count INTEGER NOT NULL "
|
|
"DEFAULT 0"
|
|
)
|
|
added = True
|
|
if not added:
|
|
return
|
|
|
|
cursor = conn.execute(f"""
|
|
UPDATE prompts SET
|
|
run_count = MAX(run_count, 1, (
|
|
SELECT COUNT(*) FROM generated_images gi
|
|
WHERE gi.prompt_id = prompts.id
|
|
)),
|
|
last_used_at = strftime('{ISO_TIMESTAMP_FORMAT}', MAX(
|
|
COALESCE(julianday(created_at), julianday('now')),
|
|
COALESCE((
|
|
SELECT MAX(julianday(gi.generation_time))
|
|
FROM generated_images gi WHERE gi.prompt_id = prompts.id
|
|
), 0)
|
|
))
|
|
WHERE last_used_at IS NULL
|
|
""")
|
|
if cursor.rowcount:
|
|
self.logger.info(f"Estimated usage for {cursor.rowcount} prompts")
|
|
except sqlite3.Error as e:
|
|
self.logger.error(f"Migration error (usage columns): {e}")
|
|
raise
|
|
|
|
def _migrate_image_uniqueness_by_path(self, conn: sqlite3.Connection) -> None:
|
|
"""
|
|
Rebuild generated_images so an image is unique per (prompt_id, file_path).
|
|
|
|
Older schemas were unique per (prompt_id, filename), i.e. the basename,
|
|
so ComfyUI's same-named files in different date folders were silently
|
|
dropped. file_path holds normalize_image_path(image_path); rows whose
|
|
paths normalise to the same file collapse to the newest one.
|
|
|
|
Raises:
|
|
sqlite3.Error: If the rebuild fails (logged, nothing half-applied)
|
|
"""
|
|
try:
|
|
columns = {
|
|
row[1] for row in conn.execute("PRAGMA table_info(generated_images)")
|
|
}
|
|
if "file_path" in columns:
|
|
return
|
|
|
|
self.logger.info("Migrating database: image uniqueness by full path")
|
|
with self._table_rebuild(conn):
|
|
rows = conn.execute(
|
|
"SELECT id, prompt_id, image_path FROM generated_images ORDER BY id"
|
|
).fetchall()
|
|
keep = {}
|
|
for row_id, prompt_id, image_path in rows:
|
|
keep[(prompt_id, normalize_image_path(image_path))] = row_id
|
|
|
|
conn.execute("DROP TABLE IF EXISTS generated_images_new")
|
|
conn.execute("""
|
|
CREATE TABLE generated_images_new (
|
|
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
|
prompt_id INTEGER NOT NULL,
|
|
image_path TEXT NOT NULL,
|
|
filename TEXT NOT NULL,
|
|
generation_time TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
|
|
file_size INTEGER,
|
|
width INTEGER,
|
|
height INTEGER,
|
|
format TEXT,
|
|
workflow_data TEXT,
|
|
prompt_metadata TEXT,
|
|
parameters TEXT,
|
|
file_path TEXT,
|
|
FOREIGN KEY (prompt_id) REFERENCES prompts(id) ON DELETE
|
|
CASCADE,
|
|
UNIQUE(prompt_id, file_path)
|
|
)
|
|
""")
|
|
conn.executemany(
|
|
"""
|
|
INSERT INTO generated_images_new
|
|
(id, prompt_id, image_path, filename, generation_time, file_size,
|
|
width, height, format, workflow_data, prompt_metadata, parameters,
|
|
file_path)
|
|
SELECT id, prompt_id, image_path, filename, generation_time,
|
|
file_size,
|
|
width, height, format, workflow_data, prompt_metadata,
|
|
parameters,
|
|
?
|
|
FROM generated_images WHERE id = ?
|
|
""",
|
|
[(file_path, row_id) for (_, file_path), row_id in keep.items()],
|
|
)
|
|
conn.execute("DROP TABLE generated_images")
|
|
conn.execute(
|
|
"ALTER TABLE generated_images_new RENAME TO generated_images"
|
|
)
|
|
dropped = len(rows) - len(keep)
|
|
if dropped:
|
|
self.logger.info(f"Collapsed {dropped} duplicate image rows")
|
|
self.logger.info("Image path uniqueness migration completed")
|
|
|
|
except sqlite3.Error as e:
|
|
self.logger.error(f"Migration error (image path uniqueness): {e}")
|
|
raise
|
|
|
|
def vacuum_database(self) -> None:
|
|
"""
|
|
Optimize database by running VACUUM command.
|
|
|
|
Reclaims unused space and defragments the database file,
|
|
improving query performance and reducing file size.
|
|
"""
|
|
try:
|
|
with closing(sqlite3.connect(self.db_path)) as conn:
|
|
conn.execute("VACUUM")
|
|
conn.commit()
|
|
except Exception as e:
|
|
self.logger.error(f"Error vacuuming database: {e}")
|
|
|
|
def get_database_info(self) -> dict:
|
|
"""
|
|
Get information about the database.
|
|
|
|
Returns:
|
|
dict: Database statistics and information
|
|
"""
|
|
try:
|
|
with self.get_connection() as conn:
|
|
cursor = conn.execute("SELECT COUNT(*) as total_prompts FROM prompts")
|
|
total_prompts = cursor.fetchone()["total_prompts"]
|
|
|
|
cursor = conn.execute(
|
|
"SELECT COUNT(DISTINCT category) as unique_categories FROM "
|
|
"prompts WHERE category IS NOT NULL"
|
|
)
|
|
unique_categories = cursor.fetchone()["unique_categories"]
|
|
|
|
cursor = conn.execute(
|
|
"SELECT AVG(rating) as avg_rating FROM prompts WHERE rating IS "
|
|
"NOT NULL"
|
|
)
|
|
avg_rating = cursor.fetchone()["avg_rating"]
|
|
|
|
# Get database file size
|
|
db_size = (
|
|
os.path.getsize(self.db_path) if os.path.exists(self.db_path) else 0
|
|
)
|
|
|
|
return {
|
|
"total_prompts": total_prompts,
|
|
"unique_categories": unique_categories,
|
|
"average_rating": round(avg_rating, 2) if avg_rating else None,
|
|
"database_size_bytes": db_size,
|
|
"database_path": os.path.abspath(self.db_path),
|
|
}
|
|
except Exception as e:
|
|
self.logger.error(f"Error getting database info: {e}")
|
|
return {}
|
|
|
|
def backup_database(self, backup_path: str) -> bool:
|
|
"""
|
|
Write a consistent copy of the database to backup_path.
|
|
|
|
Uses the SQLite online backup API through this thread's connection,
|
|
so rows that are committed but still sit in the -wal file are
|
|
included and other threads may keep reading and writing meanwhile.
|
|
|
|
Args:
|
|
backup_path: Path where the backup should be saved (overwritten)
|
|
|
|
Returns:
|
|
bool: True if backup was successful, False otherwise
|
|
"""
|
|
try:
|
|
if os.path.exists(backup_path) and os.path.samefile(
|
|
backup_path, self.db_path
|
|
):
|
|
self.logger.error("Refusing to back up the database onto itself")
|
|
return False
|
|
if os.path.exists(backup_path):
|
|
os.remove(backup_path)
|
|
source = self.get_connection()
|
|
destination = sqlite3.connect(backup_path)
|
|
try:
|
|
source.backup(destination)
|
|
finally:
|
|
destination.close()
|
|
return True
|
|
except (OSError, sqlite3.Error) as e:
|
|
self.logger.error(f"Error creating database backup: {e}")
|
|
return False
|
|
|
|
@staticmethod
|
|
def verify_database_file(
|
|
path: str, *, require_library_state: bool = False
|
|
) -> Tuple[bool, str]:
|
|
"""
|
|
Check that a file is a healthy prompts database before restoring it.
|
|
|
|
Opens the file read-only, runs PRAGMA integrity_check and confirms the
|
|
prompts table has the columns every version of this extension needs.
|
|
|
|
Args:
|
|
path: File to inspect
|
|
require_library_state: Also require the tables every current
|
|
database has (Library state and image favorites), as a
|
|
migrated restore stage must; old backups may lack them.
|
|
|
|
Returns:
|
|
(ok, reason): reason is "ok" when the file is acceptable, otherwise
|
|
a human-readable explanation. Never raises for bad input.
|
|
"""
|
|
if not os.path.isfile(path):
|
|
return False, "File not found"
|
|
try:
|
|
with open(path, "rb") as fh:
|
|
header = fh.read(len(SQLITE_HEADER))
|
|
except OSError as e:
|
|
return False, f"Cannot read file: {e}"
|
|
if header != SQLITE_HEADER:
|
|
return False, "Not a SQLite database file"
|
|
|
|
uri = Path(os.path.abspath(path)).as_uri() + "?mode=ro"
|
|
try:
|
|
conn = sqlite3.connect(uri, uri=True)
|
|
except sqlite3.Error as e:
|
|
return False, f"Invalid SQLite database: {e}"
|
|
try:
|
|
row = conn.execute("PRAGMA integrity_check").fetchone()
|
|
verdict = row[0] if row else "no result"
|
|
if verdict != "ok":
|
|
return False, f"Integrity check failed: {verdict}"
|
|
table = conn.execute(
|
|
"SELECT name FROM sqlite_master WHERE type='table' AND name='prompts'"
|
|
).fetchone()
|
|
if not table:
|
|
return False, "Database does not contain a 'prompts' table"
|
|
columns = {r[1] for r in conn.execute("PRAGMA table_info(prompts)")}
|
|
missing = [c for c in REQUIRED_PROMPT_COLUMNS if c not in columns]
|
|
if missing:
|
|
return (
|
|
False,
|
|
"prompts table is missing required columns: " + ", ".join(missing),
|
|
)
|
|
forbidden = conn.execute(
|
|
"SELECT type FROM sqlite_master WHERE type IN ('trigger', 'view') "
|
|
"LIMIT 1"
|
|
).fetchone()
|
|
if forbidden:
|
|
return False, f"Database contains an unsupported {forbidden[0]}"
|
|
pair_error = PromptModel._pair_schema_error(conn)
|
|
if pair_error:
|
|
return False, pair_error
|
|
history_error = history_schema_error(conn)
|
|
if history_error:
|
|
return False, history_error
|
|
library_error = library_schema_error(
|
|
conn, allow_missing=not require_library_state
|
|
)
|
|
if library_error:
|
|
return False, library_error
|
|
favorites_error = image_favorites_schema_error(
|
|
conn, allow_missing=not require_library_state
|
|
)
|
|
if favorites_error:
|
|
return False, favorites_error
|
|
return True, "ok"
|
|
except sqlite3.Error as e:
|
|
return False, f"Invalid SQLite database: {e}"
|
|
finally:
|
|
conn.close()
|
|
|
|
def _replace_contents_from(self, src_path: str) -> None:
|
|
"""Copy every page of *src_path* into the live database.
|
|
|
|
Goes through SQLite's online backup API into this thread's normal
|
|
connection, so SQLite takes the locks itself and the other
|
|
PromptModel instances that share the file (nodes, image monitor,
|
|
queue hook, API) simply see the new pages on their next statement.
|
|
Nothing is swapped underneath open handles and no -wal/-shm file has
|
|
to be deleted, which also keeps Windows happy. If SQLite refuses
|
|
replacement (for example, incompatible page sizes in WAL mode),
|
|
propagate the error rather than copy files under other open owners.
|
|
"""
|
|
source = sqlite3.connect(
|
|
Path(src_path).resolve().as_uri() + "?mode=ro", uri=True
|
|
)
|
|
try:
|
|
source.backup(self.get_connection())
|
|
finally:
|
|
source.close()
|
|
|
|
def restore_from_file(self, src_path: str) -> str:
|
|
"""
|
|
Replace the live database with the file at src_path.
|
|
|
|
A disposable SQLite backup of the source is migrated and verified first.
|
|
Only then is the current database backed up next to itself as
|
|
``<db_path>.backup_<YYYYmmdd_HHMMSS>`` (WAL content included), and the
|
|
staged pages replace the live pages through SQLite's backup API.
|
|
Migration failures never replace live content or modify the source.
|
|
An online replacement failure leaves the live database intact and
|
|
propagates; the completed safety backup remains available.
|
|
|
|
Args:
|
|
src_path: SQLite file to restore
|
|
|
|
Returns:
|
|
Path of the backup taken of the previous database, or "" when
|
|
there was no database to back up.
|
|
|
|
Raises:
|
|
RuntimeError: If the previous database could not be backed up
|
|
sqlite3.OperationalError: If SQLite refuses online replacement
|
|
"""
|
|
ok, reason = self.verify_database_file(src_path)
|
|
if not ok:
|
|
raise ValueError(reason)
|
|
with tempfile.TemporaryDirectory(prefix="prompt-manager-restore-") as directory:
|
|
staged_path = str(Path(directory) / "staged.db")
|
|
source = sqlite3.connect(
|
|
Path(src_path).resolve().as_uri() + "?mode=ro", uri=True
|
|
)
|
|
try:
|
|
with closing(sqlite3.connect(staged_path)) as destination:
|
|
source.backup(destination)
|
|
finally:
|
|
source.close()
|
|
staged = None
|
|
try:
|
|
staged = PromptModel(staged_path)
|
|
rotate_history_epoch(staged.get_connection())
|
|
ok, reason = self.verify_database_file(
|
|
staged_path, require_library_state=True
|
|
)
|
|
if not ok:
|
|
raise ValueError(reason)
|
|
staged.close_all()
|
|
backup_path = ""
|
|
if os.path.exists(self.db_path):
|
|
timestamp = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
|
|
backup_path = f"{self.db_path}.backup_{timestamp}"
|
|
if not self.backup_database(backup_path):
|
|
raise RuntimeError("Could not back up the current database")
|
|
self.logger.info(f"Current database backed up to: {backup_path}")
|
|
try:
|
|
self._replace_contents_from(staged_path)
|
|
except sqlite3.OperationalError as exc:
|
|
exc._prompt_manager_restore_backup_created = bool(backup_path)
|
|
raise
|
|
with PromptModel._init_lock:
|
|
PromptModel._initialized_paths.add(self._schema_key())
|
|
self.logger.info(f"Database restored from {src_path}")
|
|
from .execution_history import notify_history_restore
|
|
|
|
notify_history_restore(self.db_path)
|
|
return backup_path
|
|
finally:
|
|
if staged is not None:
|
|
staged.close_all()
|
|
with PromptModel._init_lock:
|
|
PromptModel._initialized_paths.discard(
|
|
os.path.normcase(os.path.realpath(staged_path))
|
|
)
|