Files
ComfyAssets-ComfyUI_PromptM…/database/run_attribution.py
T
Vito Sansevero 144e6b1145 fix(ingestion): link an image only to a prompt that provably produced it
An LLM fed a PromptManagerPair's prepend_text while its text editor was
empty. The node refused to save (an empty positive raised and logged a
warning), and the image monitor then linked the image to a stale tracker
entry or to the newest prompt in the database.

- Nodes: an empty text editor saves and tracks nothing (prepend and
  append text are never the stored prompt), logs at info, and marks the
  node's run key empty so no earlier entry can be used for its images.
- Tracker entries carry a run key: a digest of the prompt node and its
  whole upstream graph, the identity ComfyUI's cache uses. The monitor
  computes the same key from the image's embedded graph and uses a
  queued or snapshot entry only when the keys match (a snapshot also
  needs a known run with one entry, so a batch's last item is never
  applied to every image).
- The recency fallback is gone; anything uncertain stays unlinked and is
  logged at info.
- Recorded execution history attributes a file when exactly one run
  reported it, the file was written during that run, and the run's
  positive contexts name one stored prompt. The monitor and the output
  scan use it as their last certain source.
- The scan and pair ingestion treat a resolved pair with an empty stored
  positive as unresolved instead of raising.
- tools/review_image_links.py reviews selected links by these rules;
  dry run by default, --apply changes only named ids after a backup.

Closes #342
2026-10-25 12:58:16 -07:00

123 lines
4.4 KiB
Python

"""Attribute an output file to a stored prompt through recorded history (#342).
Execution history records, per run, the files ComfyUI reported
(``execution_run_outputs``) and the PromptManager texts the run used
(``execution_run_contexts``, whose ``positive_prompt_id`` hint is set only
while the raw text matches exactly one stored prompt). A file is attributed
only when all of this holds:
- exactly one recorded run reported the file's output location (same output
root, subfolder and name);
- the file was last written while that run was executing, from its dequeue
to its terminal event (else the finish callback): a later run that history
did not record may have reused the name;
- every positive context of that run names the same stored prompt.
Anything else returns None: the caller leaves the file unlinked. Read-only.
"""
import os
import sqlite3
from typing import Any, Optional
try:
from ..utils.execution_outputs import snapshot_output_roots
from ..utils.library_location import import_folder_paths
except ImportError:
from utils.execution_outputs import snapshot_output_roots
from utils.library_location import import_folder_paths
# File times may trail or lead the recorded run times a little (coarse file
# system clocks, the write finishing just after the host reported it).
MTIME_SLACK_MS = 2000
_RUNS_FOR_OUTPUT = (
"SELECT DISTINCT o.run_id, r.observed_dequeue_at, "
"COALESCE(r.terminal_event_at, r.observed_callback_at) "
"FROM execution_run_outputs o JOIN execution_runs r ON r.run_id = o.run_id "
"WHERE o.folder_type = 'output' AND o.path_style = ? AND o.root_key = ? "
"AND o.subfolder = ? AND o.filename = ? LIMIT 2"
)
def host_output_directory() -> Optional[str]:
"""ComfyUI's output directory, or None outside ComfyUI."""
folder_paths = import_folder_paths()
if folder_paths is None:
return None
try:
value = folder_paths.get_output_directory()
except Exception:
return None
return value if isinstance(value, str) and value else None
def _location(image_path: str, output_root: str, path_style: str):
"""(root key, subfolder, filename) as history records them, or None."""
root_key = snapshot_output_roots(path_style, output_root, output_root).output_key
if root_key is None:
return None
try:
relative = os.path.relpath(
os.path.abspath(image_path), os.path.abspath(output_root)
)
except ValueError: # another drive on Windows
return None
if os.path.isabs(relative) or relative == os.pardir:
return None
if relative.startswith(os.pardir + os.sep):
return None
subfolder, filename = os.path.split(relative)
if not filename:
return None
return root_key, subfolder, filename
def _written_during(image_path: str, started: Any, finished: Any) -> bool:
if not isinstance(started, int) or not isinstance(finished, int):
return False
try:
written = os.stat(image_path).st_mtime_ns // 1_000_000
except OSError:
return False
return started - MTIME_SLACK_MS <= written <= finished + MTIME_SLACK_MS
def stored_run_prompt(
db: Any,
image_path: str,
output_root: Optional[str],
path_style: Optional[str] = None,
) -> Optional[int]:
"""The stored prompt id history attributes to ``image_path``, else None."""
if not image_path or not output_root:
return None
style = path_style or ("windows" if os.name == "nt" else "posix")
location = _location(image_path, output_root, style)
if location is None:
return None
root_key, subfolder, filename = location
try:
rows = (
db.model.get_connection()
.execute(_RUNS_FOR_OUTPUT, (style, root_key, subfolder, filename))
.fetchall()
)
except sqlite3.Error:
return None # no history tables (a library without history)
if len(rows) != 1:
return None
run_id, started, finished = rows[0][0], rows[0][1], rows[0][2]
if not _written_during(image_path, started, finished):
return None
contexts = db.get_execution_contexts(run_id).get("contexts") or []
named = {
context.get("positive_prompt_id")
for context in contexts
if context.get("positive") is not None
}
if len(named) != 1:
return None
(prompt_id,) = named
return prompt_id if isinstance(prompt_id, int) else None