nodes/ComfyAssets-ComfyUI_PromptManager
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix(ingestion): batch history lookups instead of adding an index

Browse Source 
An index on execution_run_outputs would make the library unopenable by
older builds, whose schema check refuses any extra index there. The
migration and the schema-check allowance are reverted, so the history
schema is exactly main's. stored_run_prompts instead looks up a batch of
files with one parameterized filename IN (...) query per chunk of at
most 500 names and matches in memory; the scan computes it once per scan
batch.
This commit is contained in:
Vito Sansevero
2026-10-25 15:01:01 -07:00
parent 16e88342ad
commit 9a6a8a5312
7 changed files with 216 additions and 107 deletions
Download Patch File Download Diff File Expand all files Collapse all files
py/api/admin.py
+49 -16
View File
@@ -36,7 +36,11 @@ except ImportError:
try:
from ...database.pair_ingestion import blank_positive, ingest_resolved_pair
from ...database.run_attribution import host_output_directory, stored_run_prompt
from ...database.run_attribution import (
host_output_directory,
stored_run_prompt,
stored_run_prompts,
)
from ...utils.generation_params import (
PLACEHOLDERS,
GenerationParamsError,
@@ -47,7 +51,11 @@ try:
from ...utils.review_capture import reviewable
except ImportError:
from database.pair_ingestion import blank_positive, ingest_resolved_pair
from database.run_attribution import host_output_directory, stored_run_prompt
from database.run_attribution import (
host_output_directory,
stored_run_prompt,
stored_run_prompts,
)
from utils.generation_params import (
PLACEHOLDERS,
GenerationParamsError,
@@ -1566,6 +1574,8 @@ class AdminRoutesMixin:
if outcomes is not None:
outcomes.append(_scan_outcome(media_file, roots, status, title))
batch_results = list(batch_results)
history = self._recorded_runs_for(media for media, _meta in batch_results)
for media_file, metadata in batch_results:
if self._scan_job and self._scan_job.cancelled:
break
@@ -1579,6 +1589,7 @@ class AdminRoutesMixin:
ambiguous=ambiguous,
untraced=untraced,
records=records,
history=history,
)
except Exception as e:
self.logger.error(f"Error processing {media_file.name}: {e}")
@@ -1637,6 +1648,7 @@ class AdminRoutesMixin:
ambiguous=None,
untraced=None,
records=None,
history=None,
):
"""Enrich exact pairs; retain legacy positive-only import for absent pairs.
@@ -1656,7 +1668,7 @@ class AdminRoutesMixin:
if not metadata:
# No prompt metadata (--disable-metadata, bare savers): only the
# recorded run can say which prompt made it (#342)
return self._link_recorded_run(media_file, {}, detailed)
return self._link_recorded_run(media_file, {}, detailed, history)
canonical = dict(metadata)
for key in ("prompt", "workflow"):
if isinstance(canonical.get(key), str):
@@ -1666,7 +1678,7 @@ class AdminRoutesMixin:
# Preserve malformed metadata for conservative resolver rejection.
pass
if not canonical.get("prompt") and not canonical.get("parameters"):
return self._link_recorded_run(media_file, canonical, detailed)
return self._link_recorded_run(media_file, canonical, detailed, history)
_with_file_size(canonical, media_file)
resolution = resolve_prompt_pair(canonical)
if blank_positive(resolution):
@@ -1700,7 +1712,9 @@ class AdminRoutesMixin:
# Graphs without a recognized sampler keep the legacy extractor below.
prompt_text = self._graph_prompt_text(metadata)
if not prompt_text:
linked = self._link_recorded_run(media_file, canonical, detailed)
linked = self._link_recorded_run(
media_file, canonical, detailed, history
)
if linked is not None:
return linked
return "unresolved" if unchoosable else resolution["state"]
@@ -1726,23 +1740,42 @@ class AdminRoutesMixin:
return status
return {"status": status, "title": self._scan_title(media_file, prompt_text)}
def _link_recorded_run(self, media_file, canonical, detailed=False):
def _recorded_runs_for(self, media_files):
"""``{path: prompt id or None}`` from recorded history for a scan batch.
One output lookup per chunk of names (``stored_run_prompts``), so a
batch never queries history once per file. An empty dict on failure.
"""
try:
return stored_run_prompts(
self.db, [str(path) for path in media_files], host_output_directory()
)
except Exception:
self.logger.warning("History attribution failed for a scan batch")
return {}
def _link_recorded_run(self, media_file, canonical, detailed=False, history=None):
"""Link a file recorded history attributes to one stored prompt (#342).
Returns the scan status (with ``detailed``, a stored or linked file's
``{"status", "title"}``), or None when history names no single stored
prompt for the file (``database.run_attribution``). Never creates a
prompt. Works without any prompt metadata in the file.
prompt. Works without any prompt metadata in the file. ``history`` is
the batch's precomputed lookup; without it the file is looked up alone.
"""
try:
prompt_id = stored_run_prompt(
self.db, str(media_file), host_output_directory()
)
except Exception:
self.logger.warning(
f"History attribution failed for {media_file.name}", exc_info=True
)
return None
if history is not None:
prompt_id = history.get(str(media_file))
else:
try:
prompt_id = stored_run_prompt(
self.db, str(media_file), host_output_directory()
)
except Exception:
self.logger.warning(
f"History attribution failed for {media_file.name}",
exc_info=True,
)
return None
if prompt_id is None:
return None
try: