fix(scan): link the traced prompt when the pair resolver cannot decide

The output scan skipped every file the pair resolver called ambiguous or
unresolved, so workflows where several samplers share one prompt (a base
pass, an upscale pass and a detailer) never reached the Library from a
scan. It now links the positive prompt the shared parser traces for
those files, the prompt the inspector and the legacy pages show. Files
the resolver decides are stored as before, and graphs without a
recognized sampler keep the legacy extractor (#252).

Read-only scans of a 38,602-file output folder into temporary databases:
- links: 1,500 before, 7,954 after; none of the 1,500 dropped or changed;
- of the added links that differ from the pre-redesign scan, 1,275
  replace a number, a LoRA tag, a fragment or a truncated prompt that
  scan stored.
This commit is contained in:
Vito Sansevero
2026-10-19 20:22:53 -07:00
parent b83c3556d8
commit 1d730d8e97
3 changed files with 130 additions and 28 deletions
+52 -16
View File
@@ -27,10 +27,22 @@ except ImportError:
try:
from ...database.operations import PromptDatabase
from ...database.pair_ingestion import ingest_resolved_pair
from ...utils.generation_params import (
PLACEHOLDERS,
GenerationParamsError,
extract_generation_params,
parse_js_json,
)
from ...utils.prompt_pair_resolver import resolve_prompt_pair
except ImportError:
from database.operations import PromptDatabase
from database.pair_ingestion import ingest_resolved_pair
from utils.generation_params import (
PLACEHOLDERS,
GenerationParamsError,
extract_generation_params,
parse_js_json,
)
from utils.prompt_pair_resolver import resolve_prompt_pair
@@ -1511,6 +1523,21 @@ class AdminRoutesMixin:
counts["pair_links_added"] += outcome.get("links_added", 0)
return counts
@staticmethod
def _graph_prompt_text(metadata):
"""The positive prompt the browser parser traces from the graphs, or None."""
records = {}
for key in ("prompt", "workflow"):
value = metadata.get(key)
records[key] = parse_js_json(value) if isinstance(value, str) else value
try:
positive = extract_generation_params(records)["positivePrompt"]
except GenerationParamsError:
return None
if not isinstance(positive, str) or positive == PLACEHOLDERS["positivePrompt"]:
return None
return positive.strip() or None
def _ingest_scanned_file(self, media_file, metadata, detailed=False):
"""Enrich exact pairs; retain legacy positive-only import for absent pairs."""
if not metadata:
@@ -1531,23 +1558,32 @@ class AdminRoutesMixin:
self.db, str(media_file), canonical, resolution
)
return result if detailed else result["status"]
if resolution["state"] == "ambiguous":
return "ambiguous"
if resolution["state"] == "unresolved":
if canonical.get("prompt") or not isinstance(
canonical.get("parameters"), str
):
if canonical.get("prompt") and resolution["state"] in (
"ambiguous",
"unresolved",
):
# The resolver could not decide: link the prompt the inspector and the
# legacy pages show for this file (the browser parser, in Python).
# Graphs without a recognized sampler keep the legacy extractor below.
prompt_text = self._graph_prompt_text(metadata)
if not prompt_text:
return resolution["state"]
parsed = self._parse_comfyui_prompt(metadata)
if not (parsed.get("prompt") or parsed.get("parameters")):
return None
prompt_text = self._extract_readable_prompt(parsed)
if prompt_text is not None and not isinstance(prompt_text, str):
prompt_text = str(prompt_text)
if not (prompt_text and prompt_text.strip()):
return "found"
prompt_text = prompt_text.strip()
elif resolution["state"] == "ambiguous":
return "ambiguous"
elif resolution["state"] == "unresolved" and not isinstance(
canonical.get("parameters"), str
):
return resolution["state"]
else:
parsed = self._parse_comfyui_prompt(metadata)
if not (parsed.get("prompt") or parsed.get("parameters")):
return None
prompt_text = self._extract_readable_prompt(parsed)
if prompt_text is not None and not isinstance(prompt_text, str):
prompt_text = str(prompt_text)
if not (prompt_text and prompt_text.strip()):
return "found"
prompt_text = prompt_text.strip()
prompt_hash = generate_prompt_hash(prompt_text)
existing = self.db.get_prompt_by_hash(prompt_hash)