The post-processor stored the LLM's confidence as `_llm_confidence`, but
that value could never be read back: `BaseModelMetadata.from_dict()`
deliberately excludes underscore-prefixed keys from `_unknown_fields` and
`to_dict()` strips private fields, so it was erased by the next metadata
write and was invisible to `read_metadata()`. The enrichment evaluation
harness reads this field to score runs, so confidence was always scored
as blank.
Store it as `llm_confidence`, which round-trips as an ordinary unknown
field — the same mechanism `llm_enriched_at` already relies on. Nothing
else consumed the old name, and the harness still accepts it so sidecars
written by earlier versions keep evaluating.
Covered by a metadata load/save round-trip regression test plus
assertions that the post-processor writes the persisted key and no longer
writes the private one.
The field dates back to a development-stage bug in the enrich-metadata
(agent) pipeline, which briefly wrote trigger words at the top level of
model metadata instead of the established civitai.trainedWords location.
The write path was fixed before the feature merged to main (PR #1013)
and never shipped in any release, so no writer has existed since.
Remove the leftover pieces:
- BaseModelMetadata.trainedWords field (py/utils/models.py); sidecars
from that dev window now pass the key through _unknown_fields instead
- HF download handler's strip-empty-trainedWords special case, reverting
to saving the metadata object directly (py/routes/handlers/hf_handlers.py)
- trainedWords in the LLM enrichment context (agent_service.py)
- matching fallbacks/fixtures in the enrich_hf_validation harness and
post-processor test
Trigger words continue to live in civitai.trainedWords for all model
sources, which is what the UI, agent post-processor, and metadata sync
all read and write.
Remove tests/enrich_hf_validation/baselines/ from git tracking
(.gitignore entry + git rm --cached). These contain README snapshots
from community HF repos that may include NSFW/sensitive content.
Local files are preserved on disk for offline reference.
The bare call inside _build_prompt_context
would raise NameError because class methods don't close over class-level
scope. Use instead to trigger attribute lookup.
Update enrich_hf_metadata prompt.md clue locations for better LLM accuracy.
Update baseline report to v2 (mean 69.0, 46 models, +2.2pp vs baseline 71.1%).
Consolidate README snapshots into baselines/readmes/.
- Rename py/agent_cli/ -> py/metadata_ops/ (module was never agent-related)
- Rename tests/agent_cli/ -> tests/metadata_ops/
- Remove 9 low-value/debug INFO log points across agent_handlers.py,
agent_service.py, llm_service.py, and metadata_ops/__init__.py
- Keep LLM raw response at DEBUG level for diagnostics
- Consolidate per-model progress + LLM result into single concise
log line with basename instead of full path
- Update package/class/method docstrings to clarify this is a
pipeline infrastructure, not a true agent loop
Move the HF model list from ~/Documents/ into tests/enrich_hf_validation/test_data/
and commit the pipeline validation baseline artifacts (report.json,
preprocessing_audit.json, README snapshots) into baselines/.
Update config.py and run_validation.py defaults to use repo-relative paths
via os.path.dirname(__file__) instead of ~/Documents/ hardcode.
Originates from changes in 8fb00998 (validation pipeline audit).
- Rename md_to_html.py → readme_processor.py (file no longer just HTML conversion)
- _extract_section: include YAML frontmatter, use heading-level-aware forward
walk (sub-headings under # are included), increase walk limit past 30 lines
- _is_heading: exclude </hN> closing tags from boundary detection
- _heading_level: new helper for heading-level-aware section matching
- css: yield 0 for heading like closing tags, was unexpectedly caught by _is_heading
- extract_gallery_images: fix YAML block scalar (text: >-) prompt extraction;
use endswith instead of == to detect the block marker
- _strip_widget_section: add to clean_readme_for_llm (widget text is handled
by post-processor, not needed in LLM prompt)
- _strip_standalone_images: keep markdown image URLs intact for LLM preview
extraction (was stripping to alt text only)
- list_base_models: switch from scanner-cache aggregation to
CivitaiBaseModelService.get_base_models() - always returns full list
- Ollama: add num_ctx=32768 to payload options so thinking models have room
to both reason and produce output
- Add tests/agent_cli/test_readme_processor.py: 59 tests covering extraction,
cleaning, section matching, heading detection
- Update existing tests for behavioral changes
Will Miao