feat: page-memory fine-hierarchy trim and hierarchy path slash escaping - #212

Merged

EricNGOntos merged 39 commits into

mainfrom

feat/wuchengke/remove-h1-match

Jul 20, 2026

Commits on Jun 29, 2026

feat: implement node assembler for page memory hierarchy to support shared page content and VLM-based node summarization
EricNGOntos
committed
feat: implement page asset integration into node assembly and chunk connections with support for custom probes
EricNGOntos
committed
feat: enhance document profiling and page memory integration with skip shard plan option
EricNGOntos
committed
feat: enhance retrieval and document ingestion with new chunk types and effective parse track handling
EricNGOntos
committed
refactor: decouple page memory from image URIs and simplify node metadata structure
EricNGOntos
committed
feat: integrate summary engine for enhanced document parsing and asset handling
EricNGOntos
committed
feat: implement concurrent page tagging and enrich image and table asset metadata with LLM-extracted entities and titles
EricNGOntos
committed
feat: standardize page_memory track for PDF/PPTX, implement page-count limits, and refactor section summary publication to initialization.
EricNGOntos
committed
chore: align parser env defaults
EricNGOntos
committed
refactor: replace legacy data_type integer with flexible chunk_types set across retrieval services
EricNGOntos
committed
feat: implement intermediate node chain collapse and add utilities for cross-page table continuity analysis
EricNGOntos
committed
Add thread-safe trace logging, remove unused heading dataframes, and implement a text-only tagging mode for page memory processing.
EricNGOntos
committed
refactor: remove budget tracking dependency from page memory services
EricNGOntos
committed
chore: fix lint and type errors caught by ruff and pyright
EricNGOntos
committed
fix: resolve alembic revision ID conflict causing cycle detection failure
EricNGOntos
committed
test: fix failing tests from page-memory native hierarchy branch
EricNGOntos
committed

Commits on Jul 1, 2026

Commits on Jul 3, 2026

Commits on Jul 7, 2026

Commits on Jul 9, 2026

fix: accept title_ctx in page tagger contract test mocks

EricNGOntos
and
cursoragent
committed

Commits on Jul 20, 2026