5.0 KiB
5.0 KiB
PROGRESS.md
This file records current progress for agents. Read it before starting work, then update it after meaningful changes. Completed historical work is archived in docs/WORKARCHIVE.md.
Current Status
- Project direction is documented in
PRD.md,ARCHITECTURE.md,AGENTS.md, anddocs/KNOWLEDGEBASE.md. - MinerU 3.1.0 is fixed as the only conversion engine.
- The converter currently includes path planning, project-owned records, internal provenance, direct local MinerU adapter boundary, Obsidian Markdown normalization, local quality checks, report rendering, conversion orchestration, simplified output layout,
pdf2md convert, legacypdf2md recheck,pdf2md doctor, local MathJax render checking, conservative MathJax warning mitigation, release-gate tests, opt-in grouped page conversion, a minimal Windows UI launcher with direct-folder PDF batch conversion, pypdf-based text layer fidelity diagnostics, NVIDIA GPU inventory, optional--gpu auto, and MinerU profile tuning. docs/V1IMPLEMENTATIONPLAN.mdnow tracks current v1 state and open future decisions; completed implementation details are archived indocs/WORKARCHIVE.md.docs/Sprints/contains completed sprint contracts through Sprint 16 and the abandoned Sprint 17 offline installer contract.docs/superpowers/specs/2026-05-13-ui-folder-batch-conversion-design.mdanddocs/superpowers/plans/2026-05-13-ui-folder-batch-conversion.mdrecord the completed UI direct-folder batch work.docs/WORKARCHIVE.mdcontains completed sprint history, historical verification results, runtime setup notes, sample conversion evidence, archived UI work, and abandoned Sprint 17 planning context.samples/exists locally as fixture context.outputs/,build/, anddist/are local generated artifact locations and must stay out of commits.
Environment Notes
- OS/workspace: Windows PowerShell in
D:\Work\Repos\AICoding\ConvertPDFToMD. - Python target: 3.12.
- Local project Python observed: 3.12.7 through
uv run pdf2md doctoron 2026-05-11. uvis installed per-user atC:\Users\user\.local\bin.- Target GPU documented for this project setup: NVIDIA GTX 1070 Ti 8GB.
- Current PC GPU observed by
doctor: NVIDIA GeForce GTX 1070 Ti 8GB. - Default conversion device:
cuda:0. - Default MinerU profile:
auto. - MinerU execution mode: direct local
mineruCLI only. - Strict-local allows MinerU 3.1.0's CLI-internal temporary local
mineru-apiwhen the CLI runs without--api-url. - Strict-local prohibits
--api-url, remote APIs, router mode, HTTP client backends, and remote OpenAI-compatible backends. - Current
.venvhas project fast-test dependencies, CUDA-enabled PyTorch2.6.0+cu126,torchvision 0.21.0+cu126,mineru[core]==3.1.0, local MathJax npm dependencies, and local MinerU models. - Current
pdf2md doctorstatus is WARN because GTX 1070 Ti is Pascal/pre-Turing; MinerU, CUDA PyTorch visibility, local model config, MathJax, and strict-local checks otherwise pass. Doctor selectscuda:0for--gpu autoon this machine and recommends MinerU profilesafe. - MinerU models were downloaded from Hugging Face by explicit setup command. Runtime model loading uses
MINERU_MODEL_SOURCE=local.
Recent Completed Work
- Archived completed coordination details from
PLAN.md,PROGRESS.md, anddocs/V1IMPLEMENTATIONPLAN.mdintodocs/WORKARCHIVE.md. - Refreshed current docs so abandoned Sprint 17 offline installer planning, completed UI direct-folder batch conversion, simplified output layout, legacy-only
recheck, and no-public-metadata behavior are consistently referenced. - Updated project agent/source-document references so future document reviews and implementation work can find Sprint 15/16 contracts, abandoned Sprint 17 context, and the UI folder batch design/plan.
- Abandoned Sprint 17 offline installer planning at the user's request. The contract and plan remain as historical records only.
In Progress
- No active implementation sprint.
Blockers
- No active blocker.
- Residual risk: direct CLI conversion smokes for
samples\FourNodeQuadrilateralShellElementMITC4.pdfexceeded the 15-minute timeout on 2026-05-11 and stalled on source page 2 with Sprint 14--chunk-pageson 2026-05-12, so hands-on UI conversion smoke remains pending. - Residual risk: conversion can still be impractically slow or stall on GTX 1070 Ti 8GB for some source pages even when Sprint 14 sends one source page to MinerU at a time.
Next Actions
- Run hands-on UI smoke when practical: launch
dist\pdf2md-ui.exe, click Doctor, then run one small local conversion to ignoredoutputs/. - Preserve strict-local runtime behavior: use local model paths, direct CLI execution, and no user-specified API or remote backend.
- Decide in a future sprint whether simplified outputs need metadata-free
pdf2md recheck; current behavior intentionally remains legacy-only. - On a stronger NVIDIA GPU PC, run
uv run pdf2md doctorand an optional local conversion with--gpu auto --mineru-profile autoto validate the auto profile against ignoredoutputs/.