Files

T

kimminsungandClaude Opus 4.8 a71790070d feat: multi-format 3D viewer with large-file OBJ streaming, Z-up, projection/outline UI

Three.js viewer supporting glb/gltf/obj/fbx/dae/ifc/ply via both server (SSR)
and drag&drop (CSR) paths.

- Streaming OBJ parser (src/viewer/objStream.ts) for files past the V8 max
  string length (>~1GB text) that OBJLoader can't handle; indexed geometry,
  per-vertex color from MTL Kd, float64 recenter baked in.
- In-viewer float64 recenter (objRecenter.ts) for huge CAD/survey coordinates
  (~1e8) so float32 vertex buffers keep precision (no cracked faces).
- Z-up right-handed world; Y-up formats rotated on load.
- OBJ+MTL+texture drag&drop (LoadingManager URL-modifier maps dropped images).
- OrbitControls ground-plane panning (road/rail alignment workflow).
- UI: Zoom Fit, perspective/orthographic toggle, feature-edge outline.
- DoubleSide for CAD OBJ; PLY mesh + point-cloud support.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

2026-06-19 13:54:46 +09:00

2.0 KiB

Raw Blame History

name, description

name	description
task-graph	Multi-agent coordination protocol for hmwebviewer. Load when picking up work, dispatching agents, or reporting progress. Explains how PLAN.md and PROGRESS.md drive parallel agent work and the exact update rules.

hmwebviewer — multi-agent task-graph protocol

PLAN.md = the backlog (what to do). PROGRESS.md = the log (what happened). CLAUDE.md mandates reading both on every agent start.

Picking a task

Read PLAN.md task tables.
Find rows with status todo whose entire depends_on list is done.
Among those, pick by wave (see PLAN.md "Parallelization map") or by the task's Agent column.
Before working: flip status to in_progress(@yourname) in PLAN.md.

Dispatching parallel work

Tasks in the same wave with no mutual dependency run concurrently:

viewer-core, dnd-handler, asset-pipeline → independent, parallel-safe (different dirs: src/viewer, src/dnd, tools).
hydration depends on viewer-core signals → run after.
reviewer → last / on-demand.

Spawn each via the Agent tool in ONE message with multiple calls so they run concurrently. Pass every agent: task ID, file scope, acceptance criteria, pointer to PLAN.md.

Completing a task

Only after acceptance criteria verified with real output:

Flip the PLAN.md row to done.
Append a ## YYYY-MM-DD — <task> entry to PROGRESS.md top of Work log (Did / Result / Next / Blocker).
If a decision was made, add to PROGRESS.md "Decision log" and (if durable) to user memory.

Blocking

If you cannot proceed (missing dependency, ambiguous spec, env failure):

Flip status to blocked(<reason>) in PLAN.md.
Append PROGRESS.md entry with the blocker.
Stop. Do not guess around a real blocker.

Anti-patterns

Working without reading PLAN + PROGRESS → duplicate/conflicting work.
Marking done without verification → silent regressions.
Editing outside your task's file scope → steps on another agent.
Creating parallel loaders/state instead of using the shared singleton → crashes.

2.0 KiB Raw Blame History