Hartmut 502e2d0387 fix: use max_completion_tokens instead of max_tokens for GPT-4o ...

Azure OpenAI GPT-4o and newer models require 'max_completion_tokens'
instead of 'max_tokens'. Fixed in all 3 services:
- chat_service.py (2 call sites)
- azure_ai.py (validation service)
- tenants/router.py (test connection endpoint)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-03-15 14:20:40 +01:00

.claude

feat(M5-M7): embed canonical material names in USD via customData + pxr direct read

2026-03-12 23:04:26 +01:00

backend

fix: use max_completion_tokens instead of max_tokens for GPT-4o

2026-03-15 14:20:40 +01:00

docs

feat: extend MCP server with render/media metadata tools

2026-03-15 00:16:48 +01:00

Excel-Order-Lists

chore: remove build artifacts from tracking, extend .gitignore

2026-03-05 22:13:21 +01:00

frontend

feat: tenant AI chat agent with function calling

2026-03-15 12:46:21 +01:00

MaterialNamingSchema

feat: GPU rendering + material matching + perf improvements

2026-03-08 19:05:03 +01:00

render-worker

perf: render pipeline optimizations — sample scaling, USD logging, persistent BVH

2026-03-15 12:03:31 +01:00

scripts

refactor: rename thumbnail_rendering queue to asset_pipeline

2026-03-12 22:28:38 +01:00

step-sample-file

feat: initial commit

2026-03-05 22:12:38 +01:00

tools

feat: sharp edge pipeline V02, tessellation presets, media cache-bust, GMSH plan

2026-03-11 14:40:36 +01:00

feat: GPU rendering + material matching + perf improvements

2026-03-08 19:05:03 +01:00

.env.example

feat(A4): add MinIO service + storage abstraction (core/storage.py)

2026-03-06 15:51:06 +01:00

.gitignore

feat: sharp edge pipeline V02, tessellation presets, media cache-bust, GMSH plan

2026-03-11 14:40:36 +01:00

.mcp.json

feat: MCP server for Claude Code integration

2026-03-14 23:46:52 +01:00

CLAUDE.md

refactor: remove dead export_gltf.py, cleanup rendering tasks, improve tessellation UI

2026-03-13 10:37:35 +01:00

docker-compose.worker.yml

feat(A4): add MinIO service + storage abstraction (core/storage.py)

2026-03-06 15:51:06 +01:00

docker-compose.yml

fix: revert dual queue to single GPU — light worker caused 2x regression

2026-03-15 12:33:26 +01:00

LEARNINGS.md

feat: per-line render overrides — override any output type setting at order time

2026-03-15 12:26:38 +01:00

plan.md

feat: tenant AI chat agent with function calling

2026-03-15 12:46:21 +01:00

review-report.md

docs: update review report for UI/UX cleanup

2026-03-15 12:00:05 +01:00

ROADMAP.md

feat: performance optimizations + part-materials validation

2026-03-13 11:53:14 +01:00

schaeffler_mcp_server.py

feat: per-line render overrides — override any output type setting at order time

2026-03-15 12:26:38 +01:00

visual-audit-report.md

feat: sharp edge pipeline V02, tessellation presets, media cache-bust, GMSH plan

2026-03-11 14:40:36 +01:00

S

Description

HartOMat: CAD import, media, pricing and legacy-compatible node-based render workflow automation platform.

74 MiB

Languages

Python 58%

TypeScript 40.6%

Shell 0.7%

CSS 0.5%