Layout: main content gets mr-96 (margin-right) when chat is open,
pushing the page content left so the chat panel sits alongside it
without overlapping. Smooth 300ms transition.
ChatPanel: internal links (/products/..., /orders/...) now use
React Router navigate() instead of target="_blank" — clicking a
product link in the chat navigates without reloading the page,
keeping the chat panel open.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Added product_material filter to find_product_renders:
- Searches cad_part_materials JSONB for materials assigned to CAD parts
- find_product_renders(transparent_only=true, product_material="Durotect")
→ finds 9 products that naturally have Durotect parts with transparent renders
Two material levels explained in system prompt rule 13:
- product_material: materials from STEP/Excel (Durotect_M, Stahl, Bronze)
- material_override: single material forced on ALL parts at render time
AI now searches product_material FIRST when user asks "with Durotect material"
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Rule 13: when searching with multiple criteria (transparent + Durotect),
decompose the search. Show what exists (1220 transparent renders) and
explain what's missing (no Durotect material applied). Never say
"no renders found" when transparent renders DO exist.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
find_product_renders now reads actual render metadata from the
render_log JSONB (stored at render time) via COALESCE fallback:
- engine: render_log.engine_used > render_log.engine > output_type setting
- width/height: render_log > output_type.render_settings
- samples: render_log > output_type.render_settings
- render_type: still/turntable/cinematic from render_log.type
- has_template: whether a .blend template was used
All past renderings now have correct metadata without re-processing.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
find_product_renders now returns full render job metadata:
- material_override (effective: line override > output type override)
- output_format (with render_overrides applied)
- resolution (width x height)
- engine, samples
- order_number + order_id (for linking)
- is_animation flag
New material_override filter: search renders by material name
(e.g. transparent_only=true, material_override="Durotect" finds
renders with Durotect material on transparent background)
AI can now answer: "Show me a transparent Durotect render" by filtering
both transparency AND material in one query.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Explicitly listed all write tools that require confirmation:
create_order, dispatch_renders, set_material_override, set_render_overrides
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Split rules into read-only vs write actions:
- READ (search, list, show images, status): execute immediately
- WRITE (create orders, dispatch, set overrides): ALWAYS ask for
confirmation before executing
Prevents accidental render job creation from casual questions.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
System prompt rule 12: always format product mentions as
[ProductName](/products/UUID) and orders as [OrderNumber](/orders/UUID).
ReactMarkdown in ChatPanel already renders these as clickable links
with accent color styling, so users can navigate directly from chat.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Added list_materials tool to the chat agent:
- Searches SCHAEFFLER library materials by name, description, or alias
- Returns material name + schaeffler_code + aliases
- Enables: "zeig mir ein Bild mit Durotect-Material" → agent searches
for "durotect" → finds SCHAEFFLER_020101_Durotect-Blue → uses as
material_override
System prompt updated with rules 10-11:
- Explains alias → library material mapping
- Always use full SCHAEFFLER name for material_override
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
For 16:9 (1280x720), vertical FOV is narrower than horizontal —
products could be clipped top/bottom. Now applies an aspect ratio
correction factor to camera distance: wider formats push camera
further back proportionally.
Still render (_blender_camera.py) already handled this via
min(fov_h, fov_v); cinematic now has equivalent correction.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Blender 5.0 renamed Action.fcurves. Now tries fcurves first, falls
back to channels, and wraps in try/except so the render proceeds
even if LINEAR interpolation can't be set.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Old frame PNGs from previous render attempts persisted in the frames
directory, causing FFmpeg to stitch the wrong number of frames.
Now rmtree's the directory before creating it fresh.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Changes per user feedback:
- Keyframe interpolation: BEZIER → LINEAR (all fcurves set to LINEAR)
- Removed segment 4 (closeup) — now 3 segments only
- Frame count: 480 → 250 (10 seconds at 25fps)
- FPS: 24 → 25
- Easing removed — pure linear interpolation between segment params
- White background by default (World node Color = white)
- Transparent bg still available as override
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Two fixes for frame progress not appearing in frontend:
1. Added flush=True to all print() calls in cinematic_render.py
2. Set PYTHONUNBUFFERED=1 in subprocess environment
Without these, Python buffers stdout inside Blender, so all frame
progress lines arrive in a batch after the process exits instead
of streaming line-by-line during rendering.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The filter only matched [cinematic_render] tag but Blender outputs its
own "Saved: frame_NNNN.png" lines per frame. Now also matches "Saved:"
lines, extracts the frame number, and formats as:
[cinematic_render] Frame 84/480 rendered
This shows live frame progress in the LiveRenderLog on the frontend.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Replaced communicate() (blocking) with selectors-based line-by-line
stdout streaming — same pattern as still render. Each frame now
streams live to the frontend:
[cinematic_render] Frame 42/480 -- 55.3s elapsed (0.76 fps)
Pipeline: Blender stdout → log_callback → emit() → Redis →
LiveRenderLog poll (2s) → frontend display
Also added log_callback parameter to cinematic render task call.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The service was sending (glb, frames_dir, width, height, engine, samples...)
but the script expected turntable order (glb, frames_dir, frame_count, degrees,
width, height, engine, samples...). Fixed by adding frame_count and degrees
placeholders to match the expected positional layout.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The kanban board kept showing deleted orders until manual reload.
Added qc.invalidateQueries for 'orders' and qc.removeQueries for
the deleted order's detail cache on delete success.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Session ID saved to localStorage (schaeffler-chat-session).
On mount, restores the last session and loads messages from DB.
"New Chat" clears the stored session.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
System prompt rewritten with explicit RULES:
- Never ask user for info you can query yourself
- "Any product" / "beliebig" → just pick one, don't ask back
- Execute immediately, no confirmation needed
- Be concise, short answers preferred
find_product_renders tool:
- No longer requires product_name or product_id
- Call with empty params → returns any recent renders
- Enables "show me any render with transparent bg"
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Added find_product_renders tool to the AI agent:
- Searches completed renders by product name/ID
- Returns viewable image URLs (relative paths)
- Supports transparent_only filter
- AI formats results as Markdown images/links in chat
Frontend:
- ChatPanel ReactMarkdown renders <img> and <a> tags
- Images shown inline (max 200px height, rounded, bordered)
- Links open in new tab with accent color
System prompt updated to instruct AI to use Markdown image syntax
when showing renders: 
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Fixed: from OCP.BRepGProp import BRepGProp as brepgprop (was lowercase)
- Routed reextract_rich_metadata_task to asset_pipeline queue (render-worker
has OCC/OCP installed, worker container does not)
- Backfill verified: 45/45 products updated with volume, surface area,
part count, complexity metrics
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- All httpx tool calls use real user_id instead of uuid(int=0) for
service token — fixes 401 Unauthorized on dispatch/override
- create_order auto-submits and auto-dispatches in one step
- System prompt updated: execute immediately without asking for
confirmation, respond in user's language
- Product search returns CAD dimensions (dim_x/y/z_mm)
- query_database tool description includes cad_files schema
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- search_products now returns dim_x_mm, dim_y_mm, dim_z_mm from
cad_files.mesh_attributes->'dimensions_mm'
- query_database tool description updated with cad_files schema
including mesh_attributes->'dimensions_mm' path
- AI can now answer "what's the biggest product?" using real dimensions
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Frontend: Layout extracts order/product UUID from URL path and passes
to ChatPanel as contextType/contextId. When on /orders/{uuid}, the
chat knows which order you're viewing.
Backend: System prompt now loads actual entity data for the context:
- Order: order_number, status, line counts (completed/processing/failed)
- Product: name, PIM-ID, category, STEP file status
The AI understands "this order", "current product" etc. Example:
"What's the status of this order?" → agent knows you mean SA-2026-00164
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
When a tool like query_database fails (e.g., bad column name), the
SQLAlchemy session enters a failed transaction state. Subsequent
operations (like saving the assistant response) then also fail with
InFailedSQLTransactionError.
Fix: rollback the session in the except block of _execute_tool().
Also improved query_database tool description with correct column
names (category_key not category) to help the AI write valid SQL.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Added react-markdown to render assistant messages with proper formatting:
- **bold** text renders as bold
- Bullet/numbered lists render correctly
- Inline code renders with monospace background
- User messages stay as plain text
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Frontend interface expected 'message' and 'response' but API returns
'user_message' and 'assistant_message'. Field name mismatch caused
undefined access and page crash.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Catch all exceptions (not just ValueError) and return meaningful
error messages from OpenAI API errors instead of generic 500.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Actionable AI assistant that uses per-tenant Azure OpenAI credentials
to execute natural language commands against the render pipeline.
Backend:
- ChatMessage model + migration (session-based conversations)
- Chat service with 10 OpenAI function-calling tools:
list_orders, search_products, create_order, dispatch_renders,
get_order_status, set_material_override, set_render_overrides,
get_render_stats, check_materials, query_database
- All tools tenant-scoped (queries filtered by tenant_id)
- Write operations use httpx to call backend API internally
- Chat API: POST /chat/messages, GET /chat/sessions, DELETE session
- Conversation history preserved in DB (last 50 messages per session)
Frontend:
- Slide-out ChatPanel (right side, w-96, animated)
- User/assistant message styling with avatars and timestamps
- Session management (new chat, session history, delete)
- Typing indicator while waiting for AI response
- Floating chat button in bottom-right corner
- Error state for unconfigured AI tenants
Example: "Render all Kugellager products as WebP at 1024x1024"
→ Agent calls search_products + create_order + dispatch_renders
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Root cause: render-worker and render-worker-light shared the same GPU,
causing contention. Complex TRB renders went from 17s → 36s (2x slower).
Changes:
- Thumbnails back to asset_pipeline queue (not asset_pipeline_light)
- Dispatch routing always uses asset_pipeline (no queue splitting)
- render-worker-light gated behind "multi-gpu" profile — only starts with:
docker compose --profile multi-gpu up -d
- For single-GPU setups: all rendering is sequential on one worker
The dual queue approach is correct for multi-GPU machines where each
worker gets its own GPU. On single-GPU, serial execution is faster
than concurrent GPU contention.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Instead of duplicating output types for every variation (WebP vs PNG,
different resolution), keep one canonical output type and override
specific fields per order line via render_overrides JSONB.
Backend:
- render_overrides JSONB column on OrderLine (DB migration)
- Render task merges overrides with output type settings (format, width,
height, samples, engine, denoiser, transparent_bg, cycles_device)
- POST /orders/{id}/batch-render-overrides endpoint for bulk override
- PatchLineBody accepts render_overrides for per-line patching
Frontend:
- Batch render overrides section on OrderDetail: output format dropdown
(PNG/JPG/WebP) + resolution dropdown (512-4096)
- Clear button to remove overrides
MCP:
- create_order tool: accepts product_ids, output_type, render_overrides,
material_override — enables "render all products as WebP" via Claude
- set_render_overrides tool: batch override on existing orders
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Task 4: Dual render queue
- render-worker: heavy (asset_pipeline, concurrency=1) — HQ 2048x2048, animations
- render-worker-light: light (asset_pipeline_light, concurrency=2) — thumbnails, <=1024
- Thumbnails routed to light queue automatically
- Order line renders routed by resolution at dispatch time
Task 5: GLB caching (skip re-tessellation)
- Before tessellating, check if gltf_geometry MediaAsset exists for the cad_file_id
- If found, copy to expected path — render_blender.py finds it and skips tessellation
- Saves 7-11s per re-render of the same product
Task 6: WebP output format
- New 'webp' option in output_format (OutputType admin)
- Blender renders PNG intermediate, Pillow converts to WebP (quality=90, method=4)
- 50-70% smaller files with no visible quality loss
- Correct MIME type (image/webp) in MediaAsset
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The OptiX cache was mounted at /root/.nv but NVIDIA writes to
/var/tmp/OptixCache_root/optix7cache.db (28MB). Fixed volume mount.
Before: first render after container restart = 181s (OptiX recompilation)
After: first render after container restart = 20s (cached kernels)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Added refetchInterval to the order query that polls every 3 seconds
while render_progress has pending or processing lines. Stops polling
automatically when all renders reach a terminal state (completed/failed/cancelled).
Fixes: render log and backend status not appearing until manual page reload.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Removed from UI (saved to DB but never read by any service):
- Max Concurrent Renders, Stall Timeout, Thumbnail Format, Product Thumbnail Priority
- Render Linear/Angular Deflection (only Scene deflections are used)
- GLB Scale Factor, Smooth Normals, GLB Material Mode, PBR Roughness, PBR Metallic
Fixed Blender status check:
- Old: called is_blender_available() in backend container (Blender not installed there)
- New: dispatches Celery task on asset_pipeline queue → runs in render-worker container
- Returns: available=true, version="Blender 5.0.1", binary path
- Status card moved to System Tools tab with refresh button
Kept active: engine, device, samples, smooth angle, tessellation, scene deflections,
3D viewer zoom limits
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Admin tables (same pattern as OutputTypeTable):
- RenderTemplateTable: 11 cramped columns → expandable form row with grouped fields,
boolean flags consolidated into compact badges, .blend upload in proper section
- PricingTierTable: inline cell editing → expandable form with labeled fields,
shared renderEditFormGrid() for add/edit modes
- GlobalRenderPositionsPanel: tiny rotation inputs → expandable form with w-24 inputs,
proper labels, sensor_width_mm added to edit form
Page polish:
- WorkerManagement: larger scale controls (p-2 rounded-lg), wider number displays (w-12),
proper labels, more prominent Save button
- Billing: status select gets visible dropdown indicator (ChevronDown icon),
hover border to signal interactivity, larger action buttons with borders
- OrderDetail: batch override in proper card with title/description,
per-line override shows compact "+ override" link (expands on click),
active overrides show as amber badge with X to clear
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Replaced the 18-column inline cell editing with an expandable detail row:
- Display row always visible (no more disappearing content on edit)
- Edit form opens BELOW in a full-width colSpan row with accent border
- Fields organized in a 4-column grid with proper labels:
Row 1: Name, Renderer, Format, Animation
Row 2: Turntable, Background, Device, Engine
Row 3: Samples, Resolution, Pricing, Workflow
Row 4: Categories, Material Override, Sort Order, Active
Row 5: Denoising settings (6 cols, Blender only)
- Shared renderEditFormGrid() helper for both edit and add modes
- Save/Cancel buttons at bottom of form
- React.Fragment wrappers for dual-row rendering
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The Preferences page had its own inline accent color section that wasn't
updated with the custom picker. Now shows:
- 5 preset swatches + separator + custom swatch with pipette icon
- Color picker + hex input appear when custom is selected
- Larger swatches (w-8 h-8) matching the page's spacious layout
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Added 'custom' accent option with color picker + hex input
- Pipette icon on the custom swatch (switches to solid when active)
- Color picker appears inline when custom is selected
- Generates hover/light variants automatically from hex (darken/lighten)
- Dark mode accent-light uses rgba for translucency
- Persisted in localStorage, applied before React hydration (no flash)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Widgets scale in with staggered delays (60ms per widget, up to 12)
- Widget hover: lift 3px + accent border glow (dark mode: accent shadow)
- Inner numbers animate up with count-up effect
- Progress bars grow from left with spring curve (800ms delay for content-first feel)
- All wrapped in prefers-reduced-motion guard
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Hartmut