Delete patch_error_message.py, patch_frontend_image_gen.py, patch_image_gen.py, patch_none_guard.py, patch_openrouter_resilience.py

Upload Dockerfile

Upload patch_agent_backend.py

Upload patch_ming_models.py

Upload patch_frontend_ming_models.py

Upload BUILD_TRIGGER

Upload Dockerfile

Upload patch_image_gen.py

Upload patch_image_gen.py

Upload patch_frontend_image_gen.py

Upload patch_frontend_image_gen.py

Upload patch_none_guard.py

Upload patch_none_guard.py

Activate patch_none_guard.py to fix 'NoneType' object has no attribute 'usage'

Fix 'NoneType' object has no attribute 'usage': add terminal LLMResult after the retry for-loop in both LLM helpers + defensive None/usage guards in run_agent

Add image generation frontend: ming-image model in picker + route to /api/image/generate with rendered result

Fix silent auto-approve + add provider-aware auth error message

Add provider-aware auth error message: OpenRouter models must not be told to set HF_TOKEN

Fix silent auto-approve failure: anchor correctly, add runtime opt-out, drop dead mid-task block

Upload patch_none_guard.py

Trigger rebuild: add typesafe/jev-router, fix auto-approve patch, add OpenRouter resilience (tool-less retry + 429 backoff)

Fix ordering bug in v2: anchor after auto-approval attrs are initialized so set_auto_approval_policy is not overwritten

Add patch_openrouter_resilience.py: tool-less model retry (jev-router) + 429 backoff (qwen3.8-27b); add typesafe/jev-router

Handle tool-less models (jev-router) and OpenRouter shared-pool 429 with bounded retry

Add typesafe/jev-router to the model picker (3 chat models total)

<content>"""Patch backend: register the new chat models using the Laguna S 2.1 model-path convention.

Fix auto-approve: wrong anchor (multi-line __init__ signature) AND wrong API (auto_approval dict vs auto_approval_enabled flag)

Trigger rebuild after dropping ming-image-0.1-design and span-01-lite

Add only the 2 chat-capable models to the picker; exclude ming-image-0.1-design (image-gen) and span-01-lite (not on OpenRouter)

Fix NameError: remove stray import_anchor_holder line

Register only the 2 chat-capable models; drop ming-image-0.1-design (image-gen, chat/completions 404) and span-01-lite (absent from OpenRouter catalog)

Trigger rebuild: dots-3-note-preview, qwen3.8-27b, span-01-lite, ming-image-0.1-design

Fix idempotency bug: guard _available_models insert, assert no duplicate entries

Dockerfile: run new patches for dots-3-note / qwen3.8-27b / span-01-lite / ming-image-design

Add frontend patch for 4 new models (dots-3-note, qwen3.8-27b, span-01-lite, ming-image-design)

Add backend patch for 4 new models (dots-3-note, qwen3.8-27b, span-01-lite, ming-image-design)

Upload Dockerfile

Upload Dockerfile

Upload patch_restore_full_app.py

Upload BUILD_TRIGGER

Upload patch_frontend.py

Upload README.md

Upload patch_models.py

Upload BUILD_TRIGGER

Upload README.md

Upload Dockerfile

Upload patch_space_bunny.py

Upload patch_models.py

Fix OpenRouter models: add custom_llm_provider='openrouter' so litellm stops failing on non-provider org prefixes (upstage/nvidia/liquid)

Add 3 new OpenRouter models: UPSTAGE Solar Pro 4, NVIDIA Nemotron 3.5 Lightning:free, Liquid LFM 2.5 2.6B:free