Add Space error fix report

Fix Space startup: use sh instead of missing bash

Trigger rebuild to recover Space error

Fix dropdown names: row 4 Novita→HF Inference, row 6 name→nvidia/nemotron path

Update backend patch: add nvidia/nemotron + google/gemma model IDs

Fix dropdown: rename providers + change model IDs for rows 4,5,6,7

Fix: patch both single+double quotes for Claude rename + block API label override

Restore patch_frontend.py + rename Claude Opus 4.6 → Owl Alpha

Restore patch_models.py from 5743f66

Restore configs from 5743f66

Restore to 5743f66 + rename Claude Opus 4.6 → Owl Alpha

Fix: default model config

Fix: patch_models with openai/ prefix for OpenRouter models (owl-alpha, gemini-flash)

Fix: Owl Alpha display name + correct model paths with openai/ prefix

Fix config default model to openrouter format

Fix backend: litellm openrouter/openrouter/owl-alpha + set as default

Fix: litellm format openrouter/openrouter/owl-alpha + force display name

Fix backend: owl-alpha with openai/ prefix

Fix Owl Alpha: name display + openai/ prefix for OpenRouter routing

Fix: Space title + Owl Alpha display name + openai/ prefix for OpenRouter

Fix: model_name format for litellm OpenRouter = openrouter/owl-alpha

Update dropdown names with performance notes

Rename Space + update model dropdown names with performance notes

Update backend models to match frontend fixes

Fix model IDs: kimi→DeepSeek-V4-Pro, minimax→DeepSeek-V4-Flash(HF), glm→deepseek-v4-flash(OR)

Fix patch_models: replace kimi/minimax/glm with DeepSeek models in backend

Fix patch: kimi→DeepSeek-V4-Pro(HF), minimax→deepseek-v4-flash(OR), glm→DeepSeek-V4-Flash(HF)

Fix: patch_frontend also renames existing models in dropdown (Kimi→DeepSeek, MiniMax→Flash, GLM→Flash)

Restore 3d39bbc: patch_frontend.py (unchanged)

Restore 3d39bbc: frontend config

Restore 3d39bbc + change: Kimi→DeepSeek-V4-Pro, MiniMax→deepseek-v4-flash(OR), GLM→DeepSeek-V4-Flash(HF)

Config default to deepseek-ai/DeepSeek-V4-Pro

Fix frontend: patch existing dropdown entries exactly

Fix: patch existing dropdown items exactly as specified

Frontend: update model list

Update all model IDs as requested

Frontend: DeepSeek via OpenRouter + rename Claude to Owl Alpha

Fix: DeepSeek V4 Pro via OpenRouter + rename Claude to Owl Alpha

Fix frontend modelPath for owl-alpha

Fix: use openai/ prefix + api_base for OpenRouter models in litellm

Try openai/ prefix with api_base for OpenRouter owl-alpha

Fix frontend model path to openrouter/openrouter/owl-alpha

Fix model IDs: openrouter/openrouter/owl-alpha format for litellm

Fix: correct litellm model ID for OpenRouter = openrouter/openrouter/owl-alpha

Set DEFAULT_FREE_MODEL_ID to openrouter/owl-alpha

Set default model to openrouter/owl-alpha

Fix title generation: use openrouter/owl-alpha for title

Fix title generation: add huggingface/ prefix for litellm

Replace Grok 4.3 with owl-alpha in backend models

Replace Grok 4.3 with Owl Alpha (OpenRouter)