Skip to content

feat: sync models from router (+10 added, 6 reasoning-capable, 6 artifacts, -0 removed) #2403

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
gary149 merged 2 commits into from
Jul 2, 2026
+20 −0
Merged

feat: sync models from router (+10 added, 6 reasoning-capable, 6 artifacts, -0 removed) #2403

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5fab139
feat: sync models from router (+10 added, 6 reasoning-capable, 6 arti…
claude Jul 1, 2026
35866d0
fix: drop supportsReasoning from Ornith-1.0-35B entries
claude Jul 2, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 10 additions & 0 deletions chart/env/dev.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -82,6 +82,16 @@ envVars:
MODELS: >
[
{ "id": "omni", "supportsArtifacts": true },
{ "id": "XiaomiMiMo/MiMo-V2.5-Pro", "description": "1T MoE with 42B active params, hybrid attention, and 1M context.", "supportsReasoning": true, "supportsArtifacts": true },
{ "id": "moonshotai/Kimi-K2-Thinking", "description": "Trillion-param MoE thinking agent for deep reasoning and sustained tool chains.", "supportsReasoning": true, "supportsArtifacts": true },
{ "id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", "description": "BF16 hybrid Mamba-Transformer 550B MoE with 55B active params for agentic reasoning.", "supportsReasoning": true, "supportsArtifacts": true },
{ "id": "stepfun-ai/Step-3.7-Flash", "description": "Vision-language 198B MoE with 11B active params, reasoning modes, and 256K context.", "supportsReasoning": true, "supportsArtifacts": true },
{ "id": "deepreinforce-ai/Ornith-1.0-35B", "description": "RL-tuned 35B MoE coding agent with thinking mode and 262K context.", "supportsReasoning": true, "supportsArtifacts": true },
{ "id": "deepreinforce-ai/Ornith-1.0-35B-FP8", "description": "FP8 Ornith 35B MoE for efficient agentic coding with thinking mode.", "supportsReasoning": true, "supportsArtifacts": true },
{ "id": "google/gemma-3-12b-it", "description": "Dense 12B multimodal Gemma with 128K context and multilingual support." },
{ "id": "google/gemma-3-4b-it", "description": "Compact 4B multimodal Gemma with 128K context for lightweight tasks." },
{ "id": "microsoft/phi-4", "description": "Dense 14B model with strong math, reasoning, and coding density." },
{ "id": "speakleash/Bielik-11B-v3.0-Instruct", "description": "Polish-language 11B instruction model for chat, writing, and comprehension." },
{ "id": "zai-org/GLM-5.2", "description": "Flagship 744B MoE for agentic engineering with 1M context and thinking modes.", "parameters": { "max_tokens": 98304 }, "supportsReasoning": true, "supportsArtifacts": true },
{ "id": "zai-org/GLM-5.2-FP8", "description": "FP8 GLM-5.2 for efficient agentic engineering and extended reasoning.", "parameters": { "max_tokens": 98304 }, "supportsReasoning": true, "supportsArtifacts": true },
{ "id": "moonshotai/Kimi-K2.7-Code", "description": "1T MoE coding agent with persistent thinking across long tool workflows." , "supportsReasoning": true, "supportsArtifacts": true, "parameters": { "max_tokens": 98304 } },
Expand Down
10 changes: 10 additions & 0 deletions chart/env/prod.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -92,6 +92,16 @@ envVars:
MODELS: >
[
{ "id": "omni", "supportsArtifacts": true },
{ "id": "XiaomiMiMo/MiMo-V2.5-Pro", "description": "1T MoE with 42B active params, hybrid attention, and 1M context.", "supportsReasoning": true, "supportsArtifacts": true },
{ "id": "moonshotai/Kimi-K2-Thinking", "description": "Trillion-param MoE thinking agent for deep reasoning and sustained tool chains.", "supportsReasoning": true, "supportsArtifacts": true },
{ "id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", "description": "BF16 hybrid Mamba-Transformer 550B MoE with 55B active params for agentic reasoning.", "supportsReasoning": true, "supportsArtifacts": true },
{ "id": "stepfun-ai/Step-3.7-Flash", "description": "Vision-language 198B MoE with 11B active params, reasoning modes, and 256K context.", "supportsReasoning": true, "supportsArtifacts": true },
{ "id": "deepreinforce-ai/Ornith-1.0-35B", "description": "RL-tuned 35B MoE coding agent with thinking mode and 262K context.", "supportsReasoning": true, "supportsArtifacts": true },
{ "id": "deepreinforce-ai/Ornith-1.0-35B-FP8", "description": "FP8 Ornith 35B MoE for efficient agentic coding with thinking mode.", "supportsReasoning": true, "supportsArtifacts": true },

@chatgpt-codex-connector chatgpt-codex-connector Bot Jul 2, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Remove effort controls from Ornith entries

These two overrides mark Ornith as supportsReasoning, which in this app specifically means the model accepts a low/medium/high reasoning_effort knob (src/lib/server/models.ts), so the chat UI exposes the Effort selector and forwards the selected value. Ornith's HF/DeepInfra docs describe it as always emitting a <think>/reasoning_content trace via a parser, not as supporting configurable effort levels; when users choose Low/Medium/High, HuggingChat will send an unsupported reasoning_effort param for these models. Drop the flag or add provider-specific handling before enabling it; the same issue is present in chart/env/dev.yaml.

Useful? React with 👍 / 👎.

@gary149 gary149 Jul 2, 2026

Copy link
Copy Markdown
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Confirmed — dropped supportsReasoning from both Ornith entries in prod.yaml and dev.yaml (commit 35866d0), keeping supportsArtifacts.

Verified against the HF model card: Ornith always opens with a <think>/reasoning_content trace via a parser but documents no reasoning_effort / configurable effort levels, so it doesn't match this app's supportsReasoning semantics (accepts a low/medium/high reasoning_effort knob). One small correction to the impact: DeepInfra's reasoning docs say reasoning_effort on a model that doesn't support it "has no effect" (silently ignored, not an error), so the practical bug was an inert Effort selector rather than a broken request — but removing the flag is still the right call.

For reference, the other new reasoning flags were re-checked and do document reasoning_effort: Step-3.7-Flash (StepFun docs), MiMo-V2.5-Pro (AI/ML API docs), and Kimi-K2-Thinking (effort levels), so those stay.

Generated by Claude Code

{ "id": "google/gemma-3-12b-it", "description": "Dense 12B multimodal Gemma with 128K context and multilingual support." },
{ "id": "google/gemma-3-4b-it", "description": "Compact 4B multimodal Gemma with 128K context for lightweight tasks." },
{ "id": "microsoft/phi-4", "description": "Dense 14B model with strong math, reasoning, and coding density." },
{ "id": "speakleash/Bielik-11B-v3.0-Instruct", "description": "Polish-language 11B instruction model for chat, writing, and comprehension." },
{ "id": "zai-org/GLM-5.2", "description": "Flagship 744B MoE for agentic engineering with 1M context and thinking modes.", "parameters": { "max_tokens": 98304 }, "supportsReasoning": true, "supportsArtifacts": true },
{ "id": "zai-org/GLM-5.2-FP8", "description": "FP8 GLM-5.2 for efficient agentic engineering and extended reasoning.", "parameters": { "max_tokens": 98304 }, "supportsReasoning": true, "supportsArtifacts": true },
{ "id": "moonshotai/Kimi-K2.7-Code", "description": "1T MoE coding agent with persistent thinking across long tool workflows." , "supportsReasoning": true, "supportsArtifacts": true, "parameters": { "max_tokens": 98304 } },
Expand Down
Loading