config(llm): reprioritize models and switch to gemini-2.5-flash-lite across profiles#50
Merged
neoneye merged 8 commits intoPlanExeOrg:mainfrom Feb 19, 2026
Conversation
Add dynamic model list rendering based on selected profile in both multi-user frontend and single-user Gradio app. Mount llm_config*.json files into frontend_multi_user container, parse each profile's config to extract model names sorted by priority, and display them in the UI. Update llm_config.custom.json with cleaner priority-based model ordering and remove unused entries.
…_user container Add volume mounts and sync actions for llm_config.premium.json, llm_config.frontier.json, and llm_config.custom.json in docker-compose.yml. Update Dockerfile to copy all llm_config*.json files during build. Enables multi-profile support in single-user frontend.
…ig display Add priority prefix (P0, P1, etc.) to each model in the profile models markdown. Create separate active_config_markdown component that mirrors profile_models_markdown to display current configuration. Update all callback outputs to populate both markdown components with identical content.
Increase max_tokens from 8192 to 32000 across all OpenRouter models in custom and premium profiles. Reorder custom profile priorities (qwen3-coder-next 3→4, nemotron 4→5, gemini-3-flash comment updated to "last resort"). Swap premium profile priorities (gemini-3-flash 1→6, qwen3-coder-next 4→1). Remove local model entries (ollama-llama3.1, docker-ollama-llama3.1, ollama-qwen2.5-coder, lmstudio variants) from premium profile.
…iorities Move priority field before luigi_workers in all config files for consistency. In custom profile, demote gemini-3-flash from priority 2 to 12 and promote qwen3-coder-next from priority 4 to 2. In frontier profile, reduce max_tokens from 60000 to 32000 across all models. In premium profile, swap qwen3-5-397b-a17b to priority 1 and demote glm-4-7-flash to priority 6.
… and update custom profile models Raise temperature parameter from 0.1 to 1.0 for all models in custom, frontier, and premium profiles to increase response creativity. In custom profile, replace minimax-01 with minimax-m2.5 and swap qwq-32b-preview with qwen3.5-397b-a17b.
…across profiles Demote gpt-oss-120b from priority 1 to 11 and promote qwen3-coder-next from priority 2 to 1 in custom profile. Replace gemini-3-flash-preview with gemini-2.5-flash-lite-preview-09-2025 at priority 12. In frontier profile, demote glm-5 from priority 1 to 11, demote kimi-k2-5 from priority 2 to 111, and promote qwen3-5-397b-a17b from priority 3 to 1. In premium profile, swap qwen3-5-397b-a17b to priority 2, replace
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Reprioritize models and switch to gemini-2.5-flash-lite across custom, frontier, and premium profiles. (Based on commit 2bfdf6a)