Skip to content

feat: discover models from AI providers - #38

Merged
LittleSheep2Code merged 1 commit into
Solsynth:masterfrom
Bihrys:feat/auto-discover-agent-models
Aug 14, 2026
Merged

feat: discover models from AI providers#38
LittleSheep2Code merged 1 commit into
Solsynth:masterfrom
Bihrys:feat/auto-discover-agent-models

Conversation

@Bihrys

@Bihrys Bihrys commented Aug 14, 2026

Copy link
Copy Markdown
Contributor

Summary

  • discover models from OpenAI-compatible GET /v1/models endpoints
  • authenticate discovery requests with the provider API key
  • deduplicate and sort returned model IDs
  • automatically discover models when saving a provider and persist the full list
  • add a refresh action and model picker to the provider editor
  • retain manual model entry as a fallback for providers without model discovery
  • add English, Simplified Chinese, and Traditional Chinese labels

Validation

  • endpoint construction, authorization header, parsing, sorting, and deduplication verified with a fake HTTP adapter
  • targeted Dart analysis has no new issues (one existing agent_page.dart warning remains)
  • translation JSON files parse successfully as UTF-8
  • full Flutter tests are currently blocked on Windows by the existing tailscale 0.8.0 native build referencing POSIX-only symbols

View with [code]smith Autofix with [code]smith
Need help on this PR? Tag @codesmith-bot with what you need. Autofix is disabled.

@LittleSheep2Code LittleSheep2Code left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

The CI complaint about the warnings, please fix those in order to get merged.

@LittleSheep2Code
LittleSheep2Code merged commit 30dbdee into Solsynth:master Aug 14, 2026
2 of 3 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants