Skip to content

Conversation

@angelahning
Copy link
Collaborator

@angelahning angelahning commented Oct 21, 2025

Summary

I am porting the changes in #4342 with some modification:

  • added fetch_supported_models() for Ollama provider. Now the models UI can show an alphabetically sorted list for ollama
  • updated the leader/worker model to fetch models from providers dynamically instead of using the static known models list.

Type of Change

  • Feature
  • Bug fix
  • Refactor / Code quality
  • Performance improvement
  • Documentation
  • Tests
  • Security fix
  • Build / Release
  • Other (specify below)

Testing

Manually verified on UI

Related Issues

Fixes #4273

Screenshots/Demos (for UX changes)

After:
Screenshot 2025-10-21 at 6 02 26 PM
Screenshot 2025-10-21 at 6 02 42 PM

@angelahning angelahning marked this pull request as ready for review October 21, 2025 22:03
@angelahning
Copy link
Collaborator Author

kudos to @eugenepyvovarov

@angelahning angelahning changed the title Aning/ollama feat: dynamically load ollama models Oct 21, 2025
@angelahning angelahning assigned jamadeo and zanesq and unassigned jamadeo Oct 21, 2025
@angelahning angelahning requested a review from zanesq October 21, 2025 22:11
Copy link
Collaborator

@zanesq zanesq left a comment

Choose a reason for hiding this comment

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

Frontend changes LGTM!

Oh pls revert package-lock.json I think it might be because we upgraded node in hermit so you'll have to activate it again before running the install or it will modify package-lock with the old node

@angelahning angelahning force-pushed the aning/ollama branch 2 times, most recently from b5e7b2d to faa9fe7 Compare October 22, 2025 17:40
}))
}

/// Fetch the list of available models from Ollama
Copy link
Collaborator

Choose a reason for hiding this comment

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

rm


Ok(Some(model_names))
}
}
Copy link
Collaborator

Choose a reason for hiding this comment

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

this feels more verbos than it needs to be - do we need to sort the models?

activeProviders.forEach(({ metadata, name }) => {
if (metadata.known_models) {
metadata.known_models.forEach((model) => {
const modelPromises = activeProviders.map(async (p) => {
Copy link
Collaborator

Choose a reason for hiding this comment

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

this is near duplicated code or maybe the LLM did it, but suggest to unify it

@angelahning angelahning merged commit 7c4e368 into main Oct 23, 2025
14 checks passed
@angelahning angelahning deleted the aning/ollama branch October 23, 2025 01:17
wpfleger96 added a commit that referenced this pull request Oct 23, 2025
* main:
  Add tech-article-explainer recipe (#5333)
  doc: added beta banner for old blog post (#5332)
  feat: add code refactor recipe (#5320)
  Security audit recipe (#5319)
  feat: add generate commit message recipe (#5326)
  fix: remove dependency on gsap library (#5330)
  feat: dynamically load ollama models (#5309)
  fix: skip temperature for goose-gpt-5 model (#5311)
katzdave added a commit that referenced this pull request Oct 23, 2025
…message

# By Better-Boy (3) and others
# Via GitHub
* 'main' of github.com:block/goose:
  Create recipe dir on save (#5337)
  docs: Update Discord link (#5335)
  [recipe workflow]: Fix `Invalid revision range` error  (#5334)
  Add tech-article-explainer recipe (#5333)
  doc: added beta banner for old blog post (#5332)
  feat: add code refactor recipe (#5320)
  Security audit recipe (#5319)
  feat: add generate commit message recipe (#5326)
  fix: remove dependency on gsap library (#5330)
  feat: dynamically load ollama models (#5309)
  fix: skip temperature for goose-gpt-5 model (#5311)
  Replace compaction notifications with system notifications (#5218)

# Conflicts:
#	crates/goose/src/agents/agent.rs
michaelneale added a commit that referenced this pull request Oct 24, 2025
* main: (77 commits)
  Fix legacy import (#5343)
  Unify loading goose messages and usechatstream determines chat state (#5306)
  Docs: goose session export and goose session import (#5267)
  Create recipe dir on save (#5337)
  docs: Update Discord link (#5335)
  [recipe workflow]: Fix `Invalid revision range` error  (#5334)
  Add tech-article-explainer recipe (#5333)
  doc: added beta banner for old blog post (#5332)
  feat: add code refactor recipe (#5320)
  Security audit recipe (#5319)
  feat: add generate commit message recipe (#5326)
  fix: remove dependency on gsap library (#5330)
  feat: dynamically load ollama models (#5309)
  fix: skip temperature for goose-gpt-5 model (#5311)
  Replace compaction notifications with system notifications (#5218)
  Diagnostics (#5323)
  Fix gemini again (#5308)
  fix: synchronize local message state after conversation compaction (#5315)
  docs: replace broken links with working links (#5266)
  Add Web Accessibility Auditor recipe to cookbook (#5318)
  ...
BlairAllan pushed a commit to BlairAllan/goose that referenced this pull request Oct 25, 2025
BlairAllan pushed a commit to BlairAllan/goose that referenced this pull request Nov 29, 2025
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.

Missing list of installed Ollama models

5 participants