feat: add a Providers setting to connect Thuki to a local or remote Ollama#205
Merged
Conversation
Signed-off-by: Logan Nguyen <lg.131.dev@gmail.com>
Signed-off-by: Logan Nguyen <lg.131.dev@gmail.com>
Signed-off-by: Logan Nguyen <lg.131.dev@gmail.com>
Signed-off-by: Logan Nguyen <lg.131.dev@gmail.com>
…mmand Signed-off-by: Logan Nguyen <lg.131.dev@gmail.com>
Signed-off-by: Logan Nguyen <lg.131.dev@gmail.com>
Signed-off-by: Logan Nguyen <lg.131.dev@gmail.com>
Signed-off-by: Logan Nguyen <lg.131.dev@gmail.com>
Signed-off-by: Logan Nguyen <lg.131.dev@gmail.com>
Signed-off-by: Logan Nguyen <lg.131.dev@gmail.com>
…detection Signed-off-by: Logan Nguyen <lg.131.dev@gmail.com>
quiet-node
changed the title
quiet-node
changed the title
quiet-node
added a commit
that referenced
this pull request
Jun 8, 2026
Hold Providers (#205) out of the next release; re-land for 0.15.0 once ready. Release-As: 0.14.2 Signed-off-by: Logan Nguyen <lg.131.dev@gmail.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Overview
Thuki's inference endpoint is no longer fixed in code. A new Providers section in Settings configures where Thuki finds its Ollama server, the default local one, a custom port, or a machine on the network, and which model to use. Existing setups keep working unchanged.
What changed
How it works
Inference configuration moves from a flat
ollama_url(plus a separately stored active model) into one typed[inference]section: anactive_providerpointer and aproviderslist, where each provider carries its own id, label, URL, and selected model. Requests route to whichever provider is active.The config loader validates every value, so changes from the Settings UI and hand edits to the file follow the same rules. Older configs upgrade automatically on first launch: the existing Ollama URL and previously selected model are carried onto the Ollama provider, with nothing lost. The Ollama URL is treated as untrusted: non-URL or malformed values are rejected and reset to the local default before reaching the request layer, and only genuine loopback and private addresses count as local when deciding whether to show the remote-server warning.
Testing
bun run test:all:coverage: frontend and backend pass at 100% coverage.bun run validate-build: clean (lint, format, typecheck, clippy with warnings as errors, and the frontend and backend builds).Note: only Ollama is selectable today. The Built-in engine appears in Settings but is not yet available; selecting it shows a "not available yet" message rather than failing silently.