Add 76 LLM providers and generalized Ask streaming#195
Conversation
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 38dbaa36e4
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
38dbaa3 to
e9643a6
Compare
|
@codex review |
|
Codex Review: Didn't find any major issues. Chef's kiss. Reviewed commit: ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
If Codex has suggestions, it will comment; otherwise it will react with 👍. Codex can also answer questions or update the PR. Try commenting "@codex address that feedback". |
Summary
Why
WebBrain's provider settings were largely maintained as bespoke entries and Ask streaming was limited to the original OpenAI path. This change moves the expanded catalog into deterministic mirrored metadata, adds the required protocol adapters, and keeps streaming failures and cost accounting safe across providers.
User impact
New providers start disabled and existing stored configurations and active-provider selection remain intact. Users can configure direct API-key providers without interactive OAuth, search the expanded catalog, and receive streamed Ask responses wherever the selected adapter supports a complete streaming protocol.
Validation
node --checkon 69 changed JavaScript filesnpm test— 1,250 core tests passednpm run build:webnpm run build:zipfrom committed HEAD; Chrome, Edge, and Firefox archives contain the new catalog and iconsgit diff --check