Add Tinfoil private inference provider#875
Merged
gabrielste1n merged 3 commits intoJul 6, 2026
Merged
Conversation
# Conflicts: # README.md # docs/network-allowlist.md # package-lock.json # package.json # preload.js # src/helpers/environment.js # src/helpers/ipcHandlers.js # src/hooks/useSettings.ts # src/services/ReasoningService.ts # src/stores/settingsStore.ts # src/types/electron.ts
- Update model catalog: glm-5-1 is now glm-5-2 (384K context) per Tinfoil's current chat model list - Add descriptionKey i18n wiring for all six models across the ten locales, matching the groq registry pattern - Add supportsThinking to the reasoning-capable models so the disable-thinking toggle and suppression work like they do for groq - Cap each request attempt at 30s and disable SDK-internal retries so withRetry stays the single retry layer, matching sibling providers - Retry the tinfoil module import after a failed load instead of caching the rejection - Drop the redundant per-call verification (the client attests before every request) and an unneeded LanguageModel cast - Document the dynamically assigned enclave host in the network allowlist and drop hosts the app never contacts - Point console links at tinfoil.sh/inference with referral params
gabrielste1n
approved these changes
Jul 6, 2026
gabrielste1n
left a comment
gabrielste1n
left a comment
Collaborator
There was a problem hiding this comment.
absolutely legendary thank you sir @zachdotai
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Adds Tinfoil as a first-class private inference provider for OpenWhispr LLM workflows.
This integration uses the official Tinfoil SDK instead of the generic OpenAI-compatible fetch path so requests go through Tinfoil’s verified enclave transport. Tinfoil is now available for cleanup, note formatting, dictation agent, and chat agent flows, including AI SDK streaming/tool usage.
Changes
tinfoilSDK dependency.TINFOIL_API_KEYand Tinfoil network allowlist hosts.Test Plan
npm run typechecknpm run i18n:checknpm run lintnpm run build:renderergit diff --check