feat(db): apply full provider data-policy audit (136 providers)#6
Open
OriginalGary wants to merge 6 commits intomainfrom
Open
feat(db): apply full provider data-policy audit (136 providers)#6OriginalGary wants to merge 6 commits intomainfrom
OriginalGary wants to merge 6 commits intomainfrom
Conversation
136 providers remain with unverified data-policy metadata. Structured as JSON with provider_id, display_name, base_url, is_aggregator, is_self_hosted_chat, current_metadata, todo_url, and category for each entry. Generated from current providers.ts state (2026-05-06). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This reverts commit 2b6e559.
136 providers updated with verified trains_on_data, data_residency, retention_days, local, and e2ee values from docs/provider-audit-results.json. - 90 providers got // Verified 2026-05-06 comments (high/medium confidence) - 46 providers retain // TODO(sam) with updated citation URLs (low confidence) - Notable: chutes + lambda-ai → e2ee=true (TEE/confidential compute) - Notable: kilocode + topaz → local=true (IDE extension / desktop app) - Notable: cliproxyapi already local=true (self-hosted proxy) - Source data: docs/provider-audit-results.json (136-provider research pass) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Four providers were incorrectly classified in the initial audit pass: - chutes e2ee=false: mixed Bittensor network, TEE not guaranteed on every node; does not meet Graze's architectural-incapability bar - lambda-ai e2ee=false: forum "encrypted end-to-end" refers to TLS in transit, which the e2ee definition explicitly excludes - kilocode local=false: BYOK IDE extension — prompts leave the user's machine to the configured upstream; inference is not local - topaz local=false: Graze routes to the cloud API (Bloom/Astra), not the desktop app; cloud requests leave user's machine Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
CI Coverage Report
Coverage artifact was not available for this run. |
13 new assertions covering key value changes from the 136-provider audit: groq, deepseek, fireworks, openrouter, mistral, xai, gitlab, perplexity, cloudflare-ai (trains_on_data / data_residency / retention_days), plus regression guards for the corrected chutes/lambda-ai e2ee=false and kilocode/topaz local=false classifications. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.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
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
providers.ts, replacing conservativetrains_on_data=true / data_residency=unknown / retention_days=nulldefaults with verified valuesdocs/provider-audit-results.jsonfor audit trail and future re-runs// Verified 2026-05-06: <url>(high/medium confidence)// TODO(sam): verify policy at <updated-url>with corrected citation URLs (low confidence, conservative defaults unchanged)Notable value changes from defaults:
openrouter,fireworks,groq,perplexity,xai,mistral,codestral,nebius,oci,snowflake,sap,gitlab,gitlab-duo→trains_on_data: falsedeepgram,hyperbolic,cloudflare-ai,featherless-ai,nlpcloud,ollama-cloud→trains_on_data: false, retention_days: 0deepseek→data_residency: "CN"(was "unknown")mistral,codestral,ovhcloud,scaleway→data_residency: "FR"aimlapi,getgoapi→retention_days: 365(aggregator conservative)chutes,lambda-aie2ee=false (TLS ≠ architectural e2ee);kilocode,topazlocal=false (BYOK extension / cloud API)Test plan
node --import tsx/esm --test tests/unit/provider-metadata-schema.test.ts— 32/32 passnpm run typecheck:core— clean🤖 Generated with Claude Code