amal66 puts Gemini behind Google Cloud's guardrails

This fork makes Mike easier to run inside organisations already governed through Google Cloud.

integrationinfrastructure

amal66 adds two optional routes into Google Cloud, aimed at teams that need tighter control over where AI access and documents sit.

Google Cloud Storage support gives organisations a way to keep stored material in Google's managed cloud environment.
Vertex AI support lets Gemini, Google's AI model family, run through a company Google Cloud project instead of a shared API key.

That matters because access can be governed through existing identity permissions, project-level billing and regional deployment choices. The change is optional, so it does not alter a standard installation unless a team chooses to configure it. It also brings the usual cloud-operating questions: credentials, region selection and data-transfer costs.

Legal-ops leaders and product teams already standardised on Google Cloud should care if they want to test AI-assisted legal work without creating a parallel access-control model.

So what For Google Cloud shops, this is a practical path to use Gemini under the controls they already rely on.

View this fork on GitHub →

Spotted something wrong? Or know the PR text has fresher detail than the writeup above?

Commits in this thread

1 commit from amal66/mike, oldest first. Source extracted verbatim from the harvested git log.

SHA Subject Author Date

57c1c1b5 feat(google-cloud): GCS storage adapter + Vertex AI Gemini provider (#2) Amalanand Muthukumaran 2026-05-24 ↗ GitHub

SHA	Subject	Author	Date
`57c1c1b5`	feat(google-cloud): GCS storage adapter + Vertex AI Gemini provider (#2)	Amalanand Muthukumaran	2026-05-24	↗ GitHub
commit body * feat(google-cloud): GCS storage adapter + Vertex AI Gemini provider Adds two drop-in Google Cloud integrations following the existing extension points (StorageAdapter + LLMProviderAdapter) so no core files needed editing beyond exporting the new classes. GCS storage adapter (lib/storage/gcs.ts) - Implements the StorageAdapter interface backed by @google-cloud/storage - Auth via Application Default Credentials - covers service account key files (GOOGLE_APPLICATION_CREDENTIALS), Workload Identity on GKE / Cloud Run, and gcloud CLI for local dev (zero secrets to manage) - Enabled when GCS_PROJECT_ID or GOOGLE_APPLICATION_CREDENTIALS is set - Signed URLs use V4 signing; Content-Disposition header supported - Swap R2 for GCS with one setStorageAdapter() call at startup: import { setStorageAdapter } from "./lib/storage"; import { GCSStorageAdapter } from "./lib/storage/gcs"; setStorageAdapter(new GCSStorageAdapter()); Vertex AI Gemini provider (lib/llm/providers/vertexAI.ts) - Routes all Gemini model IDs through Google Cloud Vertex AI instead of AI Studio - same model IDs, different billing + auth + data residency - Uses @google/genai (already a dep) with vertexai: true mode - no new package required - Auth via ADC: Workload Identity on GKE/Cloud Run, or GOOGLE_APPLICATION_CREDENTIALS locally - Replaces the built-in gemini provider on re-registration (same id): import { setupVertexAI } from "lib/llm/providers/vertexAI"; setupVertexAI(); Tests: 23 new tests (16 GCS adapter, 7 Vertex AI provider); full suite 151 tests passing. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * docs(readme): rewrite as setup and contribution guide The previous README was a project retrospective - design rationale, open-source bets, a 40-row change index - with the actual setup steps buried partway through. This rewrites it as a task-oriented doc: - Quick Start: clone → install → env → database → run (5 steps) - Configuration: all env vars grouped by category with descriptions - Extending Mike: concrete code snippets for each extension point (custom LLM provider, Vertex AI, GCS, custom storage, law library plugins, Python SDK) - Development: test/lint/build/typecheck commands in one place - Troubleshooting: the four most common issues - Contributing: short version inline, CONTRIBUTING.md for the rest The commit history and design rationale move to a collapsed footnote (<details> block) so they're available without dominating the page. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>

commit body

* feat(google-cloud): GCS storage adapter + Vertex AI Gemini provider

Adds two drop-in Google Cloud integrations following the existing
extension points (StorageAdapter + LLMProviderAdapter) so no core files
needed editing beyond exporting the new classes.

**GCS storage adapter** (lib/storage/gcs.ts)
- Implements the StorageAdapter interface backed by @google-cloud/storage
- Auth via Application Default Credentials - covers service account key
  files (GOOGLE_APPLICATION_CREDENTIALS), Workload Identity on GKE /
  Cloud Run, and gcloud CLI for local dev (zero secrets to manage)
- Enabled when GCS_PROJECT_ID or GOOGLE_APPLICATION_CREDENTIALS is set
- Signed URLs use V4 signing; Content-Disposition header supported
- Swap R2 for GCS with one setStorageAdapter() call at startup:
    import { setStorageAdapter } from "./lib/storage";
    import { GCSStorageAdapter } from "./lib/storage/gcs";
    setStorageAdapter(new GCSStorageAdapter());

**Vertex AI Gemini provider** (lib/llm/providers/vertexAI.ts)
- Routes all Gemini model IDs through Google Cloud Vertex AI instead of
  AI Studio - same model IDs, different billing + auth + data residency
- Uses @google/genai (already a dep) with vertexai: true mode - no new
  package required
- Auth via ADC: Workload Identity on GKE/Cloud Run, or
  GOOGLE_APPLICATION_CREDENTIALS locally
- Replaces the built-in gemini provider on re-registration (same id):
    import { setupVertexAI } from "lib/llm/providers/vertexAI";
    setupVertexAI();

**Tests**: 23 new tests (16 GCS adapter, 7 Vertex AI provider); full
suite 151 tests passing.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* docs(readme): rewrite as setup and contribution guide

The previous README was a project retrospective - design rationale,
open-source bets, a 40-row change index - with the actual setup steps
buried partway through. This rewrites it as a task-oriented doc:

- Quick Start: clone → install → env → database → run (5 steps)
- Configuration: all env vars grouped by category with descriptions
- Extending Mike: concrete code snippets for each extension point
  (custom LLM provider, Vertex AI, GCS, custom storage, law library
  plugins, Python SDK)
- Development: test/lint/build/typecheck commands in one place
- Troubleshooting: the four most common issues
- Contributing: short version inline, CONTRIBUTING.md for the rest

The commit history and design rationale move to a collapsed footnote
(<details> block) so they're available without dominating the page.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>

Capture this thread into my fork

Download a single Markdown prompt that tells Claude how to port every commit above into your working tree — adapting paths and structure to match your repo. Run it via claude -p < capture-thread-1391.md from inside the repo you want the changes in.

⬇ Download capture-thread-1391.md