Google Gemini

Build me a personal chat client on the Gemini API to replace my Google AI Pro
subscription with per-token billing. Requirements:

- A local web app: Node + Express + better-sqlite3, one page, binds to
  localhost.
- Gemini API key in .env, with optional Claude and OpenAI keys too; a model
  picker per conversation.
- Streaming responses with Markdown and code-block rendering; history in SQLite
  with FTS5 search across old conversations.
- Upload PDFs and images and pass them through to models that accept them.
- System-prompt presets as .md files in ./prompts/, selectable per chat.
- Export any conversation to a Markdown file.
- No accounts, no telemetry; history stays on my machine, only prompts go to
  the APIs.
- Out of scope: Gmail, Docs, and Drive integrations, and mobile apps. Do not
  build Google Workspace OAuth; that ecosystem tie-in is the subscription.
- README: where to create each API key, a rough cost table per model, and state
  that per-token billing can land above or below $20/month depending on use,
  the model itself is only rentable.

# AGENTS.md — Build guide for Google Gemini

## Project scope
Build a multi-model chat app with document upload and optional Google API integrations.

Catalogue verdict: no. A chat UI is easy, but Gemini's model access, Google ecosystem integration, multimodality, storage tie-ins, and platform distribution are not solo-buildable.
Use the implementation prompt below to define the deliverable. Complete each phase's acceptance checks before extending the scope.

## Working agreement
- Inspect the repository and its existing instructions before choosing paths, dependencies or commands. Keep one coherent stack and explain changes to the proposed architecture.
- Plan a vertical slice that accepts a real input and produces the useful output described below. Persist only the state the prompt calls for; respect memory-only and upstream-managed workflows. Use fixtures only when they are clearly labelled.
- After scaffolding, document the actual install, development, check and build commands in README and keep them synchronized with the package or project manifest. Do not report commands as successful unless they ran.
- Work in small steps. At handoff, list implemented flows, checks actually performed, remaining blockers, and any credentials or provider setup the owner must supply.
- Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization.

## Prerequisites
- LLM API
- hosted app
- optional Google OAuth/API access
- storage
- file parsing

## Stack and architecture
- A local web app: Node + Express + better-sqlite3, one page, binds to localhost.
- Model source documents, editable pages, links or annotations, and exported versions; store source IDs and timestamps for each.
- Interface for this Google AI subscription workflow: a local web page with input, progress, review, and export views.

## Security and data integrity
- If LLM API is unavailable, keep the source record and show a recoverable error instead of a fabricated result.
- Keep API keys and OAuth secrets in .env; redact them from logs, generated files, and error responses.
- State the practical limit: frontier models.

## Agent implementation rules
- Project rule, data: Model source documents, editable pages, links or annotations, and exported versions; store source IDs and timestamps for each.
- Project rule, behavior: Export any conversation to a Markdown file.
- Project rule, recovery: If LLM API is unavailable, keep the source record and show a recoverable error instead of a fabricated result.

## Optional agent skills and references
No installable skill is listed for this guide; use the project rules and the stack documentation.

Read the linked SKILL.md and its dependencies before adding a skill. Select only the skills matching this project's runtime and task; their documentation does not supply API access, credentials or approval to perform external actions. Pin the reviewed revision where the tool supports it. Follow the chosen agent's documented project-level installation mechanism.

## Distribution ideas
These are optional planning notes. Obtain the owner's approval before publishing or contacting anyone.
- Demonstrate this Google AI subscription operation with sample or user-owned data: Export any conversation to a Markdown file.
- Show a concrete result or export: Export any conversation to a Markdown file.
- State the practical limit: frontier models.

## Engineering roadmap
1. Phase 1, architecture and data: A local web app: Node + Express + better-sqlite3, one page, binds to localhost. Model source documents, editable pages, links or annotations, and exported versions; store source IDs and timestamps for each.
2. Phase 2, implement: Export any conversation to a Markdown file.
3. Phase 3, implement: Build a multi-model chat app with document upload and optional Google API integrations.
4. Phase 4, review and output: Google AI assistant bundled with Gemini Advanced and Google AI Pro. Export any conversation to a Markdown file.
5. Phase 5, recovery and acceptance: If LLM API is unavailable, keep the source record and show a recoverable error instead of a fabricated result. Verify this invariant with a saved fixture: An invalid input or interrupted operation must retain the source and show a recoverable state; exported records must reload with the same IDs. State the practical limit: frontier models.

## Paid-product capabilities outside this build
- frontier models
- Google app integrations
- mobile/native distribution
- multimodal stack
- reliability

## Implementation prompt
Build me a personal chat client on the Gemini API to replace my Google AI Pro
subscription with per-token billing. Requirements:

- A local web app: Node + Express + better-sqlite3, one page, binds to
  localhost.
- Gemini API key in .env, with optional Claude and OpenAI keys too; a model
  picker per conversation.
- Streaming responses with Markdown and code-block rendering; history in SQLite
  with FTS5 search across old conversations.
- Upload PDFs and images and pass them through to models that accept them.
- System-prompt presets as .md files in ./prompts/, selectable per chat.
- Export any conversation to a Markdown file.
- No accounts, no telemetry; history stays on my machine, only prompts go to
  the APIs.
- Out of scope: Gmail, Docs, and Drive integrations, and mobile apps. Do not
  build Google Workspace OAuth; that ecosystem tie-in is the subscription.
- README: where to create each API key, a rough cost table per model, and state
  that per-token billing can land above or below $20/month depending on use,
  the model itself is only rentable.

## Completion evidence
Demonstrate the prompt's acceptance scenarios against the scoped workflow. Include setup from a clean checkout and failure recovery. Check persistence across restart and export/restore only for the state the prompt says to store; for memory-only tools, confirm that temporary content is discarded as specified. Record actual results and remaining limitations. A detailed plan alone does not establish a working replacement.