alex/voyage
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: add pre-release policy to agent instructions

Browse Source
This commit is contained in:
alex
2026-03-09 15:15:47 +00:00
parent 30fdcb078f
commit 21ef73f49d
3 changed files with 31 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
.github/copilot-instructions.md vendored
View File

@@ -4,13 +4,19 @@ Voyage is a self-hosted travel companion web application built with SvelteKit fr
**ALWAYS follow these instructions first and fallback to search or bash commands only when you encounter unexpected information that does not match the info here.** **ALWAYS follow these instructions first and fallback to search or bash commands only when you encounter unexpected information that does not match the info here.**
## Pre-Release Policy
Voyage is **pre-release** — not yet in production use. During pre-release:
- Architecture-level changes are allowed, including replacing core libraries (e.g. LiteLLM).
- Prioritize correctness, simplicity, and maintainability over backward compatibility.
- Before launch, this policy must be revisited and tightened for production stability.
## Architecture ## Architecture
**Stack**: SvelteKit 2 (TypeScript) frontend · Django REST Framework (Python) backend · PostgreSQL + PostGIS database · Memcached · Docker · Bun (frontend package manager) **Stack**: SvelteKit 2 (TypeScript) frontend · Django REST Framework (Python) backend · PostgreSQL + PostGIS database · Memcached · Docker · Bun (frontend package manager)
**Key architectural pattern — API Proxy**: The frontend never calls the Django backend directly. All API calls go to `src/routes/api/[...path]/+server.ts`, which proxies requests to the Django server (`http://server:8000`), injecting CSRF tokens and managing session cookies. This means frontend fetches use relative URLs like `/api/locations/`. **Key architectural pattern — API Proxy**: The frontend never calls the Django backend directly. All API calls go to `src/routes/api/[...path]/+server.ts`, which proxies requests to the Django server (`http://server:8000`), injecting CSRF tokens and managing session cookies. This means frontend fetches use relative URLs like `/api/locations/`.
**AI Chat**: The AI travel chat assistant is embedded in Collections → Recommendations (component: `AITravelChat.svelte`). There is no standalone `/chat` route. Chat providers are loaded dynamically from `GET /api/chat/providers/` (backed by LiteLLM runtime list + custom entries like `opencode_zen`). Chat conversations stream via SSE through `/api/chat/conversations/`. Provider config lives in `backend/server/chat/llm_client.py` (`CHAT_PROVIDER_CONFIG`). **AI Chat**: The AI travel chat assistant is embedded in Collections → Recommendations (component: `AITravelChat.svelte`). There is no standalone `/chat` route. Chat providers are loaded dynamically from `GET /api/chat/providers/` (backed by LiteLLM runtime list + custom entries like `opencode_zen`). Chat conversations stream via SSE through `/api/chat/conversations/`. Provider config lives in `backend/server/chat/llm_client.py` (`CHAT_PROVIDER_CONFIG`). Chat composer supports per-provider model override via dropdown selector fed by `GET /api/chat/providers/{provider}/models/` (persisted in browser `localStorage` key `voyage_chat_model_prefs`). Collection chats inject multi-stop itinerary context and the system prompt guides `get_trip_details`-first reasoning. LiteLLM errors are mapped to sanitized user-safe messages via `_safe_error_payload()` (never exposes raw exception text).
**Services** (docker-compose): **Services** (docker-compose):
- `web` → SvelteKit frontend at `:8015` - `web` → SvelteKit frontend at `:8015`
@@ -65,11 +71,11 @@ Run these commands in order:
- `cd frontend && bun run dev` - Start development server (requires backend running) - `cd frontend && bun run dev` - Start development server (requires backend running)
- `cd frontend && bun run format` - **6 seconds** - Fix code formatting (ALWAYS run before committing) - `cd frontend && bun run format` - **6 seconds** - Fix code formatting (ALWAYS run before committing)
- `cd frontend && bun run lint` - **6 seconds** - Check code formatting - `cd frontend && bun run lint` - **6 seconds** - Check code formatting
- `cd frontend && bun run check` - **12 seconds** - Run Svelte type checking (3 errors, 19 warnings expected) - `cd frontend && bun run check` - **12 seconds** - Run Svelte type checking (0 errors, 6 warnings expected)
**Backend (Django with Python — prefer uv for local tooling):** **Backend (Django with Python — prefer uv for local tooling):**
- Backend development requires Docker - local Python pip install fails due to network timeouts - Backend development requires Docker - local Python pip install fails due to network timeouts
- `docker compose exec server python3 manage.py test` - **7 seconds** - Run tests (2/3 tests fail, this is expected) - `docker compose exec server python3 manage.py test` - **7 seconds** - Run tests (6/30 pre-existing failures expected)
- `docker compose exec server python3 manage.py help` - View Django commands - `docker compose exec server python3 manage.py help` - View Django commands
- `docker compose exec server python3 manage.py migrate` - Run database migrations - `docker compose exec server python3 manage.py migrate` - Run database migrations
- Use `uv` for local Python dependency/tooling commands when applicable - Use `uv` for local Python dependency/tooling commands when applicable
@@ -113,8 +119,8 @@ Run these commands in order:
- Do not leave finished work lingering in long-lived feature branches or worktrees. - Do not leave finished work lingering in long-lived feature branches or worktrees.
### Expected Test Failures ### Expected Test Failures
- Frontend check: 3 errors and 19 warnings expected (accessibility and TypeScript issues) - Frontend check: 0 errors and 6 warnings expected (pre-existing in `CollectionRecommendationView.svelte` + `RegionCard.svelte`)
- Backend tests: 2 out of 3 Django tests fail (API endpoint issues) - **DO NOT fix unrelated test failures** - Backend tests: 6 out of 30 Django tests fail (pre-existing: 2 user email key errors + 4 geocoding API mocks) - **DO NOT fix unrelated test failures**
### Build Timing (NEVER CANCEL) ### Build Timing (NEVER CANCEL)
- **Docker first startup**: 25+ minutes (image downloads) - **Docker first startup**: 25+ minutes (image downloads)

12
AGENTS.md
View File

@@ -5,6 +5,12 @@
- **Purpose**: Self-hosted travel companion web app (fork of AdventureLog) - **Purpose**: Self-hosted travel companion web app (fork of AdventureLog)
- **Stack**: SvelteKit 2 (TypeScript) frontend · Django REST Framework (Python) backend · PostgreSQL + PostGIS · Memcached · Docker · Bun (frontend package manager) - **Stack**: SvelteKit 2 (TypeScript) frontend · Django REST Framework (Python) backend · PostgreSQL + PostGIS · Memcached · Docker · Bun (frontend package manager)
## Pre-Release Policy
Voyage is **pre-release** — not yet in production use. During pre-release:
- Architecture-level changes are allowed, including replacing core libraries (e.g. LiteLLM).
- Prioritize correctness, simplicity, and maintainability over backward compatibility.
- Before launch, this policy must be revisited and tightened for production stability.
## Architecture Overview ## Architecture Overview
- **API proxy pattern**: Frontend never calls Django directly. All API calls go through `frontend/src/routes/api/[...path]/+server.ts`, which proxies to `http://server:8000`, handles cookies, and injects CSRF behavior. - **API proxy pattern**: Frontend never calls Django directly. All API calls go through `frontend/src/routes/api/[...path]/+server.ts`, which proxies to `http://server:8000`, handles cookies, and injects CSRF behavior.
- **AI chat**: Embedded in Collections → Recommendations via `AITravelChat.svelte` component. No standalone `/chat` route. Provider list is dynamic from backend `GET /api/chat/providers/` (sourced from LiteLLM runtime + custom entries like `opencode_zen`). Chat conversations use SSE streaming via `/api/chat/conversations/`. Chat composer supports per-provider model override (persisted in browser `localStorage`). LiteLLM errors are mapped to sanitized user-safe messages via `_safe_error_payload()` (never exposes raw exception text). - **AI chat**: Embedded in Collections → Recommendations via `AITravelChat.svelte` component. No standalone `/chat` route. Provider list is dynamic from backend `GET /api/chat/providers/` (sourced from LiteLLM runtime + custom entries like `opencode_zen`). Chat conversations use SSE streaming via `/api/chat/conversations/`. Chat composer supports per-provider model override (persisted in browser `localStorage`). LiteLLM errors are mapped to sanitized user-safe messages via `_safe_error_payload()` (never exposes raw exception text).
@@ -60,7 +66,8 @@ Run in this order:
- Styling: use DaisyUI semantic colors/classes (`bg-primary`, `text-base-content`, etc.) - Styling: use DaisyUI semantic colors/classes (`bg-primary`, `text-base-content`, etc.)
- Security: handle CSRF tokens via `/auth/csrf/` and `X-CSRFToken` - Security: handle CSRF tokens via `/auth/csrf/` and `X-CSRFToken`
- Chat providers: dynamic catalog from `GET /api/chat/providers/`; configured in `CHAT_PROVIDER_CONFIG` - Chat providers: dynamic catalog from `GET /api/chat/providers/`; configured in `CHAT_PROVIDER_CONFIG`
- Chat model override: composer text input for per-provider model selection; persisted in `localStorage` key `voyage_chat_model_prefs`; backend accepts optional `model` param in `send_message` - Chat model override: dropdown selector fed by `GET /api/chat/providers/{provider}/models/`; persisted in `localStorage` key `voyage_chat_model_prefs`; backend accepts optional `model` param in `send_message`
- Chat context: collection chats inject multi-stop itinerary context; system prompt guides `get_trip_details`-first reasoning
- Chat error surfacing: `_safe_error_payload()` maps LiteLLM exceptions to sanitized user-safe categories (never forwards raw `exc.message`) - Chat error surfacing: `_safe_error_payload()` maps LiteLLM exceptions to sanitized user-safe categories (never forwards raw `exc.message`)
## Conventions ## Conventions
@@ -69,7 +76,8 @@ Run in this order:
- Commit and merge completed feature branches promptly once validation passes (avoid leaving finished work unmerged). - Commit and merge completed feature branches promptly once validation passes (avoid leaving finished work unmerged).
## .memory Files ## .memory Files
- At the start of any task, read `.memory/knowledge.md` and `.memory/decisions.md` for project context. - At the start of any task, read `.memory/manifest.yaml` to discover available files, then read `system.md` and relevant `knowledge/` files for project context.
- Read `.memory/decisions.md` for architectural decisions and review verdicts.
- Check relevant files in `.memory/plans/` and `.memory/research/` for prior work on related topics. - Check relevant files in `.memory/plans/` and `.memory/research/` for prior work on related topics.
- These files capture architectural decisions, code review verdicts, security findings, and implementation plans from prior sessions. - These files capture architectural decisions, code review verdicts, security findings, and implementation plans from prior sessions.
- Do **not** duplicate information from `.memory/` into code comments — keep `.memory/` as the single source of truth for project history. - Do **not** duplicate information from `.memory/` into code comments — keep `.memory/` as the single source of truth for project history.

12
CLAUDE.md
View File

@@ -5,6 +5,12 @@
- **Purpose**: Build and maintain a self-hosted travel companion web app (fork of AdventureLog). - **Purpose**: Build and maintain a self-hosted travel companion web app (fork of AdventureLog).
- **Stack**: SvelteKit 2 (TypeScript) frontend · Django REST Framework (Python) backend · PostgreSQL + PostGIS · Memcached · Docker · Bun (frontend package manager) - **Stack**: SvelteKit 2 (TypeScript) frontend · Django REST Framework (Python) backend · PostgreSQL + PostGIS · Memcached · Docker · Bun (frontend package manager)
## Pre-Release Policy
Voyage is **pre-release** — not yet in production use. During pre-release:
- Architecture-level changes are allowed, including replacing core libraries (e.g. LiteLLM).
- Prioritize correctness, simplicity, and maintainability over backward compatibility.
- Before launch, this policy must be revisited and tightened for production stability.
## Architecture Overview ## Architecture Overview
- Use the API proxy pattern: never call Django directly from frontend components. - Use the API proxy pattern: never call Django directly from frontend components.
- Route all frontend API calls through `frontend/src/routes/api/[...path]/+server.ts`. - Route all frontend API calls through `frontend/src/routes/api/[...path]/+server.ts`.
@@ -68,7 +74,8 @@ Run in this exact order:
- Styling: prefer DaisyUI semantic classes (`bg-primary`, `text-base-content`) - Styling: prefer DaisyUI semantic classes (`bg-primary`, `text-base-content`)
- CSRF handling: use `/auth/csrf/` + `X-CSRFToken` - CSRF handling: use `/auth/csrf/` + `X-CSRFToken`
- Chat providers: dynamic catalog from `GET /api/chat/providers/`; configured in `CHAT_PROVIDER_CONFIG` - Chat providers: dynamic catalog from `GET /api/chat/providers/`; configured in `CHAT_PROVIDER_CONFIG`
- Chat model override: composer text input for per-provider model selection; persisted in `localStorage` key `voyage_chat_model_prefs`; backend accepts optional `model` param in `send_message` - Chat model override: dropdown selector fed by `GET /api/chat/providers/{provider}/models/`; persisted in `localStorage` key `voyage_chat_model_prefs`; backend accepts optional `model` param in `send_message`
- Chat context: collection chats inject multi-stop itinerary context; system prompt guides `get_trip_details`-first reasoning
- Chat error surfacing: `_safe_error_payload()` maps LiteLLM exceptions to sanitized user-safe categories (never forwards raw `exc.message`) - Chat error surfacing: `_safe_error_payload()` maps LiteLLM exceptions to sanitized user-safe categories (never forwards raw `exc.message`)
## Conventions ## Conventions
@@ -77,7 +84,8 @@ Run in this exact order:
- Commit and merge completed feature branches promptly once validation passes (avoid leaving finished work unmerged). - Commit and merge completed feature branches promptly once validation passes (avoid leaving finished work unmerged).
## .memory Files ## .memory Files
- At the start of any task, read `.memory/knowledge.md` and `.memory/decisions.md` for project context. - At the start of any task, read `.memory/manifest.yaml` to discover available files, then read `system.md` and relevant `knowledge/` files for project context.
- Read `.memory/decisions.md` for architectural decisions and review verdicts.
- Check relevant files in `.memory/plans/` and `.memory/research/` for prior work on related topics. - Check relevant files in `.memory/plans/` and `.memory/research/` for prior work on related topics.
- These files capture architectural decisions, code review verdicts, security findings, and implementation plans from prior sessions. - These files capture architectural decisions, code review verdicts, security findings, and implementation plans from prior sessions.
- Do **not** duplicate information from `.memory/` into code comments — keep `.memory/` as the single source of truth for project history. - Do **not** duplicate information from `.memory/` into code comments — keep `.memory/` as the single source of truth for project history.