TripIt Pro

Build me a local trip itinerary organizer from reservation emails I provide, as a limited substitute for TripIt Pro. Requirements:

- Use Python, FastAPI, and SQLite. Accept pasted confirmation text or uploaded .eml files; never connect to my mailbox by default.
- Extract candidate dates, times, time zones, confirmation codes, places, and carrier or hotel names into a review form. Save nothing until I confirm each field.
- Organize confirmed reservations by trip and chronological day. Preserve the source email locally so I can inspect extraction mistakes.
- Export each trip as a printable HTML page and an ICS file; keep local times and time-zone identifiers explicit, and flag unknown zones for manual correction.
- Provide a compact checklist for tickets, lodging, ground transport, and documents with links to the saved source messages.
- No accounts, telemetry, booking, live flight alerts, seat tracking, fare monitoring, or disruption promises.
- README: data location, backup and export, how to inspect email attachments safely, and the limits of parsing varied reservation formats.

# AGENTS.md — Build guide for TripIt Pro

## Project scope
Parse user-forwarded reservations into an offline itinerary and calendar, map user-entered places, and organize the trip without claiming live proprietary availability.

Catalogue verdict: no. A consolation build is possible, but the paid product's decisive value sits outside a solo rebuild. For TripIt Pro, parse user-forwarded reservations into an offline itinerary and calendar. The hard boundary is live flight alerts, fare monitoring, seat tracking, account integrations, and disruption data, plus proprietary live data and network coverage.
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
- modern browser
- MapTiler or compatible map key
- user-entered reservations
- optional public transit or weather API

## Stack and architecture
- Python and FastAPI
- SQLite
- Python email parser
- ICS export library with documented timezone support

## Security and data integrity
- Treat email HTML and attachments as untrusted content
- Require review before saving extracted fields
- Keep source emails and itinerary data local

## Agent implementation rules
- Preserve source evidence for every parsed reservation
- Flag ambiguous dates and time zones instead of guessing

## 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.
- Position as an offline organizer, without live travel intelligence

## Engineering roadmap
1. Implement source ingestion and a confirm-before-save parser.
2. Build trip timeline, checklist, and HTML/ICS exports.
3. Handle ambiguity explicitly and document missing live data.

## Paid-product capabilities outside this build
- live flight alerts, fare monitoring, seat tracking, account integrations, and disruption data
- live fare and inventory data
- global routing dataset
- crowdsourced trail intelligence
- booking, disruption support, and offline map fleet

## Implementation prompt
Build me a local trip itinerary organizer from reservation emails I provide, as a limited substitute for TripIt Pro. Requirements:

- Use Python, FastAPI, and SQLite. Accept pasted confirmation text or uploaded .eml files; never connect to my mailbox by default.
- Extract candidate dates, times, time zones, confirmation codes, places, and carrier or hotel names into a review form. Save nothing until I confirm each field.
- Organize confirmed reservations by trip and chronological day. Preserve the source email locally so I can inspect extraction mistakes.
- Export each trip as a printable HTML page and an ICS file; keep local times and time-zone identifiers explicit, and flag unknown zones for manual correction.
- Provide a compact checklist for tickets, lodging, ground transport, and documents with links to the saved source messages.
- No accounts, telemetry, booking, live flight alerts, seat tracking, fare monitoring, or disruption promises.
- README: data location, backup and export, how to inspect email attachments safely, and the limits of parsing varied reservation formats.

## 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.