Fliki

Build me a focused text-to-video + voice workflow for the personal core of Fliki. Requirements:

- Use exactly this stack: Python 3.12 + FastAPI + FFmpeg + React. Model prompts, source clips, model settings, jobs, and exported videos; keep stable source IDs and timestamps.
- Paid product context: Creates narrated videos from scripts, articles, and AI voices. Build only this DIY scope: Build the closest honest personal text-to-video + voice workflow using one user-selected local or API model, job history, preview, and export.
- For text-to-video + voice, accept a prompt or user-owned source clip and record model, duration, aspect ratio, and seed.
- Queue one generation job, stream status, and save the raw model response before rendering a preview.
- Preview the result and export MP4 plus the settings used to create it.
- Use a local web page with input, progress, review, and export views. Required input or access: GPU-capable machine or model API key in .env; FFmpeg. Keep credentials in .env.
- Acceptance: with one labelled sample, show the input, saved intermediate state, and exported result; verify this invariant: A failed or cancelled job cannot be presented as finished; exported video duration and frame size must match the saved job settings.
- Out of scope: voice or likeness safety systems; low-latency inference infrastructure. Keep this a personal, inspectable workflow.
- Include a README with setup, a sample input, required keys or permissions, data location, and the supported scope.

# AGENTS.md — Build guide for Fliki

## Project scope
Build the closest honest personal text-to-video + voice workflow using one user-selected local or API model, job history, preview, and export.

Catalogue verdict: no. Do not mistake the interface for the product. Fliki's durable value is proprietary model, inference, safety, which a solo one-shot build cannot reproduce responsibly. The prompt therefore builds only the closest honest personal consolation tool.
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
- GPU-capable machine or model API key in .env
- Python 3.12
- FFmpeg
- Explicit README warning that this is a consolation build, not a production replacement

## Stack and architecture
- Use exactly this stack: Python 3.12 + FastAPI + FFmpeg + React.
- Model prompts, source clips, model settings, jobs, and exported videos; keep stable source IDs and timestamps.
- Interface for this text-to-video + voice workflow: a local web page with input, progress, review, and export views.

## Security and data integrity
- A failed or cancelled job cannot be presented as finished; exported video duration and frame size must match the saved job settings.
- Keep API keys and OAuth secrets in .env; redact them from logs, generated files, and error responses.
- State the practical limit: voice or likeness safety systems.

## Agent implementation rules
- Project rule, data: Model prompts, source clips, model settings, jobs, and exported videos; keep stable source IDs and timestamps.
- Project rule, behavior: For text-to-video + voice, accept a prompt or user-owned source clip and record model, duration, aspect ratio, and seed.
- Project rule, recovery: A failed or cancelled job cannot be presented as finished; exported video duration and frame size must match the saved job settings.

## 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 text-to-video + voice operation with sample or user-owned data: For text-to-video + voice, accept a prompt or user-owned source clip and record model, duration, aspect ratio, and seed.
- Show a concrete result or export: Preview the result and export MP4 plus the settings used to create it.
- State the practical limit: voice or likeness safety systems.

## Engineering roadmap
1. Phase 1, architecture and data: Use exactly this stack: Python 3.12 + FastAPI + FFmpeg + React. Model prompts, source clips, model settings, jobs, and exported videos; keep stable source IDs and timestamps.
2. Phase 2, implement: For text-to-video + voice, accept a prompt or user-owned source clip and record model, duration, aspect ratio, and seed.
3. Phase 3, implement: Queue one generation job, stream status, and save the raw model response before rendering a preview.
4. Phase 4, review and output: Preview the result and export MP4 plus the settings used to create it.
5. Phase 5, recovery and acceptance: Verify this invariant with a saved fixture: A failed or cancelled job cannot be presented as finished; exported video duration and frame size must match the saved job settings. State the practical limit: voice or likeness safety systems.

## Paid-product capabilities outside this build
- voice or likeness safety systems
- low-latency inference infrastructure
- licensed data, avatars, and production templates
- production codecs, rendering speed, and media templates
- frontier generation quality

## Implementation prompt
Build me a focused text-to-video + voice workflow for the personal core of Fliki. Requirements:

- Use exactly this stack: Python 3.12 + FastAPI + FFmpeg + React. Model prompts, source clips, model settings, jobs, and exported videos; keep stable source IDs and timestamps.
- Paid product context: Creates narrated videos from scripts, articles, and AI voices. Build only this DIY scope: Build the closest honest personal text-to-video + voice workflow using one user-selected local or API model, job history, preview, and export.
- For text-to-video + voice, accept a prompt or user-owned source clip and record model, duration, aspect ratio, and seed.
- Queue one generation job, stream status, and save the raw model response before rendering a preview.
- Preview the result and export MP4 plus the settings used to create it.
- Use a local web page with input, progress, review, and export views. Required input or access: GPU-capable machine or model API key in .env; FFmpeg. Keep credentials in .env.
- Acceptance: with one labelled sample, show the input, saved intermediate state, and exported result; verify this invariant: A failed or cancelled job cannot be presented as finished; exported video duration and frame size must match the saved job settings.
- Out of scope: voice or likeness safety systems; low-latency inference infrastructure. Keep this a personal, inspectable workflow.
- Include a README with setup, a sample input, required keys or permissions, data location, and the supported scope.

## 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.