Factory

Build me a focused software development agents workflow for the personal core of Factory. Requirements:

- Use exactly this stack: Python 3.12 + Typer + SQLite. Model selected repositories or projects, operations, results, revisions, and run logs; keep stable source IDs and timestamps.
- Paid product context: Droids for coding, migration, testing, and development workflows. Build only this DIY scope: Build a repository-local software development agents assistant that indexes one codebase, calls one model, proposes diffs, runs tests, and records every change.
- For software development agents, select one repository and record its branch, HEAD revision, allowed tools, and agent run ID.
- Make changes on a branch with an inspectable diff and record each command, result, and approval.
- Run the project’s verification command and show the diff plus final status before merge or export.
- Use a CLI with a dry-run or preview command and an explicit output path. Required input or access: Git; OpenAI API key in .env. Keep credentials in .env.
- Acceptance: with one labelled sample, show the input, saved intermediate state, and exported result; verify this invariant: A failed tool call or interrupted run must retain the branch and trace; no file outside the selected repository may change.
- Out of scope: frontier coding model quality; large-context 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 Factory

## Project scope
Build a repository-local software development agents assistant that indexes one codebase, calls one model, proposes diffs, runs tests, and records every change.

Catalogue verdict: no. Do not mistake the interface for the product. Factory's durable value is model, context, integration, 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
- Python 3.12
- Git
- OpenAI API key in .env
- Explicit README warning that this is a consolation build, not a production replacement

## Stack and architecture
- Use exactly this stack: Python 3.12 + Typer + SQLite.
- Model selected repositories or projects, operations, results, revisions, and run logs; keep stable source IDs and timestamps.
- Interface for this software development agents workflow: a CLI with a dry-run or preview command and an explicit output path.

## Security and data integrity
- A failed tool call or interrupted run must retain the branch and trace; no file outside the selected repository may change.
- Keep API keys and OAuth secrets in .env; redact them from logs, generated files, and error responses.
- State the practical limit: frontier coding model quality.

## Agent implementation rules
- Project rule, data: Model selected repositories or projects, operations, results, revisions, and run logs; keep stable source IDs and timestamps.
- Project rule, behavior: For software development agents, select one repository and record its branch, HEAD revision, allowed tools, and agent run ID.
- Project rule, recovery: A failed tool call or interrupted run must retain the branch and trace; no file outside the selected repository may change.

## 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 software development agents operation with sample or user-owned data: For software development agents, select one repository and record its branch, HEAD revision, allowed tools, and agent run ID.
- Show a concrete result or export: Run the project’s verification command and show the diff plus final status before merge or export.
- State the practical limit: frontier coding model quality.

## Engineering roadmap
1. Phase 1, architecture and data: Use exactly this stack: Python 3.12 + Typer + SQLite. Model selected repositories or projects, operations, results, revisions, and run logs; keep stable source IDs and timestamps.
2. Phase 2, implement: For software development agents, select one repository and record its branch, HEAD revision, allowed tools, and agent run ID.
3. Phase 3, implement: Make changes on a branch with an inspectable diff and record each command, result, and approval.
4. Phase 4, review and output: Run the project’s verification command and show the diff plus final status before merge or export.
5. Phase 5, recovery and acceptance: Verify this invariant with a saved fixture: A failed tool call or interrupted run must retain the branch and trace; no file outside the selected repository may change. State the practical limit: frontier coding model quality.

## Paid-product capabilities outside this build
- frontier coding model quality
- large-context infrastructure
- IDE-wide polish and latency
- enterprise policy, telemetry, and support

## Implementation prompt
Build me a focused software development agents workflow for the personal core of Factory. Requirements:

- Use exactly this stack: Python 3.12 + Typer + SQLite. Model selected repositories or projects, operations, results, revisions, and run logs; keep stable source IDs and timestamps.
- Paid product context: Droids for coding, migration, testing, and development workflows. Build only this DIY scope: Build a repository-local software development agents assistant that indexes one codebase, calls one model, proposes diffs, runs tests, and records every change.
- For software development agents, select one repository and record its branch, HEAD revision, allowed tools, and agent run ID.
- Make changes on a branch with an inspectable diff and record each command, result, and approval.
- Run the project’s verification command and show the diff plus final status before merge or export.
- Use a CLI with a dry-run or preview command and an explicit output path. Required input or access: Git; OpenAI API key in .env. Keep credentials in .env.
- Acceptance: with one labelled sample, show the input, saved intermediate state, and exported result; verify this invariant: A failed tool call or interrupted run must retain the branch and trace; no file outside the selected repository may change.
- Out of scope: frontier coding model quality; large-context 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.