Vibecode AdaL

You are building a lean indie version of AdaL.

Create the following project files first, then implement the application by following them. Keep the files updated as decisions change. Do not collapse this into a single README or prompt.

===== README.md =====
# AdaL indie build

## Goal

Build the smallest trustworthy replacement for the core AdaL workflow for one developer or a tiny team.

## Scope

Wire a terminal agent to several provider APIs, give it file, shell and test tools, and let a planner sub-agent hand tasks to specialized workers in one session.

## Quick start

1. Install the documented dependencies.
2. Copy `.env.example` to `.env`.
3. Run the development command chosen during implementation.
4. Complete the acceptance checks in `BUILD_PLAN.md`.

## Honest limits

This build deliberately does not replace:
- harness tuning: the planning, recovery and verification work that separates a demo agent from one that finishes long tasks
- browser-use verification of the app you just changed
- review clustering that groups a large diff into risk-ranked units
- one bill across every frontier provider instead of six metered API accounts
- SSO, SAML/SCIM, zero data retention and org-level model deny lists

If those capabilities are essential, use AdalFlow instead of pretending the gap is solved.

===== AGENTS.md =====
# Agent instructions

- Optimize for a working, understandable weekend build.
- Prefer the fewest moving parts that satisfy the brief.
- Do not invent cryptography, security guarantees, APIs, or compliance claims.
- Keep secrets out of source control and logs.
- Add focused tests for destructive, security-sensitive, and data-loss paths.
- Run the project checks before declaring the build complete.
- Record any deliberate shortcut in the README under "Tradeoffs".

===== BUILD_PLAN.md =====
# Build plan

## Original build brief

Build me a multi-model coding agent CLI to replace AdaL, in an empty folder.
Stack: Python 3.12, one file per module, no framework.

- Providers: Anthropic, OpenAI and Google, behind a single `chat(model, messages, tools)`
  function. Keys from .env via python-dotenv, never hardcoded. A `--model` flag
  switches families mid-session without restarting.
- Tools the agent can call: read_file, write_file, list_dir, run_shell, run_tests.
  run_shell prints the command and waits for y/n unless I pass --yolo.
- An orchestrator loop: a planner call splits my request into numbered steps, then
  each step runs as a fresh sub-agent with its own context window and only the tools
  it needs. Sub-agent results append to a shared markdown scratchpad on disk.
- Persist every session as JSONL under .agent/sessions/ so I can replay or resume.
  A `--resume <id>` flag reloads the scratchpad and continues.
- After any step that edits files, automatically run the test command from
  pyproject.toml and feed failures back to the same sub-agent for one retry.
- Print a running token and dollar total per provider at the end of every turn.
- Out of scope, deliberately: browser automation, a GUI, team accounts, and any
  hosted service. Those are the parts the subscription is actually selling.
- README: setup, the .env template, how to add a fourth provider, and one honest
  paragraph on where this loses to a tuned commercial harness on long tasks.

## Required capabilities

- Node 20 or Python 3.12
- API keys for at least two providers in .env
- Git repo to work against
- Playwright if you want the browser-verification worker

## Delivery order

1. Scaffold the smallest runnable application and document its commands.
2. Implement the primary data model and core workflow.
3. Add validation, safe failure states, and persistence.
4. Cover the critical path with automated tests.
5. Exercise a clean install from the README and fix every missing step.

## Done when

- A new user can go from clone to first successful workflow using only the README.
- The core workflow works without paid infrastructure unless the brief requires it.
- Tests cover the highest-risk behavior.
- Known limitations are explicit rather than hidden.

===== .env.example =====
# Copy to .env and document every variable when it is introduced.
# Never put real credentials in this file.

APP_ENV=development
# Add only values required by the selected implementation.

You are building a lean indie version of AdaL.

Create the following project files first, then implement the application by following them. Keep the files updated as decisions change. Do not collapse this into a single README or prompt.

===== README.md =====
# AdaL indie build

## Goal

Build the smallest trustworthy replacement for the core AdaL workflow for one developer or a tiny team.

## Scope

Wire a terminal agent to several provider APIs, give it file, shell and test tools, and let a planner sub-agent hand tasks to specialized workers in one session.

## Quick start

1. Install the documented dependencies.
2. Copy `.env.example` to `.env`.
3. Run the development command chosen during implementation.
4. Complete the acceptance checks in `BUILD_PLAN.md`.

## Honest limits

This build deliberately does not replace:
- harness tuning: the planning, recovery and verification work that separates a demo agent from one that finishes long tasks
- browser-use verification of the app you just changed
- review clustering that groups a large diff into risk-ranked units
- one bill across every frontier provider instead of six metered API accounts
- SSO, SAML/SCIM, zero data retention and org-level model deny lists

If those capabilities are essential, use AdalFlow instead of pretending the gap is solved.

===== AGENTS.md =====
# Agent instructions

- Optimize for a working, understandable weekend build.
- Prefer the fewest moving parts that satisfy the brief.
- Do not invent cryptography, security guarantees, APIs, or compliance claims.
- Keep secrets out of source control and logs.
- Add focused tests for destructive, security-sensitive, and data-loss paths.
- Run the project checks before declaring the build complete.
- Record any deliberate shortcut in the README under "Tradeoffs".

===== BUILD_PLAN.md =====
# Build plan

## Original build brief

Build me a multi-model coding agent CLI to replace AdaL, in an empty folder.
Stack: Python 3.12, one file per module, no framework.

- Providers: Anthropic, OpenAI and Google, behind a single `chat(model, messages, tools)`
  function. Keys from .env via python-dotenv, never hardcoded. A `--model` flag
  switches families mid-session without restarting.
- Tools the agent can call: read_file, write_file, list_dir, run_shell, run_tests.
  run_shell prints the command and waits for y/n unless I pass --yolo.
- An orchestrator loop: a planner call splits my request into numbered steps, then
  each step runs as a fresh sub-agent with its own context window and only the tools
  it needs. Sub-agent results append to a shared markdown scratchpad on disk.
- Persist every session as JSONL under .agent/sessions/ so I can replay or resume.
  A `--resume <id>` flag reloads the scratchpad and continues.
- After any step that edits files, automatically run the test command from
  pyproject.toml and feed failures back to the same sub-agent for one retry.
- Print a running token and dollar total per provider at the end of every turn.
- Out of scope, deliberately: browser automation, a GUI, team accounts, and any
  hosted service. Those are the parts the subscription is actually selling.
- README: setup, the .env template, how to add a fourth provider, and one honest
  paragraph on where this loses to a tuned commercial harness on long tasks.

## Required capabilities

- Node 20 or Python 3.12
- API keys for at least two providers in .env
- Git repo to work against
- Playwright if you want the browser-verification worker

## Delivery order

1. Scaffold the smallest runnable application and document its commands.
2. Implement the primary data model and core workflow.
3. Add validation, safe failure states, and persistence.
4. Cover the critical path with automated tests.
5. Exercise a clean install from the README and fix every missing step.

## Done when

- A new user can go from clone to first successful workflow using only the README.
- The core workflow works without paid infrastructure unless the brief requires it.
- Tests cover the highest-risk behavior.
- Known limitations are explicit rather than hidden.

===== .env.example =====
# Copy to .env and document every variable when it is introduced.
# Never put real credentials in this file.

APP_ENV=development
# Add only values required by the selected implementation.

You are building a production product version of AdaL.

Create the following project files first, then implement the application by following them. Keep the files updated as decisions change. Do not collapse this into a single README or prompt.

===== PRODUCT.md =====
# AdaL product brief

## Problem

The core loop is genuinely reachable: open-source agents already route across model families, run tools, and edit repos, and a weekend of wiring gets you a personal version. What does not fall out of a weekend is the harness around the model, which is where AdaL claims its numbers come from, plus browser-based verification, clustered code review, and the team controls. You end up with an agent that works and a noticeably worse recovery rate on long tasks.

## Product outcome

Wire a terminal agent to several provider APIs, give it file, shell and test tools, and let a planner sub-agent hand tasks to specialized workers in one session.

## Target user

A serious builder who needs a maintainable product foundation rather than a one-off demo.

## Required capabilities

- Node 20 or Python 3.12
- API keys for at least two providers in .env
- Git repo to work against
- Playwright if you want the browser-verification worker

## Explicit non-goals for v1

- harness tuning: the planning, recovery and verification work that separates a demo agent from one that finishes long tasks
- browser-use verification of the app you just changed
- review clustering that groups a large diff into risk-ranked units
- one bill across every frontier provider instead of six metered API accounts
- SSO, SAML/SCIM, zero data retention and org-level model deny lists

## Success criteria

- The primary workflow is measurable end to end.
- Setup is reproducible in a clean environment.
- Failure, recovery, and support paths are documented.
- Product claims match what the implementation actually guarantees.

===== ARCHITECTURE.md =====
# Architecture

## Starting brief

Build me a multi-model coding agent CLI to replace AdaL, in an empty folder.
Stack: Python 3.12, one file per module, no framework.

- Providers: Anthropic, OpenAI and Google, behind a single `chat(model, messages, tools)`
  function. Keys from .env via python-dotenv, never hardcoded. A `--model` flag
  switches families mid-session without restarting.
- Tools the agent can call: read_file, write_file, list_dir, run_shell, run_tests.
  run_shell prints the command and waits for y/n unless I pass --yolo.
- An orchestrator loop: a planner call splits my request into numbered steps, then
  each step runs as a fresh sub-agent with its own context window and only the tools
  it needs. Sub-agent results append to a shared markdown scratchpad on disk.
- Persist every session as JSONL under .agent/sessions/ so I can replay or resume.
  A `--resume <id>` flag reloads the scratchpad and continues.
- After any step that edits files, automatically run the test command from
  pyproject.toml and feed failures back to the same sub-agent for one retry.
- Print a running token and dollar total per provider at the end of every turn.
- Out of scope, deliberately: browser automation, a GUI, team accounts, and any
  hosted service. Those are the parts the subscription is actually selling.
- README: setup, the .env template, how to add a fourth provider, and one honest
  paragraph on where this loses to a tuned commercial harness on long tasks.

## Boundaries

Separate the product into replaceable modules for interface, application logic, persistence, external integrations, and operational concerns. Keep domain logic independent from delivery frameworks and vendors.

## Production baseline

- Configuration: validated at startup with safe local defaults where possible.
- Security: least privilege, input validation, secret redaction, rate limits on abuse-prone paths, and no invented security primitives.
- Data: explicit schema and migrations, transactional writes where integrity matters, backup and restore instructions.
- Integrations: adapters around third-party providers, idempotent webhook or job processing, bounded retries, and timeouts.
- Observability: structured logs with request or operation IDs, an error-tracking hook, and health/readiness checks where a server exists.
- Quality: unit tests for domain rules, integration tests at module boundaries, and one end-to-end critical-path test.

## Decision records

For each major dependency, document why it was chosen, its failure mode, and how it can be replaced. Do not introduce infrastructure until a requirement justifies it.

===== AGENTS.md =====
# Agent instructions

- Read `PRODUCT.md` and `ARCHITECTURE.md` before changing code.
- Implement milestone by milestone; keep each change reviewable and leave the application runnable.
- Treat authentication, payments, encryption, imports, webhooks, and destructive actions as high-risk boundaries when present.
- Never invent cryptography or silently weaken a requirement to make a test pass.
- Use provider interfaces for external services and deterministic fakes in tests.
- Add migrations and rollback or recovery notes for persistent data changes.
- Log useful operational context without credentials, tokens, passwords, or personal data.
- Update documentation and run all checks before completing a milestone.

===== MILESTONES.md =====
# Delivery milestones

## M0 — Decisions and scaffold

- Confirm the runtime, persistence model, threat boundaries, and deployment target.
- Create a reproducible local environment and continuous checks.

## M1 — Core workflow

- Implement the smallest end-to-end product path with validation and tests.
- Keep integrations behind interfaces.

## M2 — Trust layer

- Add secure failure behavior, recovery paths, audit-relevant events, and data safeguards.
- Test abuse cases and destructive operations.

## M3 — Operability

- Add structured logs, error reporting hooks, health signals, backup/restore documentation, and deployment configuration.

## M4 — Release gate

- Run a clean-install test, critical-path end-to-end test, dependency review, and documented rollback exercise.
- Compare the shipped behavior with `PRODUCT.md` and publish remaining limitations.

===== OPERATIONS.md =====
# Operations

## Before release

- Validate configuration and secrets at startup.
- Define backup, restore, and rollback procedures and test them.
- Document logs, error tracking, health signals, and alert ownership.
- Set dependency update and vulnerability review expectations.

## Incident checklist

1. Contain the issue without destroying evidence or user data.
2. Record the timeline and affected scope.
3. Rotate exposed secrets and revoke compromised sessions or credentials.
4. Restore from a verified source when needed.
5. Document the root cause, remediation, and regression test.

## Launch constraint

Do not market omitted AdaL capabilities as implemented. The v1 non-goals in `PRODUCT.md` remain user-visible limitations until they are deliberately delivered.

# AdaL indie build

## Goal

Build the smallest trustworthy replacement for the core AdaL workflow for one developer or a tiny team.

## Scope

Wire a terminal agent to several provider APIs, give it file, shell and test tools, and let a planner sub-agent hand tasks to specialized workers in one session.

## Quick start

1. Install the documented dependencies.
2. Copy `.env.example` to `.env`.
3. Run the development command chosen during implementation.
4. Complete the acceptance checks in `BUILD_PLAN.md`.

## Honest limits

This build deliberately does not replace:
- harness tuning: the planning, recovery and verification work that separates a demo agent from one that finishes long tasks
- browser-use verification of the app you just changed
- review clustering that groups a large diff into risk-ranked units
- one bill across every frontier provider instead of six metered API accounts
- SSO, SAML/SCIM, zero data retention and org-level model deny lists

If those capabilities are essential, use AdalFlow instead of pretending the gap is solved.

# Agent instructions

- Optimize for a working, understandable weekend build.
- Prefer the fewest moving parts that satisfy the brief.
- Do not invent cryptography, security guarantees, APIs, or compliance claims.
- Keep secrets out of source control and logs.
- Add focused tests for destructive, security-sensitive, and data-loss paths.
- Run the project checks before declaring the build complete.
- Record any deliberate shortcut in the README under "Tradeoffs".

# Build plan

## Original build brief

Build me a multi-model coding agent CLI to replace AdaL, in an empty folder.
Stack: Python 3.12, one file per module, no framework.

- Providers: Anthropic, OpenAI and Google, behind a single `chat(model, messages, tools)`
  function. Keys from .env via python-dotenv, never hardcoded. A `--model` flag
  switches families mid-session without restarting.
- Tools the agent can call: read_file, write_file, list_dir, run_shell, run_tests.
  run_shell prints the command and waits for y/n unless I pass --yolo.
- An orchestrator loop: a planner call splits my request into numbered steps, then
  each step runs as a fresh sub-agent with its own context window and only the tools
  it needs. Sub-agent results append to a shared markdown scratchpad on disk.
- Persist every session as JSONL under .agent/sessions/ so I can replay or resume.
  A `--resume <id>` flag reloads the scratchpad and continues.
- After any step that edits files, automatically run the test command from
  pyproject.toml and feed failures back to the same sub-agent for one retry.
- Print a running token and dollar total per provider at the end of every turn.
- Out of scope, deliberately: browser automation, a GUI, team accounts, and any
  hosted service. Those are the parts the subscription is actually selling.
- README: setup, the .env template, how to add a fourth provider, and one honest
  paragraph on where this loses to a tuned commercial harness on long tasks.

## Required capabilities

- Node 20 or Python 3.12
- API keys for at least two providers in .env
- Git repo to work against
- Playwright if you want the browser-verification worker

## Delivery order

1. Scaffold the smallest runnable application and document its commands.
2. Implement the primary data model and core workflow.
3. Add validation, safe failure states, and persistence.
4. Cover the critical path with automated tests.
5. Exercise a clean install from the README and fix every missing step.

## Done when

- A new user can go from clone to first successful workflow using only the README.
- The core workflow works without paid infrastructure unless the brief requires it.
- Tests cover the highest-risk behavior.
- Known limitations are explicit rather than hidden.

# Copy to .env and document every variable when it is introduced.
# Never put real credentials in this file.

APP_ENV=development
# Add only values required by the selected implementation.

# AdaL product brief

## Problem

The core loop is genuinely reachable: open-source agents already route across model families, run tools, and edit repos, and a weekend of wiring gets you a personal version. What does not fall out of a weekend is the harness around the model, which is where AdaL claims its numbers come from, plus browser-based verification, clustered code review, and the team controls. You end up with an agent that works and a noticeably worse recovery rate on long tasks.

## Product outcome

Wire a terminal agent to several provider APIs, give it file, shell and test tools, and let a planner sub-agent hand tasks to specialized workers in one session.

## Target user

A serious builder who needs a maintainable product foundation rather than a one-off demo.

## Required capabilities

- Node 20 or Python 3.12
- API keys for at least two providers in .env
- Git repo to work against
- Playwright if you want the browser-verification worker

## Explicit non-goals for v1

- harness tuning: the planning, recovery and verification work that separates a demo agent from one that finishes long tasks
- browser-use verification of the app you just changed
- review clustering that groups a large diff into risk-ranked units
- one bill across every frontier provider instead of six metered API accounts
- SSO, SAML/SCIM, zero data retention and org-level model deny lists

## Success criteria

- The primary workflow is measurable end to end.
- Setup is reproducible in a clean environment.
- Failure, recovery, and support paths are documented.
- Product claims match what the implementation actually guarantees.

# Architecture

## Starting brief

Build me a multi-model coding agent CLI to replace AdaL, in an empty folder.
Stack: Python 3.12, one file per module, no framework.

- Providers: Anthropic, OpenAI and Google, behind a single `chat(model, messages, tools)`
  function. Keys from .env via python-dotenv, never hardcoded. A `--model` flag
  switches families mid-session without restarting.
- Tools the agent can call: read_file, write_file, list_dir, run_shell, run_tests.
  run_shell prints the command and waits for y/n unless I pass --yolo.
- An orchestrator loop: a planner call splits my request into numbered steps, then
  each step runs as a fresh sub-agent with its own context window and only the tools
  it needs. Sub-agent results append to a shared markdown scratchpad on disk.
- Persist every session as JSONL under .agent/sessions/ so I can replay or resume.
  A `--resume <id>` flag reloads the scratchpad and continues.
- After any step that edits files, automatically run the test command from
  pyproject.toml and feed failures back to the same sub-agent for one retry.
- Print a running token and dollar total per provider at the end of every turn.
- Out of scope, deliberately: browser automation, a GUI, team accounts, and any
  hosted service. Those are the parts the subscription is actually selling.
- README: setup, the .env template, how to add a fourth provider, and one honest
  paragraph on where this loses to a tuned commercial harness on long tasks.

## Boundaries

Separate the product into replaceable modules for interface, application logic, persistence, external integrations, and operational concerns. Keep domain logic independent from delivery frameworks and vendors.

## Production baseline

- Configuration: validated at startup with safe local defaults where possible.
- Security: least privilege, input validation, secret redaction, rate limits on abuse-prone paths, and no invented security primitives.
- Data: explicit schema and migrations, transactional writes where integrity matters, backup and restore instructions.
- Integrations: adapters around third-party providers, idempotent webhook or job processing, bounded retries, and timeouts.
- Observability: structured logs with request or operation IDs, an error-tracking hook, and health/readiness checks where a server exists.
- Quality: unit tests for domain rules, integration tests at module boundaries, and one end-to-end critical-path test.

## Decision records

For each major dependency, document why it was chosen, its failure mode, and how it can be replaced. Do not introduce infrastructure until a requirement justifies it.

# Agent instructions

- Read `PRODUCT.md` and `ARCHITECTURE.md` before changing code.
- Implement milestone by milestone; keep each change reviewable and leave the application runnable.
- Treat authentication, payments, encryption, imports, webhooks, and destructive actions as high-risk boundaries when present.
- Never invent cryptography or silently weaken a requirement to make a test pass.
- Use provider interfaces for external services and deterministic fakes in tests.
- Add migrations and rollback or recovery notes for persistent data changes.
- Log useful operational context without credentials, tokens, passwords, or personal data.
- Update documentation and run all checks before completing a milestone.

# Delivery milestones

## M0 — Decisions and scaffold

- Confirm the runtime, persistence model, threat boundaries, and deployment target.
- Create a reproducible local environment and continuous checks.

## M1 — Core workflow

- Implement the smallest end-to-end product path with validation and tests.
- Keep integrations behind interfaces.

## M2 — Trust layer

- Add secure failure behavior, recovery paths, audit-relevant events, and data safeguards.
- Test abuse cases and destructive operations.

## M3 — Operability

- Add structured logs, error reporting hooks, health signals, backup/restore documentation, and deployment configuration.

## M4 — Release gate

- Run a clean-install test, critical-path end-to-end test, dependency review, and documented rollback exercise.
- Compare the shipped behavior with `PRODUCT.md` and publish remaining limitations.

# Operations

## Before release

- Validate configuration and secrets at startup.
- Define backup, restore, and rollback procedures and test them.
- Document logs, error tracking, health signals, and alert ownership.
- Set dependency update and vulnerability review expectations.

## Incident checklist

1. Contain the issue without destroying evidence or user data.
2. Record the timeline and affected scope.
3. Rotate exposed secrets and revoke compromised sessions or credentials.
4. Restore from a verified source when needed.
5. Document the root cause, remediation, and regression test.

## Launch constraint

Do not market omitted AdaL capabilities as implemented. The v1 non-goals in `PRODUCT.md` remain user-visible limitations until they are deliberately delivered.

$ choose a build depth, inspect the files, then open the complete pack in your agent