Vibecode Animam.ai

You are building a lean indie version of Animam.ai.

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 =====
# Animam.ai indie build

## Goal

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

## Scope

Crawl the sitemap, strip the chrome, store the text, retrieve the 5 best passages by keyword, stream a grounded answer, and refuse to answer outside the context.

## 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:
- Amounts computed server-side from a price grid · the model picks the SKU, it never produces the number
- Visitor identity verified by one-time code before any server-to-server action runs
- Signed outgoing webhooks with exponential backoff, delivery log and manual redelivery
- SSRF guard with DNS resolution on every URL the agent is allowed to call
- Per-tenant secrets encrypted at rest, and tenant isolation you did not have to think about
- Email deliverability · a warmed sending domain is not something you prompt into existence
- The evening the model provider changes a default and your widget starts making things up

If those capabilities are essential, use Chatwoot 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 a website chat widget that answers strictly from a site's own content. Node 20 + TypeScript, no framework.

1. Install hono, @anthropic-ai/sdk, cheerio, turndown, better-sqlite3.
2. scripts/ingest.ts takes a sitemap.xml URL as argv and fetches every page, concurrency 4, skipping non-HTML.
3. Strip nav, header, footer and script tags with cheerio, then convert what is left to markdown with turndown.
4. Upsert into SQLite pages(url PRIMARY KEY, title, body, fetched_at) so re-running updates rows instead of duplicating them.
5. src/search.ts takes the 3 to 6 most distinctive words of the question and runs SELECT url, title, substr(body,1,1200) FROM pages WHERE body LIKE ? for each.
6. Rank by number of hits and return the top 5. No embeddings: under ~500 pages LIKE is cheaper, instant, and you can read why a passage was picked.
7. src/server.ts is a Hono app with POST /chat {message, sessionId}.
8. Put the 5 passages and their URLs in the system prompt, call claude-haiku with stream:true, and pipe SSE to the client.
9. System prompt: "Answer only from the CONTEXT below, and cite the page you used."
10. Continue it: "If the answer is not in the context, say you do not know and offer to take a message."
11. And the line that matters: "Never state a price, a date or an availability that is not written in the context."
12. public/widget.js is an IIFE that injects a bubble into a shadow DOM and keeps sessionId in localStorage.
13. It consumes the SSE and writes every message with textContent, never innerHTML · the text comes from a model that read the internet.
14. Store sessions and messages in the same SQLite file, so you can read back what people actually asked.
15. ANTHROPIC_API_KEY lives in .env, server-side only, and never reaches the bundle.
16. No telemetry, no third-party script in the widget.
17. Serve /widget.js with CORS * and a 5 minute cache so a single <script> tag installs it on any page.

Out of scope on purpose, and each of these is a week rather than a line: booking on a real calendar, payments,
quotes with amounts computed server-side, human handover, transactional email that reaches the inbox,
multi-tenancy, GDPR consent, rate limiting and abuse protection.

## Required capabilities

- An LLM API key (Anthropic, OpenAI, or a local model)
- A place to run a small Node server (a 5 EUR VPS is enough)
- SQLite, or any database you already run
- A domain you can serve the widget from

## 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 Animam.ai.

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 =====
# Animam.ai indie build

## Goal

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

## Scope

Crawl the sitemap, strip the chrome, store the text, retrieve the 5 best passages by keyword, stream a grounded answer, and refuse to answer outside the context.

## 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:
- Amounts computed server-side from a price grid · the model picks the SKU, it never produces the number
- Visitor identity verified by one-time code before any server-to-server action runs
- Signed outgoing webhooks with exponential backoff, delivery log and manual redelivery
- SSRF guard with DNS resolution on every URL the agent is allowed to call
- Per-tenant secrets encrypted at rest, and tenant isolation you did not have to think about
- Email deliverability · a warmed sending domain is not something you prompt into existence
- The evening the model provider changes a default and your widget starts making things up

If those capabilities are essential, use Chatwoot 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 a website chat widget that answers strictly from a site's own content. Node 20 + TypeScript, no framework.

1. Install hono, @anthropic-ai/sdk, cheerio, turndown, better-sqlite3.
2. scripts/ingest.ts takes a sitemap.xml URL as argv and fetches every page, concurrency 4, skipping non-HTML.
3. Strip nav, header, footer and script tags with cheerio, then convert what is left to markdown with turndown.
4. Upsert into SQLite pages(url PRIMARY KEY, title, body, fetched_at) so re-running updates rows instead of duplicating them.
5. src/search.ts takes the 3 to 6 most distinctive words of the question and runs SELECT url, title, substr(body,1,1200) FROM pages WHERE body LIKE ? for each.
6. Rank by number of hits and return the top 5. No embeddings: under ~500 pages LIKE is cheaper, instant, and you can read why a passage was picked.
7. src/server.ts is a Hono app with POST /chat {message, sessionId}.
8. Put the 5 passages and their URLs in the system prompt, call claude-haiku with stream:true, and pipe SSE to the client.
9. System prompt: "Answer only from the CONTEXT below, and cite the page you used."
10. Continue it: "If the answer is not in the context, say you do not know and offer to take a message."
11. And the line that matters: "Never state a price, a date or an availability that is not written in the context."
12. public/widget.js is an IIFE that injects a bubble into a shadow DOM and keeps sessionId in localStorage.
13. It consumes the SSE and writes every message with textContent, never innerHTML · the text comes from a model that read the internet.
14. Store sessions and messages in the same SQLite file, so you can read back what people actually asked.
15. ANTHROPIC_API_KEY lives in .env, server-side only, and never reaches the bundle.
16. No telemetry, no third-party script in the widget.
17. Serve /widget.js with CORS * and a 5 minute cache so a single <script> tag installs it on any page.

Out of scope on purpose, and each of these is a week rather than a line: booking on a real calendar, payments,
quotes with amounts computed server-side, human handover, transactional email that reaches the inbox,
multi-tenancy, GDPR consent, rate limiting and abuse protection.

## Required capabilities

- An LLM API key (Anthropic, OpenAI, or a local model)
- A place to run a small Node server (a 5 EUR VPS is enough)
- SQLite, or any database you already run
- A domain you can serve the widget from

## 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 Animam.ai.

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 =====
# Animam.ai product brief

## Problem

The chat is a weekend. Everything that makes it safe to point at customers is not. Ingest a site, search it, stream an answer · that part is commoditised and the prompt below really does it. What resists is the boring half: an amount computed by the server and never by the model, a visitor email verified before it triggers anything, signed webhooks with retries, and a sending domain whose reputation you did not build in an afternoon.

## Product outcome

Crawl the sitemap, strip the chrome, store the text, retrieve the 5 best passages by keyword, stream a grounded answer, and refuse to answer outside the context.

## Target user

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

## Required capabilities

- An LLM API key (Anthropic, OpenAI, or a local model)
- A place to run a small Node server (a 5 EUR VPS is enough)
- SQLite, or any database you already run
- A domain you can serve the widget from

## Explicit non-goals for v1

- Amounts computed server-side from a price grid · the model picks the SKU, it never produces the number
- Visitor identity verified by one-time code before any server-to-server action runs
- Signed outgoing webhooks with exponential backoff, delivery log and manual redelivery
- SSRF guard with DNS resolution on every URL the agent is allowed to call
- Per-tenant secrets encrypted at rest, and tenant isolation you did not have to think about
- Email deliverability · a warmed sending domain is not something you prompt into existence
- The evening the model provider changes a default and your widget starts making things up

## 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 a website chat widget that answers strictly from a site's own content. Node 20 + TypeScript, no framework.

1. Install hono, @anthropic-ai/sdk, cheerio, turndown, better-sqlite3.
2. scripts/ingest.ts takes a sitemap.xml URL as argv and fetches every page, concurrency 4, skipping non-HTML.
3. Strip nav, header, footer and script tags with cheerio, then convert what is left to markdown with turndown.
4. Upsert into SQLite pages(url PRIMARY KEY, title, body, fetched_at) so re-running updates rows instead of duplicating them.
5. src/search.ts takes the 3 to 6 most distinctive words of the question and runs SELECT url, title, substr(body,1,1200) FROM pages WHERE body LIKE ? for each.
6. Rank by number of hits and return the top 5. No embeddings: under ~500 pages LIKE is cheaper, instant, and you can read why a passage was picked.
7. src/server.ts is a Hono app with POST /chat {message, sessionId}.
8. Put the 5 passages and their URLs in the system prompt, call claude-haiku with stream:true, and pipe SSE to the client.
9. System prompt: "Answer only from the CONTEXT below, and cite the page you used."
10. Continue it: "If the answer is not in the context, say you do not know and offer to take a message."
11. And the line that matters: "Never state a price, a date or an availability that is not written in the context."
12. public/widget.js is an IIFE that injects a bubble into a shadow DOM and keeps sessionId in localStorage.
13. It consumes the SSE and writes every message with textContent, never innerHTML · the text comes from a model that read the internet.
14. Store sessions and messages in the same SQLite file, so you can read back what people actually asked.
15. ANTHROPIC_API_KEY lives in .env, server-side only, and never reaches the bundle.
16. No telemetry, no third-party script in the widget.
17. Serve /widget.js with CORS * and a 5 minute cache so a single <script> tag installs it on any page.

Out of scope on purpose, and each of these is a week rather than a line: booking on a real calendar, payments,
quotes with amounts computed server-side, human handover, transactional email that reaches the inbox,
multi-tenancy, GDPR consent, rate limiting and abuse protection.

## 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 Animam.ai capabilities as implemented. The v1 non-goals in `PRODUCT.md` remain user-visible limitations until they are deliberately delivered.

# Animam.ai indie build

## Goal

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

## Scope

Crawl the sitemap, strip the chrome, store the text, retrieve the 5 best passages by keyword, stream a grounded answer, and refuse to answer outside the context.

## 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:
- Amounts computed server-side from a price grid · the model picks the SKU, it never produces the number
- Visitor identity verified by one-time code before any server-to-server action runs
- Signed outgoing webhooks with exponential backoff, delivery log and manual redelivery
- SSRF guard with DNS resolution on every URL the agent is allowed to call
- Per-tenant secrets encrypted at rest, and tenant isolation you did not have to think about
- Email deliverability · a warmed sending domain is not something you prompt into existence
- The evening the model provider changes a default and your widget starts making things up

If those capabilities are essential, use Chatwoot 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 a website chat widget that answers strictly from a site's own content. Node 20 + TypeScript, no framework.

1. Install hono, @anthropic-ai/sdk, cheerio, turndown, better-sqlite3.
2. scripts/ingest.ts takes a sitemap.xml URL as argv and fetches every page, concurrency 4, skipping non-HTML.
3. Strip nav, header, footer and script tags with cheerio, then convert what is left to markdown with turndown.
4. Upsert into SQLite pages(url PRIMARY KEY, title, body, fetched_at) so re-running updates rows instead of duplicating them.
5. src/search.ts takes the 3 to 6 most distinctive words of the question and runs SELECT url, title, substr(body,1,1200) FROM pages WHERE body LIKE ? for each.
6. Rank by number of hits and return the top 5. No embeddings: under ~500 pages LIKE is cheaper, instant, and you can read why a passage was picked.
7. src/server.ts is a Hono app with POST /chat {message, sessionId}.
8. Put the 5 passages and their URLs in the system prompt, call claude-haiku with stream:true, and pipe SSE to the client.
9. System prompt: "Answer only from the CONTEXT below, and cite the page you used."
10. Continue it: "If the answer is not in the context, say you do not know and offer to take a message."
11. And the line that matters: "Never state a price, a date or an availability that is not written in the context."
12. public/widget.js is an IIFE that injects a bubble into a shadow DOM and keeps sessionId in localStorage.
13. It consumes the SSE and writes every message with textContent, never innerHTML · the text comes from a model that read the internet.
14. Store sessions and messages in the same SQLite file, so you can read back what people actually asked.
15. ANTHROPIC_API_KEY lives in .env, server-side only, and never reaches the bundle.
16. No telemetry, no third-party script in the widget.
17. Serve /widget.js with CORS * and a 5 minute cache so a single <script> tag installs it on any page.

Out of scope on purpose, and each of these is a week rather than a line: booking on a real calendar, payments,
quotes with amounts computed server-side, human handover, transactional email that reaches the inbox,
multi-tenancy, GDPR consent, rate limiting and abuse protection.

## Required capabilities

- An LLM API key (Anthropic, OpenAI, or a local model)
- A place to run a small Node server (a 5 EUR VPS is enough)
- SQLite, or any database you already run
- A domain you can serve the widget from

## 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.

# Animam.ai product brief

## Problem

The chat is a weekend. Everything that makes it safe to point at customers is not. Ingest a site, search it, stream an answer · that part is commoditised and the prompt below really does it. What resists is the boring half: an amount computed by the server and never by the model, a visitor email verified before it triggers anything, signed webhooks with retries, and a sending domain whose reputation you did not build in an afternoon.

## Product outcome

Crawl the sitemap, strip the chrome, store the text, retrieve the 5 best passages by keyword, stream a grounded answer, and refuse to answer outside the context.

## Target user

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

## Required capabilities

- An LLM API key (Anthropic, OpenAI, or a local model)
- A place to run a small Node server (a 5 EUR VPS is enough)
- SQLite, or any database you already run
- A domain you can serve the widget from

## Explicit non-goals for v1

- Amounts computed server-side from a price grid · the model picks the SKU, it never produces the number
- Visitor identity verified by one-time code before any server-to-server action runs
- Signed outgoing webhooks with exponential backoff, delivery log and manual redelivery
- SSRF guard with DNS resolution on every URL the agent is allowed to call
- Per-tenant secrets encrypted at rest, and tenant isolation you did not have to think about
- Email deliverability · a warmed sending domain is not something you prompt into existence
- The evening the model provider changes a default and your widget starts making things up

## 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 a website chat widget that answers strictly from a site's own content. Node 20 + TypeScript, no framework.

1. Install hono, @anthropic-ai/sdk, cheerio, turndown, better-sqlite3.
2. scripts/ingest.ts takes a sitemap.xml URL as argv and fetches every page, concurrency 4, skipping non-HTML.
3. Strip nav, header, footer and script tags with cheerio, then convert what is left to markdown with turndown.
4. Upsert into SQLite pages(url PRIMARY KEY, title, body, fetched_at) so re-running updates rows instead of duplicating them.
5. src/search.ts takes the 3 to 6 most distinctive words of the question and runs SELECT url, title, substr(body,1,1200) FROM pages WHERE body LIKE ? for each.
6. Rank by number of hits and return the top 5. No embeddings: under ~500 pages LIKE is cheaper, instant, and you can read why a passage was picked.
7. src/server.ts is a Hono app with POST /chat {message, sessionId}.
8. Put the 5 passages and their URLs in the system prompt, call claude-haiku with stream:true, and pipe SSE to the client.
9. System prompt: "Answer only from the CONTEXT below, and cite the page you used."
10. Continue it: "If the answer is not in the context, say you do not know and offer to take a message."
11. And the line that matters: "Never state a price, a date or an availability that is not written in the context."
12. public/widget.js is an IIFE that injects a bubble into a shadow DOM and keeps sessionId in localStorage.
13. It consumes the SSE and writes every message with textContent, never innerHTML · the text comes from a model that read the internet.
14. Store sessions and messages in the same SQLite file, so you can read back what people actually asked.
15. ANTHROPIC_API_KEY lives in .env, server-side only, and never reaches the bundle.
16. No telemetry, no third-party script in the widget.
17. Serve /widget.js with CORS * and a 5 minute cache so a single <script> tag installs it on any page.

Out of scope on purpose, and each of these is a week rather than a line: booking on a real calendar, payments,
quotes with amounts computed server-side, human handover, transactional email that reaches the inbox,
multi-tenancy, GDPR consent, rate limiting and abuse protection.

## 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 Animam.ai 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