Vibecode Vapi

You are building a lean indie version of Vapi.

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 =====
# Vapi indie build

## Goal

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

## Scope

Route a SIP trunk into a realtime agent, stream speech through STT, LLM, and TTS with interruption handling, run a server-side tool, and save the call outcome.

## 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:
- managed realtime infrastructure, scaling, provider failover, and support
- assistant, squad, workflow, phone-number, and provider configuration APIs
- outbound campaigns, carrier integrations, spam mitigation, and production telephony debugging
- hosted simulations, evaluations, call logs, recordings, analytics, and retention controls
- enterprise SLAs, compliance add-ons, role controls, and data-residency options

If those capabilities are essential, use LiveKit Agents + SIP 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 focused, self-hosted alternative to Vapi for one inbound support number.
Requirements:

- Use Python 3.12 and livekit-agents~=1.5 with one named AgentServer worker.
  Use direct provider plugins, not LiveKit Inference or another managed agent host.
- Run LiveKit Server, Redis, and LiveKit SIP with Docker Compose on one Ubuntu VM.
  Put Caddy in front of HTTPS/WSS; expose only the documented SIP and UDP media ports.
- Provision one Telnyx DID and credential-authenticated SIP trunk. Include checked-in
  LiveKit inbound-trunk and dispatch-rule JSON that sends calls to support-agent.
- Build an AgentSession with Silero VAD, Deepgram Nova-3 STT, gpt-5-mini through
  the OpenAI plugin, and Cartesia Sonic-3 TTS. Load every secret from .env.
- Give the agent one narrow support prompt, interruption handling, and two tools:
  look up an order in SQLite and save a callback request after caller confirmation.
- Persist call id, timestamps, transcript, tool results, and outcome to SQLite.
  Add structured JSON logs and /healthz; recording is off by default.
- Include unit tests for both tools and scripted agent tests for lookup, refusal to
  invent an order, callback confirmation, and a caller interruption.
- Provide make setup, make dev, make smoke, and docker compose up -d commands.
  The smoke test must work in the LiveKit agent console before a real PSTN call.
- README: DNS, TLS, firewall, Telnyx, trunk, dispatch, provider-key, and test-call
  steps, plus common one-way-audio and SIP authentication checks.
- The cost section must say the Vapi fee is removed, while the DID, SIP minutes,
  model usage, VM, failed calls, monitoring, and operator time remain. Link the
  source-backed calculator at https://voice.oss.codes for changing rates.
- Out of scope: outbound campaigns, a multi-tenant dashboard, squads, billing,
  automatic provider failover, call recording, compliance claims, and high availability.

## Required capabilities

- public Linux VM, domain, TLS, and correctly restricted SIP, WebRTC, and RTP ports
- SIP trunk and phone number from a carrier such as Telnyx
- STT, LLM, and TTS provider API keys
- country-specific consent, recording, caller-ID, and outbound-calling review before real traffic

## 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 Vapi.

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 =====
# Vapi indie build

## Goal

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

## Scope

Route a SIP trunk into a realtime agent, stream speech through STT, LLM, and TTS with interruption handling, run a server-side tool, and save the call outcome.

## 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:
- managed realtime infrastructure, scaling, provider failover, and support
- assistant, squad, workflow, phone-number, and provider configuration APIs
- outbound campaigns, carrier integrations, spam mitigation, and production telephony debugging
- hosted simulations, evaluations, call logs, recordings, analytics, and retention controls
- enterprise SLAs, compliance add-ons, role controls, and data-residency options

If those capabilities are essential, use LiveKit Agents + SIP 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 focused, self-hosted alternative to Vapi for one inbound support number.
Requirements:

- Use Python 3.12 and livekit-agents~=1.5 with one named AgentServer worker.
  Use direct provider plugins, not LiveKit Inference or another managed agent host.
- Run LiveKit Server, Redis, and LiveKit SIP with Docker Compose on one Ubuntu VM.
  Put Caddy in front of HTTPS/WSS; expose only the documented SIP and UDP media ports.
- Provision one Telnyx DID and credential-authenticated SIP trunk. Include checked-in
  LiveKit inbound-trunk and dispatch-rule JSON that sends calls to support-agent.
- Build an AgentSession with Silero VAD, Deepgram Nova-3 STT, gpt-5-mini through
  the OpenAI plugin, and Cartesia Sonic-3 TTS. Load every secret from .env.
- Give the agent one narrow support prompt, interruption handling, and two tools:
  look up an order in SQLite and save a callback request after caller confirmation.
- Persist call id, timestamps, transcript, tool results, and outcome to SQLite.
  Add structured JSON logs and /healthz; recording is off by default.
- Include unit tests for both tools and scripted agent tests for lookup, refusal to
  invent an order, callback confirmation, and a caller interruption.
- Provide make setup, make dev, make smoke, and docker compose up -d commands.
  The smoke test must work in the LiveKit agent console before a real PSTN call.
- README: DNS, TLS, firewall, Telnyx, trunk, dispatch, provider-key, and test-call
  steps, plus common one-way-audio and SIP authentication checks.
- The cost section must say the Vapi fee is removed, while the DID, SIP minutes,
  model usage, VM, failed calls, monitoring, and operator time remain. Link the
  source-backed calculator at https://voice.oss.codes for changing rates.
- Out of scope: outbound campaigns, a multi-tenant dashboard, squads, billing,
  automatic provider failover, call recording, compliance claims, and high availability.

## Required capabilities

- public Linux VM, domain, TLS, and correctly restricted SIP, WebRTC, and RTP ports
- SIP trunk and phone number from a carrier such as Telnyx
- STT, LLM, and TTS provider API keys
- country-specific consent, recording, caller-ID, and outbound-calling review before real traffic

## 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 Vapi.

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 =====
# Vapi product brief

## Problem

A focused inbound agent is a credible weekend build with LiveKit Agents or Pipecat. Replacing Vapi as a product is much larger: it combines realtime orchestration, provider abstraction, phone-number and SIP workflows, outbound campaigns, tool calls, testing, observability, scaling, support, and compliance options. Self-hosting can remove Vapi's $0.05 per-minute platform fee, but model, carrier, number, infrastructure, failed-call, monitoring, and engineering costs remain.

## Product outcome

Route a SIP trunk into a realtime agent, stream speech through STT, LLM, and TTS with interruption handling, run a server-side tool, and save the call outcome.

## Target user

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

## Required capabilities

- public Linux VM, domain, TLS, and correctly restricted SIP, WebRTC, and RTP ports
- SIP trunk and phone number from a carrier such as Telnyx
- STT, LLM, and TTS provider API keys
- country-specific consent, recording, caller-ID, and outbound-calling review before real traffic

## Explicit non-goals for v1

- managed realtime infrastructure, scaling, provider failover, and support
- assistant, squad, workflow, phone-number, and provider configuration APIs
- outbound campaigns, carrier integrations, spam mitigation, and production telephony debugging
- hosted simulations, evaluations, call logs, recordings, analytics, and retention controls
- enterprise SLAs, compliance add-ons, role controls, and data-residency options

## 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 focused, self-hosted alternative to Vapi for one inbound support number.
Requirements:

- Use Python 3.12 and livekit-agents~=1.5 with one named AgentServer worker.
  Use direct provider plugins, not LiveKit Inference or another managed agent host.
- Run LiveKit Server, Redis, and LiveKit SIP with Docker Compose on one Ubuntu VM.
  Put Caddy in front of HTTPS/WSS; expose only the documented SIP and UDP media ports.
- Provision one Telnyx DID and credential-authenticated SIP trunk. Include checked-in
  LiveKit inbound-trunk and dispatch-rule JSON that sends calls to support-agent.
- Build an AgentSession with Silero VAD, Deepgram Nova-3 STT, gpt-5-mini through
  the OpenAI plugin, and Cartesia Sonic-3 TTS. Load every secret from .env.
- Give the agent one narrow support prompt, interruption handling, and two tools:
  look up an order in SQLite and save a callback request after caller confirmation.
- Persist call id, timestamps, transcript, tool results, and outcome to SQLite.
  Add structured JSON logs and /healthz; recording is off by default.
- Include unit tests for both tools and scripted agent tests for lookup, refusal to
  invent an order, callback confirmation, and a caller interruption.
- Provide make setup, make dev, make smoke, and docker compose up -d commands.
  The smoke test must work in the LiveKit agent console before a real PSTN call.
- README: DNS, TLS, firewall, Telnyx, trunk, dispatch, provider-key, and test-call
  steps, plus common one-way-audio and SIP authentication checks.
- The cost section must say the Vapi fee is removed, while the DID, SIP minutes,
  model usage, VM, failed calls, monitoring, and operator time remain. Link the
  source-backed calculator at https://voice.oss.codes for changing rates.
- Out of scope: outbound campaigns, a multi-tenant dashboard, squads, billing,
  automatic provider failover, call recording, compliance claims, and high availability.

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

# Vapi indie build

## Goal

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

## Scope

Route a SIP trunk into a realtime agent, stream speech through STT, LLM, and TTS with interruption handling, run a server-side tool, and save the call outcome.

## 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:
- managed realtime infrastructure, scaling, provider failover, and support
- assistant, squad, workflow, phone-number, and provider configuration APIs
- outbound campaigns, carrier integrations, spam mitigation, and production telephony debugging
- hosted simulations, evaluations, call logs, recordings, analytics, and retention controls
- enterprise SLAs, compliance add-ons, role controls, and data-residency options

If those capabilities are essential, use LiveKit Agents + SIP 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 focused, self-hosted alternative to Vapi for one inbound support number.
Requirements:

- Use Python 3.12 and livekit-agents~=1.5 with one named AgentServer worker.
  Use direct provider plugins, not LiveKit Inference or another managed agent host.
- Run LiveKit Server, Redis, and LiveKit SIP with Docker Compose on one Ubuntu VM.
  Put Caddy in front of HTTPS/WSS; expose only the documented SIP and UDP media ports.
- Provision one Telnyx DID and credential-authenticated SIP trunk. Include checked-in
  LiveKit inbound-trunk and dispatch-rule JSON that sends calls to support-agent.
- Build an AgentSession with Silero VAD, Deepgram Nova-3 STT, gpt-5-mini through
  the OpenAI plugin, and Cartesia Sonic-3 TTS. Load every secret from .env.
- Give the agent one narrow support prompt, interruption handling, and two tools:
  look up an order in SQLite and save a callback request after caller confirmation.
- Persist call id, timestamps, transcript, tool results, and outcome to SQLite.
  Add structured JSON logs and /healthz; recording is off by default.
- Include unit tests for both tools and scripted agent tests for lookup, refusal to
  invent an order, callback confirmation, and a caller interruption.
- Provide make setup, make dev, make smoke, and docker compose up -d commands.
  The smoke test must work in the LiveKit agent console before a real PSTN call.
- README: DNS, TLS, firewall, Telnyx, trunk, dispatch, provider-key, and test-call
  steps, plus common one-way-audio and SIP authentication checks.
- The cost section must say the Vapi fee is removed, while the DID, SIP minutes,
  model usage, VM, failed calls, monitoring, and operator time remain. Link the
  source-backed calculator at https://voice.oss.codes for changing rates.
- Out of scope: outbound campaigns, a multi-tenant dashboard, squads, billing,
  automatic provider failover, call recording, compliance claims, and high availability.

## Required capabilities

- public Linux VM, domain, TLS, and correctly restricted SIP, WebRTC, and RTP ports
- SIP trunk and phone number from a carrier such as Telnyx
- STT, LLM, and TTS provider API keys
- country-specific consent, recording, caller-ID, and outbound-calling review before real traffic

## 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.

# Vapi product brief

## Problem

A focused inbound agent is a credible weekend build with LiveKit Agents or Pipecat. Replacing Vapi as a product is much larger: it combines realtime orchestration, provider abstraction, phone-number and SIP workflows, outbound campaigns, tool calls, testing, observability, scaling, support, and compliance options. Self-hosting can remove Vapi's $0.05 per-minute platform fee, but model, carrier, number, infrastructure, failed-call, monitoring, and engineering costs remain.

## Product outcome

Route a SIP trunk into a realtime agent, stream speech through STT, LLM, and TTS with interruption handling, run a server-side tool, and save the call outcome.

## Target user

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

## Required capabilities

- public Linux VM, domain, TLS, and correctly restricted SIP, WebRTC, and RTP ports
- SIP trunk and phone number from a carrier such as Telnyx
- STT, LLM, and TTS provider API keys
- country-specific consent, recording, caller-ID, and outbound-calling review before real traffic

## Explicit non-goals for v1

- managed realtime infrastructure, scaling, provider failover, and support
- assistant, squad, workflow, phone-number, and provider configuration APIs
- outbound campaigns, carrier integrations, spam mitigation, and production telephony debugging
- hosted simulations, evaluations, call logs, recordings, analytics, and retention controls
- enterprise SLAs, compliance add-ons, role controls, and data-residency options

## 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 focused, self-hosted alternative to Vapi for one inbound support number.
Requirements:

- Use Python 3.12 and livekit-agents~=1.5 with one named AgentServer worker.
  Use direct provider plugins, not LiveKit Inference or another managed agent host.
- Run LiveKit Server, Redis, and LiveKit SIP with Docker Compose on one Ubuntu VM.
  Put Caddy in front of HTTPS/WSS; expose only the documented SIP and UDP media ports.
- Provision one Telnyx DID and credential-authenticated SIP trunk. Include checked-in
  LiveKit inbound-trunk and dispatch-rule JSON that sends calls to support-agent.
- Build an AgentSession with Silero VAD, Deepgram Nova-3 STT, gpt-5-mini through
  the OpenAI plugin, and Cartesia Sonic-3 TTS. Load every secret from .env.
- Give the agent one narrow support prompt, interruption handling, and two tools:
  look up an order in SQLite and save a callback request after caller confirmation.
- Persist call id, timestamps, transcript, tool results, and outcome to SQLite.
  Add structured JSON logs and /healthz; recording is off by default.
- Include unit tests for both tools and scripted agent tests for lookup, refusal to
  invent an order, callback confirmation, and a caller interruption.
- Provide make setup, make dev, make smoke, and docker compose up -d commands.
  The smoke test must work in the LiveKit agent console before a real PSTN call.
- README: DNS, TLS, firewall, Telnyx, trunk, dispatch, provider-key, and test-call
  steps, plus common one-way-audio and SIP authentication checks.
- The cost section must say the Vapi fee is removed, while the DID, SIP minutes,
  model usage, VM, failed calls, monitoring, and operator time remain. Link the
  source-backed calculator at https://voice.oss.codes for changing rates.
- Out of scope: outbound campaigns, a multi-tenant dashboard, squads, billing,
  automatic provider failover, call recording, compliance claims, and high availability.

## 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 Vapi 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