recall-os 0.1.0 → 0.2.0

package/examples/generated-laravel-api/.recall/config.json

@@ -0,0 +1,17 @@
+{
+  "version": "0.1.0",
+  "templateVersion": "0.1.0",
+  "preset": "laravel-api",
+  "memoryProfile": "standard",
+  "mode": "standard",
+  "aiTools": [
+    "claude",
+    "codex"
+  ],
+  "docsDir": "docs",
+  "featuresDir": "docs/40-features",
+  "modulesDir": "docs/30-modules",
+  "adrDir": "docs/adrs",
+  "writePolicy": "skip-existing",
+  "preCommitGates": []
+}

package/examples/generated-laravel-api/.recall/hooks/pre-commit

@@ -0,0 +1,9 @@
+#!/bin/sh
+# Recall OS pre-commit hook.
+# Generated by `recall init`. Edit gates in .recall/config.json (preCommitGates),
+# then re-run `recall init --force` to regenerate this hook.
+# Enable once per clone with:
+#   git config core.hooksPath .recall/hooks
+set -e
+
+recall doctor

package/examples/generated-laravel-api/AGENTS.md

@@ -0,0 +1,15 @@
+# generated-laravel-api Agent Instructions
+
+This repository uses Recall OS repository memory.
+
+Start with durable source-of-truth docs under `docs/`.
+
+Required reading:
+
+- `docs/00-product/PRD.md`
+- `docs/10-architecture/ARCHITECTURE.md`
+- `docs/20-security/SECURITY_MODEL.md`
+- `docs/50-quality/QUALITY_GATES.md`
+- `docs/60-engineering/ENGINEERING_STANDARDS.md`
+
+Repository rules override model preferences. If instructions conflict, stop and report the conflict.

package/examples/generated-laravel-api/CLAUDE.md

@@ -0,0 +1,9 @@
+# generated-laravel-api Claude Instructions
+
+This file is loaded automatically every Claude session. The durable project memory lives in `docs/`;
+do not rely on chat history as source of truth, and repository rules override model preference.
+
+@AGENTS.md
+
+Read the docs that `AGENTS.md` routes to before changing code or repository memory. A SessionStart
+hook (`.claude/hooks/session-start.sh`) also injects a memory map at the start of each session.

package/examples/generated-laravel-api/README.md

@@ -0,0 +1,11 @@
+# Laravel API Example
+
+This folder shows the repository memory generated by:
+
+```bash
+recall init --preset laravel-api
+```
+
+The Laravel API preset adds API-only guidance and proposed decisions for the framework, a versioned
+REST API with API Resources, Eloquent, Sanctum tokens, queues, and Pest. Those decisions remain
+proposed until a human accepts them in repository memory.

package/examples/generated-laravel-api/docs/00-product/BRD.md

@@ -0,0 +1,9 @@
+# BRD: generated-laravel-api
+
+## Purpose
+
+Describe the business goal, target users, and success criteria for this repository.
+
+## Current Status
+
+Draft.

package/examples/generated-laravel-api/docs/00-product/PRD.md

@@ -0,0 +1,13 @@
+# PRD: generated-laravel-api
+
+## Purpose
+
+Describe what this repository is building and why.
+
+## Current Status
+
+Draft.
+
+## Notes
+
+Keep product intent durable here. Do not rely on chat history as source of truth.

package/examples/generated-laravel-api/docs/10-architecture/ARCHITECTURE.md

@@ -0,0 +1,11 @@
+# Architecture
+
+## Purpose
+
+Describe the accepted architecture for this repository.
+
+## Current Status
+
+No architecture decisions are accepted yet.
+
+Use ADRs to accept architecture choices.

package/examples/generated-laravel-api/docs/10-architecture/FILE_WRITE_POLICY.md

@@ -0,0 +1,8 @@
+# File Write Policy
+
+Default behavior:
+
+- Skip existing files.
+- Use dry run before risky writes.
+- Require explicit force to overwrite.
+- Never write outside the repository root.

package/examples/generated-laravel-api/docs/10-architecture/MEMORY_ENGINE.md

@@ -0,0 +1,16 @@
+# Repository Memory
+
+Repository memory is the durable source of truth for humans and AI agents.
+
+Source-of-truth order:
+
+1. Accepted ADRs and repository decisions
+2. Architecture docs
+3. Engineering standards
+4. Current PRD and accepted change requests
+5. Security and testing docs
+6. Module docs
+7. Feature plans
+8. Task files
+9. External context
+10. Chat history

package/examples/generated-laravel-api/docs/20-security/SECURITY_MODEL.md

@@ -0,0 +1,11 @@
+# Security Model
+
+## Current Status
+
+Draft.
+
+## Baseline Rules
+
+- Do not commit secrets.
+- Do not read or copy `.env` files into docs.
+- Do not add network, telemetry, cloud, MCP runtime, or AI API behavior without explicit review.

package/examples/generated-laravel-api/docs/20-security/THREAT_MODEL.md

@@ -0,0 +1,7 @@
+# Threat Model
+
+## Current Status
+
+Draft.
+
+Track repository-specific risks here as the project evolves.

package/examples/generated-laravel-api/docs/30-modules/README.md

@@ -0,0 +1,17 @@
+# Module Memory
+
+Module memory records what each important module owns, how it should be tested, and which decisions
+affect it.
+
+Future module folders should use:
+
+```txt
+docs/30-modules/<module>/
+  MODULE.md
+  TASKS.md
+  TEST_PLAN.md
+  DECISIONS.md
+```
+
+Agents should update module memory when implementation changes responsibilities, boundaries, tests,
+risks, or decisions.

package/examples/generated-laravel-api/docs/40-features/README.md

@@ -0,0 +1,22 @@
+# Feature Memory
+
+Feature memory records requirements, acceptance criteria, plans, tests, reviews, and completion
+evidence.
+
+Future feature folders should use:
+
+```txt
+docs/40-features/F-###-<feature>/
+  PRD.md
+  ACCEPTANCE.md
+  ARCHITECTURE_IMPACT.md
+  CHANGE_REQUESTS.md
+  PLAN.md
+  TASKS.md
+  TEST_PLAN.md
+  REVIEW.md
+  COMPLETION_REPORT.md
+```
+
+Agents should not implement meaningful feature work without a feature plan or clear source-of-truth
+reference.

package/examples/generated-laravel-api/docs/50-quality/QUALITY_GATES.md

@@ -0,0 +1,11 @@
+# Quality Gates
+
+Do not claim completion without evidence.
+
+Completion evidence should include:
+
+- Files changed.
+- Tests run.
+- Results.
+- Skipped checks.
+- Remaining risks.

package/examples/generated-laravel-api/docs/50-quality/TESTING_STRATEGY.md

@@ -0,0 +1,5 @@
+# Testing Strategy
+
+Tests should derive from acceptance criteria, risk, security invariants, and module boundaries.
+
+Document required unit, integration, security, and golden tests as the repository grows.

package/examples/generated-laravel-api/docs/60-engineering/AI_AGENT_RULES.md

@@ -0,0 +1,6 @@
+# AI Agent Rules
+
+AI agents must follow repository memory over model preference.
+
+If a request conflicts with accepted repository memory or engineering standards, stop and report the
+conflict.

package/examples/generated-laravel-api/docs/60-engineering/ENGINEERING_STANDARDS.md

@@ -0,0 +1,11 @@
+# Engineering Standards
+
+Repository rules override model preferences.
+
+Baseline rules:
+
+- Never commit secrets.
+- Keep changes scoped.
+- Update docs when behavior or architecture changes.
+- Add tests or document why tests were skipped.
+- Do not claim completion without evidence.

package/examples/generated-laravel-api/docs/adrs/README.md

@@ -0,0 +1,9 @@
+# Architecture Decision Records
+
+Accepted ADRs live in this directory as `ADR-####-<slug>.md` with `## Status` set to `Accepted`.
+Proposed ADRs live under `docs/adrs/proposed/`.
+
+There is no `accepted/` subdirectory: accepted ADRs sit at the top level of `docs/adrs/`.
+
+Presets and AI agents may propose decisions; humans accept them with `recall adr accept <name>`,
+which promotes a proposal into an accepted ADR here.

package/examples/generated-laravel-api/docs/adrs/proposed/ADR-PROPOSED-laravel-api-api-design-rest.md

@@ -0,0 +1,31 @@
+# Proposed ADR: Expose a versioned REST API with API Resources
+
+## Status
+
+Proposed
+
+## Context
+
+A decoupled SPA or mobile client consumes Laravel over HTTP, so the API contract must be stable and
+explicit.
+
+## Decision
+
+Consider a versioned REST API (for example `/api/v1`) whose responses are shaped by API Resources,
+authenticated with Sanctum, and documented (OpenAPI). This is not accepted until a human accepts it.
+
+## Alternatives Considered
+
+- GraphQL.
+- Server-driven Inertia pages instead of a decoupled API.
+
+## Consequences
+
+- A stable, documented contract that multiple clients can rely on.
+- Versioning and serialization become an explicit, maintained concern.
+
+## Related Documents
+
+- `docs/ai/presets/laravel-api-guidance.md` — the proposed Laravel stack guidance.
+- `docs/10-architecture/ARCHITECTURE.md` — record the accepted architecture here once promoted.
+- `docs/20-security/SECURITY_MODEL.md` — record token scopes and the SPA cookie guard here.

package/examples/generated-laravel-api/docs/adrs/proposed/ADR-PROPOSED-laravel-api-application-structure.md

@@ -0,0 +1,30 @@
+# Proposed ADR: Keep controllers thin with Action and Service classes
+
+## Status
+
+Proposed
+
+## Context
+
+Business logic tends to accumulate in controllers and models, which makes it hard to test and reuse.
+
+## Decision
+
+Consider thin controllers that delegate to single-purpose Action or Service classes, with outbound
+payloads shaped by API Resources (or typed Inertia props). This is not accepted until a human
+accepts it.
+
+## Alternatives Considered
+
+- Fat controllers.
+- Fat models holding business logic.
+
+## Consequences
+
+- Reusable, unit-testable business logic and consistent response shapes.
+- More classes and a convention the team must follow.
+
+## Related Documents
+
+- `docs/ai/presets/laravel-api-guidance.md` — the proposed Laravel stack guidance.
+- `docs/10-architecture/ARCHITECTURE.md` — record the accepted architecture here once promoted.

package/examples/generated-laravel-api/docs/adrs/proposed/ADR-PROPOSED-laravel-api-auth-sanctum.md

@@ -0,0 +1,30 @@
+# Proposed ADR: Use Laravel Sanctum for authentication
+
+## Status
+
+Proposed
+
+## Context
+
+The application needs authentication for first-party clients (a separate SPA and mobile apps).
+
+## Decision
+
+Consider Laravel Sanctum: the cookie-based guard for first-party SPAs and API tokens for mobile or
+scripted clients. This is not accepted until a human reviews and accepts it.
+
+## Alternatives Considered
+
+- Laravel Passport for full OAuth2 (third-party delegated access).
+- A managed identity provider.
+
+## Consequences
+
+- Lightweight first-party auth without standing up a full OAuth2 server.
+- If third-party delegated access is ever required, revisit with Passport.
+
+## Related Documents
+
+- `docs/ai/presets/laravel-api-guidance.md` — the proposed Laravel stack guidance.
+- `docs/10-architecture/ARCHITECTURE.md` — record the accepted architecture here once promoted.
+- `docs/20-security/SECURITY_MODEL.md` — record the accepted auth and session model here.

package/examples/generated-laravel-api/docs/adrs/proposed/ADR-PROPOSED-laravel-api-database-eloquent.md

@@ -0,0 +1,31 @@
+# Proposed ADR: Use Eloquent and migrations on PostgreSQL
+
+## Status
+
+Proposed
+
+## Context
+
+The application needs a relational database and a schema workflow.
+
+## Decision
+
+Consider PostgreSQL (MySQL as the alternative) accessed through Eloquent and versioned migrations,
+awaiting human acceptance.
+
+## Alternatives Considered
+
+- MySQL or MariaDB.
+- The query builder or raw SQL without Eloquent.
+
+## Consequences
+
+- Expressive models, relationships, and reproducible schema migrations.
+- Requires discipline against N+1 queries and unbounded result sets.
+
+## Related Documents
+
+- `docs/ai/presets/laravel-api-guidance.md` — the proposed Laravel stack guidance.
+- `docs/10-architecture/ARCHITECTURE.md` — record the accepted architecture here once promoted.
+- `docs/50-quality/TESTING_STRATEGY.md` — how database tests use factories and a disposable
+  database.

package/examples/generated-laravel-api/docs/adrs/proposed/ADR-PROPOSED-laravel-api-framework.md

@@ -0,0 +1,29 @@
+# Proposed ADR: Use Laravel
+
+## Status
+
+Proposed
+
+## Context
+
+The team needs a productive, batteries-included PHP framework for a production web application.
+
+## Decision
+
+Consider Laravel 12 on PHP 8.3+ as the application framework, following its standard conventions and
+directory structure. This is not accepted until a human reviews and accepts it.
+
+## Alternatives Considered
+
+- Symfony for a more component-assembled approach.
+- A different language or framework entirely.
+
+## Consequences
+
+- A mature ecosystem (Eloquent, queues, Sanctum, Horizon) and strong conventions.
+- Couples the application to Laravel's conventions and release cadence.
+
+## Related Documents
+
+- `docs/ai/presets/laravel-api-guidance.md` — the proposed Laravel stack guidance.
+- `docs/10-architecture/ARCHITECTURE.md` — record the accepted architecture here once promoted.

package/examples/generated-laravel-api/docs/adrs/proposed/ADR-PROPOSED-laravel-api-queues-horizon.md

@@ -0,0 +1,29 @@
+# Proposed ADR: Run slow work on queues
+
+## Status
+
+Proposed
+
+## Context
+
+Email, exports, and third-party calls slow down requests and can fail independently.
+
+## Decision
+
+Consider queued jobs for slow or failure-prone work, using the database driver early and Redis with
+Laravel Horizon as throughput grows. This is not accepted until a human reviews and accepts it.
+
+## Alternatives Considered
+
+- Doing the work synchronously in the request.
+- An external task queue or serverless functions.
+
+## Consequences
+
+- Faster responses and isolated, retryable background work.
+- Adds a worker process and queue infrastructure to operate and monitor.
+
+## Related Documents
+
+- `docs/ai/presets/laravel-api-guidance.md` — the proposed Laravel stack guidance.
+- `docs/10-architecture/ARCHITECTURE.md` — record the accepted architecture here once promoted.

package/examples/generated-laravel-api/docs/adrs/proposed/ADR-PROPOSED-laravel-api-testing-pest.md

@@ -0,0 +1,30 @@
+# Proposed ADR: Use Pest for testing
+
+## Status
+
+Proposed
+
+## Context
+
+The application needs a fast, readable testing workflow.
+
+## Decision
+
+Consider Pest with model factories and feature tests that exercise real routes against a disposable
+database, awaiting human acceptance.
+
+## Alternatives Considered
+
+- PHPUnit directly.
+- A thinner test suite focused only on unit tests.
+
+## Consequences
+
+- Concise, expressive tests that cover routes, validation, and authorization.
+- The team standardizes on Pest's syntax and plugins.
+
+## Related Documents
+
+- `docs/ai/presets/laravel-api-guidance.md` — the proposed Laravel stack guidance.
+- `docs/10-architecture/ARCHITECTURE.md` — record the accepted architecture here once promoted.
+- `docs/50-quality/TESTING_STRATEGY.md` — record the accepted testing approach here.

package/examples/generated-laravel-api/docs/adrs/proposed/ADR-PROPOSED-laravel-api-validation-authorization.md

@@ -0,0 +1,30 @@
+# Proposed ADR: Validate with Form Requests and authorize with Policies
+
+## Status
+
+Proposed
+
+## Context
+
+Input validation and authorization must be consistent and centralized, not scattered across
+controllers.
+
+## Decision
+
+Consider Form Requests for validation (and request-level authorization) plus Policies and Gates for
+per-model and per-action permission checks, awaiting human acceptance.
+
+## Alternatives Considered
+
+- Inline validation and authorization in controllers.
+- A third-party permissions package layered on top.
+
+## Consequences
+
+- Controllers stay thin; validation and authorization are testable in isolation.
+- Every state-changing action must have an explicit authorization path.
+
+## Related Documents
+
+- `docs/ai/presets/laravel-api-guidance.md` — the proposed Laravel stack guidance.
+- `docs/10-architecture/ARCHITECTURE.md` — record the accepted architecture here once promoted.

package/examples/generated-laravel-api/docs/ai/AI_AGENTS_SKILLS_MCP_STRATEGY.md

@@ -0,0 +1,7 @@
+# AI Agents, Skills, And MCP Strategy
+
+Root agent files are entry points, not guarantees.
+
+Durable memory lives in `docs/`.
+
+MCP is optional external context and does not override accepted repository memory.

package/examples/generated-laravel-api/docs/ai/MCP_STRATEGY.md

@@ -0,0 +1,6 @@
+# MCP Strategy
+
+MCP is not required for this repository.
+
+If MCP is introduced later, document trusted servers, data accessed, permissions, risks, and
+source-of-truth rules.

package/examples/generated-laravel-api/docs/ai/RECALL_COMMANDS.md

@@ -0,0 +1,133 @@
+# Recall OS Commands
+
+This document records the Recall OS commands available to humans and AI agents.
+
+## Completion Gate
+
+Before claiming implementation work is complete, run:
+
+```txt
+pnpm test:run
+pnpm typecheck
+recall doctor
+```
+
+If `recall doctor` reports errors, fix them or report why they cannot be fixed. If it reports
+warnings, address them or record why they are acceptable.
+
+Package binary behavior is covered by binary integration tests.
+
+## Commands
+
+### `recall init`
+
+Initialize neutral repository memory.
+
+Options:
+
+- `--preset <id>`: apply optional preset guidance and proposed decisions.
+- `--dry-run`: show planned writes without writing files.
+- `--force`: overwrite existing files explicitly.
+- `--reinit`: required with `--force` to overwrite an existing Recall OS installation (a directory
+  that already has `.recall/config.json`). Without it, `--force` refuses, protecting existing
+  repository memory.
+
+Init also generates a tracked pre-commit hook at `.recall/hooks/pre-commit` that runs
+`recall doctor` plus any `preCommitGates` in `.recall/config.json`. Init proposes, but does not run,
+the activation command `git config core.hooksPath .recall/hooks`.
+
+### `recall adopt`
+
+Inspect an existing repository through read-only manifest and marker files, then write a proposed
+adoption report and proposed framework ADRs for human review. Adopt never executes repository code
+and never produces accepted memory.
+
+Options:
+
+- `--dry-run`: show planned writes without writing files.
+- `--force`: overwrite existing files explicitly.
+
+### `recall skill create <name>`
+
+Generate a portable AI agent skill as `SKILL.md` for both Claude Code (`.claude/skills/`) and the
+portable Agent Skills target (`.agents/skills/`). Known names use the built-in catalog; unknown
+names produce a valid skeleton. Generated skills contain no scripts.
+
+Options:
+
+- `--dry-run`: show planned writes without writing files.
+- `--force`: overwrite existing files explicitly.
+
+### `recall skill list`
+
+List the built-in catalog skills.
+
+### `recall mcp add <server>`
+
+Generate offline, proposed memory for an MCP server (for example `figma`) as
+`docs/ai/mcp/<server>.md` plus a proposed adoption ADR. Recall OS never connects to the MCP server
+or makes network calls; the agent records durable MCP-derived context into the generated memory for
+human review. It also installs a `capture-mcp-context` agent skill that prompts the agent to record
+that context.
+
+Options:
+
+- `--dry-run`: show planned writes without writing files.
+- `--force`: overwrite existing files explicitly.
+
+### `recall preset list`
+
+List built-in presets.
+
+### `recall feature create <name>`
+
+Create feature memory docs under the configured features directory.
+
+Options:
+
+- `--dry-run`: show planned writes without writing files.
+- `--force`: overwrite existing files explicitly.
+
+### `recall adr create <title>`
+
+Create a proposed ADR under the configured ADR directory.
+
+Options:
+
+- `--dry-run`: show planned writes without writing files.
+- `--force`: overwrite existing files explicitly.
+
+### `recall adr accept <name>`
+
+Promote a proposed ADR to accepted repository memory. A proposal under
+`docs/adrs/proposed/ADR-PROPOSED-<slug>.md` becomes a numbered, accepted `ADR-####-<slug>.md` and
+the proposal is removed; an existing numbered Proposed ADR is accepted in place.
+
+Options:
+
+- `--dry-run`: show planned writes without writing files.
+- `--force`: overwrite existing files explicitly.
+
+### `recall module create <name>`
+
+Create module memory docs under the configured modules directory.
+
+Options:
+
+- `--dry-run`: show planned writes without writing files.
+- `--force`: overwrite existing files explicitly.
+
+### `recall doctor`
+
+Check whether repository memory is structurally healthy enough for AI-assisted work, whether basic
+engineering evidence is present, and whether memory references decisions that exist and are
+accepted.
+
+Doctor also runs deterministic drift checks: feature or module memory that references a missing ADR
+is an error, and memory that references a not-yet-accepted ADR is a warning.
+
+Exit codes:
+
+- `0`: healthy
+- `1`: warnings only
+- `2`: errors