gb_flea/paperclip
1
0
Fork 0
forked from farhoodlabs/paperclip
Code Pull Requests Activity
Files
c0c58d6b017ec914debe5fd9800a0d59183c6056
paperclip/doc/SPEC-implementation.md
T
Dotta e8275318ba [codex] Raise agent heartbeat concurrency default (#4954) 
## Thinking Path

> - Paperclip orchestrates AI agents for zero-human companies
> - Agent heartbeat settings control how much parallel work one employee
can run
> - The previous default of 5 concurrent runs was too restrictive for
active local agent teams
> - The shared default, heartbeat clamp, docs, and route/import/UI
expectations need to agree
> - This pull request raises the default heartbeat concurrency to 20
while keeping explicit headroom up to 50 for power users
> - The benefit is higher throughput for agent teams without each new
agent needing manual runtime config edits

## What Changed

- Raised `AGENT_DEFAULT_MAX_CONCURRENT_RUNS` from 5 to 20.
- Raised the heartbeat service max clamp from 10 to 50, keeping the new
default below the ceiling.
- Updated V1 implementation docs and tests that assert default
imported/exported runtime config.
- Updated the new-agent UI runtime config test to assert the shared
default constant instead of duplicating the numeric value.

## Verification

- `pnpm exec vitest run
server/src/__tests__/agent-permissions-routes.test.ts
server/src/__tests__/company-portability.test.ts
ui/src/lib/new-agent-runtime-config.test.ts`

## Risks

- Medium risk: new agents can consume more local execution capacity by
default. The heartbeat scheduler still respects configured max
concurrency and budget/pause controls, and operators can lower or raise
the per-agent cap within the `1..50` clamp.

> For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and
discuss it in `#dev` before opening the PR. Feature PRs that overlap
with planned core work may need to be redirected — check the roadmap
first. See `CONTRIBUTING.md`.

## Model Used

- OpenAI Codex, GPT-5 coding agent, tool use and local command
execution. Exact context window was not exposed in the runtime.

## Checklist

- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] If this change affects the UI, I have included before/after
screenshots
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] I will address all Greptile and reviewer comments before
requesting merge

---------

Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-05-01 10:42:56 -05:00

942 lines
33 KiB
Markdown
Raw Blame History

# Paperclip V1 Implementation Spec
Status: Implementation contract for first release (V1)
Date: 2026-04-28
Audience: Product, engineering, and agent-integration authors
Source inputs: `GOAL.md`, `PRODUCT.md`, `SPEC.md`, `DATABASE.md`, current monorepo code
## 1. Document Role
`SPEC.md` remains the long-horizon product spec.
This document is the concrete, build-ready V1 contract.
When there is a conflict, `SPEC-implementation.md` controls V1 behavior.
## 2. V1 Outcomes
Paperclip V1 must provide a full control-plane loop for autonomous agents:
1. A human board creates a company and defines goals.
2. The board creates and manages agents in an org tree.
3. Agents receive and execute tasks via heartbeat invocations.
4. All work is tracked through tasks/comments with audit visibility.
5. Token/cost usage is reported and budget limits can stop work.
6. The board can intervene anywhere (pause agents/tasks, override decisions).
Success means one operator can run a small AI-native company end-to-end with clear visibility and control.
## 3. Explicit V1 Product Decisions
These decisions close open questions from `SPEC.md` for V1.
| Topic | V1 Decision |
|---|---|
| Tenancy | Single-tenant deployment, multi-company data model |
| Company model | Company is first-order; all business entities are company-scoped |
| Board | Single human board operator per deployment |
| Org graph | Strict tree (`reports_to` nullable root); no multi-manager reporting |
| Visibility | Full visibility to board and all agents in same company |
| Communication | Tasks + comments only (no separate chat system) |
| Task ownership | Single assignee; atomic checkout required for `in_progress` transition |
| Recovery | Liveness/watchdog recovery preserves explicit ownership: retry lost execution continuity where safe, otherwise create visible recovery issues or require human escalation (see `doc/execution-semantics.md`) |
| Agent adapters | Built-in `process`, `http`, local CLI/session adapters, and OpenClaw gateway support; external adapters can also be loaded through the adapter plugin flow |
| Plugin framework | Local/self-hosted early plugin runtime is in scope; cloud marketplace and packaged public distribution remain out of scope |
| Auth | Mode-dependent human auth (`local_trusted` implicit board in current code; authenticated mode uses sessions), API keys for agents |
| Budget period | Monthly UTC calendar window |
| Budget enforcement | Soft alerts + hard limit auto-pause |
| Deployment modes | Canonical model is `local_trusted` + `authenticated` with `private/public` exposure policy (see `doc/DEPLOYMENT-MODES.md`) |
## 4. Current Baseline (Repo Snapshot)
As of 2026-02-17, the repo already includes:
- Node + TypeScript backend with REST CRUD for `agents`, `projects`, `goals`, `issues`, `activity`
- React UI pages for dashboard/agents/projects/goals/issues lists
- PostgreSQL schema via Drizzle with embedded PostgreSQL fallback when `DATABASE_URL` is unset
V1 implementation extends this baseline into a company-centric, governance-aware control plane.
## 5. V1 Scope
## 5.1 In Scope
- Company lifecycle (create/list/get/update/archive)
- Goal hierarchy linked to company mission
- Agent lifecycle with org structure and adapter configuration
- Task lifecycle with parent/child hierarchy and comments
- Atomic task checkout and explicit task status transitions
- Board approvals for hires and CEO strategy proposal
- Heartbeat invocation, status tracking, and cancellation
- Cost event ingestion and rollups (agent/task/project/company)
- Budget settings and hard-stop enforcement
- Board web UI for dashboard, org chart, tasks, agents, approvals, costs
- Agent-facing API contract (task read/write, heartbeat report, cost report)
- Auditable activity log for all mutating actions
## 5.2 Out of Scope (V1)
- Cloud-grade plugin marketplace/distribution beyond the local/self-hosted plugin runtime
- Revenue/expense accounting beyond model/token costs
- Knowledge base subsystem
- Public marketplace (ClipHub)
- Multi-board governance or role-based human permission granularity
- Automatic self-healing orchestration (auto-reassign/retry planners)
## 6. Architecture
## 6.1 Runtime Components
- `server/`: REST API, auth, orchestration services
- `ui/`: Board operator interface
- `packages/db/`: Drizzle schema, migrations, DB clients (Postgres)
- `packages/shared/`: Shared API types, validators, constants
## 6.2 Data Stores
- Primary: PostgreSQL
- Local default: embedded PostgreSQL at `~/.paperclip/instances/default/db`
- Optional local prod-like: Docker Postgres
- Optional hosted: Supabase/Postgres-compatible
- File/object storage:
- local default: `~/.paperclip/instances/default/data/storage` (`local_disk`)
- cloud: S3-compatible object storage (`s3`)
## 6.3 Background Processing
A lightweight scheduler/worker in the server process handles:
- heartbeat trigger checks
- stuck run detection
- budget threshold checks
Separate queue infrastructure is not required for V1.
## 7. Canonical Data Model (V1)
All core tables include `id`, `created_at`, `updated_at` unless noted.
## 7.0 Auth Tables
Human auth tables (`users`, `sessions`, and provider-specific auth artifacts) are managed by the selected auth library. This spec treats them as required dependencies and references `users.id` where user attribution is needed.
## 7.1 `companies`
- `id` uuid pk
- `name` text not null
- `description` text null
- `status` enum: `active | paused | archived`
- `pause_reason` text null
- `paused_at` timestamptz null
- `issue_prefix` text not null
- `issue_counter` int not null
- `budget_monthly_cents` int not null default 0
- `spent_monthly_cents` int not null default 0
- `attachment_max_bytes` int not null
- `require_board_approval_for_new_agents` boolean not null default false
- feedback sharing consent fields
- branding fields such as `brand_color`
Invariant: every business record belongs to exactly one company.
## 7.2 `agents`
- `id` uuid pk
- `company_id` uuid fk `companies.id` not null
- `name` text not null
- `role` text not null
- `title` text null
- `icon` text null
- `status` enum: `active | paused | idle | running | error | pending_approval | terminated`
- `reports_to` uuid fk `agents.id` null
- `capabilities` text null
- `adapter_type` text; built-ins include `process`, `http`, `claude_local`, `codex_local`, `gemini_local`, `opencode_local`, `pi_local`, `cursor`, and `openclaw_gateway`
- `adapter_config` jsonb not null
- `runtime_config` jsonb not null default `{}`; may include Paperclip runtime policy such as `modelProfiles.cheap.adapterConfig` for an optional low-cost model lane that does not change the primary adapter config
- `default_environment_id` uuid fk `environments.id` null
- `context_mode` enum: `thin | fat` default `thin`
- `budget_monthly_cents` int not null default 0
- `spent_monthly_cents` int not null default 0
- pause fields: `pause_reason`, `paused_at`
- `permissions` jsonb not null default `{}`
- `last_heartbeat_at` timestamptz null
- `metadata` jsonb null
Invariants:
- agent and manager must be in same company
- no cycles in reporting tree
- `terminated` agents cannot be resumed
## 7.3 `agent_api_keys`
- `id` uuid pk
- `agent_id` uuid fk `agents.id` not null
- `company_id` uuid fk `companies.id` not null
- `name` text not null
- `key_hash` text not null
- `last_used_at` timestamptz null
- `revoked_at` timestamptz null
Invariant: plaintext key shown once at creation; only hash stored.
## 7.4 `goals`
- `id` uuid pk
- `company_id` uuid fk not null
- `title` text not null
- `description` text null
- `level` enum: `company | team | agent | task`
- `parent_id` uuid fk `goals.id` null
- `owner_agent_id` uuid fk `agents.id` null
- `status` enum: `planned | active | achieved | cancelled`
Invariant: at least one root `company` level goal per company.
## 7.5 `projects`
- `id` uuid pk
- `company_id` uuid fk not null
- `goal_id` uuid fk `goals.id` null
- `name` text not null
- `description` text null
- `status` enum: `backlog | planned | in_progress | completed | cancelled`
- `lead_agent_id` uuid fk `agents.id` null
- `target_date` date null
- `env` jsonb null (same secret-aware env binding format used by agent config)
Invariant:
- project env is merged into run environment for issues in that project and overrides conflicting agent env keys before Paperclip runtime-owned keys are injected
## 7.6 `issues` (core task entity)
- `id` uuid pk
- `company_id` uuid fk not null
- `project_id` uuid fk `projects.id` null
- `project_workspace_id` uuid fk `project_workspaces.id` null
- `goal_id` uuid fk `goals.id` null
- `parent_id` uuid fk `issues.id` null
- `title` text not null
- `description` text null
- `status` enum: `backlog | todo | in_progress | in_review | done | blocked | cancelled`
- `priority` enum: `critical | high | medium | low`
- `assignee_agent_id` uuid fk `agents.id` null
- `assignee_user_id` text null
- checkout/execution locks: `checkout_run_id`, `execution_run_id`, `execution_agent_name_key`, `execution_locked_at`
- `created_by_agent_id` uuid fk `agents.id` null
- `created_by_user_id` uuid fk `users.id` null
- identifier fields: `issue_number`, `identifier`
- origin fields: `origin_kind`, `origin_id`, `origin_run_id`, `origin_fingerprint`
- `request_depth` int not null default 0
- `billing_code` text null
- `assignee_adapter_overrides` jsonb null
- `execution_policy` jsonb null
- `execution_state` jsonb null
- execution workspace fields: `execution_workspace_id`, `execution_workspace_preference`, `execution_workspace_settings`
- `started_at` timestamptz null
- `completed_at` timestamptz null
- `cancelled_at` timestamptz null
- `hidden_at` timestamptz null
Invariants:
- single assignee only
- task must trace to company goal chain via `goal_id`, `parent_id`, or project-goal linkage
- `in_progress` requires assignee
- terminal states: `done | cancelled`
## 7.7 `issue_comments`
- `id` uuid pk
- `company_id` uuid fk not null
- `issue_id` uuid fk `issues.id` not null
- `author_agent_id` uuid fk `agents.id` null
- `author_user_id` uuid fk `users.id` null
- `body` text not null
## 7.8 `heartbeat_runs`
- `id` uuid pk
- `company_id` uuid fk not null
- `agent_id` uuid fk not null
- `invocation_source` enum: `scheduler | manual | callback`
- `status` enum: `queued | running | succeeded | failed | cancelled | timed_out`
- `started_at` timestamptz null
- `finished_at` timestamptz null
- `error` text null
- `external_run_id` text null
- `context_snapshot` jsonb null
## 7.9 `cost_events`
- `id` uuid pk
- `company_id` uuid fk not null
- `agent_id` uuid fk `agents.id` not null
- `issue_id` uuid fk `issues.id` null
- `project_id` uuid fk `projects.id` null
- `goal_id` uuid fk `goals.id` null
- `billing_code` text null
- `provider` text not null
- `model` text not null
- `input_tokens` int not null default 0
- `output_tokens` int not null default 0
- `cost_cents` int not null
- `occurred_at` timestamptz not null
Invariant: each event must attach to agent and company; rollups are aggregation, never manually edited.
## 7.10 `approvals`
- `id` uuid pk
- `company_id` uuid fk not null
- `type` enum: `hire_agent | approve_ceo_strategy | budget_override_required | request_board_approval`
- `requested_by_agent_id` uuid fk `agents.id` null
- `requested_by_user_id` uuid fk `users.id` null
- `status` enum: `pending | revision_requested | approved | rejected | cancelled`
- `payload` jsonb not null
- `decision_note` text null
- `decided_by_user_id` uuid fk `users.id` null
- `decided_at` timestamptz null
## 7.11 `activity_log`
- `id` uuid pk
- `company_id` uuid fk not null
- `actor_type` enum: `agent | user | system`
- `actor_id` uuid/text not null
- `action` text not null
- `entity_type` text not null
- `entity_id` uuid/text not null
- `details` jsonb null
- `created_at` timestamptz not null default now()
## 7.12 `company_secrets` + `company_secret_versions`
- Secret values are not stored inline in `agents.adapter_config.env`.
- Agent env entries should use secret refs for sensitive values.
- `company_secrets` tracks identity/provider metadata per company.
- `company_secret_versions` stores encrypted/reference material per version.
- Default provider in local deployments: `local_encrypted`.
Operational policy:
- Config read APIs redact sensitive plain values.
- Activity and approval payloads must not persist raw sensitive values.
- Config revisions may include redacted placeholders; such revisions are non-restorable for redacted fields.
## 7.13 Required Indexes
- `agents(company_id, status)`
- `agents(company_id, reports_to)`
- `issues(company_id, status)`
- `issues(company_id, assignee_agent_id, status)`
- `issues(company_id, parent_id)`
- `issues(company_id, project_id)`
- `cost_events(company_id, occurred_at)`
- `cost_events(company_id, agent_id, occurred_at)`
- `heartbeat_runs(company_id, agent_id, started_at desc)`
- `approvals(company_id, status, type)`
- `activity_log(company_id, created_at desc)`
- `assets(company_id, created_at desc)`
- `assets(company_id, object_key)` unique
- `issue_attachments(company_id, issue_id)`
- `company_secrets(company_id, name)` unique
- `company_secret_versions(secret_id, version)` unique
## 7.14 `assets` + `issue_attachments`
- `assets` stores provider-backed object metadata (not inline bytes):
- `id` uuid pk
- `company_id` uuid fk not null
- `provider` enum/text (`local_disk | s3`)
- `object_key` text not null
- `content_type` text not null
- `byte_size` int not null
- `sha256` text not null
- `original_filename` text null
- `created_by_agent_id` uuid fk null
- `created_by_user_id` uuid/text fk null
- `issue_attachments` links assets to issues/comments:
- `id` uuid pk
- `company_id` uuid fk not null
- `issue_id` uuid fk not null
- `asset_id` uuid fk not null
- `issue_comment_id` uuid fk null
## 7.15 `documents` + `document_revisions` + `issue_documents`
- `documents` stores editable text-first documents:
- `id` uuid pk
- `company_id` uuid fk not null
- `title` text null
- `format` text not null (`markdown`)
- `latest_body` text not null
- `latest_revision_id` uuid null
- `latest_revision_number` int not null
- `created_by_agent_id` uuid fk null
- `created_by_user_id` uuid/text fk null
- `updated_by_agent_id` uuid fk null
- `updated_by_user_id` uuid/text fk null
- `document_revisions` stores append-only history:
- `id` uuid pk
- `company_id` uuid fk not null
- `document_id` uuid fk not null
- `revision_number` int not null
- `body` text not null
- `change_summary` text null
- `issue_documents` links documents to issues with a stable workflow key:
- `id` uuid pk
- `company_id` uuid fk not null
- `issue_id` uuid fk not null
- `document_id` uuid fk not null
- `key` text not null (`plan`, `design`, `notes`, etc.)
## 7.16 Current Implementation Addenda
The current implementation includes additional V1-control-plane tables beyond the original February snapshot:
- Issue structure and review: `issue_relations` for blockers, `labels`/`issue_labels`, `issue_thread_interactions`, `issue_approvals`, `issue_execution_decisions`, `issue_work_products`, `issue_inbox_archives`, `issue_read_states`, and issue reference mention indexes.
- Execution and workspace control: `execution_workspaces`, `project_workspaces`, `workspace_runtime_services`, `workspace_operations`, `environments`, `environment_leases`, `agent_task_sessions`, `agent_runtime_state`, `agent_wakeup_requests`, heartbeat events, and watchdog decision tables.
- Plugins and routines: `plugins`, plugin config/state/entities/jobs/logs/webhooks, plugin database namespaces/migrations, plugin company settings, and `routines`.
- Access and operations: company memberships, instance roles, principal permission grants, invites, join requests, board API keys, CLI auth challenges, budget policies/incidents, feedback exports/votes, company skills, sidebar preferences, and company logos.
## 8. State Machines
## 8.1 Agent Status
Allowed transitions:
- `idle -> running`
- `running -> idle`
- `running -> error`
- `error -> idle`
- `idle -> paused`
- `running -> paused` (requires cancel flow)
- `paused -> idle`
- `* -> terminated` (board only, irreversible)
## 8.2 Issue Status
Allowed transitions:
- `backlog -> todo | cancelled`
- `todo -> in_progress | blocked | cancelled`
- `in_progress -> in_review | blocked | done | cancelled`
- `in_review -> in_progress | done | cancelled`
- `blocked -> todo | in_progress | cancelled`
- terminal: `done`, `cancelled`
Side effects:
- entering `in_progress` sets `started_at` if null
- entering `done` sets `completed_at`
- entering `cancelled` sets `cancelled_at`
V1 non-terminal liveness rule:
- agent-owned `todo`, `in_progress`, `in_review`, and `blocked` issues must have a live execution path, an explicit waiting path, or an explicit recovery path
- `in_review` is healthy only when a typed execution participant, pending issue-thread interaction or approval, user owner, active run, queued wake, or explicit recovery issue owns the next action
- a blocked chain is covered only when each unresolved leaf issue is live or explicitly waiting
- when Paperclip cannot safely infer the next action, it surfaces the problem through visible blocked/recovery work instead of silently completing or reassigning work
Detailed ownership, execution, blocker, active-run watchdog, crash-recovery, and non-terminal liveness semantics are documented in `doc/execution-semantics.md`.
## 8.3 Approval Status
- `pending -> approved | rejected | cancelled`
- terminal after decision
## 9. Auth and Permissions
## 9.1 Board Auth
- Session-based auth for human operator
- Board has full read/write across all companies in deployment
- Every board mutation writes to `activity_log`
## 9.2 Agent Auth
- Bearer API key mapped to one agent and company
- Agent key scope:
- read org/task/company context for own company
- read/write own assigned tasks and comments
- create tasks/comments for delegation
- report heartbeat status
- report cost events
- Agent cannot:
- bypass approval gates
- modify company-wide budgets directly
- mutate auth/keys
## 9.3 Permission Matrix (V1)
| Action | Board | Agent |
|---|---|---|
| Create company | yes | no |
| Hire/create agent | yes (direct) | request via approval |
| Pause/resume agent | yes | no |
| Create/update task | yes | yes |
| Force reassign task | yes | limited |
| Approve strategy/hire requests | yes | no |
| Report cost | yes | yes |
| Set company budget | yes | no |
| Set subordinate budget | yes | yes (manager subtree only) |
## 10. API Contract (REST)
All endpoints are under `/api` and return JSON.
## 10.1 Companies
- `GET /companies`
- `POST /companies`
- `GET /companies/:companyId`
- `PATCH /companies/:companyId`
- `PATCH /companies/:companyId/branding`
- `POST /companies/:companyId/archive`
## 10.2 Goals
- `GET /companies/:companyId/goals`
- `POST /companies/:companyId/goals`
- `GET /goals/:goalId`
- `PATCH /goals/:goalId`
- `DELETE /goals/:goalId` (soft delete optional, hard delete board-only)
## 10.3 Agents
- `GET /companies/:companyId/agents`
- `POST /companies/:companyId/agents`
- `GET /agents/:agentId`
- `PATCH /agents/:agentId`
- `POST /agents/:agentId/pause`
- `POST /agents/:agentId/resume`
- `POST /agents/:agentId/terminate`
- `POST /agents/:agentId/keys` (create API key)
- `POST /agents/:agentId/heartbeat/invoke`
## 10.4 Tasks (Issues)
- `GET /companies/:companyId/issues`
- `POST /companies/:companyId/issues`
- `GET /issues/:issueId`
- `PATCH /issues/:issueId`
- `GET /issues/:issueId/documents`
- `GET /issues/:issueId/documents/:key`
- `PUT /issues/:issueId/documents/:key`
- `GET /issues/:issueId/documents/:key/revisions`
- `DELETE /issues/:issueId/documents/:key`
- `POST /issues/:issueId/checkout`
- `POST /issues/:issueId/release`
- `POST /issues/:issueId/admin/force-release` (board-only lock recovery)
- `POST /issues/:issueId/comments`
- `GET /issues/:issueId/comments`
- `POST /companies/:companyId/issues/:issueId/attachments` (multipart upload)
- `GET /issues/:issueId/attachments`
- `GET /attachments/:attachmentId/content`
- `DELETE /attachments/:attachmentId`
### 10.4.1 Atomic Checkout Contract
`POST /issues/:issueId/checkout` request:
```json
{
"agentId": "uuid",
"expectedStatuses": ["todo", "backlog", "blocked", "in_review"]
}
```
Server behavior:
1. single SQL update with `WHERE id = ? AND status IN (?) AND (assignee_agent_id IS NULL OR assignee_agent_id = :agentId)`
2. if updated row count is 0, return `409` with current owner/status
3. successful checkout sets `assignee_agent_id`, `status = in_progress`, and `started_at`
`POST /issues/:issueId/admin/force-release` is an operator recovery endpoint for stale harness locks. It requires board access to the issue company, clears checkout and execution run lock fields, and may clear the agent assignee when `clearAssignee=true` is passed. The route must write an `issue.admin_force_release` activity log entry containing the previous checkout and execution run IDs.
## 10.5 Projects
- `GET /companies/:companyId/projects`
- `POST /companies/:companyId/projects`
- `GET /projects/:projectId`
- `PATCH /projects/:projectId`
## 10.6 Approvals
- `GET /companies/:companyId/approvals?status=pending`
- `POST /companies/:companyId/approvals`
- `POST /approvals/:approvalId/approve`
- `POST /approvals/:approvalId/reject`
## 10.7 Cost and Budgets
- `POST /companies/:companyId/cost-events`
- `GET /companies/:companyId/costs/summary`
- `GET /companies/:companyId/costs/by-agent`
- `GET /companies/:companyId/costs/by-project`
- `PATCH /companies/:companyId/budgets`
- `PATCH /agents/:agentId/budgets`
## 10.8 Activity and Dashboard
- `GET /companies/:companyId/activity`
- `GET /companies/:companyId/dashboard`
Dashboard payload must include:
- active/running/paused/error agent counts
- open/in-progress/blocked/done issue counts
- month-to-date spend and budget utilization
- pending approvals count
## 10.9 Error Semantics
- `400` validation error
- `401` unauthenticated
- `403` unauthorized
- `404` not found
- `409` state conflict (checkout conflict, invalid transition)
- `422` semantic rule violation
- `500` server error
## 10.10 Current Implementation API Addenda
The current app also exposes V1-supporting surfaces for:
- issue thread interactions (`suggest_tasks`, `ask_user_questions`, `request_confirmation`)
- issue approvals, issue references/search, labels, read state, inbox/archive state, and work products
- execution workspaces, project workspaces, workspace runtime services, and workspace operations
- routines and scheduled/API/webhook triggers
- plugin installation, configuration, state, jobs, logs, webhooks, and plugin database namespace migration
- company import/export preview/apply, feedback export/vote routes, instance backup/config routes, invites, join requests, memberships, and permission grants
## 11. Heartbeat and Adapter Contract
## 11.1 Adapter Interface
```ts
interface AgentAdapter {
invoke(agent: Agent, context: InvocationContext): Promise<InvokeResult>;
status(run: HeartbeatRun): Promise<RunStatus>;
cancel(run: HeartbeatRun): Promise<void>;
}
```
## 11.2 Process Adapter
Config shape:
```json
{
"command": "string",
"args": ["string"],
"cwd": "string",
"env": {"KEY": "VALUE"},
"timeoutSec": 900,
"graceSec": 15
}
```
Behavior:
- spawn child process
- stream stdout/stderr to run logs
- mark run status on exit code/timeout
- cancel sends SIGTERM then SIGKILL after grace
## 11.3 HTTP Adapter
Config shape:
```json
{
"url": "https://...",
"method": "POST",
"headers": {"Authorization": "Bearer ..."},
"timeoutMs": 15000,
"payloadTemplate": {"agentId": "{{agent.id}}", "runId": "{{run.id}}"}
}
```
Behavior:
- invoke by outbound HTTP request
- 2xx means accepted
- non-2xx marks failed invocation
- optional callback endpoint allows asynchronous completion updates
## 11.4 Context Delivery
- `thin`: send IDs and pointers only; agent fetches context via API
- `fat`: include current assignments, goal summary, budget snapshot, and recent comments
## 11.5 Scheduler Rules
Per-agent schedule fields in `adapter_config`:
- `enabled` boolean
- `intervalSec` integer (minimum 30)
- `maxConcurrentRuns` integer; new agents default to `20`; scheduler clamps configured values to `1..50`
Scheduler must skip invocation when:
- agent is paused/terminated
- an existing run is active
- hard budget limit has been hit
## 12. Governance and Approval Flows
## 12.1 Hiring
1. Agent or board creates `approval(type=hire_agent, status=pending, payload=agent draft)`.
2. Board approves or rejects.
3. On approval, server creates agent row and initial API key (optional).
4. Decision is logged in `activity_log`.
Board can bypass request flow and create agents directly via UI; direct create is still logged as a governance action.
## 12.2 CEO Strategy Approval
1. CEO posts strategy proposal as `approval(type=approve_ceo_strategy)`.
2. Board reviews payload (plan text, initial structure, high-level tasks).
3. Approval unlocks execution state for CEO-created delegated work.
Before first strategy approval, CEO may only draft tasks, not transition them to active execution states.
## 12.3 Board Override
Board can at any time:
- pause/resume/terminate any agent
- reassign or cancel any task
- edit budgets and limits
- approve/reject/cancel pending approvals
## 13. Cost and Budget System
## 13.1 Budget Layers
- company monthly budget
- agent monthly budget
- optional project budget (if configured)
## 13.2 Enforcement Rules
- soft alert default threshold: 80%
- hard limit: at 100%, trigger:
- set agent status to `paused`
- block new checkout/invocation for that agent
- emit high-priority activity event
Board may override by raising budget or explicitly resuming agent.
## 13.3 Cost Event Ingestion
`POST /companies/:companyId/cost-events` body:
```json
{
"agentId": "uuid",
"issueId": "uuid",
"provider": "openai",
"model": "gpt-5",
"inputTokens": 1234,
"outputTokens": 567,
"costCents": 89,
"occurredAt": "2026-02-17T20:25:00Z",
"billingCode": "optional"
}
```
Validation:
- non-negative token counts
- `costCents >= 0`
- company ownership checks for all linked entities
## 13.4 Rollups
Read-time aggregate queries are acceptable for V1.
Materialized rollups can be added later if query latency exceeds targets.
## 14. UI Requirements (Board App)
V1 UI routes:
- `/` dashboard
- `/companies` company list/create
- `/companies/:id/org` org chart and agent status
- `/companies/:id/tasks` task list/kanban
- `/companies/:id/agents/:agentId` agent detail
- `/companies/:id/costs` cost and budget dashboard
- `/companies/:id/approvals` pending/history approvals
- `/companies/:id/activity` audit/event stream
Required UX behaviors:
- global company selector
- quick actions: pause/resume agent, create task, approve/reject request
- conflict toasts on atomic checkout failure
- no silent background failures; every failed run visible in UI
## 15. Operational Requirements
## 15.1 Environment
- Node 20+
- `DATABASE_URL` optional
- if unset, auto-use embedded PostgreSQL under `~/.paperclip/instances/default/db`
## 15.2 Migrations
- Drizzle migrations are source of truth
- local/dev startup applies pending migrations automatically where supported
- `pnpm db:migrate` applies pending migrations manually
- no destructive migration in-place for V1 upgrade path
## 15.3 Logging and Audit
- structured logs (JSON in production)
- request ID per API call
- every mutation writes `activity_log`
## 15.4 Reliability Targets
- API p95 latency under 250 ms for standard CRUD at 1k tasks/company
- heartbeat invoke acknowledgement under 2 s for process adapter
- no lost approval decisions (transactional writes)
## 16. Security Requirements
- store only hashed agent API keys
- redact secrets in logs (`adapter_config`, auth headers, env vars)
- CSRF protection for board session endpoints
- rate limit auth and key-management endpoints
- strict company boundary checks on every entity fetch/mutation
## 17. Testing Strategy
## 17.1 Unit Tests
- state transition guards (agent, issue, approval)
- budget enforcement rules
- adapter invocation/cancel semantics
## 17.2 Integration Tests
- atomic checkout conflict behavior
- approval-to-agent creation flow
- cost ingestion and rollup correctness
- pause while run is active (graceful cancel then force kill)
## 17.3 End-to-End Tests
- board creates company -> hires CEO -> approves strategy -> CEO receives work
- agent reports cost -> budget threshold reached -> auto-pause occurs
- task delegation across teams with request depth increment
## 17.4 Regression Suite Minimum
A release candidate is blocked unless these pass:
1. auth boundary tests
2. checkout race test
3. hard budget stop test
4. agent pause/resume test
5. dashboard summary consistency test
## 18. Delivery Plan
Current implementation note: the milestones below describe the original V1 sequencing. Several systems originally framed as future work have since shipped or advanced materially, including issue documents/interactions, blockers, routines, execution workspaces, import/export portability, authenticated deployment modes, multi-user basics, and the local/self-hosted plugin runtime.
## Milestone 1: Company Core and Auth
- add `companies` and company scoping to existing entities
- add board session auth and agent API keys
- migrate existing API routes to company-aware paths
## Milestone 2: Task and Governance Semantics
- implement atomic checkout endpoint
- implement issue comments and lifecycle guards
- implement approvals table and hire/strategy workflows
## Milestone 3: Heartbeat and Adapter Runtime
- implement adapter interface
- ship `process` adapter with cancel semantics
- ship `http` adapter with timeout/error handling
- persist heartbeat runs and statuses
## Milestone 4: Cost and Budget Controls
- implement cost events ingestion
- implement monthly rollups and dashboards
- enforce hard limit auto-pause
## Milestone 5: Board UI Completion
- add company selector and org chart view
- add approvals and cost pages
## Milestone 6: Hardening and Release
- full integration/e2e suite
- seed/demo company templates for local testing
- release checklist and docs update
## 19. Acceptance Criteria (Release Gate)
V1 is complete only when all criteria are true:
1. A board user can create multiple companies and switch between them.
2. A company can run at least one active heartbeat-enabled agent.
3. Task checkout is conflict-safe with `409` on concurrent claims.
4. Agents can update tasks/comments and report costs with API keys only.
5. Board can approve/reject hire and CEO strategy requests in UI.
6. Budget hard limit auto-pauses an agent and prevents new invocations.
7. Dashboard shows accurate counts/spend from live DB data.
8. Every mutation is auditable in activity log.
9. App runs with embedded PostgreSQL by default and with external Postgres via `DATABASE_URL`.
## 20. Post-V1 Backlog (Explicitly Deferred)
- cloud-grade plugin marketplace/distribution
- richer workflow-state customization per team
- milestones/labels/dependency graph depth beyond V1 minimum
- realtime transport optimization (SSE/WebSockets)
- public template marketplace integration (ClipHub)
## 21. Company Portability Package (V1 Addendum)
V1 supports company import/export using a portable package contract:
- markdown-first package rooted at `COMPANY.md`
- implicit folder discovery by convention
- `.paperclip.yaml` sidecar for Paperclip-specific fidelity
- canonical base package is vendor-neutral and aligned with `docs/companies/companies-spec.md`
- common conventions:
- `agents/<slug>/AGENTS.md`
- `teams/<slug>/TEAM.md`
- `projects/<slug>/PROJECT.md`
- `projects/<slug>/tasks/<slug>/TASK.md`
- `tasks/<slug>/TASK.md`
- `skills/<slug>/SKILL.md`
Export/import behavior in V1:
- export emits a clean vendor-neutral markdown package plus `.paperclip.yaml`
- projects and starter tasks are opt-in export content rather than default package content
- recurring `TASK.md` entries use `recurring: true` in the base package and Paperclip routine fidelity in `.paperclip.yaml`
- Paperclip imports recurring task packages as routines instead of downgrading them to one-time issues
- export strips environment-specific paths (`cwd`, local instruction file paths, inline prompt duplication) while preserving portable project repo/workspace metadata such as `repoUrl`, refs, and workspace-policy references keyed in `.paperclip.yaml`
- export never includes secret values; env inputs are reported as portable declarations instead
- import supports target modes:
- create a new company
- import into an existing company
- import recreates exported project workspaces and remaps portable workspace keys back to target-local workspace ids
- import forces imported agent timer heartbeats off so packages never start scheduled runs implicitly
- import supports collision strategies: `rename`, `skip`, `replace`
- import supports preview (dry-run) before apply
- GitHub imports warn on unpinned refs instead of blocking
View Git Blame Copy Permalink