mirror of https://github.com/rennf93/roboco.git synced 2026-08-03 07:23:24 +02:00

Files

T

Renn F 68094d5f2a docs(0.7.0): document Grok provider, self-heal, PR-reviewer across the RAG + how-to docs

Close the doc gaps the audit found in the agent knowledge base and the human
walkthrough:
- config-reference: add the Grok provider env table (host ~/.grok subscription
  mount, grok-build, idle-kill, cost cap) and the Self-Healing CI loop toggles.
- agent-model: provider-aware Model Configuration (ANTHROPIC default / GROK) +
  add the pr_reviewer / prompter / secretary roles to the Roles table.
- tool-permissions: 'three' -> five MCP servers (roboco-optimal, roboco-docs) +
  PR Reviewer / Prompter / Secretary tool sections.
- new roles/pr-reviewer.md (the 22nd agent had no role doc); permissions +
  agent-uuids + task-tools 'PR Reviewer flow' all gain the role.
- api-endpoints: drop the removed USAGE_UPDATE event (only USAGE_SNAPSHOT exists).
- how-to: self-healing CI loop + Company Scorecard (ch.5), inbound external-PR
  review + CEO Supersede/Dismiss queue (ch.4).

Every claim verified against current code by the audit (grok model grok-build,
auth ~/.grok, no metered API; opencode fully removed).

2026-06-19 10:50:58 +02:00

2.4 KiB

Raw Blame History

Agent Model

Core Fields

Field	Type	Description
`id`	UUID	Primary key
`name`	String	Display name
`slug`	String	URL-safe ID (e.g., `be-dev-1`)
`role`	Enum	Agent role
`team`	Enum	Team affiliation
`status`	Enum	active, idle, offline

Roles

Role	Description
`ceo`	Human executive
`product_owner`	Product strategy
`head_marketing`	External comms
`auditor`	Silent observer
`main_pm`	Coordinates all cells
`cell_pm`	Manages one cell
`developer`	Writes code
`qa`	Reviews and tests
`documenter`	Writes documentation
`pr_reviewer`	Read-only reviewer of inbound external/fork + internal PRs (agent `pr-reviewer-1`)
`prompter`	On-demand intake interviewer, human-only (agent `intake-1`)
`secretary`	On-demand chief-of-staff, human-only (agent `secretary-1`)
`system`	Internal orchestrator

Teams

Team	Agents
`backend`	be-pm, be-dev-*, be-qa, be-doc
`frontend`	fe-pm, fe-dev-*, fe-qa, fe-doc
`ux_ui`	ux-pm, ux-dev-*, ux-qa, ux-doc
`main_pm`	main-pm
`board`	product-owner, head-marketing, auditor
`marketing`	head-marketing

Status

Status	Meaning
`active`	Currently working
`idle`	Available for work
`offline`	Not available

Capabilities

Example capabilities:

code_execution
git_operations
documentation
testing

Model Configuration

Stored in model_config JSON:

LLM provider
Model name
Temperature
Other settings

The provider selects the agent backend, resolved through the ProviderRegistry (roboco/llm/providers/). ModelProvider is ANTHROPIC (default — Claude Code), GROK (xAI's official grok CLI, model grok-build, on a SuperGrok subscription), LOCAL, OLLAMA_CLOUD, or OPENAI (reserved). An agent with no dedicated provider falls back to the built-in Claude Code spawn. Grok auth is the host ~/.grok subscription mount (auto-refreshed by the orchestrator), not a metered API key.

Agent-Specific Fields

Field	Description
`current_task_id`	Currently assigned task
`journal_id`	Personal journal
`system_prompt`	Base prompt
`permissions`	Channel access
`metrics`	Performance data

2.4 KiB Raw Blame History