50 lines
3.6 KiB
Markdown
50 lines
3.6 KiB
Markdown
# TOOLS.md - Available Capabilities
|
|
|
|
## Core OS tools
|
|
|
|
- **VFS / Hyperdrive** — read/write paths via agent tools (`read_file`, `write_file`, `list_directory`, …) on system and personal drives.
|
|
- **Service and timer ops** — use `list_services`, `service_status`, and `list_timers` to inspect initd state and timer drop-ins without ad-hoc shell parsing.
|
|
- **Operational logs and policy** — use `read_cron_log`, `read_audit_log`, `read_boot_policy`, and `read_kernel_extension_resolution` for bounded diagnostics.
|
|
- **Extended ops diagnostics** — `get_initd_graph`, `read_unit_journal`, `inspect_ipc_backpressure`, `get_network_summary`, `tail_telemetry_streams`, and `pkg_index_lookup`.
|
|
- **Automation gates** — `list_verification_scripts`, `run_maintenance_gate`, `run_contract_checks`, and `summarize_build_drift` provide safer wrappers for maintenance workflows.
|
|
- **Bridge diagnostics/actions** — `get_hrpc_bridge_health` and `get_hrpc_allowlist_status` are read-focused; `emit_host_notification` and `request_host_action` are policy-gated mutations.
|
|
- **`web_fetch`** — live `http(s)` fetches **only** when the operator allows them (`ctx.httpFetch`, `BARE_OS_HTTP_ALLOWLIST` / denylist). Same policy as delegated `curl` / `wget`.
|
|
- **POSIX-style utilities** — via `run_command` in the guest shell (`/bin/*`); not full GNU.
|
|
- **Swarm / Protomux** — peer discovery and replication are host/booter concerns; you see them through `/proc` and tools like `get_swarm_peers` when exposed.
|
|
- **Identity / crypto** — only with explicit user approval; never exfiltrate keys or vault material.
|
|
|
|
## Reasoning / process visibility
|
|
|
|
- Runtime process visibility can be configured in `~/.agent/config.json`:
|
|
- `show_reasoning` (boolean)
|
|
- `reasoning_mode` (`off`, `summary`, `trace`)
|
|
- `reasoning_max_chars` (bounded output)
|
|
- `reasoning_include_tools` (include tool call/result traces in process output)
|
|
- Use `edit_agent_config` to toggle these safely during a session.
|
|
- For provider `xai`, keep `rest_base_url` at `https://api.x.ai/v1` and prefer trace mode when reasoning summaries are unavailable.
|
|
- For provider `groq`, keep `rest_base_url` at `https://api.groq.com/openai/v1`; tool loops use OpenAI-compatible `chat/completions` with `parallel_tool_calls` and `max_completion_tokens`.
|
|
- For Groq debugging, use trace mode and inspect process logs for provider request shape warnings.
|
|
|
|
## Max-autonomy policy toggles
|
|
|
|
- `allow_bridge_mutations`: master gate for bridge mutation tools.
|
|
- `allow_host_notifications`: required for `emit_host_notification`.
|
|
- `allow_host_actions`: required for `request_host_action`.
|
|
- `emergency_stop_mutations`: immediate kill switch for all mutating bridge tools.
|
|
|
|
## Autonomous coding runner
|
|
|
|
- `autonomous_run` starts autonomous project execution with a goal, runtime cap, and required checks.
|
|
- `autonomous_run_status` reports active state, elapsed/runtime budget, and quality gate configuration.
|
|
- `autonomous_run_stop` requests a safe stop at the next loop checkpoint.
|
|
- Autonomous done criteria require configured checks to pass (for example `coreutils-test`, parity, man coverage) before completion is accepted.
|
|
- Guardrails enforce a denylist for dangerous operations and path restrictions even during autonomous runs.
|
|
|
|
## Skills system
|
|
|
|
The agent has access to modular **skills** under `~/.agent/workspace/skills/` (and optionally shared skills under `~/.agent/skills/`).
|
|
|
|
- A **compact** list of skill ids + short descriptions is included in the system prompt.
|
|
- When a task matches a skill, call the **`read_skill`** tool to load the full `SKILL.md`, then follow it exactly.
|
|
- Prefer using skills over reinventing workflows.
|