> ## Documentation Index > Fetch the complete documentation index at: https://docs-omnicoreagent.omnirexfloralabs.com/llms.txt > Use this file to discover all available pages before exploring further. # Agent settings > Every key agent_config takes, its default, and what it does # Agent settings Everything `OmniCoreAgent(agent_config={...})` takes. Each description is the comment above the setting in the code. | Setting | Type | Default | What it does | | -------------------------- | ------------------------------------------- | --------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `agent_version` | `str \| None` | `None` | Recorded as the trace's agent\_version; a content hash of the harness (prompt, tools, model, and settings) is used when it is not set. | | `request_limit` | `int` | `0` | Most model calls one run may make, and most tokens (in and out) it may use; over either, the run ends with termination\_reason resource\_limit. 0 is no limit. For limits in dollars, use governance budgets. | | `total_tokens_limit` | `int` | `0` | Most model calls one run may make, and most tokens (in and out) it may use; over either, the run ends with termination\_reason resource\_limit. 0 is no limit. For limits in dollars, use governance budgets. | | `max_steps` | `int` | `50` | Most model turns one run may take; then it ends with termination\_reason max\_steps. 1 to 1000. | | `tool_call_timeout` | `int` | `180` | Seconds one tool call may take before it fails with a timeout. 2 to 1000. | | `subagent_timeout` | `int \| None` | `None` | Seconds a delegation (spawn\_subagents) may take. None: a worker is bounded by its own step cap and the run's deadline, not by the timeout for one tool call. | | `mcp_enabled` | `bool` | `False` | Accepted for compatibility with 0.3.x and has no effect: MCP is on when mcp\_tools are given. | | `enable_advanced_tool_use` | `bool` | `False` | For large tool sets: a tools\_retriever tool the model uses to find tools by describing what it needs; the matching tools are offered on the next turn. | | `enable_subagents` | `bool` | `False` | Let the agent spawn focused workers (spawn\_subagents), each under the same policy and budgets with its own linked trace. Turns workspace files on. | | `enable_agent_skills` | `bool` | `False` | Offer the skills found in skills\_dir: their instructions, files and scripts. | | `skills_dir` | `str \| None` | `None` | Where skills are found; None is ./.agents/skills in the working directory. A harness names its own, so the task's directory stays the task's. | | `completion_review` | `int` | `0` | How many times a final answer is reviewed before it is accepted: the model is asked for each requirement and the check that showed it, and the run goes on in the same trace. Off by default. | | `skill_script_env` | `list[str]` | `[]` | Environment variables host skill scripts receive beyond the minimal set (PATH, HOME, locale, TMPDIR, TERM); secrets are not passed by default. | | `run_lease_seconds` | `int` | `60` | A live run refreshes its heartbeat within this many seconds; a run whose heartbeat is older can be recovered by another process. | | `code_mode` | `dict[str, Any]` | `{}` | Code mode: a run\_code tool that runs Python in Monty (omnicoreagent\[codemode]). | | `agents_md` | `dict[str, Any]` | `{}` | A project's own instructions for the agent (AGENTS.md), by path. | | `memory_config` | `dict[str, Any]` | see below | How much of a session's history a run is given: a sliding window of messages or tokens, and optional summaries of what falls out of it. | | `enable_workspace_files` | `bool` | `True` | File tools over the agent's workspace (ls, read\_file, write\_file, edit\_file, glob, grep, ...). The workspace itself is set by workspace\_config. | | `guardrail_config` | `dict[str, Any]` | `{}` | The prompt-injection guardrail: guardrail\_mode is full (input and tool results), input\_only, or off; guardrail\_config tunes its detection. | | `guardrail_mode` | `str` | `"full"` | The prompt-injection guardrail: guardrail\_mode is full (input and tool results), input\_only, or off; guardrail\_config tunes its detection. | | `privacy_config` | `dict[str, Any]` | see below | Personal data (email, phone, SSN, card numbers) redacted per boundary. By default only the record (telemetry and its exports) is redacted; the model, memory, files, stream and answer see the real data. | | `context_management` | `dict[str, Any]` | see below | Keeps a run's context under a token budget before each model call: past threshold\_percent of value, older messages are truncated or summarized, keeping the preserve\_recent latest. | | `tool_offload` | `dict[str, Any]` | see below | A tool result over the thresholds is saved to the workspace, and the model gets a preview and an artifact it can read in full. | | `governance_config` | `dict[str, Any]` | see below | The policy (a profile, a policy, or a policy file), budgets, the sandbox provider and its manifest, and how unanswered approvals are handled. Off by default; see the security model. | | `workspace_config` | `WorkspaceConfig \| dict[str, Any] \| None` | `None` | Where the agent's workspace lives: workspace\_dir on local disk (default ./workspace), or S3 / R2 storage. | ## Defaults in full ### `memory_config` How much of a session's history a run is given: a sliding window of messages or tokens, and optional summaries of what falls out of it. ```json theme={"theme":{"light":"github-light","dark":"github-dark"}} { "mode": "sliding_window", "summary": { "enabled": false, "retention_policy": "keep" }, "value": 10000 } ``` ### `privacy_config` Personal data (email, phone, SSN, card numbers) redacted per boundary. By default only the record (telemetry and its exports) is redacted; the model, memory, files, stream and answer see the real data. ```json theme={"theme":{"light":"github-light","dark":"github-dark"}} { "categories": [ "credit_card", "email", "phone", "ssn" ], "enabled": true, "redact_memory": false, "redact_model_io": false, "redact_public": false, "redact_stream": false, "redact_telemetry": true, "redact_workspace": false } ``` ### `context_management` Keeps a run's context under a token budget before each model call: past threshold\_percent of value, older messages are truncated or summarized, keeping the preserve\_recent latest. ```json theme={"theme":{"light":"github-light","dark":"github-dark"}} { "enabled": true, "mode": "token_budget", "preserve_recent": 4, "strategy": "truncate", "threshold_percent": 75, "value": 100000 } ``` ### `tool_offload` A tool result over the thresholds is saved to the workspace, and the model gets a preview and an artifact it can read in full. ```json theme={"theme":{"light":"github-light","dark":"github-dark"}} { "enabled": true, "max_preview_lines": 10, "max_preview_tokens": 150, "threshold_bytes": 2000, "threshold_tokens": 500 } ``` ### `governance_config` The policy (a profile, a policy, or a policy file), budgets, the sandbox provider and its manifest, and how unanswered approvals are handled. Off by default; see the security model. ```json theme={"theme":{"light":"github-light","dark":"github-dark"}} { "allow_static_high_risk_approvals": false, "allow_test_sandbox_runtime": false, "approval_mode": "suspend", "approval_resolver": null, "budgets": null, "enabled": false, "policy": null, "policy_path": null, "profile": "interactive-dev", "project_root": null, "sandbox_config": null, "sandbox_manifest": null, "sandbox_runtime": null, "workspace_bridge": null } ```