Search

model_context_window: manual context window token setting for the active model.

model_auto_compact_token_limit: token threshold for automatic history compaction.

model_catalog_json: load a custom model catalog file.

model_instructions_file: replace built-in instructions with a file.

model_reasoning_summary: control reasoning summary detail.

model_supports_reasoning_summaries: force-enable or force-disable reasoning metadata handling.

model_verbosity: GPT-5 verbosity override.

review_model: separate review-only model.

service_tier: preferred tier for new turns.

oss_provider: choose lmstudio or ollama for --oss.

web_search: global search mode, disabled | cached | live.

tools.web_search: per-tool search config; object form supports context_size, allowed_domains, and location.

tools.view_image: enable/disable the local image-viewing tool.

apps._default.enabled: default app/connector enablement.

apps._default.destructive_enabled: default permission for destructive app tools.

apps._default.open_world_enabled: default permission for open-world app tools.

apps.<id>.enabled: enable/disable a specific app.

apps.<id>.destructive_enabled: allow destructive tools for one app.

apps.<id>.open_world_enabled: allow open-world tools for one app.

apps.<id>.default_tools_enabled: default tool enablement for one app.

apps.<id>.default_tools_approval_mode: default approval mode for one app’s tools.

apps.<id>.tools.<tool>.enabled: enable/disable one specific app tool.

apps.<id>.tools.<tool>.approval_mode: set approval behavior for one app tool.

mcp_servers.<id>.env: env vars passed to an MCP stdio server.

mcp_servers.<id>.env_vars: whitelist extra inherited env vars for an MCP server.

mcp_servers.<id>.cwd: working directory for an MCP stdio server.
mcp_servers.<id>.http_headers: static headers for MCP HTTP servers.

mcp_servers.<id>.env_http_headers: headers sourced from env vars.

mcp_servers.<id>.enabled: disable a configured MCP server without deleting it.

mcp_servers.<id>.required: fail startup/resume if that server is unavailable.

mcp_servers.<id>.startup_timeout_ms: millisecond alias of startup timeout.

mcp_servers.<id>.tool_timeout_sec: per-tool MCP timeout.

mcp_servers.<id>.enabled_tools: allowlist exposed MCP tools.

mcp_servers.<id>.disabled_tools: denylist exposed MCP tools.

mcp_servers.<id>.scopes: OAuth scopes to request.

mcp_servers.<id>.oauth_resource: optional OAuth resource parameter.

agents.max_threads: maximum concurrent agent threads.

agents.max_depth: maximum nested agent depth.

agents.job_max_runtime_seconds: default worker runtime for agent jobs.

agents.<name>.description: role guidance for a named agent type.

agents.<name>.config_file: TOML overlay file for that agent role.

agents.<name>.nickname_candidates: display nicknames for that role.

approval_policy.granular.sandbox_approval: allow sandbox escalation prompts.

approval_policy.granular.rules: allow prompts triggered by execpolicy rules.

approval_policy.granular.mcp_elicitations: allow MCP elicitation prompts.

approval_policy.granular.request_permissions: allow request_permissions prompts.

approval_policy.granular.skill_approval: allow skill-script approval prompts.

allow_login_shell: allow login-shell semantics for shell tools.

default_permissions: choose a named permissions profile by default.

permissions.<name>.filesystem: define filesystem permissions profile.

permissions.<name>.filesystem.<path>: read/write/none for a specific path.

permissions.<name>.filesystem.":project_roots".<subpath>: scoped access relative to project roots.

permissions.<name>.network.enabled: enable network in that profile.

permissions.<name>.network.mode: limited | full.

permissions.<name>.network.proxy_url: HTTP proxy.

permissions.<name>.network.socks_url: SOCKS proxy.

permissions.<name>.network.enable_socks5: expose SOCKS5 listener.

permissions.<name>.network.enable_socks5_udp: allow UDP via SOCKS5.

permissions.<name>.network.allow_upstream_proxy: allow chained proxying.

permissions.<name>.network.allowed_domains: network allowlist.

permissions.<name>.network.denied_domains: network denylist.

permissions.<name>.network.allow_unix_sockets: allow specific Unix sockets.

permissions.<name>.network.allow_local_binding: allow local bind/listen.

permissions.<name>.network.dangerously_allow_non_loopback_proxy: allow non-loopback proxy listener.

permissions.<name>.network.dangerously_allow_all_unix_sockets: allow arbitrary Unix sockets.

sandbox_workspace_write.writable_roots: extra writable roots in workspace-write mode.