А ну и напоследок - у кодекса появилось оказывается ДОХУИЩЕ флажков которыми мож

А ну и напоследок - у кодекса появилось оказывается ДОХУИЩЕ флажков которыми можно управлять своим юзерэкспириенсом. в Codex APP.

Я сегодня многие из них сконфигурил для более лучших результатов =) Например по дефолту там 6 агентов, почему бы не воткнуть 12, и не дать способность каждому агенту спаунить до 3х собственных агентов при надобности?

Ну и там есть вебхуки тоже, что значит что эту же хуйню которую я только что сделал для клода можно клонировать и на кодекс)

Вот список всех флажков для конфига, если кто о них еще не знает:

Best Power Knobs
If your goal is “full possible power mode”, these are the highest-value unused public options:

agents.max_threads: raises concurrent subagent count; this is one of the biggest real “power” knobs. Official default is 6 when unset.
agents.max_depth: lets spawned agents spawn more agents. Default is 1 when unset.
agents.job_max_runtime_seconds: increases worker timeout for long delegated jobs.
web_search: explicitly set search mode. live is the strongest/most current mode.
tools.web_search: tunes search with context_size = "low|medium|high", allowed_domains, and location { country, region, city, timezone }.
tools.view_image: explicitly keeps local image viewing enabled.
review_model: separate stronger model just for /review.
model_reasoning_summary: auto | concise | detailed | none; useful if you want maximum visibility into what Codex is doing.
model_verbosity: low | medium | high; useful if you want fuller answers and richer summaries.
service_tier: flex | fast; this affects responsiveness, not raw intelligence.
model_instructions_file: lets you add a permanent instruction file in addition to or instead of relying on AGENTS.md.
features.codex_hooks: experimental lifecycle hooks. Powerful, but only if you actually want automation around turns.
mcp_servers.<id>.tool_timeout_sec: important if some MCP tools are timing out before finishing.
mcp_servers.<id>.required: forces startup failure if a critical MCP server is unavailable.
Unused Public Options
Grouped by family, with what each one does:

review_model: override model used only by /review.

model_provider: choose which configured provider to use instead of the built-in OpenAI provider.

openai_base_url: override the built-in OpenAI provider base URL.

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.

sandbox_workspace_write.network_access: network access inside workspace-write mode.

sandbox_workspace_write.exclude_tmpdir_env_var: remove $TMPDIR from writable roots.

sandbox_workspace_write.exclude_slash_tmp: remove /tmp from writable roots.

profile: default named profile at startup.

profiles.<name>.*: profile-scoped overrides.

profiles.<name>.service_tier: per-profile tier.

profiles.<name>.plan_mode_reasoning_effort: per-profile plan reasoning.

profiles.<name>.web_search: per-profile search mode.

profiles.<name>.personality: per-profile personality.

profiles.<name>.model_catalog_json: per-profile model catalog.

profiles.<name>.model_instructions_file: per-profile instruction file.

profiles.<name>.experimental_use_unified_exec_tool: legacy unified-exec alias per profile.

profiles.<name>.oss_provider: per-profile OSS provider.

profiles.<name>.tools_view_image: per-profile image tool toggle.

profiles.<name>.analytics.enabled: per-profile analytics.

profiles.<name>.windows.sandbox: per-profile Windows sandbox.

plan_mode_reasoning_effort: dedicated reasoning setting for Plan mode.

model_providers.<id>.name: custom provider display name.

model_providers.<id>.base_url: custom provider base URL.
model_providers.<id>.env_key: env var for provider API key.

model_providers.<id>.env_key_instructions: setup guidance for provider key.

model_providers.<id>.experimental_bearer_token: direct bearer token; documented as discouraged.

model_providers.<id>.requires_openai_auth: whether provider uses OpenAI auth.

model_providers.<id>.wire_api: protocol; docs say only responses.

model_providers.<id>.query_params: extra query params.

model_providers.<id>.http_headers: static request headers.

model_providers.<id>.env_http_headers: headers from env vars.

model_providers.<id>.request_max_retries: HTTP retry count.

model_providers.<id>.stream_max_retries: SSE retry count.

model_providers.<id>.stream_idle_timeout_ms: SSE idle timeout.

model_providers.<id>.supports_websockets: whether Responses WebSocket transport is supported.

features.codex_hooks: under-development lifecycle hooks.

features.shell_tool: enable shell tool; stable and on by default.

features.enable_request_compression: zstd-compress streaming request bodies; stable and on by default.

features.skill_mcp_dependency_install: prompt/install missing MCP deps for skills; stable and on by default.

features.fast_mode: enables Fast mode selection; stable and on by default.

features.smart_approvals: experimental guardian-reviewer approval routing.

features.web_search: deprecated old toggle; prefer web_search.

features.web_search_cached: deprecated old toggle mapping to cached mode.

features.web_search_request: deprecated old toggle mapping to live mode.

experimental_use_unified_exec_tool: deprecated legacy alias for unified exec.

suppress_unstable_features_warning: hide warning when under-development features are enabled.

shell_environment_policy.inherit: baseline env inheritance, all | core | none.

shell_environment_policy.ignore_default_excludes: keep KEY/SECRET/TOKEN vars before filtering.

shell_environment_policy.exclude: env var exclude globs.

shell_environment_policy.include_only: env var allowlist globs.

shell_environment_policy.set: explicit env var overrides.

shell_environment_policy.experimental_use_profile: load shell profile when spawning subprocesses.

history.persistence: save-all | none transcript storage.

history.max_bytes: cap history file size.

tool_output_token_limit: cap stored tool-output tokens.

compact_prompt: inline history-compaction prompt override.

experimental_compact_prompt_file: file-backed compaction prompt override.

background_terminal_max_timeout: max poll window for background terminal reads.

notify: external notification command.

file_opener: app used for opening citations.

tui.animations: terminal animations.

tui.alternate_screen: alternate-screen behavior.

tui.show_tooltips: onboarding tooltips.

tui.status_line: footer status-line composition.

tui.theme: syntax-highlighting theme.

tui.model_availability_nux.<model>: internal model-tooltip state.

hide_agent_reasoning: suppress reasoning events.

disable_paste_burst: disable burst-paste detection.

feedback.enabled: enable /feedback.

analytics.enabled: machine/profile analytics.

log_dir: log file directory.

sqlite_home: SQLite runtime state directory.

otel.environment: OTEL environment tag.

otel.exporter: log exporter selection.

otel.trace_exporter: trace exporter selection.

otel.metrics_exporter: metrics exporter selection.

otel.log_user_prompt: include raw user prompts in OTEL.

otel.exporter.<id>.endpoint|protocol|headers|tls.*: exporter transport config.

otel.trace_exporter.<id>.endpoint|protocol|headers|tls.*: trace exporter transport config.

instructions: reserved for future use; docs say prefer model_instructions_file or AGENTS.md.

developer_instructions: extra developer instructions injected into the session.

commit_attribution: override co-author trailer.

project_root_markers: files used to detect project roots.

project_doc_max_bytes: max bytes read from AGENTS.md.

project_doc_fallback_filenames: fallback project-doc filenames.

check_for_update_on_startup: auto-update check behavior.
cli_auth_credentials_store: where CLI credentials are cached.

mcp_oauth_credentials_store: where MCP OAuth credentials are cached.

mcp_oauth_callback_port: fixed local OAuth callback port.

mcp_oauth_callback_url: override OAuth callback URL.

chatgpt_base_url: override ChatGPT login base URL.

forced_login_method: restrict auth method to chatgpt or api.

forced_chatgpt_workspace_id: lock ChatGPT login to one workspace.

windows.sandbox, windows.sandbox_private_desktop, profiles.<name>.windows.sandbox, windows_wsl_setup_acknowledged: Windows-only controls.

notice.hide_world_writable_warning, notice.hide_rate_limit_model_nudge, notice.hide_gpt5_1_migration_prompt: acknowledgement/suppression flags; no power impact.