System Settings Inventory Reference

System settings inventory

This reference teaches the kernel-level catch-all behind system(action="settings", input={}). System owns a genuine adjustable LingTai setting only when no other concrete ToolPlugin owns it. SHOW returns exactly key, current, default, configurable, and comment; it never sets, resets, writes, refreshes, or mutates process environment. A row with configurable: true says only that an authorized external procedure below exists. It does not authorize the caller to perform that procedure.

SHOW resolves one complete fresh snapshot. A malformed/unreadable init.json, active preset, System owner document, or risky-action gate document makes the whole inventory unavailable—there are no partial rows and no exception details. Sensitive rows replace both current and default with <redacted> before JSON serialization.

Root and manifest inputs

The canonical source is the real init.json reader: JSONC parse, active-preset materialization, provider inheritance, schema validation, and path resolution. No environment peers are invented for these fields. An active preset replaces the authored manifest.llm block, but its llm.context_limit remains preset-local for fit/authorization checks and is removed before effective init materialization; the System runtime-policy row reports the separate environment/v2/default result. Psyche owns configurable prompt pairs through its separate closed owner document; System neither resolves nor projects them. Derived system/manifest.resolved.json is never authority.

The seven ordinary runtime-policy rows are not init/preset rows. They resolve from valid LINGTAI_<FIELD> environment values, then a valid closed-v2 settings/system.json field, then the fixed runtime default. Each row's comment points here directly; the System entry keeps only legacy aliases:

The corresponding environment names are LINGTAI_CONTEXT_LIMIT, LINGTAI_SNAPSHOT_INTERVAL, LINGTAI_MAX_RPM, LINGTAI_MAX_AED_ATTEMPTS, LINGTAI_AED_TIMEOUT, LINGTAI_STREAMING, and LINGTAI_ACTIVENESS.

Legacy manifest.context_limit, snapshot_interval, max_rpm, max_aed_attempts, aed_timeout, streaming, and activeness are recognized-and-ignored compatibility data. SHOW never reports them as current truth and an active preset cannot override these runtime-policy rows. The row comment points directly to this document shape and authorized procedure; the System router does not own another copy of this policy.

Runtime-policy v2 document shape

The same settings/system.json file may be a closed v2 document naming any subset of the seven ordinary runtime-policy fields above plus cache_miss_budget (positive integer; see "Cache-miss budget" below) and notification_max_chars (positive integer; Core still clamps it to 2048–10000 and LINGTAI_NOTIFICATION_MAX_CHARS still wins), and auto_molt_idle_seconds (positive finite seconds, default 7200), for example:

{"schema_version": 2, "context_limit": 200000, "auto_molt_idle_seconds": 7200}

The inactivity duration resolves live on each eligible heartbeat as valid env > valid v2 file > 7200 seconds; a file edit needs no refresh. A persisted env-file edit still needs refresh. The continuous IDLE/ASLEEP and strict current-context

100000 gate are unchanged; this changes cadence, not cache-hit guarantees.

Booleans never stand in for numbers, NaN/Infinity are rejected, and an unknown, duplicate, or invalid key rejects the whole document so nothing is applied partially. An absent key and an explicit null are different: absent falls through to the fixed default, null is the configured value. The kernel-fixed context-pressure thresholds (0.85 / 1.0 / 3 rounds / 0.75) and the legacy molt_* fields are not settings: naming them makes the document invalid. The seven ordinary runtime-policy fields are resolved at CLI boot, before the first LLM service is built, and once on every refresh, so the service, AgentConfig, and the session streaming flag always agree; init.json and system/manifest.resolved.json are never rewritten to reflect it. Enabling snapshot_interval by refresh on a running agent initializes the snapshot repository first; if that fails, snapshots stay off for the process and snapshot_initialize_failed is logged.

After explicit owner/human authorization, edit the intended environment value at its launcher owner or the corresponding v2 field with Shell, preserving unrelated fields. Follow refresh-precheck before applying a change at the boot/refresh timing in the table, then query System settings again. An invalid owner document applies no partial subset; this does not authorize repair, runtime refresh or configuration writes by itself. Cache-budget live resolution is separate and described below.

Cache-miss budget

Default-only row illustration (query SHOW for the actual current value):

{"key":"cache_miss_budget","current":2000000,"default":2000000,"configurable":true,"comment":"system-manual/reference/settings-inventory#cache-miss-budget"}

current resolves from a valid live LINGTAI_CACHE_MISS_BUDGET, then a live valid settings/system.json (the v1-only document below, or the v2 cache_miss_budget field above), then the fixed 2,000,000 default. The environment value is a positive base-10 integer string; the owner-file value is a positive JSON integer (a boolean is not an integer here). Invalid environment input falls through. A missing owner file selects the default; a present unreadable, malformed, duplicate-key, wrong-version, or otherwise invalid owner document makes SHOW return the fixed whole-inventory unavailable failure unless a valid environment value bypasses it. The runtime consumer retains its existing safe-default fallback on missing, unreadable, malformed or invalid owner JSON; this is distinct from SHOW failing the whole inventory. The reader never creates or rewrites the owner file. configurable: true means an authorized owner procedure exists outside SHOW; SHOW itself never writes, resets, or removes anything. This advisory budget is public, not sensitive, and is not redacted.

The v1-only document shape (for an agent that only ever needs this one setting) is:

{"schema_version": 1, "cache_miss_budget": 2000000}

Both values must be JSON integers (not booleans), the version must be 1, the budget must be positive, and no other or duplicate keys are accepted.

Authorized change procedure: after explicit owner/human authorization, set LINGTAI_CACHE_MISS_BUDGET in the launcher or the agent's configured env_file (an env_file edit needs refresh before the running agent sees it), or use the existing Shell capability to write one of the two document shapes above to settings/system.json (remove the file through the same capability to return to the default), then call system(action="settings", input={}) again and verify current. If the environment source still wins, change or remove it at its launcher/env_file owner instead of editing the lower-precedence file repeatedly. Direct process-env and unshadowed file changes apply on the next metadata snapshot; an env_file edit still needs refresh. Threshold changes and refreshes do not reset cumulative token_usage.session.cache_miss_tokens; only molt does. The threshold is advisory and never blocks a request. This path is unrelated to .notification/system.json. Legacy init.json manifest.cache_miss_budget is ignored and has no runtime effect.

manifest.summarize_notification_threshold remains System-owned: it controls cross-cutting Agent/ToolExecutor result hints, not the Context ToolPlugin's public summarize action. Conversely, manifest.pseudo_agent_subscriptions belongs to the concrete Email ToolPlugin because CLI composition hands it directly to PosixFilesystemMailAdapter, which resolves the subscription paths. It is intentionally absent from System SHOW. The Email-owner inventory uses the generic sensitive-value seam to fully redact both current and default path lists; System neither duplicates that row nor exposes the paths.

Authorized change procedure: after explicit owner/human authorization, edit the exact init.json field with the existing Shell capability. For a preset-owned LLM/context value, edit the authorized preset outside SHOW or use the existing system(action="refresh", input={"preset": ...}) workflow; never edit the derived resolved manifest or widen preset.allowed as a shortcut. Run the refresh precheck, refresh/relaunch at the timing above, then call SHOW again. Psyche-owned prompt/file pairs are changed only through the procedure in psyche-manual; changing or removing a pointer never changes or deletes the referenced file. Existing identity changes use system(action="name_set"|"name_nickname"); editing manifest.agent_name is not a supported rename procedure.

LLM and provider inputs

Every effective manifest.llm axis is System-owned because no LLM ToolPlugin exists. Selected-factory rows are classified by registered factory identity across the four families openai, anthropic, codex, and claude-code. Precedence is active preset over authored init for the whole block. The credential path is the exception inside the materialized block: a named non-empty api_key_env value wins inline api_key. Initial boot uses only those two authored sources through resolve_env_checked; it does not consult an invented {PROVIDER}_API_KEY fallback. No secret, alias value, header, auth path, endpoint pool, or credential-bearing URL is ever projected.

Authorized change procedure: after explicit owner/human authorization, update the selected preset (when active) or init.json, keep credentials in the supported private env/file source, run the refresh precheck, refresh, and SHOW again. Never print a before/after credential, header, prompt, token, auth path, or endpoint-pool value. SHOW never edits a preset, credential file, header map, or process environment.

Kernel environment controls

These are genuine kernel/LLM settings without another ToolPlugin owner. Direct process-environment changes apply at the canonical read point; an env_file edit first needs System refresh. Missing/invalid values fall back exactly as shown. LINGTAI_CODEX_WS is a compatibility alias under the single llm.codex_transport row: a non-empty canonical LINGTAI_CODEX_TRANSPORT always decides first.

Authorized environment procedure: after explicit deployment-owner approval, change the launcher environment or the agent's configured env_file; do not mutate os.environ through a tool. Refresh when the source is env_file, and restart only where the table says import/boot/session construction. Call SHOW again and verify the effective value. Changing a threshold never grants access, cleans files, resets counters, or authorizes a risky operation.

For LINGTAI_TUI_DIR, use that launcher procedure and a full relaunch. The kernel does not create or validate the directory eagerly: an unexpandable ~ can fail adapter construction, while a missing directory or unreadable/invalid codex-auth.json fails the later Codex account or request path closed. Never print the resolved directory or credential paths; SHOW fully redacts the env-selected and fallback paths.

Explicit non-settings and exclusions

These classifications are tested against the canonical schemas/registry so future fields cannot vanish silently:

• Concrete ToolPlugin owners stay out of System: Shell; Daemon; Notification; Vision; Web; Task Card; Plugin/Psyche; Skills; unified Pad memory; MCP, curated addons, and their config/session paths. Psyche owns the live Pad prompt inputs at root pad/pad_file and the four configurable system-prompt inputs in settings/psyche.json. manifest.capabilities, manifest.plugins, and root addons/mcp therefore are not System rows. Old lingtai/lingtai_file strings remain accepted one-way memory migration inputs, not live settings sources.
• Inert/compatibility init inputs are not settings sources: manifest.context_limit, manifest.snapshot_interval, manifest.max_rpm, manifest.max_aed_attempts, manifest.aed_timeout, manifest.streaming, manifest.activeness, manifest.llm.codex_thread_salt, and nested init manifest.llm.context_limit, manifest.max_turns, context-serialization template fields, retired molt/stamina fields, retired prompt fields, and the retired manifest.soul block of the removed Soul subsystem.
• Retired LLM keys are recognized-and-ignored, never rows: manifest.llm.compact_threshold, manifest.llm.codex_auth_pool_path, and the per-vendor wire-routing keys retired with the four-family collapse — manifest.llm.api_compat, manifest.llm.reasoning_effort_vocab, and manifest.llm.use_responses_api (thinking is sent verbatim and wire_api alone selects the openai wire).
• Kernel-fixed context-pressure thresholds, the hidden idle-sleep timeout, and fixed tool-loop safety limits are code policy rather than settings.

Do not infer product ownership from a registry source-path cell: the concrete ToolPlugin rule and System catch-all rule above are authoritative.

Concrete ToolPlugin environment exclusions

These registered production variables belong to concrete tools/integrations, not System:

• LINGTAI_CLAUDE_INTERACTIVE_FIFO
• LINGTAI_CLAUDE_MANAGED_ROOT
• LINGTAI_CLOUD_MAIL_CONFIG
• LINGTAI_DAEMON_MANAGER_POOL_SIZE
• LINGTAI_DAEMON_MAX_TURNS
• LINGTAI_DAEMON_SYSTEM_PROMPT_BUDGET_CHARS
• LINGTAI_FEISHU_CONFIG
• LINGTAI_IMAP_CONFIG
• LINGTAI_NOTIFICATION_DELAY_MAX_SECONDS
• LINGTAI_NOTIFICATION_MAX_CHARS
• LINGTAI_PUFFO_V0_REGISTRY
• LINGTAI_SHELL
• LINGTAI_TASKCARD_POLL_INTERVAL
• LINGTAI_TELEGRAM_CONFIG
• LINGTAI_TOOL_TIMEOUT_MAX_SECONDS
• LINGTAI_WEB_ENGINE
• LINGTAI_WEB_MAX_CHARS
• LINGTAI_WECHAT_CONFIG
• LINGTAI_WHATSAPP_CONFIG
• LINGTAI_WHATSAPP_SESSION_DIR

Injected or handoff environment exclusions

These values describe one launcher/process edge, descriptor, or run identity, not an adjustable kernel policy:

• LINGTAI_AGENT_DIR
• LINGTAI_DAEMON_CAPSULE_FD
• LINGTAI_DAEMON_CAPSULE_HANDLE
• LINGTAI_DAEMON_COMPLETION_FILE
• LINGTAI_DAEMON_MANAGER_TOKEN
• LINGTAI_DAEMON_RUN_ID
• LINGTAI_DAEMON_RUN_DIR
• LINGTAI_DERIVED_AVATAR_EXECUTION
• LINGTAI_DRIVER_AUTHORITY_FD
• LINGTAI_MCP_NAME
• LINGTAI_REFRESH_ENV_OVERWRITE
• LINGTAI_RUNTIME_PYTHON
• LINGTAI_RUNTIME_VENV

Test-only environment exclusions

• LINGTAI_AVATAR_BOOT_WAIT_SECONDS
• LINGTAI_DAEMON_SUPERVISOR_TEST_FAKE_LLM
• LINGTAI_DAEMON_SUPERVISOR_TEST_FAKE_LLM_FINISH
• LINGTAI_DAEMON_SUPERVISOR_TEST_FAKE_LLM_SCENARIO
• LINGTAI_DAEMON_SUPERVISOR_TEST_FAKE_LLM_SLEEP
• LINGTAI_FAKE_APP_SERVER_MODE
• LINGTAI_FAKE_CLI_REPORT
• LINGTAI_TEST_CONFIG
• LINGTAI_TEST_FAKE_CLAUDE_SIGNAL_RECORD