Settings reference
Per-tool details for the fields on the settings page.
Effort by target
effort reaches the tools below. A value the tool does not accept, or effort on any other tool, raises a sync note instead. x-<target> wins, so x-claude.effortLevel overrides the portable value. import fills effort from these keys when the tool accepts the value and no other settings spec for that tool sets it; otherwise the value goes under x-<target>. Kimi import does not read effort.
| Target | Native key | Accepted values |
|---|---|---|
| Augment | defaultThinkingLevel in .augment/settings.json, read by Auggie 1.x | off, minimal, low, medium, high, xhigh |
| Claude Code | effortLevel in .claude/settings.json | low, medium, high, xhigh |
| Copilot | effortLevel in .github/copilot/settings.json | none, minimal, low, medium, high, xhigh, max; each model accepts a subset |
| Codex | model_reasoning_effort in .codex/config.toml | any string; outputs.codex.config.model-reasoning-effort and the captured overlay win |
| CodeBuddy | reasoningEffort in .codebuddy/settings.json | minimal, low, medium, high, xhigh, max |
| Factory | reasoningEffort in .factory/settings.json | none, dynamic, off, minimal, low, medium, high, xhigh, max; each model accepts a subset |
| Junie | effort in .junie/config.json | any string |
| Kimi | [thinking].effort in the config.toml that outputs.kimi.conf-file names | any value |
| Qwen Code | model.reasoningEffort in .qwen/settings.json (0.28.0 or later) | low, medium, high, xhigh, max; each provider maps the value to its active model |
| Pi | defaultThinkingLevel in .pi/settings.json | off, minimal, low, medium, high, xhigh, max |
Support by target
| Target | permissions | model |
|---|---|---|
| Claude Code, Qoder, Kilo Code, OpenCode | yes | yes |
| Factory | Bash rules only; ask goes to commandDenylist (which prompts), deny to commandBlocklist | yes |
| Codex | Bash rules via outputs.codex.exec-policies-from-permissions (translation); otherwise a note | yes |
| Windsurf | yes | no |
| Augment | allow, ask, and deny, for whole tools and Bash prefixes; path rules raise a note | defaultModel, read by Auggie 1.x |
| Cursor | allow and deny in .cursor/cli.json, for the Cursor CLI (details) | no |
| Copilot, Junie, Gemini, Kiro | no; Copilot, Junie, and Kiro report the whole policy in a note | yes |
Other targets support neither field. Unsupported fields raise a sync note; output for other tools continues. A rule the vendor cannot scope, such as a path rule on Factory's shell lists, raises a note instead of widening.
A shared Claude model name raises the same note as an agent model on Codex, Gemini, OpenCode, Kilo Code, Factory, and Kiro; Codex skips it when outputs.codex.config.model or the captured overlay sets the model. Import writes a tool's model only for that tool, as model: {<tool>: <name>}, because model names differ between vendors.
Target-specific keys
Tool-specific keys go under x-<target> and merge into that tool's settings file (x-factory.sandbox reaches .factory/settings.json). When sync also writes the same key:
- Lists are joined, with the entries sync writes first.
- Objects merge key by key, at every level.
- A single value such as
modelis replaced. - A list and a string cannot merge. The
x-<target>value wins, with a sync note. - Maps of whole records (
x-qoder.mcpServers,x-augment.mcpServers) merge by name. A server both sides name comes whole from thex-<target>block. - Blocks with a fixed order (
x-qoder.hooks,x-augment.hooks) keep their order, with your own events added at the end.
Four keys take one type each: x-augment.toolPermissions a list, and x-windsurf.permissions, x-kilo.permission, and x-opencode.permission an object. Any other type is skipped with a sync note naming the key, and the rules from your permissions are still written.
Exceptions:
- Codex:
.codex/config.tomlcomes from the captured overlay plusoutputs.codex.config, so anx-codexblock raises a sync note that names both. - Ellipsis reads no portable field, only
x-ellipsis: its reviewer, pull request filters, posting rules, and budget go to.ellipsis/code-review.yaml, and the environment, its repository, and native options to.ellipsis/environments/<name>.yaml. A later spec replaces each top-level block it sets (details). - OpenCode V2 MCP imports use
x-opencode.mcpto keep native connection details, disabled states, OAuth settings, and separate timeouts. Keep it in a settings spec, not in MCP specs. See OpenCode.
Session retention
Keep this personal setting under ~/.agnostic-ai/settings/, outside team project specs:
# ~/.agnostic-ai/settings/retention.yaml
session-retention-days: 3650
sync --global writes the tool's own age limit; unset leaves it alone. Values that are not an integer of 1 or more fail validation (LINT045). Project sync only prints a note.
| Tool | User settings file | Native key |
|---|---|---|
| Claude Code | ~/.claude/settings.json | cleanupPeriodDays: 3650 |
| CodeBuddy Code | ~/.codebuddy/settings.json | cleanupPeriodDays: 3650 |
| Gemini CLI | ~/.gemini/settings.json | general.sessionRetention.maxAge: "3650d" |
| Qoder CLI | ~/.qoder/settings.json | general.sessionRetention.maxAge: "3650d" |
- An
x-claude.cleanupPeriodDaysorx-codebuddy.cleanupPeriodDaysvalue wins for its target. - An existing invalid Claude value, including
cleanupPeriodDays: 0, can pause cleanup. Sync leaves it unchanged, even with--backup, and asks you to fix it by hand or setx-claude.cleanupPeriodDays. - If Gemini or Qoder has
general.sessionRetention.enabled: false, sync leaves its age limit alone and prints a note. It never sets the cleanup switch ormaxCount, and Gemini's existingmaxCountcan still remove younger sessions. - Other targets print a note. Kilo's deletion switch and Factory's organization setting are outside this field.
- Lowering the limit warns that older sessions will be deleted, including when removing the field restores a shorter native limit. Pass
--backupto replace a native value set outside agnostic-ai. - Removing the field restores the original value's bytes, even one that already matched, and removes an empty file that sync created. A value changed by hand stays yours. This restore data needs ownership state version 7 or later. Global sync now writes version 10; older releases refuse that state rather than discard it.
explain --global settings/retention.yamllists the mapped keys.
agnostic-ai changes settings only; it never reads, copies, or archives transcripts. Claude Code also applies this cutoff to some other session data and orphaned worktrees, and Desktop and Cowork transcripts have a separate setting. See Claude cleanup, Gemini configuration, and Qoder settings.
Voice dictation
Keep this personal setting under ~/.agnostic-ai/settings/, outside team project specs:
# ~/.agnostic-ai/settings/voice.yaml
voice:
enabled: true
mode: tap
language: es
sync --global writes each member the tool has a key for; an unset member leaves the tool's value alone. mode is hold (hold a key while you talk) or tap (tap to start and stop). language is passed as written. Other values fail validation (LINT054). Project sync only prints a note.
| Tool | User settings file | Native keys |
|---|---|---|
| Claude Code | ~/.claude/settings.json | voice.enabled, voice.mode |
| Qwen Code | ~/.qwen/settings.json | general.voice.enabled, general.voice.mode, general.voice.language |
| Gemini CLI | ~/.gemini/settings.json | experimental.voiceMode, experimental.voice.activationMode (hold becomes push-to-talk, tap becomes toggle) |
| Grok Build | ~/.grok/config.toml | ui.voice_capture_mode (tap becomes toggle), ui.voice_stt_language |
| Mistral Vibe | ~/.vibe/config.toml | voice_mode_enabled |
| Kiro CLI | ~/.kiro/settings/cli.json | Literal root key voice.language |
| Warp | Platform settings file | agents.voice.voice_input_enabled, agents.voice.voice_input_language |
- Claude Code takes its dictation language from its response language, so sync does not write
voice.languagethere and prints a note. Setx-claude.languageto change both. - Qwen keeps dictation off until a voice model is chosen. Run
/model --voiceor setx-qwen.voiceModel; sync prints a note when no model is configured. - Gemini's voice keys and Vibe's voice mode are experimental. Gemini has no language key; Vibe has no mode or language key. Sync prints a note for each member without a native key.
- Grok has no dictation on/off key:
/voicealways works. Setx-grok.ui.voice_keybind_enabledto control its shortcut separately.GROK_HOMEmoves its user configuration directory. - Kiro CLI maps language only;
autodetects it. Its on/off and capture mode members print a note.KIRO_HOMEmoves the global directory. Nativex-kirokeys use literal dotted names, such asvoice.language. - Other targets print a note naming their limit.
- An
x-<target>key wins over the portable member it overlaps, including a parent map. Set keys such asx-claude.voice.autoSubmitthere. - Pass
--backupto replace a native value set outside agnostic-ai. - Removing the field restores each key's original bytes, removes an empty
voiceobject that sync created, and removes an empty file that sync created. A value changed by hand stays yours. explain --global settings/voice.yamllists the mapped keys.
import --global reads these keys into one shared voice map. Tool arguments select the native files to read, so importing Claude alone can supply voice settings to Qwen on a later sync. A tool whose home spec already sets voice is skipped. Import excludes those tools with targets-exclude to keep their existing values; model and effort values for excluded tools go into settings/imported-models.yaml.
An earlier model import can receive a missing voice field without changing its existing values or comments. Import uses settings/imported-voice.yaml when scope, formatting, or other incoming settings require a separate file. If that name is already in use by either layer, it selects a numbered name.
Values from the first tool named win when tools disagree; import prints the values it skipped. Claude's response language stays out of voice.language. Its older voiceEnabled key is read when the voice object is absent; sync reuses a matching legacy value without adding a nested key.
See Claude voice dictation, Qwen settings, Gemini's voice schema, Grok settings, and Vibe voice mode.