config.json
Last updated
The model, routing, and channel keys in ~/.config/agenvoy/config.json. Runtime limits are in config.json Limits; policy keys are in config.json Policies.
Model, routing, and channel settings:
| Key | Description |
|---|---|
models | Registered models as "<provider>@<model>" strings; the order is the fallback priority (pass-tier models are skipped since v1.1.0) |
model_tag | {model: tier} with tiers S A B C pass; written as {} when missing. Since v1.1.0 a pass model is never picked by auto routing, subagents or fallback, even when a request names it; only a session whose own model is set to it uses it |
dispatcher_model / summary_model | Dispatcher and summary roles |
dispatcher_beta | Removed in v1.3.2; a leftover entry is ignored. Decision-model dispatch now runs whenever decision_model is set |
decision_model | Added in v1.3.1. The decision model as typesafe@<model> or openrouter@<model>; "" or off is off. While set, each routed request runs it alongside dispatcher_model and takes the first valid answer, and background_command uses it to check flagged output |
image_generator / stt_model / tts_model | Image provider endpoint and audio models |
compats | Custom OpenAI-compatible endpoints, [{provider, url}] |
keys | Names of credentials stored in the keychain (never the values) |
telegram_enabled / discord_enabled | Channel flags; telegram_username / discord_username are filled in by the daemon |
admin_channel | Verification-code relay target (set from /config → Admin Channel in the TUI since v1.1.0) |
reply_lang | Reply language, default "auto" (match the user). Since v1.3.1 a set language is the default rather than a fixed rule: the language the user writes in does not change it, but a request or a skill, template or tool that asks for another language gets it for the output it covers. It also applies to the session summary since v1.3.1. Accepts a code from configs/jsons/reply_lang.json (en, zh-TW, zh-HK, zh-CN, ja, ko, es, fr, de, pt, it, ru, vi, th, id, ar) or any language name |
output_dir | Where files made for the user land when no location is named; default "" means ~/Downloads, or ~/.config/agenvoy/download when that folder does not exist. ~ is expanded; an unusable path falls back to the default |
official_guide_disabled | Added in v1.2.0. true stops injecting the per-model official guide (## Model Guide) into the system prompt; set from /config → Official guide, the dashboard's System tab, or POST /v1/config/official_guide |
skill_source_disabled | Added in v1.2.0. External skill sources to skip when scanning, any of claude, codex, copilot, opencode, agents (openai: Removed in v1.2.1); set from /skill → source, the dashboard's Skills page, or POST /v1/config/skill_source |
Since v1.3.18,
reply_lang also selects built-in labels and notices for tool approvals, question prompts and chatbot notices. If the configured language has no matching strings, the interface uses English. Since v1.3.20, invalid translations also fall back to English; the same fallback applies to browser verification prompts and refusal messages.reply_lang and output_dir are set from /config in the TUI or GET / POST /v1/config/system and /v1/config/output_dir; /config also toggles Startup on login (/v1/config/startup). The separate startup, reply-language, and output-dir TUI commands were removed; use /config. The daemon watches config.json and reloads the agent registry and Telegram / Discord on every write.auto_reasoning (added in v1.0.18) was removed in v1.1.0: reasoning is now a per-session setting, and a session whose reasoning is auto gets its level from the model selector per request. An auto_reasoning entry left in config.json is ignored.