@aiiware/aii 0.19.5 → 0.19.6

package/README.md

@@ -240,7 +240,7 @@ While a goal is **active**, the agent sees the objective every turn and auto-con
 
 | Command | What It Does |
 |---------|-------------|
-| `/goal <objective>` | Set the goal — flags: `--verify "cmd"` (repeatable), `--budget`, `--auto-turns` (`0` or `unlimited`; default: unlimited — a goal runs until achieved), `--max-time`, `--max-tokens`, `--no-proof`, `--auto` |
+| `/goal <objective>` | Set the goal — flags: `--verify "cmd"` (repeatable), `--budget`, `--auto-turns` (`0` or `unlimited`; default: unlimited — a goal runs until achieved), `--max-time`, `--max-tokens`, `--no-proof`, `--no-auto`/`--auto-approve`, `--auto` |
 | `/goal` | Status view — objective, status, verify, limits, usage |
 | `/goal draft <description>` | The model proposes a strong goal contract; you edit + submit |
 | `/goal edit <text and/or flags>` | Revise in place |
@@ -248,7 +248,7 @@ While a goal is **active**, the agent sees the objective every turn and auto-con
 
 **Verified completion** — with `--verify` armed, `GOAL COMPLETE` only counts when every command exits 0; failures keep the goal active and feed back to the agent, so "done" means *provably* done. Even without `--verify`, a bare completion isn't taken at face value: the agent gets one nudge to show proof, self-contradicting evidence is rejected, and an uncapped goal (the default) **never ends on an unverified claim** (opt out with `--no-proof` or `goal.proof_expected: false` in config).
 
-Guardrails: a goal **runs until achieved** by default — cap it with `--auto-turns <n>` or a durable `goal.auto_turns` in config; anti-spin pauses a goal that stops doing work, limit stops hand off with measured progress/remaining/next, typing always wins the turn, Esc pauses, and the `◎ Goal` status-bar segment keeps the state in view. Goals survive restarts via `aii agent --continue`.
+Guardrails: a goal **runs until achieved** by default and its own turns **auto-approve tools** (workspace-fenced; your typed turns keep prompting — opt out with `--no-auto` or `goal.auto_approve: false` in config) — cap it with `--auto-turns <n>` or a durable `goal.auto_turns` in config; anti-spin pauses a goal that stops doing work, limit stops hand off with measured progress/remaining/next, typing always wins the turn, Esc pauses, and the `◎ Goal` status-bar segment keeps the state in view. Goals survive restarts via `aii agent --continue`.
 
 `/goal` vs `/loop`: a loop grinds a fixed prompt with fresh context each iteration; a goal keeps one **conversation** converging on an outcome. Starting a loop auto-pauses an active goal.