autopilot-ai 1.18.0 → 1.19.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md CHANGED
@@ -98,7 +98,7 @@ Earlier kimiflare versions ran on Cloudflare Workers AI / AI Gateway. On the fir
98
98
 
99
99
  For substantial tasks, the agent can hand independent investigations to **subagents**: separate Autopilot instances that each explore the repository in their own local [Hotcell](https://github.com/sinameraji/hotcell) sandbox and report back cited findings. Several subagents run in parallel behind a single approval while the main agent keeps the conversation and does the edits. You don't need to ask for them; say "don't use subagents" to opt out, or "use subagents" to insist.
100
100
 
101
- Setup: install and start Hotcell, then add your OpenRouter key to its host key store (`hotcell keys add openrouter`). The real key never enters a sandbox. Subagents are read-only (no edits, shell, PRs, or MCP) and see your current working tree, including uncommitted changes (secrets like `.env` are never copied). The first subagent after an install builds a cached runtime (about two minutes, once per version); later ones start in seconds. See [docs/subagents.md](docs/subagents.md) for limits and troubleshooting.
101
+ Setup: install and start Hotcell, then add your OpenRouter key to its host key store (`hotcell keys add openrouter`). The real key never enters a sandbox. Subagents are read-only (no edits, shell, PRs, or MCP) and see your current working tree, including uncommitted changes — it is streamed into the sandbox, so private repositories work and nothing needs to be pushed (secrets like `.env` are never copied). The first subagent after an install builds a cached runtime (about two minutes, once per version); later ones start in seconds. See [docs/subagents.md](docs/subagents.md) for limits and troubleshooting.
102
102
 
103
103
  While subagents run they are listed above the prompt (Ink) or in the activity panel (`/agents`, Camouflage). `/subagents cancel <n>` stops one without interrupting the turn, and `/subagents stats` shows how often subagents were offered, used, and succeeded over the last week (kept locally in `~/.local/share/kimiflare/subagents.jsonl`; no prompts or code are recorded).
104
104
 
@@ -319,7 +319,11 @@ autopilot
319
319
 
320
320
  `/subagents auto` is the default: on substantial tasks the agent is asked to look for independent parts and delegate them, and it decides whether delegation is worth it. `suggest` only hints at delegation for likely parallel work, and `off` disables harness guidance (you can still ask for subagents explicitly). Explicit requests to use subagents or to work without them always win. Set the policy with `/subagents`, `KIMIFLARE_SUBAGENT_POLICY`, or `subagentPolicy` in config.
321
321
 
322
- The harness never starts a subagent by itself: the agent calls the `subagent` tool, which always needs normal tool permission (one prompt covers a parallel batch) and obeys provider, read-only, spend, concurrency, and timeout limits. In Code Mode the `subagent` tool stays a direct tool next to `execute_code`. Jev is consulted only in `suggest` mode for substantial but ambiguous requests, receives at most 1,200 characters of redacted task text, and has a 4-second timeout.
322
+ The harness never starts a subagent by itself: the agent calls the `subagent` tool, which always needs normal tool permission (one prompt covers a parallel batch) and obeys provider, read-only, spend, concurrency, and timeout limits. In Code Mode the `subagent` tool stays a direct tool next to `execute_code`. Jev (a fast yes/no decision model on OpenRouter) sharpens this: in `auto` mode it checks whether a substantial request has independent parts (strong delegation guidance at ≥80%, otherwise the softer nudge), and in `suggest` mode it decides whether to suggest at all. It receives at most 1,200 characters of redacted request text, runs alongside other pre-turn work, and any failure falls back to the default guidance.
323
+
324
+ ### Finishing the job
325
+
326
+ When a substantial turn ends without the agent asking you anything, a Jev yes/no check asks whether it actually finished — or clearly explained a blocker — rather than stopping after a plan or "next I'll…". If it clearly didn't, the agent is told to continue (once per turn), so you don't have to type "go on". Typically under a second; OpenRouter only. Turn it off with `"completionCheck": false` in config or `KIMIFLARE_COMPLETION_CHECK=0`.
323
327
 
324
328
  ## Running shell commands yourself
325
329