public/galaxy
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add Galaxy Decides risk reviews and focus implementation prompts

Browse Source
This commit is contained in:
rkw6086
2026-09-28 12:23:49 -05:00
parent 2a89d03866
commit cc064d4050
17 changed files with 1015 additions and 114 deletions
Download Patch File Download Diff File Expand all files Collapse all files
AGENTS.md
+8
View File
@@ -216,6 +216,14 @@ Key invariants:
- `StartAgentWaitPolicy` follows child execution ownership, not parent `run_id`: grouped local children use `LocalStartup`, legacy local completion waits retain `Completion`, and hosted children use `Startup` with the hosted timeout. Direct-provider `start_agent` is normalized to a one-child `RunAgents` group. Cancelling or replacing a parent turn must not cancel independently running children or erase their group membership.
- Hosted `RunAgents` startup timeouts detach the exact `StartAgentRequestId`; late launch callbacks must not register the child after the timeout result, while children linked before cancellation remain independently running
### Galaxy Decides Permissions
- `GalaxyDecides` is an opt-in execution-profile permission for Galaxy-owned files, commands, PTY input, MCP, computer use, and agent coordination. External CLI agents retain their own permission flows. Existing profile defaults remain unchanged.
- `app/src/ai/blocklist/action_model/risk_review.rs` assesses the exact pending action with the active terminal-use model in a separate, tool-free request, falling back to the base model when the terminal-use model is unconfigured. Risk 0–3 permits automatic execution; 4–5 requires user approval. Existing denylist/protected-path/organization restrictions still require confirmation.
- Invalid, unavailable, oversized, or timed-out assessments never grant execution. Assessment calls are bounded to 30 seconds; approval requests expire after 60 seconds and return a correlated denial telling the agent to choose another approach.
- Reviews are scoped to conversation, action contents, and provider execution identity. Cancellation, replacement, and conversation cleanup invalidate them and cancel the reviewer request. Never treat a late callback or expired approval click as authorization.
- Output polling and user-question behavior retain their existing policies. Risk assessment must not add another model call for each command-output poll.
### Platform Setup
- `./script/bootstrap` - Platform-specific setup plus common agent skill installation from `skills-lock.json`; prompts for project/global when an install or update is needed unless a target flag or environment override is provided.
- `./script/bootstrap --skip-common-skills` - Platform setup without installing or updating common agent skills.