agent-blocked 0.1.3 → 0.1.4
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 +2 -2
- package/bin/agent-blocked.mjs +5 -1
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -16,9 +16,9 @@ Report a blocker manually:
|
|
|
16
16
|
npx agent-blocked@latest report --event=needs_direction --severity=medium --reason="Need human direction"
|
|
17
17
|
```
|
|
18
18
|
|
|
19
|
-
The installer adds a small `.agent-blocked/` directory plus tool-specific config or instruction files for the selected agent tools. Those files tell the agent when to escalate
|
|
19
|
+
The installer adds a small `.agent-blocked/` directory plus tool-specific config or instruction files for the selected agent tools. Those files tell the agent when to escalate during goal mode, autonomous mode, background execution, hook-driven automation, CI-style runs, or another CLI-specific automated mode. They also provide a local reporter command that sends blocker events to your Agent Blocked alert profile.
|
|
20
20
|
|
|
21
|
-
Agents should notify when continuing would waste time, create risk, or require a decision only the human can make:
|
|
21
|
+
Agents should not notify during normal interactive paired work when the human is already present and responding in the current conversation. In automated modes, agents should notify when continuing would waste time, create risk, or require a decision only the human can make:
|
|
22
22
|
|
|
23
23
|
- `needs_credentials` for missing API keys, OAuth, permissions, roles, or secrets.
|
|
24
24
|
- `needs_direction` for ambiguous goals, tradeoffs, architecture, product behavior, or priorities.
|
package/bin/agent-blocked.mjs
CHANGED
|
@@ -156,7 +156,11 @@ try {
|
|
|
156
156
|
|
|
157
157
|
const instructions = `# Agent Blocked instructions for coding agents
|
|
158
158
|
|
|
159
|
-
|
|
159
|
+
Use Agent Blocked only when this agent is running without an actively engaged human in the loop, such as goal mode, autonomous mode, background execution, hook-driven automation, CI-style runs, or another CLI-specific automated mode.
|
|
160
|
+
|
|
161
|
+
Do not report during normal interactive paired work when the human is already present and responding in the current conversation. In that case, ask the human directly in chat instead of sending an Agent Blocked alert.
|
|
162
|
+
|
|
163
|
+
When operating in an automated mode and blocked by missing credentials, unclear direction, approval requirements, repeated tool failures, low confidence, or external context, stop burning tokens and report the blockage.
|
|
160
164
|
|
|
161
165
|
Notify the human when continuing would waste time, create risk, or require a decision only the human can make. Do not notify for routine recoverable errors that you can fix yourself in one or two attempts.
|
|
162
166
|
|