open-agents-ai 0.187.246 → 0.187.247

package/dist/index.js

@@ -327005,6 +327005,7 @@ function createTaskCompleteTool(modelTier) {
               error: `task_complete BLOCKED — ${incomplete.length} todo item(s) still incomplete. You must either:
   1. Continue working on the remaining items, OR
   2. If they're actually done, call todo_write with status='completed' for each one, THEN call task_complete again.
+  3. If you are in an interactive session (call, chat, monitoring), RESUME THE LOOP — do not stall.
 
 Incomplete items:
 ${incompleteList}${more}`

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "open-agents-ai",
-  "version": "0.187.246",
+  "version": "0.187.247",
   "description": "AI coding agent powered by open-source models (Ollama/vLLM) — interactive TUI with agentic tool-calling loop",
   "type": "module",
   "main": "./dist/index.js",

package/prompts/agentic/system-medium.md

@@ -64,6 +64,14 @@ For tasks requiring 3+ tool calls — plan before acting:
 7. For multi-file changes: read all relevant files first, plan the change order (dependencies before dependents), then execute in order.
 8. COMPLETE: Call task_complete when ALL steps are verified done
 
+## Interactive / Long-Running Sessions
+
+For ongoing interactions (phone calls, live chat, polling, monitoring, streaming):
+- These are LOOPS — do NOT call task_complete until the remote side signals the session ended (e.g. "ended", "disconnected", "closed", error, hangup). The user expects you to keep going.
+- When the other party asks you to look something up or perform an action: acknowledge first ("One moment, let me check"), then research, then deliver the answer. Emit the acknowledgment and research tools together when possible — they run concurrently.
+- If task_complete is blocked or rejected, RESUME the interaction loop immediately. Do not stall or give up.
+- Each turn of a conversation is NOT a separate task. One session = one task. Keep looping until termination signal.
+
 ## Document Generation Strategy
 
 For long documents (reports, SOWs, proposals, contracts, plans):

package/prompts/agentic/system-small.md

@@ -37,7 +37,11 @@ Rules:
 
 When working with tool results, write down any important information you might need later in your response, as older tool results may be cleared to save context space.
 
-Real-time interactions (phone calls, live chat): When a caller asks you to look something up, ALWAYS acknowledge first, THEN research. Send multiple tool calls in one response when possible — they run concurrently. Example: emit shell(say "Let me look that up") AND web_search("query") together. The ack reaches the caller while the search runs.
+Interactive loops (phone calls, live chat, polling, monitoring):
+- These are ONGOING — do NOT call task_complete until the remote side signals completion (e.g. "ended", "disconnected", "closed", exit code). If the user said "keep going" or "until I stop", that means LOOP until the session ends.
+- When the other party asks you to look something up: acknowledge FIRST ("let me check"), THEN research, THEN deliver the answer. Send multiple tool calls in one response when possible — they run concurrently.
+- If task_complete is blocked or fails, do NOT stall — resume the interaction loop immediately. The block means you have more work to do.
+- Each turn of a conversation is NOT a separate task. One conversation = one task. Keep looping.
 
 Calculations — EXECUTE, never guess:
 - For ANY math with 2+ operations: use `repl_exec(code="print(847.50 * 0.15)")` or `shell`. Python is exact. In-head arithmetic is not.