open-agents-ai 0.185.63 → 0.185.64

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/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "open-agents-ai",
3
- "version": "0.185.63",
3
+ "version": "0.185.64",
4
4
  "description": "AI coding agent powered by open-source models (Ollama/vLLM) — interactive TUI with agentic tool-calling loop",
5
5
  "type": "module",
6
6
  "main": "./dist/index.js",
@@ -104,6 +104,10 @@ Answer: $119.63
104
104
 
105
105
  This applies to: currency conversion, percentages, statistics, financial calculations, unit conversions, date math. If code execution fails, reason through the expected output step by step and mark with [ESTIMATED].
106
106
 
107
+ ## Knowledge Gaps — Search, Don't Hallucinate
108
+
109
+ When a task involves specific regulations (BSA/AML, GDPR, HIPAA), industry standards, legal requirements, or domain facts you're uncertain about — use `web_search` to look them up. A wrong answer is worse than a searched answer. This is especially important for compliance, legal, and regulatory questions where precision matters.
110
+
107
111
  ## Debugging — Observe Before Reasoning
108
112
 
109
113
  When uncertain about runtime behavior (types, return values, edge cases), run a quick test instead of guessing:
@@ -32,6 +32,9 @@ Calculations — EXECUTE, never guess:
32
32
  - 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.
33
33
  - Currency, percentages, statistics, dates — ALWAYS execute code. If execution fails, reason step-by-step and mark [ESTIMATED].
34
34
 
35
+ Knowledge gaps — SEARCH, don't hallucinate:
36
+ - If a question involves specific regulations, standards, laws, or domain facts you're unsure about, use `web_search` to look them up rather than guessing. A wrong answer is worse than a searched answer.
37
+
35
38
  Debugging — OBSERVE before reasoning:
36
39
  - When unsure how code behaves at runtime, DO NOT guess. Write a short test script and RUN it:
37
40
  shell(command="node -e \"console.log(JSON.parse(JSON.stringify({d: new Date()})))\"")