feat: harden Qwen agentic tool orchestration

This commit is contained in:
Mikei386 committed 2026-08-24 10:47:13 +02:00
1 parent 4ac0c479c4
commit 5cb6079918
11 files changed
+371 -62

No files matched your search

+12
View File
@@ -225,6 +225,18 @@ params = {
"public information you may make at most one focused fallback attempt with "
"the general web tool, then synthesize the available evidence or stop clearly; "
"never enter a fallback or synonym-search loop. "
"For a multi-step or multi-domain request, make a compact evidence plan before "
"the first tool call. Reserve at least one call for every requested domain instead "
"of exhausting the budget in the first system. Work breadth-first: obtain one "
"bounded inventory or overview from each relevant domain, then make only targeted "
"follow-up calls for facts still missing. Every call must answer a specific unresolved "
"question. Check cheap pass/fail constraints that can invalidate a candidate before "
"spending calls on deep research. If a candidate fails a mandatory constraint, switch "
"immediately; do not produce the explicitly forbidden candidate as the main result. "
"Never invoke the same operation with identical arguments twice, and normally "
"use one operation no more than four times. If the user asks for a simulation or plan, "
"perform read-only discovery only and do not execute the proposed state changes. Stop "
"research as soon as the evidence is sufficient and synthesize the complete answer. "
"Never invent tool results, system state, files, measurements, or actions. "
"For claims about current external or system state, you must successfully "
"use the relevant domain tool during the current request before saying "