fix(heretic2-nvfp4): parse tool_call arguments string->dict for Qwen3.6 template

render-verify caught it: Dvalin's calib tool_calls carry OpenAI wire-form JSON
string arguments, but the Qwen3.6 chat template does .items() on arguments (needs
a dict) → jinja TypeError. Parse string->dict in render_verify + the quant's
load_calib_chat. Confirmed: renders the exact qwen3_coder XML the seat emits
(prefixed bifrost.soong-lab.*, v0.3.13 generate_portrait, <think>, <tool_response>).

services/heretic2-nvfp4-quant/quant_nvfp4.py

@@ -61,6 +61,14 @@ def load_calib_chat(path, tokenizer, seqlen):
     rows = [json.loads(l) for l in open(path) if l.strip()]
     out = []
     for r in rows:
+        # Tool_call arguments arrive as OpenAI wire-form JSON *strings*; the Qwen3.6
+        # template does .items() on them → needs a dict. Parse string→dict so the
+        # forward-pass sees the qwen3_coder XML the seat emits. (render_verify finding.)
+        for m in r["messages"]:
+            for tc in (m.get("tool_calls") or []):
+                a = tc.get("function", {}).get("arguments")
+                if isinstance(a, str):
+                    tc["function"]["arguments"] = json.loads(a)
         text = tokenizer.apply_chat_template(
             r["messages"], tools=r.get("tools"),
             tokenize=False, add_generation_prompt=False, enable_thinking=True,

services/heretic2-nvfp4-quant/render_verify.py

@@ -0,0 +1,44 @@
+#!/usr/bin/env python3
+"""Render-verify a tool-call-XML calib row through the Qwen3.6 chat template.
+
+brokkr's last gate before the production calib enters the quant: confirm the
+assistant tool_calls serialize to the qwen3_coder XML the LIVE seat emits
+(`<tool_call>\n<function=NAME>\n<parameter=KEY>...`), so the calibration
+forward-pass sees the seat's REAL tool-call activations (#355-preservation).
+
+Usage: python3 render_verify.py <tokenizer_dir> <calib.jsonl> [row_index]
+"""
+import json
+import sys
+
+from transformers import AutoTokenizer
+
+tok_dir, calib = sys.argv[1], sys.argv[2]
+idx = int(sys.argv[3]) if len(sys.argv) > 3 else 0
+
+tok = AutoTokenizer.from_pretrained(tok_dir, trust_remote_code=True)
+with open(calib) as f:
+    row = json.loads([l for l in f if l.strip()][idx])
+
+# Tool_call arguments arrive in OpenAI wire form (a JSON *string*), but the Qwen3.6
+# chat template does .items() on them → needs a dict. Parse string→dict so the
+# template renders the qwen3_coder <parameter=...> XML. (render-verify finding.)
+for m in row["messages"]:
+    for tc in (m.get("tool_calls") or []):
+        a = tc.get("function", {}).get("arguments")
+        if isinstance(a, str):
+            tc["function"]["arguments"] = json.loads(a)
+
+tools = row.get("tools", [])
+print("=== tools:", [t.get("function", {}).get("name") for t in tools])
+print("=== message roles:", [m.get("role") for m in row["messages"]])
+
+text = tok.apply_chat_template(
+    row["messages"], tools=tools,
+    tokenize=False, add_generation_prompt=False, enable_thinking=True,
+)
+print(f"=== rendered ({len(text)} chars) ===")
+print(text)
+print("=== qwen3_coder XML markers present? ===")
+for m in ("<tool_call>", "<function=", "<parameter=", "</think>", "bifrost.soong-lab."):
+    print(f"  {m!r}: {m in text}")