Document Ollama tool-calling gap honestly

Ollama refuses tool-call requests with "<model> does not support tools"
on both /api/chat and /v1/chat/completions because our Modelfile has no
TEMPLATE directive exposing the Qwen 3.6 tool-jinja blocks — Ollama
falls back to the trivial {{ .Prompt }} template and its capability
detector reports completion only.

README "Tool / function calling" and Known limitations now reflect
reality. examples/ollama_chat.py:tool_round_trip keeps the function as
a reference for the request shape but adds a docstring warning, and the
demo wraps the call in try/except so it prints [skip] instead of
crashing with HTTPError 400.

Plain chat, streaming, system overrides, and the OpenAI-compat endpoint
all still work — verified end-to-end against the running daemon.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

CHANGELOG.md

@@ -7,6 +7,16 @@ and documentation**, not the underlying base model.
 
 ## [Unreleased]
 
+### Documented
+- Tool calling via Ollama is currently rejected with `does not support
+  tools` because the Modelfile has no `TEMPLATE` directive exposing the
+  Qwen 3.6 tool-jinja blocks. Verified against both `/api/chat` and
+  `/v1/chat/completions`. README "Tool / function calling" + Known
+  limitations updated to reflect reality. `examples/ollama_chat.py:
+  tool_round_trip` keeps the helper as a reference shape but adds a
+  docstring warning, and the demo wraps the call in a try/except so it
+  prints `[skip]` instead of crashing.
+
 ### Fixed
 - `Modelfile`: added explicit `PARAMETER stop` directives for `<|im_end|>`,
   `<|endoftext|>`, and `<|im_start|>`. Ollama was only picking up

README.md

@@ -295,7 +295,7 @@ client doesn't.
 
 #### Tool / function calling
 
-The embedded template uses Qwen's XML format:
+Qwen 3.6's chat template uses Qwen's XML format:
 
 ```text
 <tool_call>
@@ -306,15 +306,29 @@ The embedded template uses Qwen's XML format:
 </tool_call>
 ```
 
-Most OpenAI-compatible servers (Ollama, LM Studio, vLLM) translate
-between this and the JSON `tool_calls` shape automatically. See
-`examples/ollama_chat.py:tool_round_trip` for a working round-trip.
+> **Tool calling via Ollama is currently disabled for this Modelfile.**
+> Both `/api/chat` and `/v1/chat/completions` reject requests with
+> `"<model> does not support tools"` because Ollama's tool-capability
+> detection requires an explicit Modelfile `TEMPLATE` directive
+> containing tool-jinja blocks, and we currently fall back to the
+> trivial `{{ .Prompt }}` template (the GGUF's embedded jinja isn't
+> picked up by Ollama's detector). Plain chat, streaming, and
+> system-prompt overrides all work — only the `tools` array is
+> rejected.
+>
+> If you need tool calling, use **llama.cpp** / **llama-cpp-python**
+> directly (they read the GGUF's embedded chat template), or write a
+> Modelfile `TEMPLATE` mirroring the official Qwen 3.6 chat template.
+> The reference Python helper `examples/ollama_chat.py:tool_round_trip`
+> is shipped for documentation but raises `HTTPError 400` against
+> Ollama until the above is fixed.
 
 ## Known limitations
 
 - **Slower per token than the 35B-A3B sibling.** Dense 27B beats sparse 35B/3B-active on steps-per-second benchmarks because every parameter contributes; if you optimize for tokens-per-second, the MoE wins.
 - **No mmproj in this release**, and **vision via Ollama is broken upstream** (qwen35/qwen35moe arch entries missing from Ollama's vendored llama.cpp fork — see the [Vision](#vision) section). For image input use llama.cpp directly until that's fixed.
 - **Q4_K_M quality loss** is real. Use Q5_K_M or Q6_K if you have the VRAM (~20-22 GB).
+- **Tool calling via Ollama is currently disabled** because the Modelfile has no `TEMPLATE` directive exposing the Qwen 3.6 tool-jinja blocks; Ollama returns `does not support tools` for any request with a `tools` array. Use llama.cpp directly for tool calling, or contribute a Modelfile `TEMPLATE`. See [Tool / function calling](#tool--function-calling).
 - **No formal evaluation in this card.** Numbers above are estimates.
 
 ## Related models

examples/ollama_chat.py

@@ -109,7 +109,15 @@ def fake_weather(city: str, unit: str) -> str:
 
 
 def tool_round_trip(prompt: str) -> str:
-    """Single-shot tool call: model -> tool -> model -> final answer."""
+    """Single-shot tool call: model -> tool -> model -> final answer.
+
+    NOTE: Currently fails against Ollama with HTTPError 400
+    "<model> does not support tools" because the project Modelfile has
+    no TEMPLATE directive exposing the Qwen 3.6 tool-jinja blocks. The
+    function is shipped as a reference for the request shape — wire it
+    against llama-cpp-python or a custom-templated Modelfile to actually
+    run it. See README "Tool / function calling".
+    """
     history: list[dict[str, Any]] = [{"role": "user", "content": prompt}]
     r = requests.post(
         f"{HOST}/api/chat",
@@ -183,7 +191,14 @@ def _demo() -> None:
     print()
 
     print("\n=== 3. tool round-trip ===")
-    print(tool_round_trip("What is the weather in Paris in celsius?"))
+    try:
+        print(tool_round_trip("What is the weather in Paris in celsius?"))
+    except requests.HTTPError as e:
+        if e.response is not None and "does not support tools" in e.response.text:
+            print("[skip] Ollama refuses tools for this Modelfile (no TEMPLATE).")
+            print("       See README 'Tool / function calling' for context.")
+        else:
+            raise
 
     print("\n=== 4. OpenAI-compat ===")
     print(openai_chat("Say 'OpenAI endpoint OK' and nothing else."))