docs(oci-dac): tutorial 40 + empirical Qwen confirmation + website

README.md

@@ -103,6 +103,7 @@ the [documentation](https://oracle-samples.github.io/locus/).
 | **[📊 Evaluation](https://oracle-samples.github.io/locus/concepts/evaluation/)** | `EvalCase` / `EvalRunner` / `EvalReport` — regression suites, custom evaluators, pass / score / duration reporting. |
 | **[🛂 Termination algebra](https://oracle-samples.github.io/locus/concepts/termination/)** | Eight composable stop conditions on `Agent(termination=…)`: `MaxIterations \| TextMention("DONE") & ConfidenceMet(0.9)` is real Python (`__or__` / `__and__` overloads). |
 | **[🧰 Models](https://oracle-samples.github.io/locus/concepts/models/)** | OCI GenAI native (V1 + SDK transport, 90+ models, day-0) · OpenAI · Anthropic · Ollama. One auth surface for OCI: profile, session token, instance / resource principal. |
+| **[🏗 OCI Dedicated AI Cluster](https://oracle-samples.github.io/locus/how-to/oci-dac/)** | Pass an `ocid1.generativeaiendpoint.<region>....` OCID and locus auto-routes to `DedicatedServingMode` with real SSE streaming. Live-tested against Qwen on a London DAC. |
 
 ## The agent loop
 
@@ -206,7 +207,7 @@ print(agent.run_sync(
 
 ## Tutorials
 
-[`examples/`](examples/) has 39 progressive tutorials, each a single
+[`examples/`](examples/) has 40 progressive tutorials, each a single
 runnable file. The full set runs end-to-end in CI on every commit;
 each tutorial is a working program against a real model.
 
@@ -218,6 +219,7 @@ each tutorial is a working program against a real model.
 | **Multi-agent** | [`11_swarm_multiagent`](examples/tutorial_11_swarm_multiagent.py) · [`16_agent_handoff`](examples/tutorial_16_agent_handoff.py) · [`17_orchestrator_pattern`](examples/tutorial_17_orchestrator_pattern.py) · [`34_a2a_protocol`](examples/tutorial_34_a2a_protocol.py) |
 | **RAG** | [`22_rag_basics`](examples/tutorial_22_rag_basics.py) · [`24_rag_agents`](examples/tutorial_24_rag_agents.py) |
 | **Production** | [`19_guardrails_security`](examples/tutorial_19_guardrails_security.py) · [`20_checkpoint_backends`](examples/tutorial_20_checkpoint_backends.py) · [`28_agent_server`](examples/tutorial_28_agent_server.py) · [`37_termination`](examples/tutorial_37_termination.py) |
+| **OCI** | [`29_model_providers`](examples/tutorial_29_model_providers.py) · [`40_oci_dac`](examples/tutorial_40_oci_dac.py) — Dedicated AI Cluster endpoints |
 
 End-to-end demos:
 

docs/how-to/oci-dac.md

@@ -36,6 +36,48 @@ get_model("oci:ocid1.generativeaiendpoint....")
   → SDK chat() routes to your DAC.
 ```
 
+## Confirmed working — Qwen on a London DAC
+
+Live-tested against a `uk-london-1` DAC endpoint running Qwen
+(Alibaba Cloud) on 2026-05-01. End-to-end results from the live run
+(see [`examples/tutorial_40_oci_dac.py`](https://github.com/oracle-samples/locus/blob/main/examples/tutorial_40_oci_dac.py)):
+
+```text
+=== Part 3: complete() against the DAC ===
+Reply:        'I am a large-scale language model developed by Alibaba Cloud, known as Qwen.'
+usage:        {'prompt_tokens': 17, 'completion_tokens': 18}
+stop_reason:  stop
+
+=== Part 4: stream() against the DAC ===
+Streaming reply (chunks shown inline):
+  1, 2, 3, 4, 5
+```
+
+What's proven by the run:
+
+- **Routing** — `oci:ocid1.generativeaiendpoint....` resolved to
+  `OCIModel`, not `OCIOpenAIModel`.
+- **Serving mode** — `DedicatedServingMode(endpoint_id=...)` was
+  accepted by the live endpoint.
+- **Real SSE** — chunks arrived as character-by-character deltas, not
+  the fallback path.
+- **Token accounting** — `usage` populated correctly (17 / 18 tokens).
+
+What's still model-specific (Qwen on this DAC, with the deployment as
+provisioned by Luigi's tenancy):
+
+- Tool calls come back as `<tool_call>{...}</tool_call>` text blocks
+  inside `message.content`, not as structured `tool_calls` array
+  entries. Locus's `GenericProvider.parse_response()` doesn't extract
+  them as `ToolCall`s. Two ways to fix:
+  1. **Deploy-side**: configure the DAC with a Qwen3-family flag like
+     `--enable-auto-tool-choice` so the model emits OpenAI-style
+     `tool_calls`. Locus picks them up automatically.
+  2. **Caller-side**: post-process `result.message` for
+     `<tool_call>{...}</tool_call>` blocks and re-issue them via
+     `agent.run_sync(...)` with the parsed call. A small regex
+     extraction; not built into locus today.
+
 ## Streaming
 
 `OCIModel.stream()` flips `is_stream=True` on the underlying

docs/index.md

@@ -280,6 +280,7 @@ them in one process; stream events from any of them in the same
 | **📊 Evaluation** | `EvalCase` / `EvalRunner` / `EvalReport` regression suites. |
 | **🛂 Termination algebra** | Eight composable stop conditions. `Or` and `And` compose them. |
 | **🧰 Models** | OCI GenAI native (V1 + SDK) · OpenAI · Anthropic · Ollama. |
+| **🏗 OCI Dedicated AI Cluster** | Pass an `ocid1.generativeaiendpoint....` OCID, get `DedicatedServingMode` with real SSE streaming. Live-tested on Qwen / London. |
 
 ## Hello, agent
 
@@ -350,7 +351,7 @@ Read the [concepts](concepts/agent.md) for the *why*; read the
 ## Learn locus in an afternoon
 
 The [`examples/`](https://github.com/oracle-samples/locus/tree/main/examples)
-tree is **39 tutorials** plus **3 end-to-end demos**. Every tutorial
+tree is **40 tutorials** plus **3 end-to-end demos**. Every tutorial
 is one runnable file and adds exactly one idea on top of the previous.
 
 ### Track 1 — basics (first hour)
@@ -394,7 +395,7 @@ The six in-process patterns plus A2A:
 [RAG agents](https://github.com/oracle-samples/locus/blob/main/examples/tutorial_24_rag_agents.py) ·
 [Skills](https://github.com/oracle-samples/locus/blob/main/examples/tutorial_32_skills.py).
 
-### Track 5 — production (12, 19–21, 26–30, 33, 35, 37–39)
+### Track 5 — production (12, 19–21, 26–30, 33, 35, 37–40)
 
 [MCP](https://github.com/oracle-samples/locus/blob/main/examples/tutorial_12_mcp_integration.py) ·
 [Guardrails](https://github.com/oracle-samples/locus/blob/main/examples/tutorial_19_guardrails_security.py) ·
@@ -410,7 +411,8 @@ The six in-process patterns plus A2A:
 [Graph advanced](https://github.com/oracle-samples/locus/blob/main/examples/tutorial_35_graph_advanced.py) ·
 [Termination](https://github.com/oracle-samples/locus/blob/main/examples/tutorial_37_termination.py) ·
 [Multi-modal providers](https://github.com/oracle-samples/locus/blob/main/examples/tutorial_38_multimodal_providers.py) ·
-[GSAR typed grounding](https://github.com/oracle-samples/locus/blob/main/examples/tutorial_39_gsar_typed_grounding.py).
+[GSAR typed grounding](https://github.com/oracle-samples/locus/blob/main/examples/tutorial_39_gsar_typed_grounding.py) ·
+[OCI Dedicated AI Cluster (DAC)](https://github.com/oracle-samples/locus/blob/main/examples/tutorial_40_oci_dac.py).
 
 ### End-to-end demos