cookbook: add Confident AI observability example (#10257)

## Summary

Adds a runnable observability cookbook for [Confident
AI](https://www.confident-ai.com/) using its OpenTelemetry-native
`confident-trace` SDK, which detects Agno automatically.

- Add `cookbook/observability/confident_ai.py`: calls `init()` once at
startup, runs a Hacker News agent (OpenAIResponses, `gpt-5.6-luna`)
twice, wraps the second run in `trace_context` to attach tags, metadata,
and a user ID, and calls `shutdown()` in a `finally` block to flush
spans.
- List the example in `cookbook/observability/README.md`.
- Record the test run in `cookbook/observability/TEST_LOG.md`.

Companion docs: agno-agi/docs#767 (Mintlify) and agno-agi/agno-docs#141
(in-house). The in-house examples page links to this cookbook on `main`.

## Type of change

- [ ] Bug fix
- [ ] New feature
- [ ] Breaking change
- [x] Improvement
- [ ] Model update
- [ ] Other:

---

## Checklist

- [x] Code complies with style guidelines
- [x] Ran format/validation scripts (`./scripts/format.sh` and
`./scripts/validate.sh`)
- [x] Self-review completed
- [x] Documentation updated (comments, docstrings)
- [x] Examples and guides: Relevant cookbook examples have been included
or updated (if applicable)
- [x] Tested in clean environment
- [ ] Tests added/updated (if applicable)

### Duplicate and AI-Generated PR Check

- [x] I have searched existing [open pull
requests](https://github.com/agno-agi/agno/pulls) and confirmed that no
other PR already addresses this issue
- [ ] If a similar PR exists, I have explained below why this PR is a
better approach
- [x] Check if this PR was entirely AI-generated (by Copilot, Claude
Code, Cursor, etc.)

---

## Additional Notes

- Verified against `confident-trace==0.1.3`. Its OpenAI integration
patches the Responses API, so `OpenAIResponses` model spans are captured
alongside the Agno agent and tool spans.
- Ran end to end with `CONFIDENT_API_KEY` and `OPENAI_API_KEY` set. Both
runs completed and span batches were accepted by the collector with HTTP
200.
- `CONFIDENT_OTEL_ENDPOINT` must match the project's region. A US
project key sent to the EU endpoint returns 401 on export, so only set
it for EU projects. The module docstring calls this out.
- `cookbook/scripts/check_cookbook_pattern.py` passes for the new file.
The two existing violations it reports in `mlflow_via_autolog.py` are
pre-existing and untouched.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

cookbook/observability/README.md

@@ -9,6 +9,7 @@ Observability examples for tracing and monitoring Agno agents, teams, and workfl
 - `arize_phoenix_via_openinference.py`
 - `arize_phoenix_via_openinference_local.py`
 - `atla_op.py`
+- `confident_ai.py`
 - `langfuse_via_openinference.py`
 - `langfuse_via_openinference_response_model.py`
 - `langfuse_via_openlit.py`

cookbook/observability/TEST_LOG.md

@@ -7,3 +7,12 @@
 **Result:** Validation passed with zero violations. Runtime execution of individual cookbook scripts was not performed in this pass.
 
 ---
+### confident_ai.py
+
+**Status:** PASS
+
+**Description:** Sends Agno agent traces to Confident AI through `confident-trace`. Calls `init()` once at startup, runs a HackerNews agent twice (one plain run, one inside `trace_context` with tags, metadata, and a user ID), and calls `shutdown()` in a `finally` block to flush spans. Verified with `ruff format`, `ruff check`, `cookbook/scripts/check_cookbook_pattern.py`, and a module import against `confident-trace==0.1.3` in `.venvs/demo`.
+
+**Result:** Static checks and import pass. Ran end to end with `CONFIDENT_API_KEY` and `OPENAI_API_KEY` set: both agent runs completed, tool and model calls executed, and span batches were accepted by the Confident AI collector with HTTP 200. Note that `CONFIDENT_OTEL_ENDPOINT` must match the project's region; a US project key against the EU endpoint returns 401 on export.
+
+---

cookbook/observability/confident_ai.py

@@ -0,0 +1,65 @@
+"""
+Confident AI Observability Integration
+======================================
+
+Demonstrates sending Agno agent traces to Confident AI with confident-trace.
+
+confident-trace is an OpenTelemetry-native tracing SDK that detects Agno
+automatically. Call init() once at startup and your agent, tool, and model
+calls show up in the Confident AI Observatory with no other changes.
+
+Setup:
+    pip install agno openai confident-trace
+
+Set CONFIDENT_API_KEY and OPENAI_API_KEY before running this example.
+For the EU region, also set CONFIDENT_OTEL_ENDPOINT to
+https://eu.otel.confident-ai.com/v1/traces.
+See https://www.confident-ai.com/docs/llm-tracing/introduction for details.
+"""
+
+from agno.agent import Agent
+from agno.models.openai import OpenAIResponses
+from agno.tools.hackernews import HackerNewsTools
+from confident_trace import init, shutdown, trace_context
+
+# ---------------------------------------------------------------------------
+# Setup
+# ---------------------------------------------------------------------------
+# Initialize once at startup. This reads CONFIDENT_API_KEY from the
+# environment and instruments Agno and the OpenAI SDK.
+init()
+
+
+# ---------------------------------------------------------------------------
+# Create Agent
+# ---------------------------------------------------------------------------
+agent = Agent(
+    name="Hacker News Agent",
+    model=OpenAIResponses(id="gpt-5.6-luna"),
+    tools=[HackerNewsTools()],
+    instructions="You summarize Hacker News stories. Be concise and cite story titles.",
+    markdown=True,
+)
+
+
+# ---------------------------------------------------------------------------
+# Run Example
+# ---------------------------------------------------------------------------
+if __name__ == "__main__":
+    try:
+        # A plain run is traced automatically.
+        agent.print_response("What are the top 3 stories on Hacker News right now?")
+
+        # Attach tags, metadata, and a user ID to the trace before the run starts.
+        with trace_context(
+            tags=["cookbook"],
+            metadata={"release": "2026-09"},
+            user_id="user-42",
+        ):
+            agent.print_response(
+                "Pick one of those stories and explain why it is trending.",
+                stream=True,
+            )
+    finally:
+        # Flush pending spans before the process exits.
+        shutdown()