Fix five issues found running the agent examples

examples/agentic_workflows/mcp_weather_agent.py

@@ -90,7 +90,7 @@ def create_mcp_agent_workflow(executor: WorkflowExecutor, mcp_server: str) -> Co
     plan_task = LlmChatComplete(
         task_ref_name="plan_action",
         llm_provider="anthropic",
-        model="claude-sonnet-4-20250514",
+        model="claude-sonnet-5",
         messages=[
             ChatMessage(
                 role="system",

examples/agents/56_rag_agent.py

@@ -65,7 +65,7 @@
         "text": (
             "Agent Configuration. Agents are defined with a name, model, instructions, "
             "and tools. The model field uses the format 'provider/model_name', e.g. "
-            "'openai/gpt-4o' or 'anthropic/claude-sonnet-4-20250514'. Instructions can be "
+            "'openai/gpt-4o' or 'anthropic/claude-sonnet-5'. Instructions can be "
             "a string or a PromptTemplate referencing a stored prompt. Tools can be "
             "@tool-decorated Python functions, http_tool for REST APIs, mcp_tool for "
             "MCP servers, or agent_tool to wrap another agent as a callable tool. "

examples/agents/59_coding_agent.py

@@ -26,7 +26,7 @@
 
 qa_tester = Agent(
     name="qa_tester",
-    model="anthropic/claude-sonnet-4-20250514",
+    model="anthropic/claude-sonnet-4-6",
     instructions=(
         "You are a meticulous QA engineer. Review the code written by the "
         "coder for correctness, edge cases, and bugs. Write and execute test "
@@ -45,7 +45,7 @@
 
 coder = Agent(
     name="coder",
-    model="anthropic/claude-sonnet-4-20250514",
+    model="anthropic/claude-sonnet-4-6",
     instructions=(
         "You are an expert Python developer. Write clean, well-structured "
         "Python code to solve the given problem. Always execute your code to "

examples/agents/60_github_coding_agent.py

@@ -249,7 +249,7 @@ def create_pull_request(title: str, body: str, issue_number: int = 0) -> str:
 
 github_agent = Agent(
     name="github_agent",
-    model="anthropic/claude-sonnet-4-20250514",
+    model="anthropic/claude-sonnet-4-6",
     instructions=(
         "You are a GitHub operations specialist. You handle all git and "
         "GitHub CLI interactions.\n\n"
@@ -282,7 +282,7 @@ def create_pull_request(title: str, body: str, issue_number: int = 0) -> str:
 
 coder = Agent(
     name="coder",
-    model="anthropic/claude-sonnet-4-20250514",
+    model="anthropic/claude-sonnet-4-6",
     instructions=(
         "You are an expert developer. Write clean, well-structured code.\n\n"
         "WHEN YOU RECEIVE A TASK:\n"
@@ -311,7 +311,7 @@ def create_pull_request(title: str, body: str, issue_number: int = 0) -> str:
 
 qa_tester = Agent(
     name="qa_tester",
-    model="anthropic/claude-sonnet-4-20250514",
+    model="anthropic/claude-sonnet-4-6",
     instructions=(
         "You are a meticulous QA engineer. Review the code written by the "
         "coder for correctness, edge cases, and bugs.\n\n"
@@ -340,7 +340,7 @@ def create_pull_request(title: str, body: str, issue_number: int = 0) -> str:
 
 coding_team = Agent(
     name="coding_team",
-    model="anthropic/claude-sonnet-4-20250514",
+    model="anthropic/claude-sonnet-4-6",
     instructions=(
         "You are a coding team coordinator. Delegate the incoming request "
         "to github_agent to get started — it will pick an issue and set "

examples/agents/60a_github_coding_agent_simple.py

@@ -41,7 +41,7 @@
 
 github_agent = Agent(
     name="github_agent",
-    model="anthropic/claude-sonnet-4-20250514",
+    model="anthropic/claude-sonnet-4-6",
     instructions=(
         "You are a GitHub operations specialist. You handle all git and "
         "GitHub CLI interactions.\n\n"
@@ -77,7 +77,7 @@
 
 coder = Agent(
     name="coder",
-    model="anthropic/claude-sonnet-4-20250514",
+    model="anthropic/claude-sonnet-4-6",
     instructions=(
         "You are an expert developer. You write clean, well-structured code.\n\n"
         f"The repo is cloned at {WORK_DIR}.\n\n"
@@ -109,7 +109,7 @@
 
 qa_tester = Agent(
     name="qa_tester",
-    model="anthropic/claude-sonnet-4-20250514",
+    model="anthropic/claude-sonnet-4-6",
     instructions=(
         "You are a meticulous QA engineer. Review the code written by the "
         "coder for correctness, edge cases, and bugs.\n\n"
@@ -134,7 +134,7 @@
 
 coding_team = Agent(
     name="coding_team",
-    model="anthropic/claude-sonnet-4-20250514",
+    model="anthropic/claude-sonnet-4-6",
     instructions=(
         "You are a coding team coordinator. Delegate the incoming request "
         "to github_agent to get started — it will pick an issue and set "

examples/agents/74_cli_error_output.py

@@ -36,7 +36,7 @@
     with AgentRuntime() as rt:
         result = rt.run(agent, prompt)
         result.print_result()
-        output = result.output or ""
+        output = str(result.output)
 
         # Verify the agent saw the error output
         assert "No such file or directory" in output or "nonexistent" in output, (

examples/agents/adk/35_rag_agent.py

@@ -76,7 +76,7 @@
         "text": (
             "Agent Configuration. Agents are defined with a name, model, instructions, "
             "and tools. The model field uses the format 'provider/model_name', e.g. "
-            "'openai/gpt-4o' or 'anthropic/claude-sonnet-4-20250514'. Instructions can be "
+            "'openai/gpt-4o' or 'anthropic/claude-sonnet-5'. Instructions can be "
             "a string or a PromptTemplate referencing a stored prompt. Tools can be "
             "@tool-decorated Python functions, http_tool for REST APIs, mcp_tool for "
             "MCP servers, or agent_tool to wrap another agent as a callable tool. "

examples/agents/langgraph/46_crash_and_resume.py

@@ -104,80 +104,80 @@ def generate_report(analysis: str) -> str:
 )
 
 
-# -- Phase 1: Deploy, start, serve briefly, then crash --------------------
-
-print("=" * 60)
-print("Phase 1: Deploy + start, then simulate crash")
-print("=" * 60)
-
-with AgentRuntime() as runtime:
-    # Deploy the workflow definition (in production, do this once in CI/CD)
-    runtime.deploy(graph)
-    print("Agent deployed to server.")
-
-    # Start an execution by name — the agent is already deployed on the server,
-    # so we only need to send the name and prompt (not the full graph object).
-    handle = runtime.start(
-        "sales_analyst",
-        "Fetch the Q4 2025 sales data, run a full trend analysis on it, "
-        "then generate an executive summary report. "
-        "Call each tool in sequence — do not skip any step.",
-    )
-    print(f"Execution started: {handle.execution_id}")
-
-    # Save execution_id so we can check status later
-    with open(SESSION_FILE, "w") as f:
-        f.write(handle.execution_id)
-
-    # Serve workers just long enough for the first tool to start
-    print("\nServing workers briefly...")
-    runtime.serve(graph, blocking=False)
-    time.sleep(8)
-
-print("\nRuntime closed — workers are dead, workflow persists on server.")
-print()
-
-with open(SESSION_FILE) as f:
-    saved_execution_id = f.read().strip()
-
-# -- Pause: let the user see the stalled execution in the UI --------------
-
-ui_link = f"{UI_BASE}/execution/{saved_execution_id}"
-print("-" * 60)
-print("Open the Conductor UI to see the execution in RUNNING state:")
-print(f"  {ui_link}")
-print()
-print("The workflow is alive on the server but stalled — no workers are")
-print("polling to pick up the next task.  The completed steps are")
-print("preserved; only the remaining steps need to run.")
-print("-" * 60)
-input("\nPress Enter to resume (restart workers)...")
-print()
-
-
-# -- Phase 2: Restart serve — workers pick up stalled tasks ----------------
-
-print("=" * 60)
-print("Phase 2: Restart serve() — workers reconnect automatically")
-print("=" * 60)
-
-with AgentRuntime() as runtime:
-    # serve() re-registers the same workers.  The server dispatches
-    # stalled tasks to them — no resume() call needed.
-    print("\nServing workers (non-blocking for demo)...")
-    runtime.serve(graph, blocking=False)
-
-    # Poll until the execution completes
-    print(f"Polling execution: {saved_execution_id}")
-    status = runtime.get_status(saved_execution_id)
-    while not status.is_complete:
-        time.sleep(2)
+if __name__ == "__main__":
+    # -- Phase 1: Deploy, start, serve briefly, then crash --------------------
+
+    print("=" * 60)
+    print("Phase 1: Deploy + start, then simulate crash")
+    print("=" * 60)
+
+    with AgentRuntime() as runtime:
+        # Deploy the workflow definition (in production, do this once in CI/CD)
+        runtime.deploy(graph)
+        print("Agent deployed to server.")
+
+        # Start an execution by name — the agent is already deployed on the server,
+        # so we only need to send the name and prompt (not the full graph object).
+        handle = runtime.start(
+            "sales_analyst",
+            "Fetch the Q4 2025 sales data, run a full trend analysis on it, "
+            "then generate an executive summary report. "
+            "Call each tool in sequence — do not skip any step.",
+        )
+        print(f"Execution started: {handle.execution_id}")
+
+        # Save execution_id so we can check status later
+        with open(SESSION_FILE, "w") as f:
+            f.write(handle.execution_id)
+
+        # Serve workers just long enough for the first tool to start
+        print("\nServing workers briefly...")
+        runtime.serve(graph, blocking=False)
+        time.sleep(8)
+
+    print("\nRuntime closed — workers are dead, workflow persists on server.")
+    print()
+
+    with open(SESSION_FILE) as f:
+        saved_execution_id = f.read().strip()
+
+    # -- Pause: let the user see the stalled execution in the UI --------------
+
+    ui_link = f"{UI_BASE}/execution/{saved_execution_id}"
+    print("-" * 60)
+    print("Open the Conductor UI to see the execution in RUNNING state:")
+    print(f"  {ui_link}")
+    print()
+    print("The workflow is alive on the server but stalled — no workers are")
+    print("polling to pick up the next task.  The completed steps are")
+    print("preserved; only the remaining steps need to run.")
+    print("-" * 60)
+    input("\nPress Enter to resume (restart workers)...")
+    print()
+
+    # -- Phase 2: Restart serve — workers pick up stalled tasks ----------------
+
+    print("=" * 60)
+    print("Phase 2: Restart serve() — workers reconnect automatically")
+    print("=" * 60)
+
+    with AgentRuntime() as runtime:
+        # serve() re-registers the same workers.  The server dispatches
+        # stalled tasks to them — no resume() call needed.
+        print("\nServing workers (non-blocking for demo)...")
+        runtime.serve(graph, blocking=False)
+
+        # Poll until the execution completes
+        print(f"Polling execution: {saved_execution_id}")
         status = runtime.get_status(saved_execution_id)
-        print(f"  status: {status.status}")
+        while not status.is_complete:
+            time.sleep(2)
+            status = runtime.get_status(saved_execution_id)
+            print(f"  status: {status.status}")
 
-    print(f"\nStatus: {status.status}")
-    print(f"Output: {status.output}")
-    print("\nCheck the completed execution in the UI:")
-    print(f"  {ui_link}")
+        print(f"\nStatus: {status.status}")
+        print(f"Output: {status.output}")
+        print("\nCheck the completed execution in the UI:")
+        print(f"  {ui_link}")
 
-print("\nDone — same workflow, seamless resume after simulated crash.")
+    print("\nDone — same workflow, seamless resume after simulated crash.")

examples/agents/settings.py

@@ -3,10 +3,10 @@
 Set ``CONDUCTOR_AGENT_LLM_MODEL`` as an environment variable to override the
 default model used by all examples::
 
-    export CONDUCTOR_AGENT_LLM_MODEL=anthropic/claude-sonnet-4-20250514
+    export CONDUCTOR_AGENT_LLM_MODEL=anthropic/claude-sonnet-4-6
     export CONDUCTOR_AGENT_LLM_MODEL=google_gemini/gemini-2.0-flash
 
-If unset, defaults to ``anthropic/claude-sonnet-4-6``.
+If unset, defaults to ``openai/gpt-4o``.
 
 ``CONDUCTOR_AGENT_SECONDARY_LLM_MODEL`` provides a second model for multi-model examples
 (e.g., cheap triage vs capable specialist). Defaults to ``openai/gpt-4o``.

scripts/run_examples.sh

@@ -15,24 +15,55 @@
 set -euo pipefail
 
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
-EXAMPLES_DIR="$(cd "$SCRIPT_DIR/../examples" && pwd)"
+EXAMPLES_DIR="$(cd "$SCRIPT_DIR/../examples/agents" && pwd)"
 TIMEOUT="${EXAMPLE_TIMEOUT:-300}"
 
 # Cross-platform python: honour PYTHON env var, then try python3, then python.
 PYTHON="${PYTHON:-$(command -v python3 2>/dev/null || command -v python 2>/dev/null || echo python3)}"
 
+# Cross-platform timeout: GNU coreutils provides `timeout`; macOS ships it as
+# `gtimeout`, and only when coreutils is installed. Without either, run the
+# examples unbounded rather than failing every one of them.
+TIMEOUT_BIN="$(command -v timeout 2>/dev/null || command -v gtimeout 2>/dev/null || true)"
+if [[ -z "$TIMEOUT_BIN" ]]; then
+    echo "Warning: neither 'timeout' nor 'gtimeout' found; examples will run" >&2
+    echo "         without a time limit. On macOS: brew install coreutils" >&2
+fi
+
 # Cross-platform temp dir: honour TMPDIR (set on macOS/Linux), fall back to /tmp.
 TMP_BASE="${TMPDIR:-${TEMP:-/tmp}}"
 
 # Examples that require external services not typically available in a
-# standard test environment.
+# standard test environment.  Run them with --all once the services and
+# credentials they need are in place.
 SKIP_BY_DEFAULT=(
     "04_http_and_mcp_tools"    # needs MCP server running
     "04_mcp_weather"           # needs MCP server running
     "24_code_execution"        # needs Docker
     "25_semantic_memory"       # needs vector store / extra deps
     "26_opentelemetry_tracing" # needs OTel collector
     "28_gpt_assistant_agent"   # needs OpenAI Assistants API key
+
+    # Act on real third-party accounts: these clone, branch, push, open pull
+    # requests or post messages, so a default run must not reach them.
+    "16c_credentials_cli_tools"          # needs AWS credentials; can open PRs
+    "16d_credentials_gh_cli"             # needs an authenticated gh CLI
+    "60_github_coding_agent"             # pushes branches, opens PRs
+    "60a_github_coding_agent_simple"     # clones and pushes to a real repo
+    "61_github_coding_agent_chained"     # needs GITHUB_TOKEN; pushes branches
+    "61a_github_coding_agent_claude_code" # needs GITHUB_TOKEN; pushes branches
+    "91_slack_autofix_agent"             # pushes, opens PRs, posts to Slack
+
+    # Block on stdin with no canned response in HITL_STDIN below, so they would
+    # sit until the per-example timeout.
+    "09d_human_tool"
+    "18_manual_selection"
+    "32_human_guardrail"
+    "62_coding_agent_openai"
+    "78_approval_workflow"
+    "81_chat_repl"
+    "82_coding_agent"
+    "82b_coding_agent_tui"
 )
 
 # HITL examples that call input() — we pipe automated responses via stdin.
@@ -117,7 +148,11 @@ echo " Running ${#EXAMPLES[@]} examples"
 if [[ ${#SKIPPED[@]} -gt 0 ]]; then
     echo " Skipping ${#SKIPPED[@]}: ${SKIPPED[*]}"
 fi
-echo " Timeout: ${TIMEOUT}s per example"
+if [[ -n "$TIMEOUT_BIN" ]]; then
+    echo " Timeout: ${TIMEOUT}s per example"
+else
+    echo " Timeout: none (no timeout binary found)"
+fi
 echo "=========================================="
 echo ""
 
@@ -141,9 +176,9 @@ for example in "${EXAMPLES[@]}"; do
     if [[ -n "$STDIN_RESPONSE" ]]; then
         # Use `yes` to provide unlimited identical responses — handles
         # cases where the LLM calls an approval tool multiple times.
-        RUN_CMD="yes '$STDIN_RESPONSE' | timeout $TIMEOUT $PYTHON $example"
+        RUN_CMD="yes '$STDIN_RESPONSE' | ${TIMEOUT_BIN:+$TIMEOUT_BIN $TIMEOUT }$PYTHON $example"
     else
-        RUN_CMD="timeout $TIMEOUT $PYTHON $example"
+        RUN_CMD="${TIMEOUT_BIN:+$TIMEOUT_BIN $TIMEOUT }$PYTHON $example"
     fi
 
     if eval "$RUN_CMD" > "$LOG_FILE" 2>&1; then