fix(nemo-relay): align adaptive config with tool_parallelism mode

Signed-off-by: mnajafian-nv <mnajafian@nvidia.com>

plugins/observability/nemo_relay/README.md

@@ -173,8 +173,8 @@ include an adaptive component in the same `plugins.toml`:
 kind = "adaptive"
 enabled = true
 
-[components.config]
-mode = "route"
+[components.config.tool_parallelism]
+mode = "observe_only"
 ```
 
 When the adaptive component is enabled and the installed NeMo Relay runtime
@@ -182,15 +182,16 @@ exposes `llm.execute(...)` / `tools.execute(...)`, Hermes routes LLM and tool
 execution through those middleware boundaries. The observer hooks still emit
 session, turn, approval, and subagent marks; the plugin skips its manual
 `llm.call` and `tools.call` spans for executions that are already managed by
-NeMo Relay.
+NeMo Relay. `tool_parallelism.mode = "observe_only"` keeps tool scheduling
+observational while still wrapping the real execution boundary.
 
 For the full generic Hermes middleware contract, see
 [`docs/middleware/README.md`](../../../docs/middleware/README.md).
 
 ## Canonical Local Examples
 
-The examples below use the official `nemo-relay==0.3` distribution and a local
-Ollama model served through the OpenAI-compatible API.
+The observe-only examples in this section use the official `nemo-relay==0.3`
+distribution and a local Ollama model served through the OpenAI-compatible API.
 
 ```bash
 pip install "nemo-relay==0.3"
@@ -404,8 +405,8 @@ version = 1
 kind = "adaptive"
 enabled = true
 
-[components.config]
-mode = "route"
+[components.config.tool_parallelism]
+mode = "observe_only"
 ```
 
 Enable it for Hermes:
@@ -438,11 +439,12 @@ for the same execution.
 ### Local Adaptive E2E
 
 This example enables both NeMo Relay observability export and adaptive execution
-middleware for a local Hermes run.
+middleware for a local Hermes run. This path requires a NeMo Relay runtime that
+supports `[components.config.tool_parallelism]`; the `nemo-relay==0.3`
+install used by the earlier observability-only examples does not support this
+adaptive config.
 
 ```bash
-pip install "nemo-relay==0.3"
-
 export HERMES_HOME=/tmp/hermes-middleware-test/hermes-home
 mkdir -p "$HERMES_HOME" /tmp/hermes-middleware-test/nemo-relay
 
@@ -484,8 +486,8 @@ agent_version = "local"
 kind = "adaptive"
 enabled = true
 
-[components.config]
-mode = "route"
+[components.config.tool_parallelism]
+mode = "observe_only"
 TOML
 
 export HERMES_NEMO_RELAY_PLUGINS_TOML=/tmp/hermes-middleware-test/nemo-relay/plugins.toml
@@ -510,8 +512,8 @@ middleware_execution_ok
 Expected ATOF shape:
 
 ```jsonl
-{"kind":"scope","category":"llm","name":"custom","scope_category":"start","metadata":{"session_id":"middleware-demo-session"},"data":{"mode":"route"}}
-{"kind":"scope","category":"tool","name":"terminal","scope_category":"start","metadata":{"session_id":"middleware-demo-session","tool_call_id":"call_terminal"},"data":{"mode":"route"}}
+{"kind":"scope","category":"llm","name":"custom","scope_category":"start","metadata":{"session_id":"middleware-demo-session"},"data":{"mode":"observe_only"}}
+{"kind":"scope","category":"tool","name":"terminal","scope_category":"start","metadata":{"session_id":"middleware-demo-session","tool_call_id":"call_terminal"},"data":{"mode":"observe_only"}}
 {"kind":"scope","category":"tool","name":"terminal","scope_category":"end","metadata":{"session_id":"middleware-demo-session","tool_call_id":"call_terminal","status":"ok"},"data":"{\"output\":\"middleware_execution_ok\",\"exit_code\":0,\"error\":null}"}
 ```
 

plugins/observability/nemo_relay/__init__.py

@@ -44,7 +44,7 @@ class _Settings:
     plugins_toml_path: str = ""
     plugins_config: dict[str, Any] | None = None
     adaptive_enabled: bool = False
-    adaptive_mode: str = "observe"
+    adaptive_mode: str = "observe_only"
     atof_enabled: bool = False
     atof_output_directory: str = ""
     atof_filename: str = "hermes-atof.jsonl"
@@ -611,11 +611,16 @@ def _enabled_component_config(
 
 def _adaptive_mode(config: dict[str, Any] | None) -> str:
     if not isinstance(config, dict):
-        return "observe"
+        return "observe_only"
+    tool_parallelism = config.get("tool_parallelism")
+    if isinstance(tool_parallelism, dict):
+        mode = tool_parallelism.get("mode")
+        if isinstance(mode, str) and mode.strip():
+            return mode.strip()
     mode = config.get("mode")
     if isinstance(mode, str) and mode.strip():
         return mode.strip()
-    return "observe"
+    return "observe_only"
 
 
 def _env(name: str) -> str:

tests/plugins/test_nemo_relay_plugin.py

@@ -457,8 +457,8 @@ version = 1
 kind = "adaptive"
 enabled = true
 
-[components.config]
-mode = "route"
+[components.config.tool_parallelism]
+mode = "observe_only"
 """,
         encoding="utf-8",
     )
@@ -506,7 +506,7 @@ mode = "route"
     assert response.choices == [raw_choice]
     assert seen_request["intercepted"] is True
     execute_start = next(event for event in fake.events if event[0] == "llm.execute.start")
-    assert execute_start[3]["data"]["mode"] == "route"
+    assert execute_start[3]["data"]["mode"] == "observe_only"
     execute_end = next(event for event in fake.events if event[0] == "llm.execute.end")
     assert execute_end[2] == {
         "model": "demo-model",
@@ -527,6 +527,84 @@ mode = "route"
     }
 
 
+def _adaptive_llm_execute_mode(tmp_path, monkeypatch, plugins_toml_text: str) -> str:
+    fake = _FakeNemoRelay()
+    plugin = _fresh_plugin(monkeypatch, fake)
+    plugins_toml = tmp_path / "plugins.toml"
+    plugins_toml.write_text(plugins_toml_text, encoding="utf-8")
+    monkeypatch.setenv("HERMES_NEMO_RELAY_PLUGINS_TOML", str(plugins_toml))
+
+    plugin.on_llm_execution_middleware(
+        session_id="s1",
+        provider="anthropic",
+        model="demo-model",
+        request={"messages": [{"role": "user", "content": "hi"}]},
+        next_call=lambda request: {"raw": request},
+    )
+
+    execute_start = next(event for event in fake.events if event[0] == "llm.execute.start")
+    return execute_start[3]["data"]["mode"]
+
+
+def test_nemo_relay_adaptive_llm_execution_middleware_defaults_to_observe_only_when_mode_is_unset(
+    tmp_path, monkeypatch
+):
+    mode = _adaptive_llm_execute_mode(
+        tmp_path,
+        monkeypatch,
+        """
+version = 1
+
+[[components]]
+kind = "adaptive"
+enabled = true
+
+[components.config]
+version = 1
+""",
+    )
+    assert mode == "observe_only"
+
+
+def test_nemo_relay_adaptive_llm_execution_middleware_accepts_legacy_top_level_mode(tmp_path, monkeypatch):
+    mode = _adaptive_llm_execute_mode(
+        tmp_path,
+        monkeypatch,
+        """
+version = 1
+
+[[components]]
+kind = "adaptive"
+enabled = true
+
+[components.config]
+mode = "route"
+""",
+    )
+    assert mode == "route"
+
+
+def test_nemo_relay_adaptive_llm_execution_middleware_prefers_tool_parallelism_mode(tmp_path, monkeypatch):
+    mode = _adaptive_llm_execute_mode(
+        tmp_path,
+        monkeypatch,
+        """
+version = 1
+
+[[components]]
+kind = "adaptive"
+enabled = true
+
+[components.config]
+mode = "route"
+
+[components.config.tool_parallelism]
+mode = "schedule"
+""",
+    )
+    assert mode == "schedule"
+
+
 def test_nemo_relay_llm_execution_middleware_calls_through_without_adaptive(monkeypatch):
     fake = _FakeNemoRelay()
     plugin = _fresh_plugin(monkeypatch, fake)
@@ -555,8 +633,8 @@ version = 1
 kind = "adaptive"
 enabled = true
 
-[components.config]
-mode = "route"
+[components.config.tool_parallelism]
+mode = "observe_only"
 """,
         encoding="utf-8",
     )
@@ -582,7 +660,7 @@ mode = "route"
     assert response == {"raw": True, "args": {"command": "pwd", "intercepted": True}}
     assert seen_args["intercepted"] is True
     execute_start = next(event for event in fake.events if event[0] == "tool.execute.start")
-    assert execute_start[3]["data"]["mode"] == "route"
+    assert execute_start[3]["data"]["mode"] == "observe_only"
     assert execute_start[3]["data"]["tool_call_id"] == "tool-1"
 
 
@@ -613,8 +691,8 @@ version = 1
 kind = "adaptive"
 enabled = true
 
-[components.config]
-mode = "route"
+[components.config.tool_parallelism]
+mode = "observe_only"
 """,
         encoding="utf-8",
     )