fix(evals): honor --base-url/--api-key for first-party eval backends (#535)

`jarvis eval run --base-url ... --api-key ...` was silently dropped for
jarvis-direct/jarvis-agent (_build_backend only forwarded the flags to
hermes/openclaw) and ignored by terminalbench-native, which hardcoded
api_base="http://localhost:8000/v1". Worse, with --base-url set the
engine-discovery fallback silently substituted ANY healthy local engine
(observed: requested vllm + healthy endpoint at --base-url, got
OllamaEngine@localhost:11434 — the requested URL was never contacted).

Changes:
- _OpenAICompatibleEngine gains an api_key param (Bearer Authorization
  header on the httpx client; {ENGINE_ID}_API_KEY env fallback with
  hyphen-sanitized names; no header when unset).
- New non-registered OpenAICompatEngine + normalize_openai_base_url()
  (strips a single literal trailing "/v1" so request paths don't double).
- SystemBuilder.engine_instance() injects a pre-built engine; build()
  health-checks it and fails loudly naming the host instead of falling
  back to discovery. Discovery substitution after an explicit -e key now
  logs a warning.
- JarvisDirectBackend/JarvisAgentBackend accept base_url/api_key; on
  base_url they pin an OpenAICompatEngine to that endpoint with a
  fail-fast pre-flight (actionable error naming the URL and probe).
- _build_backend forwards base_url/api_key to first-party backends on
  the CLI path; _run_terminalbench_native receives --base-url as
  api_base (single /v1 suffix) and exports OPENAI_API_KEY around the
  in-process harness run (terminus-2 routes via LiteLLM).
- Suite TOML [backend.external] stays scoped to hermes/openclaw
  (suite_mode=True in the suite drivers) — first-party suite semantics
  are explicitly deferred. The config-host path is untouched.
- Help text updated on both CLI surfaces; KNOWN_BACKENDS now lists
  hermes/openclaw/terminalbench-native.

Fixes the eval-CLI endpoint gap reported by the downstream team.

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

src/openjarvis/cli/compose_cmd.py

@@ -332,7 +332,7 @@ def compose_bench(
         for i, rc in enumerate(run_configs, 1):
             console.print(f"\n[bold]Run {i}/{len(run_configs)}:[/bold] {rc.benchmark}")
             try:
-                summary = _run_single(rc, console=console)
+                summary = _run_single(rc, console=console, suite_mode=True)
                 results_table.add_row(
                     rc.benchmark,
                     f"{summary.accuracy:.4f}",

src/openjarvis/cli/eval_cmd.py

@@ -61,6 +61,12 @@ KNOWN_BENCHMARKS = {
 KNOWN_BACKENDS = {
     "jarvis-direct": "Engine-level inference (local or cloud)",
     "jarvis-agent": "Agent-level inference with tool calling",
+    "hermes": "Real Hermes Agent (Nous Research) via subprocess",
+    "openclaw": "Real OpenClaw via Node subprocess",
+    "terminalbench-native": (
+        "TerminalBench V2.1 via terminal-bench Harness "
+        "(selected with -b terminalbench-native)"
+    ),
 }
 
 
@@ -146,7 +152,9 @@ def eval_list() -> None:
     "base_url",
     default=None,
     help=(
-        "OpenAI-compat endpoint URL for hermes/openclaw backends "
+        "OpenAI-compatible endpoint for the model under eval. Required for "
+        "hermes/openclaw; for jarvis-direct/jarvis-agent/terminalbench-native "
+        "it bypasses engine discovery and targets this URL directly "
         "(env: JARVIS_BACKEND_BASE_URL)."
     ),
 )
@@ -154,7 +162,11 @@ def eval_list() -> None:
     "--api-key",
     "api_key",
     default=None,
-    help=("API key for the hermes/openclaw endpoint (env: JARVIS_BACKEND_API_KEY)."),
+    help=(
+        "API key for the --base-url endpoint, sent as a Bearer token. "
+        "Required for hermes/openclaw; optional for first-party backends "
+        "(env: JARVIS_BACKEND_API_KEY)."
+    ),
 )
 @click.option(
     "--agent",
@@ -347,7 +359,7 @@ def eval_run(
                 f"{rc.benchmark} / {rc.model}"
             )
             try:
-                summary = _run_single(rc, console=console)
+                summary = _run_single(rc, console=console, suite_mode=True)
                 console.print(
                     f"  [green]{summary.accuracy:.4f}[/green] "
                     f"({summary.correct}/{summary.scored_samples})"
@@ -399,8 +411,10 @@ def eval_run(
         sheets_spreadsheet_id=sheets_spreadsheet_id,
         sheets_worksheet=sheets_worksheet,
         sheets_credentials_path=sheets_credentials_path,
-        # Spec §6.2 — for hermes/openclaw external backends. Falls back to env vars
-        # so users can also set JARVIS_BACKEND_BASE_URL/JARVIS_BACKEND_API_KEY.
+        # OpenAI-compatible endpoint for the model under eval. Required for
+        # hermes/openclaw (Spec §6.2); honored by first-party backends too on
+        # this CLI path. Falls back to env vars so users can also set
+        # JARVIS_BACKEND_BASE_URL/JARVIS_BACKEND_API_KEY.
         base_url=base_url or os.environ.get("JARVIS_BACKEND_BASE_URL"),
         api_key=api_key or os.environ.get("JARVIS_BACKEND_API_KEY"),
     )

src/openjarvis/engine/_openai_compat.py

@@ -28,12 +28,31 @@ class _OpenAICompatibleEngine(InferenceEngine):
     _default_host: str = "http://localhost:8000"
     _api_prefix: str = "/v1"
 
-    def __init__(self, host: str | None = None, *, timeout: float = 600.0) -> None:
+    def __init__(
+        self,
+        host: str | None = None,
+        *,
+        api_key: str | None = None,
+        timeout: float = 600.0,
+    ) -> None:
         import os
 
-        env_key = f"{self.engine_id.upper()}_HOST"
-        self._host = (host or os.environ.get(env_key) or self._default_host).rstrip("/")
-        self._client = httpx.Client(base_url=self._host, timeout=timeout)
+        # Sanitize the engine id for env-var lookup ("openai-compat" ->
+        # "OPENAI_COMPAT_..."); shells cannot set hyphenated variable names.
+        env_prefix = self.engine_id.upper().replace("-", "_")
+        self._host = (
+            host or os.environ.get(f"{env_prefix}_HOST") or self._default_host
+        ).rstrip("/")
+        # Bearer auth for endpoints started with e.g. ``vllm serve --api-key``.
+        # Setting it on the client covers generate/stream/stream_full/
+        # list_models/health alike; ``None`` keeps requests header-free.
+        self._api_key = api_key or os.environ.get(f"{env_prefix}_API_KEY") or None
+        headers = (
+            {"Authorization": f"Bearer {self._api_key}"} if self._api_key else None
+        )
+        self._client = httpx.Client(
+            base_url=self._host, timeout=timeout, headers=headers
+        )
 
     # -- InferenceEngine interface ------------------------------------------
 

src/openjarvis/engine/openai_compat_engines.py

@@ -1,5 +1,7 @@
 """Data-driven registration of OpenAI-compatible inference engines."""
 
+from __future__ import annotations
+
 from openjarvis.core.registry import EngineRegistry
 from openjarvis.engine._openai_compat import _OpenAICompatibleEngine
 
@@ -25,4 +27,35 @@ for _key, (_cls_name, _default_host, _api_prefix) in _ENGINES.items():
     EngineRegistry.register(_key)(_cls)
     globals()[_cls_name] = _cls
 
-__all__ = [name for name, _, _ in _ENGINES.values()]
+
+def normalize_openai_base_url(url: str) -> str:
+    """Strip a single trailing ``/v1`` segment from a user-supplied base URL.
+
+    Users habitually pass ``http://host:8000/v1`` (the full OpenAI-compatible
+    prefix); the engine's ``_api_prefix`` re-appends ``/v1`` to every request
+    path, so a trailing copy would double up as ``/v1/v1``. Only a literal
+    trailing ``/v1`` is stripped — proxy/gateway path prefixes are preserved.
+    """
+    base = url.rstrip("/")
+    if base.endswith("/v1"):
+        base = base[: -len("/v1")]
+    return base
+
+
+class OpenAICompatEngine(_OpenAICompatibleEngine):
+    """Generic engine for an explicitly-provided OpenAI-compatible endpoint.
+
+    Deliberately NOT registered in ``EngineRegistry``: it is only ever
+    constructed with an explicit host (e.g. ``jarvis eval --base-url``), so
+    registering it would just add a useless localhost discovery probe and
+    interact with the per-test registry wipe.
+    """
+
+    engine_id = "openai-compat"
+    _api_prefix = "/v1"
+
+
+__all__ = [name for name, _, _ in _ENGINES.values()] + [
+    "OpenAICompatEngine",
+    "normalize_openai_base_url",
+]

src/openjarvis/evals/backends/_endpoint_util.py

@@ -0,0 +1,52 @@
+"""Shared helper for targeting an explicit OpenAI-compatible endpoint.
+
+Used by the first-party eval backends (jarvis-direct, jarvis-agent) when
+``--base-url`` is given: the eval must use exactly that endpoint, with no
+silent fallback to whatever other engine discovery happens to find.
+"""
+
+from __future__ import annotations
+
+import logging
+from typing import Optional
+
+logger = logging.getLogger(__name__)
+
+
+def build_endpoint_engine(
+    base_url: str,
+    api_key: Optional[str] = None,
+    engine_key: Optional[str] = None,
+):
+    """Construct an :class:`OpenAICompatEngine` pinned to ``base_url``.
+
+    Pre-flight health-checks the endpoint and raises a loud, actionable
+    error when it is unreachable — engine discovery is never consulted.
+    """
+    from openjarvis.engine.openai_compat_engines import (
+        OpenAICompatEngine,
+        normalize_openai_base_url,
+    )
+
+    if engine_key:
+        logger.warning(
+            "Both an engine key (%r) and base_url (%r) were given; "
+            "base_url wins — targeting the endpoint directly.",
+            engine_key,
+            base_url,
+        )
+    host = normalize_openai_base_url(base_url)
+    engine = OpenAICompatEngine(host=host, api_key=api_key)
+    if not engine.health():
+        engine.close()
+        raise RuntimeError(
+            f"--base-url endpoint not reachable: {base_url} "
+            f"(GET {host}/v1/models failed). Is an OpenAI-compatible server "
+            "(e.g. `vllm serve`) running at that address? If it requires "
+            "authentication (HTTP 401), pass --api-key or set "
+            "JARVIS_BACKEND_API_KEY."
+        )
+    return engine
+
+
+__all__ = ["build_endpoint_engine"]

src/openjarvis/evals/backends/jarvis_agent.py

@@ -31,6 +31,8 @@ class JarvisAgentBackend(InferenceBackend):
         max_turns: Optional[int] = None,
         skills_enabled: bool = True,
         overlay_dir: Optional[Path] = None,
+        base_url: Optional[str] = None,
+        api_key: Optional[str] = None,
     ) -> None:
         from openjarvis.system import SystemBuilder
 
@@ -40,7 +42,17 @@ class JarvisAgentBackend(InferenceBackend):
         self._gpu_metrics = gpu_metrics
 
         builder = SystemBuilder()
-        if engine_key:
+        if base_url:
+            # Explicit endpoint targeting (--base-url): pin the eval to
+            # exactly this OpenAI-compatible endpoint. Fails fast if it is
+            # unreachable; never falls back to a discovered engine.
+            from openjarvis.evals.backends._endpoint_util import (
+                build_endpoint_engine,
+            )
+
+            engine = build_endpoint_engine(base_url, api_key, engine_key)
+            builder.engine_instance(engine, key=engine_key or "openai-compat")
+        elif engine_key:
             builder.engine(engine_key)
         if model:
             builder.model(model)

src/openjarvis/evals/backends/jarvis_direct.py

@@ -24,6 +24,8 @@ class JarvisDirectBackend(InferenceBackend):
         engine_key: Optional[str] = None,
         telemetry: bool = False,
         gpu_metrics: bool = False,
+        base_url: Optional[str] = None,
+        api_key: Optional[str] = None,
     ) -> None:
         from openjarvis.system import SystemBuilder
 
@@ -31,7 +33,17 @@ class JarvisDirectBackend(InferenceBackend):
         self._gpu_metrics = gpu_metrics
 
         builder = SystemBuilder()
-        if engine_key:
+        if base_url:
+            # Explicit endpoint targeting (--base-url): pin the eval to
+            # exactly this OpenAI-compatible endpoint. Fails fast if it is
+            # unreachable; never falls back to a discovered engine.
+            from openjarvis.evals.backends._endpoint_util import (
+                build_endpoint_engine,
+            )
+
+            engine = build_endpoint_engine(base_url, api_key, engine_key)
+            builder.engine_instance(engine, key=engine_key or "openai-compat")
+        elif engine_key:
             builder.engine(engine_key)
         # Propagate gpu_metrics to the runtime config so SystemBuilder
         # creates an EnergyMonitor / GpuMonitor for the InstrumentedEngine.

src/openjarvis/evals/cli.py

@@ -183,14 +183,28 @@ def _build_backend(
     max_turns: Optional[int] = None,
     base_url: Optional[str] = None,
     api_key: Optional[str] = None,
+    first_party_endpoint: bool = True,
 ):
     """Construct the appropriate backend.
 
-    For "hermes" and "openclaw" backends, ``base_url`` and ``api_key`` are
-    REQUIRED — these foreign frameworks need an OpenAI-compatible endpoint
-    to send model calls to. Pass them via the eval config's
-    ``[backend.external]`` section or env vars.
+    ``base_url``/``api_key`` point at the OpenAI-compatible endpoint serving
+    the model under eval:
+
+    - For "hermes" and "openclaw" they are REQUIRED — these foreign
+      frameworks always call out to an external endpoint.
+    - "jarvis-direct" and "jarvis-agent" honor them when
+      ``first_party_endpoint`` is True (the CLI ``--base-url`` path): the
+      eval targets exactly that endpoint — no engine-discovery fallback —
+      and fails fast if it is unreachable. Suite mode passes
+      ``first_party_endpoint=False`` so the suite TOML's
+      ``[backend.external]`` section stays scoped to hermes/openclaw
+      (extending it to first-party backends is explicitly deferred).
     """
+    if not first_party_endpoint:
+        fp_base_url = fp_api_key = None
+    else:
+        fp_base_url, fp_api_key = base_url, api_key
+
     if backend_name == "jarvis-agent":
         from openjarvis.evals.backends.jarvis_agent import JarvisAgentBackend
 
@@ -202,6 +216,8 @@ def _build_backend(
             gpu_metrics=gpu_metrics,
             model=model,
             max_turns=max_turns,
+            base_url=fp_base_url,
+            api_key=fp_api_key,
         )
     elif backend_name == "jarvis-direct":
         from openjarvis.evals.backends.jarvis_direct import JarvisDirectBackend
@@ -210,6 +226,8 @@ def _build_backend(
             engine_key=engine_key,
             telemetry=telemetry,
             gpu_metrics=gpu_metrics,
+            base_url=fp_base_url,
+            api_key=fp_api_key,
         )
     elif backend_name == "hermes":
         from openjarvis.evals.backends.external import HermesBackend
@@ -656,8 +674,20 @@ def _build_trackers(config) -> list:
     return trackers
 
 
-def _run_terminalbench_native(config, console: Console) -> object:
-    """Run TerminalBench V2.1 natively via terminal-bench Harness."""
+def _run_terminalbench_native(
+    config,
+    console: Console,
+    *,
+    base_url: Optional[str] = None,
+    api_key: Optional[str] = None,
+) -> object:
+    """Run TerminalBench V2.1 natively via terminal-bench Harness.
+
+    ``base_url`` (from ``--base-url`` / JARVIS_BACKEND_BASE_URL) targets an
+    already-running OpenAI-compatible endpoint; when unset, the legacy local
+    vLLM default (http://localhost:8000/v1) is used.
+    """
+    from openjarvis.engine.openai_compat_engines import normalize_openai_base_url
     from openjarvis.evals.backends.terminalbench_native import (
         TerminalBenchNativeBackend,
     )
@@ -668,9 +698,16 @@ def _run_terminalbench_native(config, console: Console) -> object:
     litellm_model = f"openai/{model}"
     output_dir = getattr(config, "output_path", None) or "results/terminalbench-native/"
 
+    # Normalize to exactly one trailing "/v1" — LiteLLM's api_base wants the
+    # full OpenAI-compatible prefix, and users pass both forms of the URL.
+    if base_url:
+        api_base = normalize_openai_base_url(base_url) + "/v1"
+    else:
+        api_base = "http://localhost:8000/v1"
+
     backend = TerminalBenchNativeBackend(
         model=litellm_model,
-        api_base="http://localhost:8000/v1",
+        api_base=api_base,
         temperature=config.temperature,
         max_samples=config.max_samples,
         output_dir=output_dir,
@@ -683,9 +720,25 @@ def _run_terminalbench_native(config, console: Console) -> object:
     model_slug = re.sub(r"[^a-z0-9_-]", "-", model.lower().replace("/", "-"))
     run_id = f"tb21-{model_slug}"
     console.print(f"  Running TerminalBench V2.1 natively: {model}")
+    console.print(f"  API base: {api_base}")
     console.print(f"  Harness run_id: {run_id}")
 
-    results = backend.run_harness(run_id)
+    if api_key:
+        # terminus-2 routes model calls through LiteLLM with the "openai/"
+        # prefix, which reads OPENAI_API_KEY from the environment. The
+        # harness runs in-process, so set the var for the duration of the
+        # run and restore the previous value afterwards.
+        prev_key = os.environ.get("OPENAI_API_KEY")
+        os.environ["OPENAI_API_KEY"] = api_key
+        try:
+            results = backend.run_harness(run_id)
+        finally:
+            if prev_key is None:
+                os.environ.pop("OPENAI_API_KEY", None)
+            else:
+                os.environ["OPENAI_API_KEY"] = prev_key
+    else:
+        results = backend.run_harness(run_id)
 
     # Convert BenchmarkResults to RunSummary
     total = len(results.trial_results) if hasattr(results, "trial_results") else 0
@@ -711,18 +764,47 @@ def _run_terminalbench_native(config, console: Console) -> object:
     )
 
 
-def _run_single(config, console: Optional[Console] = None) -> object:
-    """Run a single eval from a RunConfig and return the summary."""
+def _run_single(
+    config,
+    console: Optional[Console] = None,
+    *,
+    suite_mode: bool = False,
+) -> object:
+    """Run a single eval from a RunConfig and return the summary.
+
+    ``suite_mode=True`` (TOML-suite drivers) scopes ``config.base_url`` /
+    ``config.api_key`` — stamped from the suite's ``[backend.external]``
+    section onto every RunConfig — to the hermes/openclaw backends only;
+    extending suite-level endpoint targeting to first-party backends is
+    explicitly deferred. The CLI single-run path (``suite_mode=False``)
+    honors ``--base-url``/``--api-key`` for every backend.
+    """
     from openjarvis.evals.core.runner import EvalRunner
 
     if console is None:
         console = Console()
 
+    _metadata = getattr(config, "metadata", None) or {}
+    base_url = (
+        getattr(config, "base_url", None)
+        or _metadata.get("base_url")
+        or os.environ.get("JARVIS_BACKEND_BASE_URL")
+    )
+    api_key = (
+        getattr(config, "api_key", None)
+        or _metadata.get("api_key")
+        or os.environ.get("JARVIS_BACKEND_API_KEY")
+    )
+
     # TerminalBench V2.1 native: use terminal-bench Harness directly
     if config.benchmark == "terminalbench-native":
-        return _run_terminalbench_native(config, console)
+        return _run_terminalbench_native(
+            config,
+            console,
+            base_url=None if suite_mode else base_url,
+            api_key=None if suite_mode else api_key,
+        )
 
-    _metadata = getattr(config, "metadata", None) or {}
     eval_backend = _build_backend(
         config.backend,
         config.engine_key,
@@ -732,16 +814,9 @@ def _run_single(config, console: Optional[Console] = None) -> object:
         gpu_metrics=getattr(config, "gpu_metrics", False),
         model=config.model,
         max_turns=getattr(config, "max_turns", None),
-        base_url=(
-            getattr(config, "base_url", None)
-            or _metadata.get("base_url")
-            or os.environ.get("JARVIS_BACKEND_BASE_URL")
-        ),
-        api_key=(
-            getattr(config, "api_key", None)
-            or _metadata.get("api_key")
-            or os.environ.get("JARVIS_BACKEND_API_KEY")
-        ),
+        base_url=base_url,
+        api_key=api_key,
+        first_party_endpoint=not suite_mode,
     )
     dataset = _build_dataset(config.benchmark)
     # Inject engine config for benchmarks that run their own simulation
@@ -1070,7 +1145,7 @@ def _run_from_config(
             f"Run {i}/{len(run_configs)}: {rc.benchmark} / {rc.model}",
         )
         try:
-            summary = _run_single(rc, console=console)
+            summary = _run_single(rc, console=console, suite_mode=True)
             summaries.append(summary)
             console.print(
                 f"  [green]{summary.accuracy:.4f}[/green] "
@@ -1115,12 +1190,21 @@ def main():
 @click.option(
     "--base-url",
     default=None,
-    help="OpenAI-compat endpoint for hermes/openclaw",
+    help=(
+        "OpenAI-compatible endpoint for the model under eval. Required for "
+        "hermes/openclaw; for jarvis-direct/jarvis-agent/terminalbench-native "
+        "it bypasses engine discovery and targets this URL directly "
+        "(env: JARVIS_BACKEND_BASE_URL)."
+    ),
 )
 @click.option(
     "--api-key",
     default=None,
-    help="API key for hermes/openclaw endpoint",
+    help=(
+        "API key for the --base-url endpoint, sent as a Bearer token. "
+        "Required for hermes/openclaw; optional for first-party backends "
+        "(env: JARVIS_BACKEND_API_KEY)."
+    ),
 )
 @click.option("-m", "--model", default=None, help="Model identifier")
 @click.option(
@@ -1526,8 +1610,7 @@ def summarize(jsonl_path):
     default=None,
     type=click.Path(),
     help=(
-        "Output JSONL path. Defaults to <jsonl>.reparsed when "
-        "--in-place is not set."
+        "Output JSONL path. Defaults to <jsonl>.reparsed when --in-place is not set."
     ),
 )
 @click.option(
@@ -1642,9 +1725,7 @@ def reparse_judge(jsonl_path, out_path, in_place, summary_out):
         _json.dump(summary, f, indent=2)
 
     old_cont = [float(s) for s in old_scores if s is not None]
-    old_acc = (
-        sum(1 for s in old_cont if s >= 0.5) / len(old_cont) if old_cont else 0.0
-    )
+    old_acc = sum(1 for s in old_cont if s >= 0.5) / len(old_cont) if old_cont else 0.0
     old_mean = sum(old_cont) / len(old_cont) if old_cont else 0.0
     new_mean = sum(cont) / len(cont) if cont else 0.0
     mean_shift = new_mean - old_mean

src/openjarvis/evals/tests/test_backends.py

@@ -4,6 +4,27 @@ from __future__ import annotations
 
 from unittest.mock import MagicMock, patch
 
+import httpx
+import pytest
+import respx
+
+
+def _mock_builder() -> MagicMock:
+    """A SystemBuilder mock whose fluent methods chain like the real one."""
+    builder = MagicMock()
+    for method in (
+        "engine",
+        "engine_instance",
+        "model",
+        "agent",
+        "tools",
+        "telemetry",
+        "traces",
+    ):
+        getattr(builder, method).return_value = builder
+    builder.build.return_value = MagicMock()
+    return builder
+
 
 class TestJarvisDirectBackend:
     @patch("openjarvis.system.SystemBuilder")
@@ -137,3 +158,130 @@ class TestJarvisAgentBackend:
         assert result["content"] == "The answer is 4."
         assert result["turns"] == 2
         assert len(result["tool_results"]) == 1
+
+
+class TestJarvisDirectBackendBaseUrl:
+    """--base-url targeting for the jarvis-direct backend."""
+
+    @patch("openjarvis.system.SystemBuilder")
+    def test_base_url_injects_pinned_openai_compat_engine(self, mock_builder_cls):
+        from openjarvis.engine.openai_compat_engines import OpenAICompatEngine
+        from openjarvis.evals.backends.jarvis_direct import JarvisDirectBackend
+
+        mock_builder = _mock_builder()
+        mock_builder_cls.return_value = mock_builder
+
+        with respx.mock:
+            respx.get("http://127.0.0.1:18999/v1/models").mock(
+                return_value=httpx.Response(200, json={"data": []})
+            )
+            JarvisDirectBackend(base_url="http://127.0.0.1:18999/v1", api_key="sk-x")
+
+        mock_builder.engine_instance.assert_called_once()
+        injected = mock_builder.engine_instance.call_args[0][0]
+        assert isinstance(injected, OpenAICompatEngine)
+        # Trailing /v1 is normalized away so request paths don't double up.
+        assert injected._host == "http://127.0.0.1:18999"
+        assert injected._api_key == "sk-x"
+        # The discovery path must not be engaged at all.
+        mock_builder.engine.assert_not_called()
+
+    @patch("openjarvis.system.SystemBuilder")
+    def test_unreachable_base_url_fails_fast_naming_url(self, mock_builder_cls):
+        from openjarvis.evals.backends.jarvis_direct import JarvisDirectBackend
+
+        mock_builder = _mock_builder()
+        mock_builder_cls.return_value = mock_builder
+
+        with respx.mock:
+            respx.get("http://127.0.0.1:18998/v1/models").mock(
+                side_effect=httpx.ConnectError("connection refused")
+            )
+            with pytest.raises(RuntimeError, match=r"http://127\.0\.0\.1:18998"):
+                JarvisDirectBackend(base_url="http://127.0.0.1:18998")
+
+        # No silent engine substitution: the system is never built.
+        mock_builder.engine_instance.assert_not_called()
+        mock_builder.build.assert_not_called()
+
+    @patch("openjarvis.system.SystemBuilder")
+    def test_no_base_url_keeps_engine_key_path(self, mock_builder_cls):
+        from openjarvis.evals.backends.jarvis_direct import JarvisDirectBackend
+
+        mock_builder = _mock_builder()
+        mock_builder_cls.return_value = mock_builder
+
+        JarvisDirectBackend(engine_key="vllm")
+        mock_builder.engine.assert_called_with("vllm")
+        mock_builder.engine_instance.assert_not_called()
+
+    @patch("openjarvis.system.SystemBuilder")
+    def test_base_url_wins_over_engine_key(self, mock_builder_cls):
+        from openjarvis.evals.backends.jarvis_direct import JarvisDirectBackend
+
+        mock_builder = _mock_builder()
+        mock_builder_cls.return_value = mock_builder
+
+        with respx.mock:
+            respx.get("http://127.0.0.1:18999/v1/models").mock(
+                return_value=httpx.Response(200, json={"data": []})
+            )
+            JarvisDirectBackend(engine_key="vllm", base_url="http://127.0.0.1:18999")
+
+        mock_builder.engine.assert_not_called()
+        mock_builder.engine_instance.assert_called_once()
+        # The engine key is kept as the label for the injected engine.
+        assert mock_builder.engine_instance.call_args.kwargs["key"] == "vllm"
+
+
+class TestJarvisAgentBackendBaseUrl:
+    """--base-url targeting for the jarvis-agent backend."""
+
+    @patch("openjarvis.system.SystemBuilder")
+    def test_base_url_injects_pinned_openai_compat_engine(self, mock_builder_cls):
+        from openjarvis.engine.openai_compat_engines import OpenAICompatEngine
+        from openjarvis.evals.backends.jarvis_agent import JarvisAgentBackend
+
+        mock_builder = _mock_builder()
+        mock_builder_cls.return_value = mock_builder
+
+        with respx.mock:
+            respx.get("http://127.0.0.1:18999/v1/models").mock(
+                return_value=httpx.Response(200, json={"data": []})
+            )
+            JarvisAgentBackend(base_url="http://127.0.0.1:18999/v1", api_key="sk-x")
+
+        mock_builder.engine_instance.assert_called_once()
+        injected = mock_builder.engine_instance.call_args[0][0]
+        assert isinstance(injected, OpenAICompatEngine)
+        assert injected._host == "http://127.0.0.1:18999"
+        assert injected._api_key == "sk-x"
+        mock_builder.engine.assert_not_called()
+
+    @patch("openjarvis.system.SystemBuilder")
+    def test_unreachable_base_url_fails_fast_naming_url(self, mock_builder_cls):
+        from openjarvis.evals.backends.jarvis_agent import JarvisAgentBackend
+
+        mock_builder = _mock_builder()
+        mock_builder_cls.return_value = mock_builder
+
+        with respx.mock:
+            respx.get("http://127.0.0.1:18998/v1/models").mock(
+                side_effect=httpx.ConnectError("connection refused")
+            )
+            with pytest.raises(RuntimeError, match=r"http://127\.0\.0\.1:18998"):
+                JarvisAgentBackend(base_url="http://127.0.0.1:18998")
+
+        mock_builder.engine_instance.assert_not_called()
+        mock_builder.build.assert_not_called()
+
+    @patch("openjarvis.system.SystemBuilder")
+    def test_no_base_url_keeps_engine_key_path(self, mock_builder_cls):
+        from openjarvis.evals.backends.jarvis_agent import JarvisAgentBackend
+
+        mock_builder = _mock_builder()
+        mock_builder_cls.return_value = mock_builder
+
+        JarvisAgentBackend(engine_key="vllm")
+        mock_builder.engine.assert_called_with("vllm")
+        mock_builder.engine_instance.assert_not_called()

src/openjarvis/evals/tests/test_cli_endpoint.py

@@ -0,0 +1,190 @@
+"""--base-url/--api-key forwarding through the eval CLI plumbing.
+
+Covers the fix for the eval-CLI endpoint gap: the flags used to be silently
+dropped for jarvis-direct/jarvis-agent and ignored by terminalbench-native
+(which hardcoded api_base="http://localhost:8000/v1").
+"""
+
+from __future__ import annotations
+
+import io
+import os
+from types import SimpleNamespace
+from unittest.mock import MagicMock, patch
+
+import click
+import pytest
+from rich.console import Console
+
+from openjarvis.evals.cli import _build_backend, _run_terminalbench_native
+from openjarvis.evals.core.types import RunConfig
+
+
+def _quiet_console() -> Console:
+    return Console(file=io.StringIO())
+
+
+def _tb_config(**overrides) -> RunConfig:
+    defaults = dict(
+        benchmark="terminalbench-native",
+        backend="jarvis-direct",
+        model="my-model",
+        max_samples=1,
+        max_workers=1,
+        temperature=0.2,
+    )
+    defaults.update(overrides)
+    return RunConfig(**defaults)
+
+
+class TestBuildBackendForwardsEndpoint:
+    @patch("openjarvis.evals.backends.jarvis_direct.JarvisDirectBackend")
+    def test_jarvis_direct_receives_base_url_and_api_key(self, mock_cls):
+        _build_backend(
+            "jarvis-direct",
+            "vllm",
+            "orchestrator",
+            [],
+            base_url="http://node7:8123/v1",
+            api_key="sk-k",
+        )
+        kwargs = mock_cls.call_args.kwargs
+        assert kwargs["base_url"] == "http://node7:8123/v1"
+        assert kwargs["api_key"] == "sk-k"
+
+    @patch("openjarvis.evals.backends.jarvis_agent.JarvisAgentBackend")
+    def test_jarvis_agent_receives_base_url_and_api_key(self, mock_cls):
+        _build_backend(
+            "jarvis-agent",
+            "vllm",
+            "orchestrator",
+            ["calculator"],
+            base_url="http://node7:8123/v1",
+            api_key="sk-k",
+        )
+        kwargs = mock_cls.call_args.kwargs
+        assert kwargs["base_url"] == "http://node7:8123/v1"
+        assert kwargs["api_key"] == "sk-k"
+
+    @patch("openjarvis.evals.backends.jarvis_direct.JarvisDirectBackend")
+    def test_suite_mode_scopes_endpoint_to_external_backends(self, mock_cls):
+        """[backend.external] suite semantics stay hermes/openclaw-only:
+        first_party_endpoint=False must not forward to first-party."""
+        _build_backend(
+            "jarvis-direct",
+            "vllm",
+            "orchestrator",
+            [],
+            base_url="http://node7:8123/v1",
+            api_key="sk-k",
+            first_party_endpoint=False,
+        )
+        kwargs = mock_cls.call_args.kwargs
+        assert kwargs["base_url"] is None
+        assert kwargs["api_key"] is None
+
+    def test_hermes_still_requires_base_url_and_api_key(self):
+        with pytest.raises(click.UsageError, match="hermes"):
+            _build_backend("hermes", None, "orchestrator", [])
+
+    def test_openclaw_still_requires_base_url_and_api_key(self):
+        with pytest.raises(click.UsageError, match="openclaw"):
+            _build_backend("openclaw", None, "orchestrator", [])
+
+
+class TestTerminalBenchNativeApiBase:
+    @patch("openjarvis.evals.backends.terminalbench_native.TerminalBenchNativeBackend")
+    def test_base_url_passed_through_as_api_base(self, mock_cls):
+        mock_backend = MagicMock()
+        mock_backend.run_harness.return_value = SimpleNamespace(trial_results=[])
+        mock_cls.return_value = mock_backend
+
+        _run_terminalbench_native(
+            _tb_config(),
+            _quiet_console(),
+            base_url="http://node7:8123/v1",
+        )
+        assert mock_cls.call_args.kwargs["api_base"] == "http://node7:8123/v1"
+
+    @patch("openjarvis.evals.backends.terminalbench_native.TerminalBenchNativeBackend")
+    def test_base_url_without_v1_gets_single_v1_suffix(self, mock_cls):
+        mock_backend = MagicMock()
+        mock_backend.run_harness.return_value = SimpleNamespace(trial_results=[])
+        mock_cls.return_value = mock_backend
+
+        _run_terminalbench_native(
+            _tb_config(),
+            _quiet_console(),
+            base_url="http://node7:8123",
+        )
+        assert mock_cls.call_args.kwargs["api_base"] == "http://node7:8123/v1"
+
+    @patch("openjarvis.evals.backends.terminalbench_native.TerminalBenchNativeBackend")
+    def test_default_api_base_unchanged_without_base_url(self, mock_cls):
+        mock_backend = MagicMock()
+        mock_backend.run_harness.return_value = SimpleNamespace(trial_results=[])
+        mock_cls.return_value = mock_backend
+
+        _run_terminalbench_native(_tb_config(), _quiet_console())
+        assert mock_cls.call_args.kwargs["api_base"] == "http://localhost:8000/v1"
+
+    @patch("openjarvis.evals.backends.terminalbench_native.TerminalBenchNativeBackend")
+    def test_api_key_exported_as_openai_api_key_during_run(self, mock_cls, monkeypatch):
+        """terminus-2 reads OPENAI_API_KEY via LiteLLM; the var must be set
+        during harness.run() and restored afterwards."""
+        monkeypatch.delenv("OPENAI_API_KEY", raising=False)
+        seen: dict = {}
+
+        def fake_run_harness(run_id):
+            seen["openai_api_key"] = os.environ.get("OPENAI_API_KEY")
+            return SimpleNamespace(trial_results=[])
+
+        mock_backend = MagicMock()
+        mock_backend.run_harness.side_effect = fake_run_harness
+        mock_cls.return_value = mock_backend
+
+        _run_terminalbench_native(
+            _tb_config(),
+            _quiet_console(),
+            base_url="http://node7:8123/v1",
+            api_key="sk-tb",
+        )
+        assert seen["openai_api_key"] == "sk-tb"
+        assert "OPENAI_API_KEY" not in os.environ  # restored
+
+    @patch("openjarvis.evals.backends.terminalbench_native.TerminalBenchNativeBackend")
+    def test_preexisting_openai_api_key_restored(self, mock_cls, monkeypatch):
+        monkeypatch.setenv("OPENAI_API_KEY", "sk-original")
+        mock_backend = MagicMock()
+        mock_backend.run_harness.return_value = SimpleNamespace(trial_results=[])
+        mock_cls.return_value = mock_backend
+
+        _run_terminalbench_native(
+            _tb_config(),
+            _quiet_console(),
+            base_url="http://node7:8123/v1",
+            api_key="sk-tb",
+        )
+        assert os.environ["OPENAI_API_KEY"] == "sk-original"
+
+
+class TestRunSingleSuiteModeGating:
+    @patch("openjarvis.evals.cli._run_terminalbench_native")
+    def test_suite_mode_drops_endpoint_for_terminalbench(self, mock_tb):
+        from openjarvis.evals.cli import _run_single
+
+        mock_tb.return_value = SimpleNamespace(accuracy=0.0)
+        config = _tb_config(base_url="http://node7:8123/v1", api_key="sk-k")
+        _run_single(config, console=_quiet_console(), suite_mode=True)
+        assert mock_tb.call_args.kwargs["base_url"] is None
+        assert mock_tb.call_args.kwargs["api_key"] is None
+
+    @patch("openjarvis.evals.cli._run_terminalbench_native")
+    def test_cli_mode_forwards_endpoint_for_terminalbench(self, mock_tb):
+        from openjarvis.evals.cli import _run_single
+
+        mock_tb.return_value = SimpleNamespace(accuracy=0.0)
+        config = _tb_config(base_url="http://node7:8123/v1", api_key="sk-k")
+        _run_single(config, console=_quiet_console())
+        assert mock_tb.call_args.kwargs["base_url"] == "http://node7:8123/v1"
+        assert mock_tb.call_args.kwargs["api_key"] == "sk-k"

src/openjarvis/system/builder.py

@@ -33,6 +33,8 @@ class SystemBuilder:
             self._config = load_config()
 
         self._engine_key: Optional[str] = None
+        self._engine_instance: Optional[InferenceEngine] = None
+        self._engine_instance_key: Optional[str] = None
         self._model: Optional[str] = None
         self._agent_name: Optional[str] = None
         self._tool_names: Optional[List[str]] = None
@@ -50,6 +52,20 @@ class SystemBuilder:
         self._engine_key = key
         return self
 
+    def engine_instance(
+        self, engine: InferenceEngine, key: str = "openai-compat"
+    ) -> SystemBuilder:
+        """Inject a pre-built engine instance, bypassing engine discovery.
+
+        Used by callers that must target one exact endpoint (e.g.
+        ``jarvis eval --base-url``). ``build()`` health-checks the instance
+        and raises a loud error if it is unreachable — it never silently
+        substitutes a different discovered engine.
+        """
+        self._engine_instance = engine
+        self._engine_instance_key = key
+        return self
+
     def model(self, name: str) -> SystemBuilder:
         self._model = name
         return self
@@ -303,6 +319,23 @@ class SystemBuilder:
         return system
 
     def _resolve_engine(self, config: JarvisConfig):
+        # An explicitly injected engine instance always wins and is never
+        # silently replaced: when the caller pinned an endpoint (e.g.
+        # ``jarvis eval --base-url``) and it is down, substituting whatever
+        # other engine discovery finds would silently run against the wrong
+        # model server. Fail loudly instead.
+        if self._engine_instance is not None:
+            engine = self._engine_instance
+            key = self._engine_instance_key or "openai-compat"
+            if not engine.health():
+                host = getattr(engine, "_host", "<unknown host>")
+                raise RuntimeError(
+                    f"Injected engine {key!r} is not reachable at {host} — "
+                    "is the endpoint running and serving GET /v1/models? "
+                    "Refusing to fall back to engine discovery."
+                )
+            return engine, key
+
         from openjarvis.engine._discovery import get_engine
 
         pref = config.intelligence.preferred_engine
@@ -313,7 +346,18 @@ class SystemBuilder:
                 "No inference engine available. "
                 "Make sure an engine is running (e.g. ollama serve)."
             )
-        return resolved[1], resolved[0]
+        resolved_key, engine = resolved
+        if self._engine_key and resolved_key != self._engine_key:
+            # get_engine() falls back to any healthy discovered engine; make
+            # the substitution visible when the caller asked for a specific
+            # engine (observed: requested vllm, silently got ollama@11434).
+            logger.warning(
+                "Requested engine %r is unavailable; using %r at %s instead",
+                self._engine_key,
+                resolved_key,
+                getattr(engine, "_host", "<unknown host>"),
+            )
+        return engine, resolved_key
 
     def _resolve_model(self, config: JarvisConfig, engine: InferenceEngine) -> str:
         if self._model:

tests/engine/test_openai_compat_api_key.py

@@ -0,0 +1,109 @@
+"""API-key (Authorization header) support in the OpenAI-compat engine base."""
+
+from __future__ import annotations
+
+import httpx
+import pytest
+import respx
+
+from openjarvis.core.types import Message, Role
+from openjarvis.engine.openai_compat_engines import (
+    OpenAICompatEngine,
+    VLLMEngine,
+    normalize_openai_base_url,
+)
+
+_CHAT_RESPONSE = {
+    "choices": [{"message": {"content": "ok"}, "finish_reason": "stop"}],
+    "usage": {"prompt_tokens": 1, "completion_tokens": 1, "total_tokens": 2},
+    "model": "m",
+}
+
+
+class TestAuthorizationHeader:
+    def test_bearer_header_sent_when_api_key_set(self) -> None:
+        engine = OpenAICompatEngine(host="http://testhost:9000", api_key="sk-test")
+        with respx.mock:
+            route = respx.post("http://testhost:9000/v1/chat/completions").mock(
+                return_value=httpx.Response(200, json=_CHAT_RESPONSE)
+            )
+            engine.generate([Message(role=Role.USER, content="hi")], model="m")
+        assert route.calls.last.request.headers["Authorization"] == "Bearer sk-test"
+
+    def test_no_authorization_header_without_api_key(self) -> None:
+        engine = OpenAICompatEngine(host="http://testhost:9000")
+        with respx.mock:
+            route = respx.post("http://testhost:9000/v1/chat/completions").mock(
+                return_value=httpx.Response(200, json=_CHAT_RESPONSE)
+            )
+            engine.generate([Message(role=Role.USER, content="hi")], model="m")
+        assert "authorization" not in route.calls.last.request.headers
+
+    def test_health_check_sends_bearer_header(self) -> None:
+        engine = OpenAICompatEngine(host="http://testhost:9000", api_key="sk-test")
+        with respx.mock:
+            route = respx.get("http://testhost:9000/v1/models").mock(
+                return_value=httpx.Response(200, json={"data": []})
+            )
+            assert engine.health() is True
+        assert route.calls.last.request.headers["Authorization"] == "Bearer sk-test"
+
+    def test_env_var_fallback_sanitizes_hyphen(
+        self, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
+        # engine_id "openai-compat" must map to OPENAI_COMPAT_API_KEY —
+        # shells cannot set hyphenated env-var names.
+        monkeypatch.setenv("OPENAI_COMPAT_API_KEY", "sk-env")
+        engine = OpenAICompatEngine(host="http://testhost:9000")
+        with respx.mock:
+            route = respx.get("http://testhost:9000/v1/models").mock(
+                return_value=httpx.Response(200, json={"data": []})
+            )
+            engine.health()
+        assert route.calls.last.request.headers["Authorization"] == "Bearer sk-env"
+
+    def test_vllm_env_var_fallback(self, monkeypatch: pytest.MonkeyPatch) -> None:
+        monkeypatch.setenv("VLLM_API_KEY", "sk-vllm")
+        engine = VLLMEngine(host="http://testhost:8000")
+        with respx.mock:
+            route = respx.get("http://testhost:8000/v1/models").mock(
+                return_value=httpx.Response(200, json={"data": []})
+            )
+            engine.health()
+        assert route.calls.last.request.headers["Authorization"] == "Bearer sk-vllm"
+
+    def test_explicit_api_key_beats_env_var(
+        self, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
+        monkeypatch.setenv("OPENAI_COMPAT_API_KEY", "sk-env")
+        engine = OpenAICompatEngine(host="http://testhost:9000", api_key="sk-explicit")
+        assert engine._api_key == "sk-explicit"
+
+
+class TestNormalizeOpenAIBaseUrl:
+    @pytest.mark.parametrize(
+        ("url", "expected"),
+        [
+            ("http://h:8000", "http://h:8000"),
+            ("http://h:8000/", "http://h:8000"),
+            ("http://h:8000/v1", "http://h:8000"),
+            ("http://h:8000/v1/", "http://h:8000"),
+            ("http://h:8000/gateway/v1", "http://h:8000/gateway"),
+            # Only a literal trailing "/v1" is stripped — never other paths.
+            ("http://h:8000/v1x", "http://h:8000/v1x"),
+            ("http://h:8000/v2", "http://h:8000/v2"),
+        ],
+    )
+    def test_normalization(self, url: str, expected: str) -> None:
+        assert normalize_openai_base_url(url) == expected
+
+    def test_engine_requests_have_single_v1_prefix(self) -> None:
+        """End to end: a user-supplied .../v1 URL must not produce /v1/v1."""
+        host = normalize_openai_base_url("http://testhost:9000/v1")
+        engine = OpenAICompatEngine(host=host)
+        with respx.mock:
+            route = respx.get("http://testhost:9000/v1/models").mock(
+                return_value=httpx.Response(200, json={"data": []})
+            )
+            assert engine.health() is True
+        assert route.calls.last.request.url.path == "/v1/models"

tests/sdk/test_system.py

@@ -2,7 +2,7 @@
 
 from __future__ import annotations
 
-from unittest.mock import MagicMock
+from unittest.mock import MagicMock, patch
 
 import pytest
 
@@ -327,6 +327,85 @@ class TestSystemBuilder:
         assert builder._engine_key == "ollama"
 
 
+class TestSystemBuilderEngineInstance:
+    """Explicit engine injection (jarvis eval --base-url path)."""
+
+    @staticmethod
+    def _fake_engine(healthy: bool = True) -> MagicMock:
+        engine = MagicMock(
+            spec=["health", "can_serve", "generate", "list_models", "close"]
+        )
+        engine.health.return_value = healthy
+        engine._host = "http://127.0.0.1:18999"
+        return engine
+
+    def test_engine_instance_is_fluent(self):
+        builder = SystemBuilder(JarvisConfig())
+        engine = self._fake_engine()
+        result = builder.engine_instance(engine, key="my-endpoint")
+        assert result is builder
+        assert builder._engine_instance is engine
+        assert builder._engine_instance_key == "my-endpoint"
+
+    def test_resolve_engine_returns_injected_instance(self):
+        config = JarvisConfig()
+        engine = self._fake_engine(healthy=True)
+        builder = SystemBuilder(config).engine_instance(engine, key="endpoint")
+        resolved_engine, resolved_key = builder._resolve_engine(config)
+        assert resolved_engine is engine
+        assert resolved_key == "endpoint"
+
+    def test_unhealthy_injected_instance_raises_naming_host(self):
+        config = JarvisConfig()
+        engine = self._fake_engine(healthy=False)
+        builder = SystemBuilder(config).engine_instance(engine, key="endpoint")
+        with pytest.raises(RuntimeError, match=r"http://127\.0\.0\.1:18999"):
+            builder._resolve_engine(config)
+
+    def test_unhealthy_injected_instance_never_consults_discovery(self):
+        """The observed failure mode: an explicit endpoint must NOT be
+        silently replaced by whatever other engine discovery finds."""
+        config = JarvisConfig()
+        engine = self._fake_engine(healthy=False)
+        builder = SystemBuilder(config).engine_instance(engine)
+        with patch("openjarvis.engine._discovery.get_engine") as mock_get_engine:
+            with pytest.raises(RuntimeError, match="Refusing to fall back"):
+                builder._resolve_engine(config)
+        mock_get_engine.assert_not_called()
+
+    def test_healthy_injected_instance_never_consults_discovery(self):
+        config = JarvisConfig()
+        engine = self._fake_engine(healthy=True)
+        builder = SystemBuilder(config).engine_instance(engine, key="endpoint")
+        with patch("openjarvis.engine._discovery.get_engine") as mock_get_engine:
+            resolved_engine, _ = builder._resolve_engine(config)
+        assert resolved_engine is engine
+        mock_get_engine.assert_not_called()
+
+    def test_build_wires_injected_engine(self):
+        """build() must use the injected engine (possibly behind security
+        wrappers) instead of running discovery."""
+        config = JarvisConfig()
+        engine = self._fake_engine(healthy=True)
+        engine.list_models.return_value = ["stub-model"]
+        builder = (
+            SystemBuilder(config)
+            .engine_instance(engine, key="endpoint")
+            .model("stub-model")
+            .telemetry(False)
+            .traces(False)
+        )
+        system = builder.build()
+        try:
+            inner = system.engine
+            while hasattr(inner, "_engine"):
+                inner = inner._engine
+            assert inner is engine
+            assert system.engine_key == "endpoint"
+        finally:
+            system.close()
+
+
 class TestJarvisSystemClose:
     def test_close_with_scheduler_store(self):
         engine = MagicMock()