OpenJarvis 1.0.3.dev821__tar.gz → 1.0.3.dev823__tar.gz

{openjarvis-1.0.3.dev821 → openjarvis-1.0.3.dev823}/.github/clone-stats/badge.json

@@ -1,7 +1,7 @@
 {
   "schemaVersion": 1,
   "label": "Git Clones",
-  "message": "107,695",
+  "message": "110,366",
   "color": "green",
   "namedLogo": "git"
 }

{openjarvis-1.0.3.dev821 → openjarvis-1.0.3.dev823}/.github/clone-stats/clone-data.json

@@ -1,6 +1,6 @@
 {
-  "total_clones": 107695,
-  "last_updated": "2026-06-10T07:32:26Z",
+  "total_clones": 110366,
+  "last_updated": "2026-06-11T07:44:18Z",
   "daily": {
     "2026-03-27": 2189,
     "2026-03-28": 1874,
@@ -75,6 +75,8 @@
     "2026-06-05": 2127,
     "2026-06-06": 2204,
     "2026-06-07": 1174,
-    "2026-06-08": 2369
+    "2026-06-08": 2369,
+    "2026-06-09": 1361,
+    "2026-06-10": 1310
   }
 }

{openjarvis-1.0.3.dev821 → openjarvis-1.0.3.dev823}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: OpenJarvis
-Version: 1.0.3.dev821
+Version: 1.0.3.dev823
 Summary: OpenJarvis — modular AI assistant backend with composable intelligence primitives
 Project-URL: Homepage, https://github.com/open-jarvis/OpenJarvis
 Project-URL: Documentation, https://open-jarvis.github.io/OpenJarvis/

{openjarvis-1.0.3.dev821 → openjarvis-1.0.3.dev823}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "OpenJarvis"
-version = "1.0.3.dev821"
+version = "1.0.3.dev823"
 description = "OpenJarvis — modular AI assistant backend with composable intelligence primitives"
 readme = "README.md"
 # Upper bound: numpy 2.2.x (pinned transitively via datasets/pandas) ships no

{openjarvis-1.0.3.dev821 → openjarvis-1.0.3.dev823}/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}",

{openjarvis-1.0.3.dev821 → openjarvis-1.0.3.dev823}/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"),
     )

{openjarvis-1.0.3.dev821 → openjarvis-1.0.3.dev823}/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 ------------------------------------------
 

openjarvis-1.0.3.dev823/src/openjarvis/engine/openai_compat_engines.py

@@ -0,0 +1,61 @@
+"""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
+
+_ENGINES = {
+    "vllm": ("VLLMEngine", "http://localhost:8000", "/v1"),
+    "sglang": ("SGLangEngine", "http://localhost:30000", "/v1"),
+    "llamacpp": ("LlamaCppEngine", "http://localhost:8080", "/v1"),
+    "mlx": ("MLXEngine", "http://localhost:8080", "/v1"),
+    "lmstudio": ("LMStudioEngine", "http://localhost:1234", "/v1"),
+    "exo": ("ExoEngine", "http://localhost:52415", "/v1"),
+    "nexa": ("NexaEngine", "http://localhost:18181", "/v1"),
+    "uzu": ("UzuEngine", "http://localhost:8000", ""),
+    "apple_fm": ("AppleFmEngine", "http://localhost:8079", "/v1"),
+    "lemonade": ("LemonadeEngine", "http://localhost:13305", "/v1"),
+}
+
+for _key, (_cls_name, _default_host, _api_prefix) in _ENGINES.items():
+    _cls = type(
+        _cls_name,
+        (_OpenAICompatibleEngine,),
+        {"engine_id": _key, "_default_host": _default_host, "_api_prefix": _api_prefix},
+    )
+    EngineRegistry.register(_key)(_cls)
+    globals()[_cls_name] = _cls
+
+
+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",
+]

openjarvis-1.0.3.dev823/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"]

{openjarvis-1.0.3.dev821 → openjarvis-1.0.3.dev823}/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)

{openjarvis-1.0.3.dev821 → openjarvis-1.0.3.dev823}/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.

{openjarvis-1.0.3.dev821 → openjarvis-1.0.3.dev823}/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