Compare commits
1 Commits
am/350-177
...
claude/iss
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
a90162bafc |
@@ -32,6 +32,27 @@ _PROVIDER_PREFIXES: frozenset[str] = frozenset({
|
||||
"glm", "z-ai", "z.ai", "zhipu", "github", "github-copilot",
|
||||
"github-models", "kimi", "moonshot", "claude", "deep-seek",
|
||||
"opencode", "zen", "go", "vercel", "kilo", "dashscope", "aliyun", "qwen",
|
||||
# Additional cloud vendor prefixes (fixes #628)
|
||||
"cohere", "mistralai", "mistral", "meta-llama", "databricks", "together",
|
||||
"togetherai", "together-ai", "nousresearch", "moonshotai", "fireworks",
|
||||
"perplexity", "ai21", "groq", "cerebras", "nebius",
|
||||
})
|
||||
|
||||
# Vendor prefixes that appear in cloud model IDs (e.g. "openai/gpt-4").
|
||||
# Used by _classify_runtime to detect cloud runtimes from the model name
|
||||
# when no base URL is available.
|
||||
_CLOUD_MODEL_PREFIXES: frozenset[str] = frozenset({
|
||||
# Providers present before #628
|
||||
"nous", "nousresearch", "openrouter", "anthropic", "openai",
|
||||
"zai", "kimi", "moonshotai", "gemini", "google", "minimax",
|
||||
# Providers added by #628 fix
|
||||
"deepseek", "cohere", "mistralai", "mistral", "meta-llama",
|
||||
"databricks", "together", "togetherai",
|
||||
# Other common cloud vendors
|
||||
"microsoft", "amazon", "huggingface", "fireworks",
|
||||
"perplexity", "ai21", "groq", "cerebras", "nebius",
|
||||
"qwen", "alibaba", "aliyuncs", "dashscope",
|
||||
"github", "copilot",
|
||||
})
|
||||
|
||||
|
||||
@@ -253,6 +274,67 @@ def is_local_endpoint(base_url: str) -> bool:
|
||||
return False
|
||||
|
||||
|
||||
# Provider names that are definitively local (never cloud).
|
||||
_LOCAL_PROVIDER_NAMES: frozenset[str] = frozenset({
|
||||
"ollama", "custom", "local",
|
||||
})
|
||||
|
||||
# Provider names that are definitively cloud (not local).
|
||||
_CLOUD_PROVIDER_NAMES: frozenset[str] = frozenset({
|
||||
"nous", "openrouter", "anthropic", "openai", "openai-codex",
|
||||
"zai", "kimi-coding", "gemini", "minimax", "minimax-cn",
|
||||
"deepseek", "cohere", "mistral", "meta-llama", "databricks", "together",
|
||||
"huggingface", "copilot", "copilot-acp", "ai-gateway", "kilocode",
|
||||
"alibaba", "opencode-zen", "opencode-go",
|
||||
})
|
||||
|
||||
|
||||
def _classify_runtime(
|
||||
model: str = "",
|
||||
base_url: str = "",
|
||||
provider: str = "",
|
||||
) -> str:
|
||||
"""Classify a model/endpoint runtime as 'cloud' or 'local'.
|
||||
|
||||
Checks in priority order:
|
||||
1. ``base_url`` — localhost / RFC-1918 → ``"local"``; known external URL → ``"cloud"``
|
||||
2. ``provider`` name — matches a known local or cloud provider set
|
||||
3. Model vendor prefix — e.g. ``"openai/gpt-4"`` → ``"cloud"``
|
||||
4. Default — ``"cloud"`` when the runtime cannot be determined to be local
|
||||
|
||||
The cloud-prefix list covers both the providers present before issue #628
|
||||
(nous, openrouter, anthropic, openai, zai, kimi, gemini, minimax) and the
|
||||
previously missing ones (deepseek, cohere, mistral, meta-llama, databricks,
|
||||
together).
|
||||
|
||||
Returns ``"cloud"`` or ``"local"``.
|
||||
"""
|
||||
# 1. URL-based check — most reliable signal
|
||||
if base_url:
|
||||
if is_local_endpoint(base_url):
|
||||
return "local"
|
||||
return "cloud"
|
||||
|
||||
# 2. Provider name check
|
||||
provider_norm = (provider or "").strip().lower()
|
||||
if provider_norm in _LOCAL_PROVIDER_NAMES:
|
||||
return "local"
|
||||
if provider_norm in _CLOUD_PROVIDER_NAMES:
|
||||
return "cloud"
|
||||
|
||||
# 3. Model vendor prefix check (e.g. "openai/gpt-4" → vendor "openai")
|
||||
model_norm = (model or "").strip().lower()
|
||||
if "/" in model_norm:
|
||||
vendor = model_norm.split("/")[0].strip()
|
||||
if vendor in _CLOUD_MODEL_PREFIXES:
|
||||
return "cloud"
|
||||
# An unknown vendor with a slash is still likely a cloud model
|
||||
return "cloud"
|
||||
|
||||
# 4. Default — without a URL we cannot confirm local, so assume cloud
|
||||
return "cloud"
|
||||
|
||||
|
||||
def detect_local_server_type(base_url: str) -> Optional[str]:
|
||||
"""Detect which local server is running at base_url by probing known endpoints.
|
||||
|
||||
|
||||
@@ -26,7 +26,7 @@ from cron.jobs import (
|
||||
trigger_job,
|
||||
JOBS_FILE,
|
||||
)
|
||||
from cron.scheduler import tick
|
||||
from cron.scheduler import tick, ModelContextError, CRON_MIN_CONTEXT_TOKENS
|
||||
|
||||
__all__ = [
|
||||
"create_job",
|
||||
@@ -39,4 +39,6 @@ __all__ = [
|
||||
"trigger_job",
|
||||
"tick",
|
||||
"JOBS_FILE",
|
||||
"ModelContextError",
|
||||
"CRON_MIN_CONTEXT_TOKENS",
|
||||
]
|
||||
|
||||
@@ -186,14 +186,7 @@ _SCRIPT_FAILURE_PHRASES = (
|
||||
"unable to execute",
|
||||
"permission denied",
|
||||
"no such file",
|
||||
"no such file or directory",
|
||||
"command not found",
|
||||
"hermes binary not found",
|
||||
"hermes not found",
|
||||
"traceback",
|
||||
"ssh: connect to host",
|
||||
"connection timed out",
|
||||
"host key verification failed",
|
||||
)
|
||||
|
||||
|
||||
|
||||
@@ -1,192 +0,0 @@
|
||||
"""SSH dispatch utilities for VPS agent operations.
|
||||
|
||||
Provides validated SSH execution with proper failure detection.
|
||||
Used by cron jobs that dispatch work to remote VPS agents.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import os
|
||||
import subprocess
|
||||
import time
|
||||
from typing import Optional
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
_SSH_TIMEOUT = int(os.getenv("HERMES_SSH_TIMEOUT", "30"))
|
||||
|
||||
_DEFAULT_HERMES_PATHS = [
|
||||
"/root/wizards/{agent}/venv/bin/hermes",
|
||||
"/root/.local/bin/hermes",
|
||||
"/usr/local/bin/hermes",
|
||||
"~/.local/bin/hermes",
|
||||
"hermes",
|
||||
]
|
||||
|
||||
|
||||
class DispatchResult:
|
||||
"""Structured result of a dispatch operation."""
|
||||
|
||||
__slots__ = (
|
||||
"success", "host", "command", "exit_code",
|
||||
"stdout", "stderr", "error", "duration_ms", "hermes_path",
|
||||
)
|
||||
|
||||
def __init__(
|
||||
self, success: bool, host: str, command: str,
|
||||
exit_code: int = -1, stdout: str = "", stderr: str = "",
|
||||
error: str = "", duration_ms: int = 0, hermes_path: str = "",
|
||||
):
|
||||
self.success = success
|
||||
self.host = host
|
||||
self.command = command
|
||||
self.exit_code = exit_code
|
||||
self.stdout = stdout
|
||||
self.stderr = stderr
|
||||
self.error = error
|
||||
self.duration_ms = duration_ms
|
||||
self.hermes_path = hermes_path
|
||||
|
||||
def to_dict(self) -> dict:
|
||||
return {
|
||||
"success": self.success, "host": self.host,
|
||||
"exit_code": self.exit_code, "error": self.error,
|
||||
"duration_ms": self.duration_ms, "hermes_path": self.hermes_path,
|
||||
"stderr_tail": self.stderr[-200:] if self.stderr else "",
|
||||
}
|
||||
|
||||
@property
|
||||
def failure_reason(self) -> str:
|
||||
if self.success:
|
||||
return ""
|
||||
if self.error:
|
||||
return self.error
|
||||
if "No such file" in self.stderr or "command not found" in self.stderr:
|
||||
return f"Hermes binary not found on {self.host}"
|
||||
if self.exit_code != 0:
|
||||
return f"Remote command exited {self.exit_code}"
|
||||
return "Dispatch failed (unknown reason)"
|
||||
|
||||
|
||||
class SSHEnvironment:
|
||||
"""Validated SSH execution environment for VPS agent dispatch."""
|
||||
|
||||
def __init__(
|
||||
self, host: str, agent: str = "", ssh_key: str = "",
|
||||
ssh_port: int = 22, timeout: int = _SSH_TIMEOUT,
|
||||
hermes_path: str = "",
|
||||
):
|
||||
self.host = host
|
||||
self.agent = agent
|
||||
self.ssh_key = ssh_key
|
||||
self.ssh_port = ssh_port
|
||||
self.timeout = timeout
|
||||
self.hermes_path = hermes_path
|
||||
self._validated_path: str = ""
|
||||
|
||||
def _ssh_base_cmd(self) -> list[str]:
|
||||
cmd = ["ssh", "-o", "StrictHostKeyChecking=accept-new"]
|
||||
cmd.extend(["-o", "ConnectTimeout=10", "-o", "BatchMode=yes"])
|
||||
if self.ssh_key:
|
||||
cmd.extend(["-i", self.ssh_key])
|
||||
if self.ssh_port != 22:
|
||||
cmd.extend(["-p", str(self.ssh_port)])
|
||||
cmd.append(self.host)
|
||||
return cmd
|
||||
|
||||
def _resolve_hermes_paths(self) -> list[str]:
|
||||
if self.hermes_path:
|
||||
return [self.hermes_path]
|
||||
return [t.format(agent=self.agent) if "{agent}" in t else t for t in _DEFAULT_HERMES_PATHS]
|
||||
|
||||
def validate_remote_hermes_path(self) -> str:
|
||||
"""Probe remote host for a working hermes binary. Returns path or raises."""
|
||||
if self._validated_path:
|
||||
return self._validated_path
|
||||
for path in self._resolve_hermes_paths():
|
||||
try:
|
||||
result = subprocess.run(
|
||||
self._ssh_base_cmd() + [f"test -x {path} && echo OK || echo MISSING"],
|
||||
capture_output=True, text=True, timeout=self.timeout,
|
||||
)
|
||||
if result.returncode == 0 and "OK" in (result.stdout or ""):
|
||||
logger.info("SSH %s: hermes validated at %s", self.host, path)
|
||||
self._validated_path = path
|
||||
return path
|
||||
except subprocess.TimeoutExpired:
|
||||
logger.warning("SSH %s: timeout probing %s", self.host, path)
|
||||
except Exception as exc:
|
||||
logger.debug("SSH %s: probe %s failed: %s", self.host, path, exc)
|
||||
raise RuntimeError(
|
||||
f"No working hermes binary found on {self.host}. "
|
||||
f"Checked: {', '.join(self._resolve_hermes_paths())}."
|
||||
)
|
||||
|
||||
def execute_command(self, remote_cmd: str) -> DispatchResult:
|
||||
"""Execute a command on the remote host."""
|
||||
t0 = time.monotonic()
|
||||
try:
|
||||
result = subprocess.run(
|
||||
self._ssh_base_cmd() + [remote_cmd],
|
||||
capture_output=True, text=True, timeout=self.timeout,
|
||||
)
|
||||
elapsed = int((time.monotonic() - t0) * 1000)
|
||||
stderr = (result.stderr or "").strip()
|
||||
stdout = (result.stdout or "").strip()
|
||||
if result.returncode != 0:
|
||||
return DispatchResult(
|
||||
success=False, host=self.host, command=remote_cmd,
|
||||
exit_code=result.returncode, stdout=stdout, stderr=stderr,
|
||||
error=stderr.split("\n")[0] if stderr else f"exit code {result.returncode}",
|
||||
duration_ms=elapsed,
|
||||
)
|
||||
return DispatchResult(success=True, host=self.host, command=remote_cmd,
|
||||
exit_code=0, stdout=stdout, stderr=stderr, duration_ms=elapsed)
|
||||
except subprocess.TimeoutExpired:
|
||||
return DispatchResult(success=False, host=self.host, command=remote_cmd,
|
||||
error=f"SSH timed out after {self.timeout}s",
|
||||
duration_ms=int((time.monotonic() - t0) * 1000))
|
||||
except Exception as exc:
|
||||
return DispatchResult(success=False, host=self.host, command=remote_cmd,
|
||||
error=str(exc), duration_ms=int((time.monotonic() - t0) * 1000))
|
||||
|
||||
def dispatch(self, hermes_args: str, validate: bool = True) -> DispatchResult:
|
||||
"""Dispatch a hermes command. Only success=True if command actually ran."""
|
||||
if validate:
|
||||
try:
|
||||
hermes_path = self.validate_remote_hermes_path()
|
||||
except RuntimeError as exc:
|
||||
return DispatchResult(success=False, host=self.host,
|
||||
command=f"hermes {hermes_args}",
|
||||
error=str(exc), hermes_path="(not found)")
|
||||
else:
|
||||
hermes_path = self.hermes_path or "hermes"
|
||||
result = self.execute_command(f"{hermes_path} {hermes_args}")
|
||||
result.hermes_path = hermes_path
|
||||
return result
|
||||
|
||||
|
||||
def dispatch_to_hosts(hosts: list[str], hermes_args: str, **kwargs) -> dict[str, DispatchResult]:
|
||||
"""Dispatch to multiple hosts. Returns host -> DispatchResult."""
|
||||
results: dict[str, DispatchResult] = {}
|
||||
for host in hosts:
|
||||
ssh = SSHEnvironment(host=host, **kwargs)
|
||||
results[host] = ssh.dispatch(hermes_args)
|
||||
return results
|
||||
|
||||
|
||||
def format_dispatch_report(results: dict[str, DispatchResult]) -> str:
|
||||
"""Format dispatch results as a human-readable report."""
|
||||
ok = [r for r in results.values() if r.success]
|
||||
failed = [r for r in results.values() if not r.success]
|
||||
lines = [f"Dispatch report: {len(ok)} OK, {len(failed)} failed", ""]
|
||||
for host, r in results.items():
|
||||
s = "OK" if r.success else f"FAILED -- {r.failure_reason}"
|
||||
lines.append(f" {host}: {s}" + (f" ({r.duration_ms}ms)" if r.duration_ms else ""))
|
||||
if failed:
|
||||
lines += ["", "Failed dispatches:"]
|
||||
for host, r in results.items():
|
||||
if not r.success:
|
||||
lines.append(f" {host}: {r.failure_reason}")
|
||||
return "\n".join(lines)
|
||||
@@ -7,7 +7,7 @@ terminal access.
|
||||
"""
|
||||
|
||||
import pytest
|
||||
from agent.model_metadata import is_local_endpoint
|
||||
from agent.model_metadata import is_local_endpoint, _classify_runtime
|
||||
|
||||
|
||||
class TestIsLocalEndpoint:
|
||||
@@ -71,3 +71,98 @@ class TestCronDisabledToolsetsLogic:
|
||||
def test_empty_url_disables_terminal(self):
|
||||
disabled = self._build_disabled("")
|
||||
assert "terminal" in disabled
|
||||
|
||||
|
||||
class TestClassifyRuntime:
|
||||
"""Verify _classify_runtime correctly classifies runtimes as cloud or local.
|
||||
|
||||
Covers the bug fixed in #628: missing cloud model prefixes for deepseek,
|
||||
cohere, mistral, meta-llama, databricks, and together.
|
||||
"""
|
||||
|
||||
# ── URL-based classification ──────────────────────────────────────────
|
||||
|
||||
def test_localhost_url_is_local(self):
|
||||
assert _classify_runtime(base_url="http://localhost:11434/v1") == "local"
|
||||
|
||||
def test_127_loopback_is_local(self):
|
||||
assert _classify_runtime(base_url="http://127.0.0.1:8080/v1") == "local"
|
||||
|
||||
def test_rfc1918_is_local(self):
|
||||
assert _classify_runtime(base_url="http://192.168.1.10:11434/v1") == "local"
|
||||
|
||||
def test_openrouter_url_is_cloud(self):
|
||||
assert _classify_runtime(base_url="https://openrouter.ai/api/v1") == "cloud"
|
||||
|
||||
def test_anthropic_url_is_cloud(self):
|
||||
assert _classify_runtime(base_url="https://api.anthropic.com") == "cloud"
|
||||
|
||||
def test_deepseek_url_is_cloud(self):
|
||||
assert _classify_runtime(base_url="https://api.deepseek.com/v1") == "cloud"
|
||||
|
||||
# ── Provider-name classification ──────────────────────────────────────
|
||||
|
||||
def test_ollama_provider_is_local(self):
|
||||
assert _classify_runtime(provider="ollama") == "local"
|
||||
|
||||
def test_custom_provider_is_local(self):
|
||||
assert _classify_runtime(provider="custom") == "local"
|
||||
|
||||
def test_openrouter_provider_is_cloud(self):
|
||||
assert _classify_runtime(provider="openrouter") == "cloud"
|
||||
|
||||
def test_nous_provider_is_cloud(self):
|
||||
assert _classify_runtime(provider="nous") == "cloud"
|
||||
|
||||
def test_anthropic_provider_is_cloud(self):
|
||||
assert _classify_runtime(provider="anthropic") == "cloud"
|
||||
|
||||
# ── Previously-missing cloud prefixes (issue #628) ────────────────────
|
||||
|
||||
def test_deepseek_model_prefix_is_cloud(self):
|
||||
assert _classify_runtime(model="deepseek/deepseek-v2") == "cloud"
|
||||
|
||||
def test_cohere_model_prefix_is_cloud(self):
|
||||
assert _classify_runtime(model="cohere/command-r-plus") == "cloud"
|
||||
|
||||
def test_mistralai_model_prefix_is_cloud(self):
|
||||
assert _classify_runtime(model="mistralai/mistral-large-2407") == "cloud"
|
||||
|
||||
def test_meta_llama_model_prefix_is_cloud(self):
|
||||
assert _classify_runtime(model="meta-llama/llama-3.1-70b-instruct") == "cloud"
|
||||
|
||||
def test_databricks_model_prefix_is_cloud(self):
|
||||
assert _classify_runtime(model="databricks/dbrx-instruct") == "cloud"
|
||||
|
||||
def test_together_model_prefix_is_cloud(self):
|
||||
assert _classify_runtime(model="together/together-api-model") == "cloud"
|
||||
|
||||
# ── Providers that were already detected before #628 ─────────────────
|
||||
|
||||
def test_openai_model_prefix_is_cloud(self):
|
||||
assert _classify_runtime(model="openai/gpt-4.1") == "cloud"
|
||||
|
||||
def test_anthropic_model_prefix_is_cloud(self):
|
||||
assert _classify_runtime(model="anthropic/claude-opus-4.6") == "cloud"
|
||||
|
||||
def test_google_model_prefix_is_cloud(self):
|
||||
assert _classify_runtime(model="google/gemini-3-pro") == "cloud"
|
||||
|
||||
def test_minimax_model_prefix_is_cloud(self):
|
||||
assert _classify_runtime(model="minimax/minimax-m2.7") == "cloud"
|
||||
|
||||
# ── Fallback / edge cases ────────────────────────────────────────────
|
||||
|
||||
def test_no_args_defaults_to_cloud(self):
|
||||
assert _classify_runtime() == "cloud"
|
||||
|
||||
def test_empty_strings_default_to_cloud(self):
|
||||
assert _classify_runtime(model="", base_url="", provider="") == "cloud"
|
||||
|
||||
def test_url_takes_priority_over_provider(self):
|
||||
# Explicit local URL wins even if provider looks like cloud
|
||||
assert _classify_runtime(model="openai/gpt-4", base_url="http://localhost:11434/v1", provider="openai") == "local"
|
||||
|
||||
def test_bare_model_name_without_slash_defaults_to_cloud(self):
|
||||
# No slash → can't infer vendor → cloud (safe default)
|
||||
assert _classify_runtime(model="gpt-4o") == "cloud"
|
||||
|
||||
Reference in New Issue
Block a user