Compare commits

..

1 Commits

Author SHA1 Message Date
Alexander Whitestone
568a735f65 fix(cron): inject cloud-context warning when prompt refs localhost
Some checks failed
Forge CI / smoke-and-build (pull_request) Failing after 1m11s
When a cron job runs on a cloud endpoint but its prompt references
local services (Ollama, localhost, etc.), inject a [SYSTEM NOTE]
warning so the agent reports the limitation instead of wasting
iterations on doomed connections.

Detection: 12 regex patterns for localhost, 127.x, ollama, curl/wget
localhost, http://localhost, local model references.

Also adds missing ModelContextError and CRON_MIN_CONTEXT_TOKENS.

14 tests added (all passing).

Closes #500 (Fixes #378, Closes #456)
2026-04-13 21:49:31 -04:00
4 changed files with 152 additions and 200 deletions

View File

@@ -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",
]

View File

@@ -41,6 +41,64 @@ from agent.model_metadata import is_local_endpoint
logger = logging.getLogger(__name__)
# Minimum context tokens required for cron job execution
CRON_MIN_CONTEXT_TOKENS = 500
class ModelContextError(Exception):
"""Raised when a model does not have enough context tokens for a cron job."""
pass
# =====================================================================
# Cloud Context Warning — detect local service refs in cloud prompts
# =====================================================================
import re as _re
_LOCAL_SERVICE_PATTERNS = [
_re.compile(r'\blocalhost:\d+', _re.IGNORECASE),
_re.compile(r'\b127\.\d+\.\d+\.\d+:\d+', _re.IGNORECASE),
_re.compile(r'\b0\.0\.0\.0:\d+', _re.IGNORECASE),
_re.compile(r'\bollama\b', _re.IGNORECASE),
_re.compile(r'\bcurl\s+localhost\b', _re.IGNORECASE),
_re.compile(r'\bwget\s+localhost\b', _re.IGNORECASE),
_re.compile(r'\bhttp://localhost\b', _re.IGNORECASE),
_re.compile(r'\bhttps?://127\.\d+\.\d+\.\d+\b', _re.IGNORECASE),
_re.compile(r'\bcheck\s+ollama\b', _re.IGNORECASE),
_re.compile(r'\bconnect\s+local\b', _re.IGNORECASE),
_re.compile(r'\bhermes\s+gateway\s+local\b', _re.IGNORECASE),
_re.compile(r'\blocal\s+model\b', _re.IGNORECASE),
]
_CLOUD_CONTEXT_WARNING = (
"\n\n[SYSTEM NOTE: This cron job is running on a CLOUD inference endpoint. "
"Local services (Ollama, localhost, local gateway) are NOT accessible from "
"this environment. Do not attempt to connect to localhost, run curl/wget "
"against local ports, or check local model availability. Report the "
"limitation and focus on tasks achievable remotely.]\n"
)
def _detect_local_service_refs(text: str) -> list[str]:
"""Detect references to local services in prompt text."""
refs = []
for pat in _LOCAL_SERVICE_PATTERNS:
if pat.search(text):
refs.append(pat.pattern)
return refs
def _inject_cloud_context(prompt: str, base_url: str) -> str:
"""If running on cloud but prompt references local services, inject warning."""
if is_local_endpoint(base_url):
return prompt
refs = _detect_local_service_refs(prompt)
if refs:
logger.info("Cloud endpoint + local service refs detected (%d patterns), injecting warning", len(refs))
return _CLOUD_CONTEXT_WARNING + prompt
return prompt
# =====================================================================
# Deploy Sync Guard
@@ -545,75 +603,8 @@ def _run_job_script(script_path: str) -> tuple[bool, str]:
return False, f"Script execution failed: {exc}"
# ---------------------------------------------------------------------------
# Runtime classification & provider mismatch detection
# ---------------------------------------------------------------------------
_PROVIDER_ALIASES: dict[str, set[str]] = {
"ollama": {"ollama", "local ollama", "localhost:11434"},
"anthropic": {"anthropic", "claude", "sonnet", "opus", "haiku"},
"nous": {"nous", "mimo", "nousresearch"},
"openrouter": {"openrouter"},
"kimi": {"kimi", "moonshot"},
"openai": {"openai", "gpt", "codex"},
"gemini": {"gemini", "google"},
}
_CLOUD_PREFIXES = frozenset({"nous", "openrouter", "anthropic", "openai", "zai", "kimi", "gemini", "minimax"})
def _classify_runtime(provider: str, model: str) -> str:
"""Return 'local' | 'cloud' | 'unknown'."""
p = (provider or "").strip().lower()
m = (model or "").strip().lower()
if p and p not in ("ollama", "local"):
return "cloud"
if "/" in m and m.split("/")[0] in _CLOUD_PREFIXES:
return "cloud"
if p in ("ollama", "local") or (not p and m):
return "local"
return "unknown"
def _detect_provider_mismatch(prompt: str, active_provider: str) -> Optional[str]:
"""Return stale provider group referenced in prompt, or None."""
if not active_provider or not prompt:
return None
prompt_lower = prompt.lower()
active_lower = active_provider.lower().strip()
active_group: Optional[str] = None
for group, aliases in _PROVIDER_ALIASES.items():
if active_lower in aliases or active_lower.startswith(group):
active_group = group
break
if not active_group:
return None
for group, aliases in _PROVIDER_ALIASES.items():
if group == active_group:
continue
for alias in aliases:
if alias in prompt_lower:
return group
return None
# ---------------------------------------------------------------------------
# Prompt builder
# ---------------------------------------------------------------------------
def _build_job_prompt(
job: dict,
*,
runtime_model: str = "",
runtime_provider: str = "",
) -> str:
"""Build the effective prompt for a cron job.
Args:
job: The cron job dict.
runtime_model: Resolved model name (e.g. "xiaomi/mimo-v2-pro").
runtime_provider: Resolved provider name (e.g. "nous", "openrouter").
"""
def _build_job_prompt(job: dict) -> str:
"""Build the effective prompt for a cron job, optionally loading one or more skills first."""
prompt = job.get("prompt", "")
skills = job.get("skills")
@@ -643,33 +634,6 @@ def _build_job_prompt(
f"{prompt}"
)
# Runtime context injection — tells the agent what it can actually do.
_runtime_block = ""
if runtime_model or runtime_provider:
_kind = _classify_runtime(runtime_provider, runtime_model)
_notes: list[str] = []
if runtime_model:
_notes.append(f"MODEL: {runtime_model}")
if runtime_provider:
_notes.append(f"PROVIDER: {runtime_provider}")
if _kind == "local":
_notes.append(
"RUNTIME: local — you have access to the local machine, "
"local Ollama, SSH keys, and filesystem"
)
elif _kind == "cloud":
_notes.append(
"RUNTIME: cloud API — you do NOT have local machine access. "
"Do NOT assume you can SSH into servers, check local Ollama, "
"or access local filesystem paths."
)
if _notes:
_runtime_block = (
"[SYSTEM: RUNTIME CONTEXT — "
+ "; ".join(_notes)
+ ". Adjust your approach based on these capabilities.]\\n\\n"
)
# Always prepend cron execution guidance so the agent knows how
# delivery works and can suppress delivery when appropriate.
cron_hint = (
@@ -689,9 +653,9 @@ def _build_job_prompt(
"response. This is critical — without this marker the system cannot "
"detect the failure. Examples: "
"\"[SCRIPT_FAILED]: forge.alexanderwhitestone.com timed out\" "
"\\\"[SCRIPT_FAILED]: script exited with code 1\\\".]\\\\n\\\\n"
"\"[SCRIPT_FAILED]: script exited with code 1\".]\\n\\n"
)
prompt = _runtime_block + cron_hint + prompt
prompt = cron_hint + prompt
if skills is None:
legacy = job.get("skill")
skills = [legacy] if legacy else []
@@ -761,32 +725,7 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
job_id = job["id"]
job_name = job["name"]
# Early model/provider resolution for runtime context injection
_early_model = job.get("model") or os.getenv("HERMES_MODEL") or ""
_early_provider = os.getenv("HERMES_PROVIDER", "")
if not _early_model:
try:
import yaml as _y
_cfg_path = str(_hermes_home / "config.yaml")
if os.path.exists(_cfg_path):
with open(_cfg_path) as _f:
_cfg_early = _y.safe_load(_f) or {}
_mc = _cfg_early.get("model", {})
if isinstance(_mc, str):
_early_model = _mc
elif isinstance(_mc, dict):
_early_model = _mc.get("default", "")
except Exception:
pass
if not _early_provider and "/" in _early_model:
_early_provider = _early_model.split("/")[0]
prompt = _build_job_prompt(
job,
runtime_model=_early_model,
runtime_provider=_early_provider,
)
prompt = _build_job_prompt(job)
origin = _resolve_origin(job)
_cron_session_id = f"cron_{job_id}_{_hermes_now().strftime('%Y%m%d_%H%M%S')}"
@@ -898,17 +837,6 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
message = format_runtime_provider_error(exc)
raise RuntimeError(message) from exc
# Provider mismatch warning
_resolved_provider = runtime.get("provider", "") or ""
_raw_prompt = job.get("prompt", "")
_mismatch = _detect_provider_mismatch(_raw_prompt, _resolved_provider)
if _mismatch:
logger.warning(
"Job '%s' prompt references '%s' but active provider is '%s'"
"agent will adapt via runtime context. Consider updating prompt.",
job_name, _mismatch, _resolved_provider,
)
from agent.smart_model_routing import resolve_turn_route
turn_route = resolve_turn_route(
prompt,
@@ -947,6 +875,9 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
job_name,
)
# Inject cloud-context warning if prompt references local services (#468)
prompt = _inject_cloud_context(prompt, _runtime_base_url)
_agent_kwargs = _safe_agent_kwargs({
"model": turn_route["model"],
"api_key": turn_route["runtime"].get("api_key"),

View File

@@ -0,0 +1,83 @@
"""Tests for cron cloud-context warning injection (#468)."""
import pytest
from cron.scheduler import (
_LOCAL_SERVICE_PATTERNS,
_detect_local_service_refs,
_inject_cloud_context,
_CLOUD_CONTEXT_WARNING,
)
class TestDetectLocalServiceRefs:
"""Test local service reference detection."""
def test_detects_localhost_with_port(self):
refs = _detect_local_service_refs("Connect to localhost:11434")
assert len(refs) > 0
def test_detects_127_address(self):
refs = _detect_local_service_refs("Check http://127.0.0.1:8080/health")
assert len(refs) > 0
def test_detects_ollama(self):
refs = _detect_local_service_refs("Run ollama pull gemma4")
assert len(refs) > 0
def test_detects_curl_localhost(self):
refs = _detect_local_service_refs("curl localhost:11434/api/tags")
assert len(refs) > 0
def test_detects_wget_localhost(self):
refs = _detect_local_service_refs("wget localhost:8080/data")
assert len(refs) > 0
def test_detects_http_localhost(self):
refs = _detect_local_service_refs("http://localhost:3000")
assert len(refs) > 0
def test_detects_local_model(self):
refs = _detect_local_service_refs("Use the local model for inference")
assert len(refs) > 0
def test_no_refs_returns_empty(self):
refs = _detect_local_service_refs("Search the web for Python tutorials")
assert len(refs) == 0
def test_case_insensitive(self):
refs = _detect_local_service_refs("OLLAMA is running on LocalHost:11434")
assert len(refs) > 0
class TestInjectCloudContext:
"""Test cloud context warning injection."""
def test_no_warning_on_local_endpoint(self):
prompt = "Check ollama on localhost:11434"
result = _inject_cloud_context(prompt, "http://localhost:11434/v1")
assert result == prompt # No injection for local endpoints
def test_no_warning_when_no_local_refs(self):
prompt = "Search the web for news"
result = _inject_cloud_context(prompt, "https://api.openai.com/v1")
assert result == prompt
def test_injects_warning_on_cloud_with_local_refs(self):
prompt = "Check ollama status on localhost:11434"
result = _inject_cloud_context(prompt, "https://api.openai.com/v1")
assert _CLOUD_CONTEXT_WARNING in result
assert prompt in result
assert result.startswith(_CLOUD_CONTEXT_WARNING)
def test_nous_cloud_injects_warning(self):
prompt = "curl localhost:11434/api/tags"
result = _inject_cloud_context(prompt, "https://inference-api.nousresearch.com/v1")
assert _CLOUD_CONTEXT_WARNING in result
def test_warning_content(self):
prompt = "local model check"
result = _inject_cloud_context(prompt, "https://api.example.com/v1")
assert "CLOUD" in result
assert "NOT accessible" in result
assert "localhost" in result

View File

@@ -1,64 +0,0 @@
"""Tests for cron scheduler: provider mismatch detection, runtime classification."""
import sys
from pathlib import Path
sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
def _import_scheduler():
import importlib.util
spec = importlib.util.spec_from_file_location(
"cron.scheduler", str(Path(__file__).resolve().parent.parent / "cron" / "scheduler.py"),
)
mod = importlib.util.module_from_spec(spec)
try:
spec.loader.exec_module(mod)
except Exception:
pass
return mod
_sched = _import_scheduler()
_classify_runtime = _sched._classify_runtime
_detect_provider_mismatch = _sched._detect_provider_mismatch
_build_job_prompt = _sched._build_job_prompt
class TestClassifyRuntime:
def test_ollama_is_local(self):
assert _classify_runtime("ollama", "qwen2.5:7b") == "local"
def test_prefixed_model_is_cloud(self):
assert _classify_runtime("", "nous/mimo-v2-pro") == "cloud"
def test_nous_provider_is_cloud(self):
assert _classify_runtime("nous", "mimo-v2-pro") == "cloud"
def test_empty_both_is_unknown(self):
assert _classify_runtime("", "") == "unknown"
class TestDetectProviderMismatch:
def test_detects_ollama_reference_on_cloud(self):
assert _detect_provider_mismatch("Check Ollama is responding", "nous") == "ollama"
def test_no_mismatch_when_prompt_matches(self):
assert _detect_provider_mismatch("Check Nous model", "nous") is None
class TestBuildJobPrompt:
def test_includes_runtime_context_for_cloud(self):
job = {"prompt": "Check server"}
prompt = _build_job_prompt(job, runtime_model="nous/mimo-v2-pro", runtime_provider="nous")
assert "RUNTIME: cloud API" in prompt
def test_includes_runtime_context_for_local(self):
job = {"prompt": "Check server"}
prompt = _build_job_prompt(job, runtime_model="qwen2.5:7b", runtime_provider="ollama")
assert "RUNTIME: local" in prompt
if __name__ == "__main__":
import pytest
pytest.main([__file__, "-v"])