Compare commits
1 Commits
burn/323-1
...
burn/372-1
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
412ee7329a |
@@ -544,8 +544,78 @@ def _run_job_script(script_path: str) -> tuple[bool, str]:
|
||||
return False, f"Script execution failed: {exc}"
|
||||
|
||||
|
||||
def _build_job_prompt(job: dict) -> str:
|
||||
"""Build the effective prompt for a cron job, optionally loading one or more skills first."""
|
||||
# ---------------------------------------------------------------------------
|
||||
# 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", "kimi-coding"},
|
||||
"zai": {"zai", "glm", "zhipu"},
|
||||
"openai": {"openai", "gpt", "codex"},
|
||||
"gemini": {"gemini", "google"},
|
||||
}
|
||||
|
||||
|
||||
def _classify_runtime(provider: str, model: str) -> str:
|
||||
"""Return 'local' | 'cloud' | 'unknown' for a provider/model pair."""
|
||||
p = (provider or "").strip().lower()
|
||||
m = (model or "").strip().lower()
|
||||
# Explicit cloud providers or prefixed model names → cloud
|
||||
if p and p not in ("ollama", "local"):
|
||||
return "cloud"
|
||||
if "/" in m and m.split("/")[0] in ("nous", "openrouter", "anthropic", "openai", "zai", "kimi", "gemini", "minimax"):
|
||||
return "cloud"
|
||||
# Ollama / local / empty provider with non-prefixed model → local
|
||||
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 the 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()
|
||||
# Find active group
|
||||
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
|
||||
# Check for references to a different group
|
||||
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").
|
||||
"""
|
||||
prompt = job.get("prompt", "")
|
||||
skills = job.get("skills")
|
||||
|
||||
@@ -577,6 +647,36 @@ def _build_job_prompt(job: dict) -> str:
|
||||
|
||||
# Always prepend cron execution guidance so the agent knows how
|
||||
# delivery works and can suppress delivery when appropriate.
|
||||
#
|
||||
# Runtime context injection — tells the agent what it can actually do.
|
||||
# Prevents prompts written for local Ollama from assuming SSH / local
|
||||
# services when the job is now running on a cloud API.
|
||||
_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. Use terminal tools only "
|
||||
"for commands that work from this environment."
|
||||
)
|
||||
if _notes:
|
||||
_runtime_block = (
|
||||
"[SYSTEM: RUNTIME CONTEXT — "
|
||||
+ "; ".join(_notes)
|
||||
+ ". Adjust your approach based on these capabilities.]\\n\\n"
|
||||
)
|
||||
cron_hint = (
|
||||
"[SYSTEM: You are running as a scheduled cron job. "
|
||||
"DELIVERY: Your final response will be automatically delivered "
|
||||
@@ -596,7 +696,7 @@ def _build_job_prompt(job: dict) -> str:
|
||||
"\"[SCRIPT_FAILED]: forge.alexanderwhitestone.com timed out\" "
|
||||
"\"[SCRIPT_FAILED]: script exited with code 1\".]\\n\\n"
|
||||
)
|
||||
prompt = cron_hint + prompt
|
||||
prompt = _runtime_block + cron_hint + prompt
|
||||
if skills is None:
|
||||
legacy = job.get("skill")
|
||||
skills = [legacy] if legacy else []
|
||||
@@ -666,7 +766,36 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
|
||||
|
||||
job_id = job["id"]
|
||||
job_name = job["name"]
|
||||
prompt = _build_job_prompt(job)
|
||||
|
||||
# ── Early model/provider resolution ───────────────────────────────────
|
||||
# We need the model name before building the prompt so the runtime
|
||||
# context block can be injected. Full provider resolution happens
|
||||
# later (smart routing, etc.) but the basic name is enough here.
|
||||
_early_model = job.get("model") or os.getenv("HERMES_MODEL") or ""
|
||||
_early_provider = os.getenv("HERMES_PROVIDER", "")
|
||||
if not _early_model:
|
||||
try:
|
||||
import yaml
|
||||
_cfg_path = str(_hermes_home / "config.yaml")
|
||||
if os.path.exists(_cfg_path):
|
||||
with open(_cfg_path) as _f:
|
||||
_cfg_early = yaml.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
|
||||
# Derive provider from model prefix when not explicitly set
|
||||
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,
|
||||
)
|
||||
origin = _resolve_origin(job)
|
||||
_cron_session_id = f"cron_{job_id}_{_hermes_now().strftime('%Y%m%d_%H%M%S')}"
|
||||
|
||||
@@ -762,6 +891,20 @@ 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 ─────────────────────────────────
|
||||
# If the job prompt references a provider different from the one
|
||||
# we actually resolved, warn so operators know which prompts are stale.
|
||||
_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 be told to adapt via runtime context. "
|
||||
"Consider updating this job's prompt.",
|
||||
job_name, _mismatch, _resolved_provider,
|
||||
)
|
||||
|
||||
from agent.smart_model_routing import resolve_turn_route
|
||||
turn_route = resolve_turn_route(
|
||||
prompt,
|
||||
|
||||
104
hermes_state.py
104
hermes_state.py
@@ -32,7 +32,7 @@ T = TypeVar("T")
|
||||
|
||||
DEFAULT_DB_PATH = get_hermes_home() / "state.db"
|
||||
|
||||
SCHEMA_VERSION = 7
|
||||
SCHEMA_VERSION = 6
|
||||
|
||||
SCHEMA_SQL = """
|
||||
CREATE TABLE IF NOT EXISTS schema_version (
|
||||
@@ -66,7 +66,6 @@ CREATE TABLE IF NOT EXISTS sessions (
|
||||
cost_source TEXT,
|
||||
pricing_version TEXT,
|
||||
title TEXT,
|
||||
profile TEXT,
|
||||
FOREIGN KEY (parent_session_id) REFERENCES sessions(id)
|
||||
);
|
||||
|
||||
@@ -87,7 +86,6 @@ CREATE TABLE IF NOT EXISTS messages (
|
||||
);
|
||||
|
||||
CREATE INDEX IF NOT EXISTS idx_sessions_source ON sessions(source);
|
||||
CREATE INDEX IF NOT EXISTS idx_sessions_profile ON sessions(profile);
|
||||
CREATE INDEX IF NOT EXISTS idx_sessions_parent ON sessions(parent_session_id);
|
||||
CREATE INDEX IF NOT EXISTS idx_sessions_started ON sessions(started_at DESC);
|
||||
CREATE INDEX IF NOT EXISTS idx_messages_session ON messages(session_id, timestamp);
|
||||
@@ -332,19 +330,6 @@ class SessionDB:
|
||||
except sqlite3.OperationalError:
|
||||
pass # Column already exists
|
||||
cursor.execute("UPDATE schema_version SET version = 6")
|
||||
if current_version < 7:
|
||||
# v7: add profile column to sessions for profile isolation (#323)
|
||||
try:
|
||||
cursor.execute('ALTER TABLE sessions ADD COLUMN "profile" TEXT')
|
||||
except sqlite3.OperationalError:
|
||||
pass # Column already exists
|
||||
try:
|
||||
cursor.execute(
|
||||
"CREATE INDEX IF NOT EXISTS idx_sessions_profile ON sessions(profile)"
|
||||
)
|
||||
except sqlite3.OperationalError:
|
||||
pass
|
||||
cursor.execute("UPDATE schema_version SET version = 7")
|
||||
|
||||
# Unique title index — always ensure it exists (safe to run after migrations
|
||||
# since the title column is guaranteed to exist at this point)
|
||||
@@ -377,19 +362,13 @@ class SessionDB:
|
||||
system_prompt: str = None,
|
||||
user_id: str = None,
|
||||
parent_session_id: str = None,
|
||||
profile: str = None,
|
||||
) -> str:
|
||||
"""Create a new session record. Returns the session_id.
|
||||
|
||||
Args:
|
||||
profile: Profile name for session isolation. When set, sessions
|
||||
are tagged so queries can filter by profile. (#323)
|
||||
"""
|
||||
"""Create a new session record. Returns the session_id."""
|
||||
def _do(conn):
|
||||
conn.execute(
|
||||
"""INSERT OR IGNORE INTO sessions (id, source, user_id, model, model_config,
|
||||
system_prompt, parent_session_id, profile, started_at)
|
||||
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)""",
|
||||
system_prompt, parent_session_id, started_at)
|
||||
VALUES (?, ?, ?, ?, ?, ?, ?, ?)""",
|
||||
(
|
||||
session_id,
|
||||
source,
|
||||
@@ -398,7 +377,6 @@ class SessionDB:
|
||||
json.dumps(model_config) if model_config else None,
|
||||
system_prompt,
|
||||
parent_session_id,
|
||||
profile,
|
||||
time.time(),
|
||||
),
|
||||
)
|
||||
@@ -527,23 +505,19 @@ class SessionDB:
|
||||
session_id: str,
|
||||
source: str = "unknown",
|
||||
model: str = None,
|
||||
profile: str = None,
|
||||
) -> None:
|
||||
"""Ensure a session row exists, creating it with minimal metadata if absent.
|
||||
|
||||
Used by _flush_messages_to_session_db to recover from a failed
|
||||
create_session() call (e.g. transient SQLite lock at agent startup).
|
||||
INSERT OR IGNORE is safe to call even when the row already exists.
|
||||
|
||||
Args:
|
||||
profile: Profile name for session isolation. (#323)
|
||||
"""
|
||||
def _do(conn):
|
||||
conn.execute(
|
||||
"""INSERT OR IGNORE INTO sessions
|
||||
(id, source, model, profile, started_at)
|
||||
VALUES (?, ?, ?, ?, ?)""",
|
||||
(session_id, source, model, profile, time.time()),
|
||||
(id, source, model, started_at)
|
||||
VALUES (?, ?, ?, ?)""",
|
||||
(session_id, source, model, time.time()),
|
||||
)
|
||||
self._execute_write(_do)
|
||||
|
||||
@@ -814,7 +788,6 @@ class SessionDB:
|
||||
limit: int = 20,
|
||||
offset: int = 0,
|
||||
include_children: bool = False,
|
||||
profile: str = None,
|
||||
) -> List[Dict[str, Any]]:
|
||||
"""List sessions with preview (first user message) and last active timestamp.
|
||||
|
||||
@@ -826,10 +799,6 @@ class SessionDB:
|
||||
|
||||
By default, child sessions (subagent runs, compression continuations)
|
||||
are excluded. Pass ``include_children=True`` to include them.
|
||||
|
||||
Args:
|
||||
profile: Filter sessions to this profile name. Pass None to see all.
|
||||
(#323)
|
||||
"""
|
||||
where_clauses = []
|
||||
params = []
|
||||
@@ -844,9 +813,6 @@ class SessionDB:
|
||||
placeholders = ",".join("?" for _ in exclude_sources)
|
||||
where_clauses.append(f"s.source NOT IN ({placeholders})")
|
||||
params.extend(exclude_sources)
|
||||
if profile:
|
||||
where_clauses.append("s.profile = ?")
|
||||
params.append(profile)
|
||||
|
||||
where_sql = f"WHERE {' AND '.join(where_clauses)}" if where_clauses else ""
|
||||
query = f"""
|
||||
@@ -1192,52 +1158,34 @@ class SessionDB:
|
||||
source: str = None,
|
||||
limit: int = 20,
|
||||
offset: int = 0,
|
||||
profile: str = None,
|
||||
) -> List[Dict[str, Any]]:
|
||||
"""List sessions, optionally filtered by source and profile.
|
||||
|
||||
Args:
|
||||
profile: Filter sessions to this profile name. Pass None to see all.
|
||||
(#323)
|
||||
"""
|
||||
where_clauses = []
|
||||
params = []
|
||||
if source:
|
||||
where_clauses.append("source = ?")
|
||||
params.append(source)
|
||||
if profile:
|
||||
where_clauses.append("profile = ?")
|
||||
params.append(profile)
|
||||
|
||||
where_sql = f"WHERE {' AND '.join(where_clauses)}" if where_clauses else ""
|
||||
query = f"SELECT * FROM sessions {where_sql} ORDER BY started_at DESC LIMIT ? OFFSET ?"
|
||||
params.extend([limit, offset])
|
||||
"""List sessions, optionally filtered by source."""
|
||||
with self._lock:
|
||||
cursor = self._conn.execute(query, params)
|
||||
if source:
|
||||
cursor = self._conn.execute(
|
||||
"SELECT * FROM sessions WHERE source = ? ORDER BY started_at DESC LIMIT ? OFFSET ?",
|
||||
(source, limit, offset),
|
||||
)
|
||||
else:
|
||||
cursor = self._conn.execute(
|
||||
"SELECT * FROM sessions ORDER BY started_at DESC LIMIT ? OFFSET ?",
|
||||
(limit, offset),
|
||||
)
|
||||
return [dict(row) for row in cursor.fetchall()]
|
||||
|
||||
# =========================================================================
|
||||
# Utility
|
||||
# =========================================================================
|
||||
|
||||
def session_count(self, source: str = None, profile: str = None) -> int:
|
||||
"""Count sessions, optionally filtered by source and profile.
|
||||
|
||||
Args:
|
||||
profile: Filter to this profile name. Pass None to count all. (#323)
|
||||
"""
|
||||
where_clauses = []
|
||||
params = []
|
||||
if source:
|
||||
where_clauses.append("source = ?")
|
||||
params.append(source)
|
||||
if profile:
|
||||
where_clauses.append("profile = ?")
|
||||
params.append(profile)
|
||||
|
||||
where_sql = f"WHERE {' AND '.join(where_clauses)}" if where_clauses else ""
|
||||
def session_count(self, source: str = None) -> int:
|
||||
"""Count sessions, optionally filtered by source."""
|
||||
with self._lock:
|
||||
cursor = self._conn.execute(f"SELECT COUNT(*) FROM sessions {where_sql}", params)
|
||||
if source:
|
||||
cursor = self._conn.execute(
|
||||
"SELECT COUNT(*) FROM sessions WHERE source = ?", (source,)
|
||||
)
|
||||
else:
|
||||
cursor = self._conn.execute("SELECT COUNT(*) FROM sessions")
|
||||
return cursor.fetchone()[0]
|
||||
|
||||
def message_count(self, session_id: str = None) -> int:
|
||||
|
||||
129
tests/test_cron_provider_mismatch.py
Normal file
129
tests/test_cron_provider_mismatch.py
Normal file
@@ -0,0 +1,129 @@
|
||||
"""Tests for cron scheduler: provider mismatch detection, runtime classification,
|
||||
and capability-aware prompt building."""
|
||||
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
|
||||
|
||||
|
||||
def _import_scheduler():
|
||||
"""Import the scheduler module, bypassing __init__.py re-exports that may
|
||||
reference symbols not yet merged upstream."""
|
||||
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 # some top-level imports may fail in CI; functions are still defined
|
||||
return mod
|
||||
|
||||
|
||||
_sched = _import_scheduler()
|
||||
_classify_runtime = _sched._classify_runtime
|
||||
_detect_provider_mismatch = _sched._detect_provider_mismatch
|
||||
_build_job_prompt = _sched._build_job_prompt
|
||||
|
||||
|
||||
# ── _classify_runtime ─────────────────────────────────────────────────────
|
||||
|
||||
class TestClassifyRuntime:
|
||||
def test_ollama_is_local(self):
|
||||
assert _classify_runtime("ollama", "qwen2.5:7b") == "local"
|
||||
|
||||
def test_empty_provider_is_local(self):
|
||||
assert _classify_runtime("", "my-local-model") == "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_openrouter_is_cloud(self):
|
||||
assert _classify_runtime("openrouter", "anthropic/claude-sonnet-4") == "cloud"
|
||||
|
||||
def test_empty_both_is_unknown(self):
|
||||
assert _classify_runtime("", "") == "unknown"
|
||||
|
||||
|
||||
# ── _detect_provider_mismatch ─────────────────────────────────────────────
|
||||
|
||||
class TestDetectProviderMismatch:
|
||||
def test_no_mismatch_when_not_mentioned(self):
|
||||
assert _detect_provider_mismatch("Check system health", "nous") is None
|
||||
|
||||
def test_detects_ollama_when_nous_active(self):
|
||||
assert _detect_provider_mismatch("Check Ollama is responding", "nous") == "ollama"
|
||||
|
||||
def test_detects_anthropic_when_nous_active(self):
|
||||
assert _detect_provider_mismatch("Use Claude to analyze", "nous") == "anthropic"
|
||||
|
||||
def test_no_mismatch_same_provider(self):
|
||||
assert _detect_provider_mismatch("Check Ollama models", "ollama") is None
|
||||
|
||||
def test_empty_prompt(self):
|
||||
assert _detect_provider_mismatch("", "nous") is None
|
||||
|
||||
def test_empty_provider(self):
|
||||
assert _detect_provider_mismatch("Check Ollama", "") is None
|
||||
|
||||
def test_detects_kimi_when_openrouter(self):
|
||||
assert _detect_provider_mismatch("Use Kimi for coding", "openrouter") == "kimi"
|
||||
|
||||
def test_detects_glm_when_nous(self):
|
||||
assert _detect_provider_mismatch("Use GLM for analysis", "nous") == "zai"
|
||||
|
||||
|
||||
# ── _build_job_prompt ─────────────────────────────────────────────────────
|
||||
|
||||
class TestBuildJobPrompt:
|
||||
def _job(self, prompt="Do something"):
|
||||
return {"prompt": prompt, "skills": []}
|
||||
|
||||
def test_no_runtime_no_block(self):
|
||||
result = _build_job_prompt(self._job())
|
||||
assert "Do something" in result
|
||||
assert "RUNTIME CONTEXT" not in result
|
||||
|
||||
def test_cloud_runtime_injected(self):
|
||||
result = _build_job_prompt(
|
||||
self._job(),
|
||||
runtime_model="xiaomi/mimo-v2-pro",
|
||||
runtime_provider="nous",
|
||||
)
|
||||
assert "MODEL: xiaomi/mimo-v2-pro" in result
|
||||
assert "PROVIDER: nous" in result
|
||||
assert "cloud API" in result
|
||||
assert "Do NOT assume you can SSH" in result
|
||||
|
||||
def test_local_runtime_injected(self):
|
||||
result = _build_job_prompt(
|
||||
self._job(),
|
||||
runtime_model="qwen2.5:7b",
|
||||
runtime_provider="ollama",
|
||||
)
|
||||
assert "RUNTIME: local" in result
|
||||
assert "SSH keys" in result
|
||||
|
||||
def test_empty_runtime_no_block(self):
|
||||
result = _build_job_prompt(self._job(), runtime_model="", runtime_provider="")
|
||||
assert "RUNTIME CONTEXT" not in result
|
||||
|
||||
def test_cron_hint_always_present(self):
|
||||
result = _build_job_prompt(self._job())
|
||||
assert "scheduled cron job" in result
|
||||
assert "[SYSTEM:" in result
|
||||
|
||||
def test_runtime_block_before_cron_hint(self):
|
||||
result = _build_job_prompt(
|
||||
self._job("Check Ollama"),
|
||||
runtime_model="mimo-v2-pro",
|
||||
runtime_provider="nous",
|
||||
)
|
||||
runtime_pos = result.index("RUNTIME CONTEXT")
|
||||
cron_pos = result.index("scheduled cron job")
|
||||
assert runtime_pos < cron_pos
|
||||
Reference in New Issue
Block a user