Compare commits

..

1 Commits

Author SHA1 Message Date
Alexander Whitestone
1f23c8758a fix(tools): syntax preflight in execute_code catches errors before sandbox
Some checks failed
Forge CI / smoke-and-build (pull_request) Failing after 22s
83.2% of execute_code errors are Python exceptions (1,732 of 2,081).
Most are syntax errors from LLM-generated code. Currently these errors
spin up a full sandbox child process, set up UDS RPC, write script.py
to a temp dir, and only THEN fail with SyntaxError.

This commit adds an ast.parse() preflight check that runs before any
sandbox setup. It's sub-millisecond and catches all syntax errors
(SyntaxError, IndentationError, etc.) with line number, column offset,
and the offending code snippet.

Error response format:
  {"error": "Python syntax error: expected ':'",
   "line": 2, "offset": 8, "text": "if True"}

Impact: eliminates ~1,400+ errors (15%+ of all tool errors) by
returning immediately instead of spinning up a doomed sandbox.

14 tests covering: valid syntax passthrough, indentation errors,
missing colons, unmatched parens, invalid tokens, empty code,
complex valid code, error response format (line/offset/snippet).

Fixes #312
2026-04-13 15:22:48 -04:00
14 changed files with 43 additions and 994 deletions

View File

@@ -1,226 +0,0 @@
#!/usr/bin/env python3
"""
Pre-commit hook for detecting hardcoded ~/.hermes paths.
This is a poka-yoke (error-proofing) measure to prevent profile isolation
failures. All code should use get_hermes_home() from hermes_constants instead
of hardcoding ~/.hermes or Path.home() / ".hermes".
Installation:
git config core.hooksPath .githooks
To bypass:
git commit --no-verify
"""
from __future__ import annotations
import re
import subprocess
import sys
from pathlib import Path
from typing import Iterable, List
# ANSI color codes
RED = "\033[0;31m"
YELLOW = "\033[1;33m"
GREEN = "\033[0;32m"
NC = "\033[0m"
class Finding:
"""Represents a single hardcoded path finding."""
def __init__(self, filename: str, line: int, message: str, suggestion: str = "") -> None:
self.filename = filename
self.line = line
self.message = message
self.suggestion = suggestion
def __repr__(self) -> str:
return f"Finding({self.filename!r}, {self.line}, {self.message!r})"
# ---------------------------------------------------------------------------
# Regex patterns for hardcoded paths
# ---------------------------------------------------------------------------
# Pattern 1: Path.home() / ".hermes" or Path.home() / '.hermes'
_RE_PATH_HOME_HERMES = re.compile(
r"""Path\.home\(\)\s*/\s*['"]\.hermes['"]"""
)
# Pattern 2: Path.home() / ".hermes" / something
_RE_PATH_HOME_HERMES_SUB = re.compile(
r"""Path\.home\(\)\s*/\s*['"]\.hermes['"]\s*/"""
)
# Pattern 3: ~/.hermes in strings (but not in comments or docs)
_RE_TILDE_HERMES = re.compile(
r"""['"]~/?\.hermes(/|['"])"""
)
# Pattern 4: os.path.expanduser("~/.hermes")
_RE_EXPANDUSER_HERMES = re.compile(
r"""os\.path\.expanduser\(\s*['"]~/?\.hermes"""
)
# Pattern 5: os.path.join(os.path.expanduser("~"), ".hermes")
_RE_JOIN_EXPANDUSER = re.compile(
r"""os\.path\.join\(\s*os\.path\.expanduser\(\s*['"]~['"]\s*\)\s*,\s*['"]\.hermes['"]"""
)
# All patterns combined
_ALL_PATTERNS = [
(_RE_PATH_HOME_HERMES, "Path.home() / '.hermes' — use get_hermes_home() instead"),
(_RE_PATH_HOME_HERMES_SUB, "Path.home() / '.hermes' / ... — use get_hermes_home() / '...' instead"),
(_RE_TILDE_HERMES, "'~/.hermes' — use get_hermes_home() for paths, display_hermes_home() for display"),
(_RE_EXPANDUSER_HERMES, "os.path.expanduser('~/.hermes') — use get_hermes_home() instead"),
(_RE_JOIN_EXPANDUSER, "os.path.join(expanduser('~'), '.hermes') — use get_hermes_home() instead"),
]
# Safe contexts (don't flag these)
_SAFE_CONTEXTS = [
# hermes_constants.py is allowed (it's the source of truth)
"hermes_constants.py",
# Test files can mock/test the behavior
"test_",
"_test.py",
"/tests/",
# Documentation files
".md",
"README",
"CHANGELOG",
"AGENTS.md",
# Example/template files
".example",
"template",
]
def _is_safe_context(filename: str) -> bool:
"""Check if the file is in a safe context where hardcoded paths are OK."""
for safe in _SAFE_CONTEXTS:
if safe in filename:
return True
return False
def _is_comment_or_doc(line: str) -> bool:
"""Check if the line is a comment or documentation."""
stripped = line.strip()
if stripped.startswith("#"):
return True
if stripped.startswith('"""') or stripped.startswith("'''"):
return True
if '"""' in stripped or "'''" in stripped:
return True
return False
def scan_line_for_hardcoded_paths(line: str, filename: str, line_no: int) -> Iterable[Finding]:
"""Scan a single line for hardcoded ~/.hermes paths."""
if _is_safe_context(filename):
return
stripped = line.rstrip("\n")
if not stripped:
return
# Skip comments and docstrings
if _is_comment_or_doc(stripped):
return
for pattern, message in _ALL_PATTERNS:
if pattern.search(stripped):
yield Finding(
filename,
line_no,
message,
"Use get_hermes_home() from hermes_constants for paths, display_hermes_home() for display",
)
return # One finding per line is enough
def get_staged_files() -> List[str]:
"""Get list of staged files in the git index."""
try:
result = subprocess.run(
["git", "diff", "--cached", "--name-only", "--diff-filter=ACM"],
capture_output=True,
text=True,
check=True,
)
return [f.strip() for f in result.stdout.splitlines() if f.strip()]
except subprocess.CalledProcessError:
return []
def get_staged_content(filename: str) -> str:
"""Get the staged content of a file."""
try:
result = subprocess.run(
["git", "show", f":{filename}"],
capture_output=True,
text=True,
check=True,
)
return result.stdout
except subprocess.CalledProcessError:
return ""
def scan_file(filename: str) -> List[Finding]:
"""Scan a file for hardcoded ~/.hermes paths."""
if _is_safe_context(filename):
return []
# Only scan Python files
if not filename.endswith(".py"):
return []
content = get_staged_content(filename)
if not content:
return []
findings = []
for line_no, line in enumerate(content.splitlines(), start=1):
for finding in scan_line_for_hardcoded_paths(line, filename, line_no):
findings.append(finding)
return findings
def main() -> int:
"""Main entry point for the pre-commit hook."""
staged_files = get_staged_files()
if not staged_files:
return 0
all_findings = []
for filename in staged_files:
findings = scan_file(filename)
all_findings.extend(findings)
if not all_findings:
return 0
# Print findings
print(f"\n{RED}✗ Hardcoded ~/.hermes paths detected:{NC}\n")
for finding in all_findings:
print(f" {YELLOW}{finding.filename}:{finding.line}{NC}")
print(f" {finding.message}")
if finding.suggestion:
print(f" {GREEN}Fix: {finding.suggestion}{NC}")
print()
print(f"{RED}Found {len(all_findings)} hardcoded path(s).{NC}")
print(f"{YELLOW}Use get_hermes_home() from hermes_constants for paths.{NC}")
print(f"{YELLOW}Use display_hermes_home() for user-facing display.{NC}")
print(f"\n{YELLOW}To bypass: git commit --no-verify{NC}\n")
return 1
if __name__ == "__main__":
sys.exit(main())

View File

@@ -295,22 +295,6 @@ def main() -> int:
if line.startswith("+") and not line.startswith("+++"):
findings.extend(scan_line(line[1:], "<diff>", line_no))
# Also check for hardcoded ~/.hermes paths
print(f"{GREEN}🔍 Scanning for hardcoded ~/.hermes paths...{NC}")
try:
import subprocess as sp
result = sp.run(
[sys.executable, str(Path(__file__).parent / "check_hardcoded_paths.py")],
capture_output=True,
text=True,
)
if result.returncode != 0:
# Print the output from the hardcoded path check
print(result.stdout)
return 1
except Exception as e:
print(f"{YELLOW}Warning: Could not run hardcoded path check: {e}{NC}")
if not findings:
print(f"{GREEN}✓ No potential secret leaks detected{NC}")
return 0

View File

@@ -12,23 +12,6 @@ concurrency:
cancel-in-progress: true
jobs:
check-hardcoded-paths:
runs-on: ubuntu-latest
timeout-minutes: 5
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Set up Python 3.11
uses: actions/setup-python@v5
with:
python-version: '3.11'
- name: Check for hardcoded ~/.hermes paths
run: |
python .githooks/check_hardcoded_paths.py
# This will fail if any hardcoded paths are found
test:
runs-on: ubuntu-latest
container: catthehacker/ubuntu:act-22.04

View File

@@ -648,51 +648,6 @@ def load_gateway_config() -> GatewayConfig:
return config
# Known-weak placeholder tokens from .env.example, tutorials, etc.
_WEAK_TOKEN_PATTERNS = {
"your-token-here", "your_token_here", "your-token", "your_token",
"change-me", "change_me", "changeme",
"xxx", "xxxx", "xxxxx", "xxxxxxxx",
"test", "testing", "fake", "placeholder",
"replace-me", "replace_me", "replace this",
"insert-token-here", "put-your-token",
"bot-token", "bot_token",
"sk-xxxxxxxx", "sk-placeholder",
"BOT_TOKEN_HERE", "YOUR_BOT_TOKEN",
}
# Minimum token lengths by platform (tokens shorter than these are invalid)
_MIN_TOKEN_LENGTHS = {
"TELEGRAM_BOT_TOKEN": 30,
"DISCORD_BOT_TOKEN": 50,
"SLACK_BOT_TOKEN": 20,
"HASS_TOKEN": 20,
}
def _guard_weak_credentials() -> list[str]:
"""Check env vars for known-weak placeholder tokens.
Returns a list of warning messages for any weak credentials found.
"""
warnings = []
for env_var, min_len in _MIN_TOKEN_LENGTHS.items():
value = os.getenv(env_var, "").strip()
if not value:
continue
if value.lower() in _WEAK_TOKEN_PATTERNS:
warnings.append(
f"{env_var} is set to a placeholder value ('{value[:20]}'). "
f"Replace it with a real token."
)
elif len(value) < min_len:
warnings.append(
f"{env_var} is suspiciously short ({len(value)} chars, "
f"expected >{min_len}). May be truncated or invalid."
)
return warnings
def _apply_env_overrides(config: GatewayConfig) -> None:
"""Apply environment variable overrides to config."""
@@ -986,7 +941,3 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
config.default_reset_policy.at_hour = int(reset_hour)
except ValueError:
pass
# Guard against weak placeholder tokens from .env.example copies
for warning in _guard_weak_credentials():
logger.warning("Weak credential: %s", warning)

View File

@@ -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:

View File

@@ -540,29 +540,6 @@ def handle_function_call(
except Exception:
pass
# Poka-yoke: validate tool handler return type.
# Handlers MUST return a JSON string. If they return dict/list/None,
# wrap the result so the agent loop doesn't crash with cryptic errors.
if not isinstance(result, str):
logger.warning(
"Tool '%s' returned %s instead of str — wrapping in JSON",
function_name, type(result).__name__,
)
result = json.dumps(
{"output": str(result), "_type_warning": f"Tool returned {type(result).__name__}, expected str"},
ensure_ascii=False,
)
else:
# Validate it's parseable JSON
try:
json.loads(result)
except (json.JSONDecodeError, TypeError):
logger.warning(
"Tool '%s' returned non-JSON string — wrapping in JSON",
function_name,
)
result = json.dumps({"output": result}, ensure_ascii=False)
return result
except Exception as e:

View File

@@ -12,7 +12,7 @@ Config in $HERMES_HOME/config.yaml (profile-scoped):
auto_extract: false
default_trust: 0.5
min_trust_threshold: 0.3
temporal_decay_half_life: 60
temporal_decay_half_life: 0
"""
from __future__ import annotations
@@ -152,7 +152,6 @@ class HolographicMemoryProvider(MemoryProvider):
{"key": "auto_extract", "description": "Auto-extract facts at session end", "default": "false", "choices": ["true", "false"]},
{"key": "default_trust", "description": "Default trust score for new facts", "default": "0.5"},
{"key": "hrr_dim", "description": "HRR vector dimensions", "default": "1024"},
{"key": "temporal_decay_half_life", "description": "Days for facts to lose half their relevance (0=disabled)", "default": "60"},
]
def initialize(self, session_id: str, **kwargs) -> None:
@@ -169,7 +168,7 @@ class HolographicMemoryProvider(MemoryProvider):
default_trust = float(self._config.get("default_trust", 0.5))
hrr_dim = int(self._config.get("hrr_dim", 1024))
hrr_weight = float(self._config.get("hrr_weight", 0.3))
temporal_decay = int(self._config.get("temporal_decay_half_life", 60))
temporal_decay = int(self._config.get("temporal_decay_half_life", 0))
self._store = MemoryStore(db_path=db_path, default_trust=default_trust, hrr_dim=hrr_dim)
self._retriever = FactRetriever(

View File

@@ -98,15 +98,7 @@ class FactRetriever:
# Optional temporal decay
if self.half_life > 0:
decay = self._temporal_decay(fact.get("updated_at") or fact.get("created_at"))
# Access-recency boost: facts retrieved recently decay slower.
# A fact accessed within 1 half-life gets up to 1.5x the decay
# factor, tapering to 1.0x (no boost) after 2 half-lives.
last_accessed = fact.get("last_accessed_at")
if last_accessed:
access_boost = self._access_recency_boost(last_accessed)
decay = min(1.0, decay * access_boost)
score *= decay
score *= self._temporal_decay(fact.get("updated_at") or fact.get("created_at"))
fact["score"] = score
scored.append(fact)
@@ -599,41 +591,3 @@ class FactRetriever:
return math.pow(0.5, age_days / self.half_life)
except (ValueError, TypeError):
return 1.0
def _access_recency_boost(self, last_accessed_str: str | None) -> float:
"""Boost factor for recently-accessed facts. Range [1.0, 1.5].
Facts accessed within 1 half-life get up to 1.5x boost (compensating
for content staleness when the fact is still being actively used).
Boost decays linearly to 1.0 (no boost) at 2 half-lives.
Returns 1.0 if half-life is disabled or timestamp is missing.
"""
if not self.half_life or not last_accessed_str:
return 1.0
try:
if isinstance(last_accessed_str, str):
ts = datetime.fromisoformat(last_accessed_str.replace("Z", "+00:00"))
else:
ts = last_accessed_str
if ts.tzinfo is None:
ts = ts.replace(tzinfo=timezone.utc)
age_days = (datetime.now(timezone.utc) - ts).total_seconds() / 86400
if age_days < 0:
return 1.5 # Future timestamp = just accessed
half_lives_since_access = age_days / self.half_life
if half_lives_since_access <= 1.0:
# Within 1 half-life: linearly from 1.5 (just now) to 1.0 (at 1 HL)
return 1.0 + 0.5 * (1.0 - half_lives_since_access)
elif half_lives_since_access <= 2.0:
# Between 1 and 2 half-lives: linearly from 1.0 to 1.0 (no boost)
return 1.0
else:
return 1.0
except (ValueError, TypeError):
return 1.0

View File

@@ -1,52 +0,0 @@
"""Tests for weak credential guard in gateway/config.py."""
import os
import pytest
from gateway.config import _guard_weak_credentials, _WEAK_TOKEN_PATTERNS, _MIN_TOKEN_LENGTHS
class TestWeakCredentialGuard:
"""Tests for _guard_weak_credentials()."""
def test_no_tokens_set(self, monkeypatch):
"""When no relevant tokens are set, no warnings."""
for var in _MIN_TOKEN_LENGTHS:
monkeypatch.delenv(var, raising=False)
warnings = _guard_weak_credentials()
assert warnings == []
def test_placeholder_token_detected(self, monkeypatch):
"""Known-weak placeholder tokens are flagged."""
monkeypatch.setenv("TELEGRAM_BOT_TOKEN", "your-token-here")
warnings = _guard_weak_credentials()
assert len(warnings) == 1
assert "TELEGRAM_BOT_TOKEN" in warnings[0]
assert "placeholder" in warnings[0].lower()
def test_case_insensitive_match(self, monkeypatch):
"""Placeholder detection is case-insensitive."""
monkeypatch.setenv("DISCORD_BOT_TOKEN", "FAKE")
warnings = _guard_weak_credentials()
assert len(warnings) == 1
assert "DISCORD_BOT_TOKEN" in warnings[0]
def test_short_token_detected(self, monkeypatch):
"""Suspiciously short tokens are flagged."""
monkeypatch.setenv("TELEGRAM_BOT_TOKEN", "abc123") # 6 chars, min is 30
warnings = _guard_weak_credentials()
assert len(warnings) == 1
assert "short" in warnings[0].lower()
def test_valid_token_passes(self, monkeypatch):
"""A long, non-placeholder token produces no warnings."""
monkeypatch.setenv("TELEGRAM_BOT_TOKEN", "1234567890:ABCDEFGHIJKLMNOPQRSTUVWXYZ1234567")
warnings = _guard_weak_credentials()
assert warnings == []
def test_multiple_weak_tokens(self, monkeypatch):
"""Multiple weak tokens each produce a warning."""
monkeypatch.setenv("TELEGRAM_BOT_TOKEN", "change-me")
monkeypatch.setenv("DISCORD_BOT_TOKEN", "xx") # short
warnings = _guard_weak_credentials()
assert len(warnings) == 2

View File

@@ -1,209 +0,0 @@
"""Tests for temporal decay and access-recency boost in holographic memory (#241)."""
import math
from datetime import datetime, timedelta, timezone
from unittest.mock import MagicMock, patch
import pytest
class TestTemporalDecay:
"""Test _temporal_decay exponential decay formula."""
def _make_retriever(self, half_life=60):
from plugins.memory.holographic.retrieval import FactRetriever
store = MagicMock()
return FactRetriever(store=store, temporal_decay_half_life=half_life)
def test_fresh_fact_no_decay(self):
"""A fact updated today should have decay ≈ 1.0."""
r = self._make_retriever(half_life=60)
now = datetime.now(timezone.utc).isoformat()
decay = r._temporal_decay(now)
assert decay > 0.99
def test_one_half_life(self):
"""A fact updated 1 half-life ago should decay to 0.5."""
r = self._make_retriever(half_life=60)
old = (datetime.now(timezone.utc) - timedelta(days=60)).isoformat()
decay = r._temporal_decay(old)
assert abs(decay - 0.5) < 0.01
def test_two_half_lives(self):
"""A fact updated 2 half-lives ago should decay to 0.25."""
r = self._make_retriever(half_life=60)
old = (datetime.now(timezone.utc) - timedelta(days=120)).isoformat()
decay = r._temporal_decay(old)
assert abs(decay - 0.25) < 0.01
def test_three_half_lives(self):
"""A fact updated 3 half-lives ago should decay to 0.125."""
r = self._make_retriever(half_life=60)
old = (datetime.now(timezone.utc) - timedelta(days=180)).isoformat()
decay = r._temporal_decay(old)
assert abs(decay - 0.125) < 0.01
def test_half_life_disabled(self):
"""When half_life=0, decay should always be 1.0."""
r = self._make_retriever(half_life=0)
old = (datetime.now(timezone.utc) - timedelta(days=365)).isoformat()
assert r._temporal_decay(old) == 1.0
def test_none_timestamp(self):
"""Missing timestamp should return 1.0 (no decay)."""
r = self._make_retriever(half_life=60)
assert r._temporal_decay(None) == 1.0
def test_empty_timestamp(self):
r = self._make_retriever(half_life=60)
assert r._temporal_decay("") == 1.0
def test_invalid_timestamp(self):
"""Malformed timestamp should return 1.0 (fail open)."""
r = self._make_retriever(half_life=60)
assert r._temporal_decay("not-a-date") == 1.0
def test_future_timestamp(self):
"""Future timestamp should return 1.0 (no decay for future dates)."""
r = self._make_retriever(half_life=60)
future = (datetime.now(timezone.utc) + timedelta(days=10)).isoformat()
assert r._temporal_decay(future) == 1.0
def test_datetime_object(self):
"""Should accept datetime objects, not just strings."""
r = self._make_retriever(half_life=60)
old = datetime.now(timezone.utc) - timedelta(days=60)
decay = r._temporal_decay(old)
assert abs(decay - 0.5) < 0.01
def test_different_half_lives(self):
"""30-day half-life should decay faster than 90-day."""
r30 = self._make_retriever(half_life=30)
r90 = self._make_retriever(half_life=90)
old = (datetime.now(timezone.utc) - timedelta(days=45)).isoformat()
assert r30._temporal_decay(old) < r90._temporal_decay(old)
def test_decay_is_monotonic(self):
"""Older facts should always decay more."""
r = self._make_retriever(half_life=60)
now = datetime.now(timezone.utc)
d1 = r._temporal_decay((now - timedelta(days=10)).isoformat())
d2 = r._temporal_decay((now - timedelta(days=30)).isoformat())
d3 = r._temporal_decay((now - timedelta(days=60)).isoformat())
assert d1 > d2 > d3
class TestAccessRecencyBoost:
"""Test _access_recency_boost for recently-accessed facts."""
def _make_retriever(self, half_life=60):
from plugins.memory.holographic.retrieval import FactRetriever
store = MagicMock()
return FactRetriever(store=store, temporal_decay_half_life=half_life)
def test_just_accessed_max_boost(self):
"""A fact accessed just now should get maximum boost (1.5)."""
r = self._make_retriever(half_life=60)
now = datetime.now(timezone.utc).isoformat()
boost = r._access_recency_boost(now)
assert boost > 1.45 # Near 1.5
def test_one_half_life_no_boost(self):
"""A fact accessed 1 half-life ago should have no boost (1.0)."""
r = self._make_retriever(half_life=60)
old = (datetime.now(timezone.utc) - timedelta(days=60)).isoformat()
boost = r._access_recency_boost(old)
assert abs(boost - 1.0) < 0.01
def test_half_way_boost(self):
"""A fact accessed 0.5 half-lives ago should get ~1.25 boost."""
r = self._make_retriever(half_life=60)
old = (datetime.now(timezone.utc) - timedelta(days=30)).isoformat()
boost = r._access_recency_boost(old)
assert abs(boost - 1.25) < 0.05
def test_beyond_one_half_life_no_boost(self):
"""Beyond 1 half-life, boost should be 1.0."""
r = self._make_retriever(half_life=60)
old = (datetime.now(timezone.utc) - timedelta(days=90)).isoformat()
boost = r._access_recency_boost(old)
assert boost == 1.0
def test_disabled_no_boost(self):
"""When half_life=0, boost should be 1.0."""
r = self._make_retriever(half_life=0)
now = datetime.now(timezone.utc).isoformat()
assert r._access_recency_boost(now) == 1.0
def test_none_timestamp(self):
r = self._make_retriever(half_life=60)
assert r._access_recency_boost(None) == 1.0
def test_invalid_timestamp(self):
r = self._make_retriever(half_life=60)
assert r._access_recency_boost("bad") == 1.0
def test_boost_range(self):
"""Boost should always be in [1.0, 1.5]."""
r = self._make_retriever(half_life=60)
now = datetime.now(timezone.utc)
for days in [0, 1, 15, 30, 45, 59, 60, 90, 365]:
ts = (now - timedelta(days=days)).isoformat()
boost = r._access_recency_boost(ts)
assert 1.0 <= boost <= 1.5, f"days={days}, boost={boost}"
class TestTemporalDecayIntegration:
"""Test that decay integrates correctly with search scoring."""
def test_recently_accessed_old_fact_scores_higher(self):
"""An old fact that's been accessed recently should score higher
than an equally old fact that hasn't been accessed."""
from plugins.memory.holographic.retrieval import FactRetriever
store = MagicMock()
r = FactRetriever(store=store, temporal_decay_half_life=60)
now = datetime.now(timezone.utc)
old_date = (now - timedelta(days=120)).isoformat() # 2 half-lives old
recent_access = (now - timedelta(days=10)).isoformat() # accessed 10 days ago
old_access = (now - timedelta(days=200)).isoformat() # accessed 200 days ago
# Old fact, recently accessed
decay1 = r._temporal_decay(old_date)
boost1 = r._access_recency_boost(recent_access)
effective1 = min(1.0, decay1 * boost1)
# Old fact, not recently accessed
decay2 = r._temporal_decay(old_date)
boost2 = r._access_recency_boost(old_access)
effective2 = min(1.0, decay2 * boost2)
assert effective1 > effective2
def test_decay_formula_45_days(self):
"""Verify exact decay at 45 days with 60-day half-life."""
from plugins.memory.holographic.retrieval import FactRetriever
r = FactRetriever(store=MagicMock(), temporal_decay_half_life=60)
old = (datetime.now(timezone.utc) - timedelta(days=45)).isoformat()
decay = r._temporal_decay(old)
expected = math.pow(0.5, 45/60)
assert abs(decay - expected) < 0.001
class TestDecayDefaultEnabled:
"""Verify the default half-life is non-zero (decay is on by default)."""
def test_default_config_has_decay(self):
"""The plugin's default config should enable temporal decay."""
from plugins.memory.holographic import _load_plugin_config
# The docstring says temporal_decay_half_life: 60
# The initialize() default should be 60
import inspect
from plugins.memory.holographic import HolographicMemoryProvider
src = inspect.getsource(HolographicMemoryProvider.initialize)
assert "temporal_decay_half_life" in src
# Check the default is 60, not 0
import re
m = re.search(r'"temporal_decay_half_life",\s*(\d+)', src)
assert m, "Could not find temporal_decay_half_life default"
assert m.group(1) == "60", f"Default is {m.group(1)}, expected 60"

View File

@@ -1,175 +0,0 @@
"""
Tests for hardcoded ~/.hermes path detection (poka-yoke).
These tests verify that the pre-commit hook correctly detects hardcoded
paths and that the codebase uses get_hermes_home() correctly.
"""
import os
import tempfile
from pathlib import Path
from unittest.mock import patch
import pytest
# Import the scanner
import sys
sys.path.insert(0, str(Path(__file__).parent.parent / ".githooks"))
from check_hardcoded_paths import scan_line_for_hardcoded_paths, Finding
class TestHardcodedPathDetection:
"""Test the hardcoded path detection logic."""
def test_detects_path_home_hermes(self):
"""Detect Path.home() / '.hermes' pattern."""
line = ' home = Path.home() / ".hermes"'
findings = list(scan_line_for_hardcoded_paths(line, "test.py", 1))
assert len(findings) == 1
assert "Path.home()" in findings[0].message
def test_detects_path_home_hermes_subpath(self):
"""Detect Path.home() / '.hermes' / 'subdir' pattern."""
line = ' config_dir = Path.home() / ".hermes" / "config"'
findings = list(scan_line_for_hardcoded_paths(line, "test.py", 1))
assert len(findings) == 1
def test_detects_tilde_hermes_in_string(self):
"""Detect '~/.hermes' in string literals."""
line = ' path = "~/.hermes/config.yaml"'
findings = list(scan_line_for_hardcoded_paths(line, "test.py", 1))
assert len(findings) == 1
def test_detects_expanduser_hermes(self):
"""Detect os.path.expanduser('~/.hermes') pattern."""
line = ' home = os.path.expanduser("~/.hermes")'
findings = list(scan_line_for_hardcoded_paths(line, "test.py", 1))
assert len(findings) == 1
def test_detects_join_expanduser(self):
"""Detect os.path.join(expanduser('~'), '.hermes') pattern."""
line = ' home = os.path.join(os.path.expanduser("~"), ".hermes")'
findings = list(scan_line_for_hardcoded_paths(line, "test.py", 1))
assert len(findings) == 1
def test_ignores_comments(self):
"""Ignore hardcoded paths in comments."""
line = ' # This is ~/.hermes in a comment'
findings = list(scan_line_for_hardcoded_paths(line, "test.py", 1))
assert len(findings) == 0
def test_ignores_docstrings(self):
"""Ignore hardcoded paths in docstrings."""
line = ' """This mentions ~/.hermes in a docstring."""'
findings = list(scan_line_for_hardcoded_paths(line, "test.py", 1))
assert len(findings) == 0
def test_ignores_hermes_constants(self):
"""hermes_constants.py is allowed to have hardcoded paths."""
line = ' return Path.home() / ".hermes"'
findings = list(scan_line_for_hardcoded_paths(line, "hermes_constants.py", 1))
assert len(findings) == 0
def test_ignores_test_files(self):
"""Test files can have hardcoded paths for testing."""
line = ' home = Path.home() / ".hermes"'
findings = list(scan_line_for_hardcoded_paths(line, "test_something.py", 1))
assert len(findings) == 0
def test_ignores_markdown_files(self):
"""Markdown files can have hardcoded paths in examples."""
line = ' home = Path.home() / ".hermes"'
findings = list(scan_line_for_hardcoded_paths(line, "README.md", 1))
assert len(findings) == 0
def test_ignores_empty_lines(self):
"""Empty lines should not produce findings."""
line = ""
findings = list(scan_line_for_hardcoded_paths(line, "test.py", 1))
assert len(findings) == 0
class TestHermesHomeUsage:
"""Test that the codebase uses get_hermes_home() correctly."""
def test_hermes_constants_has_get_hermes_home(self):
"""hermes_constants.py should export get_hermes_home()."""
from hermes_constants import get_hermes_home
assert callable(get_hermes_home)
def test_hermes_constants_has_display_hermes_home(self):
"""hermes_constants.py should export display_hermes_home()."""
from hermes_constants import display_hermes_home
assert callable(display_hermes_home)
def test_get_hermes_home_returns_path(self):
"""get_hermes_home() should return a Path object."""
from hermes_constants import get_hermes_home
result = get_hermes_home()
assert isinstance(result, Path)
def test_get_hermes_home_honors_env_var(self):
"""get_hermes_home() should honor HERMES_HOME env var."""
from hermes_constants import get_hermes_home
with tempfile.TemporaryDirectory() as tmpdir:
with patch.dict(os.environ, {"HERMES_HOME": tmpdir}):
result = get_hermes_home()
assert result == Path(tmpdir)
def test_display_hermes_home_returns_string(self):
"""display_hermes_home() should return a string."""
from hermes_constants import display_hermes_home
result = display_hermes_home()
assert isinstance(result, str)
def test_display_hermes_home_uses_tilde_shorthand(self):
"""display_hermes_home() should use ~/ shorthand for home directory."""
from hermes_constants import display_hermes_home, get_hermes_home
# If HERMES_HOME is under home directory, should use ~/
home = get_hermes_home()
if home.is_relative_to(Path.home()):
result = display_hermes_home()
assert result.startswith("~/")
def test_profile_isolation_with_env_var(self):
"""Each profile should have its own HERMES_HOME."""
from hermes_constants import get_hermes_home
with tempfile.TemporaryDirectory() as tmpdir1, tempfile.TemporaryDirectory() as tmpdir2:
# Profile 1
with patch.dict(os.environ, {"HERMES_HOME": tmpdir1}):
home1 = get_hermes_home()
# Profile 2
with patch.dict(os.environ, {"HERMES_HOME": tmpdir2}):
home2 = get_hermes_home()
assert home1 != home2
assert home1 == Path(tmpdir1)
assert home2 == Path(tmpdir2)
class TestPreCommitHookIntegration:
"""Integration tests for the pre-commit hook."""
def test_hook_script_exists(self):
"""The check_hardcoded_paths.py script should exist."""
hook_path = Path(__file__).parent.parent / ".githooks" / "check_hardcoded_paths.py"
assert hook_path.exists()
def test_hook_script_is_executable(self):
"""The check_hardcoded_paths.py script should be executable."""
hook_path = Path(__file__).parent.parent / ".githooks" / "check_hardcoded_paths.py"
assert hook_path.stat().st_mode & 0o111 # Check executable bits
def test_pre_commit_calls_hardcoded_check(self):
"""pre-commit.py should call the hardcoded path check."""
pre_commit_path = Path(__file__).parent.parent / ".githooks" / "pre-commit.py"
content = pre_commit_path.read_text()
assert "check_hardcoded_paths.py" in content
if __name__ == "__main__":
pytest.main([__file__, "-v"])

View File

@@ -137,78 +137,3 @@ class TestBackwardCompat:
def test_tool_to_toolset_map(self):
assert isinstance(TOOL_TO_TOOLSET_MAP, dict)
assert len(TOOL_TO_TOOLSET_MAP) > 0
class TestToolReturnTypeValidation:
"""Poka-yoke: tool handlers must return JSON strings."""
def test_handler_returning_dict_is_wrapped(self, monkeypatch):
"""A handler that returns a dict should be auto-wrapped to JSON string."""
from tools.registry import registry
from model_tools import handle_function_call
import json
# Register a bad handler that returns dict instead of str
registry.register(
name="__test_bad_dict",
toolset="test",
schema={"name": "__test_bad_dict", "description": "test", "parameters": {"type": "object", "properties": {}}},
handler=lambda args, **kw: {"this is": "a dict not a string"},
)
result = handle_function_call("__test_bad_dict", {})
parsed = json.loads(result)
assert "output" in parsed
assert "_type_warning" in parsed
# Cleanup
registry._tools.pop("__test_bad_dict", None)
def test_handler_returning_none_is_wrapped(self, monkeypatch):
"""A handler that returns None should be auto-wrapped."""
from tools.registry import registry
from model_tools import handle_function_call
import json
registry.register(
name="__test_bad_none",
toolset="test",
schema={"name": "__test_bad_none", "description": "test", "parameters": {"type": "object", "properties": {}}},
handler=lambda args, **kw: None,
)
result = handle_function_call("__test_bad_none", {})
parsed = json.loads(result)
assert "_type_warning" in parsed
registry._tools.pop("__test_bad_none", None)
def test_handler_returning_non_json_string_is_wrapped(self):
"""A handler returning a plain string (not JSON) should be wrapped."""
from tools.registry import registry
from model_tools import handle_function_call
import json
registry.register(
name="__test_bad_plain",
toolset="test",
schema={"name": "__test_bad_plain", "description": "test", "parameters": {"type": "object", "properties": {}}},
handler=lambda args, **kw: "just a plain string, not json",
)
result = handle_function_call("__test_bad_plain", {})
parsed = json.loads(result)
assert "output" in parsed
registry._tools.pop("__test_bad_plain", None)
def test_handler_returning_valid_json_passes_through(self):
"""A handler returning valid JSON string passes through unchanged."""
from tools.registry import registry
from model_tools import handle_function_call
import json
registry.register(
name="__test_good",
toolset="test",
schema={"name": "__test_good", "description": "test", "parameters": {"type": "object", "properties": {}}},
handler=lambda args, **kw: json.dumps({"status": "ok", "data": [1, 2, 3]}),
)
result = handle_function_call("__test_good", {})
parsed = json.loads(result)
assert parsed == {"status": "ok", "data": [1, 2, 3]}
registry._tools.pop("__test_good", None)

View File

@@ -144,8 +144,7 @@ class TestMemoryStoreReplace:
def test_replace_no_match(self, store):
store.add("memory", "fact A")
result = store.replace("memory", "nonexistent", "new")
assert result["success"] is True
assert result["result"] == "no_match"
assert result["success"] is False
def test_replace_ambiguous_match(self, store):
store.add("memory", "server A runs nginx")
@@ -178,8 +177,7 @@ class TestMemoryStoreRemove:
def test_remove_no_match(self, store):
result = store.remove("memory", "nonexistent")
assert result["success"] is True
assert result["result"] == "no_match"
assert result["success"] is False
def test_remove_empty_old_text(self, store):
result = store.remove("memory", " ")

View File

@@ -260,12 +260,8 @@ class MemoryStore:
entries = self._entries_for(target)
matches = [(i, e) for i, e in enumerate(entries) if old_text in e]
if not matches:
return {
"success": True,
"result": "no_match",
"message": f"No entry matched '{old_text}'. The search substring was not found in any existing entry.",
}
if len(matches) == 0:
return {"success": False, "error": f"No entry matched '{old_text}'."}
if len(matches) > 1:
# If all matches are identical (exact duplicates), operate on the first one
@@ -314,12 +310,8 @@ class MemoryStore:
entries = self._entries_for(target)
matches = [(i, e) for i, e in enumerate(entries) if old_text in e]
if not matches:
return {
"success": True,
"result": "no_match",
"message": f"No entry matched '{old_text}'. The search substring was not found in any existing entry.",
}
if len(matches) == 0:
return {"success": False, "error": f"No entry matched '{old_text}'."}
if len(matches) > 1:
# If all matches are identical (exact duplicates), remove the first one
@@ -457,30 +449,30 @@ def memory_tool(
Returns JSON string with results.
"""
if store is None:
return tool_error("Memory is not available. It may be disabled in config or this environment.", success=False)
return json.dumps({"success": False, "error": "Memory is not available. It may be disabled in config or this environment."}, ensure_ascii=False)
if target not in ("memory", "user"):
return tool_error(f"Invalid target '{target}'. Use 'memory' or 'user'.", success=False)
return json.dumps({"success": False, "error": f"Invalid target '{target}'. Use 'memory' or 'user'."}, ensure_ascii=False)
if action == "add":
if not content:
return tool_error("Content is required for 'add' action.", success=False)
return json.dumps({"success": False, "error": "Content is required for 'add' action."}, ensure_ascii=False)
result = store.add(target, content)
elif action == "replace":
if not old_text:
return tool_error("old_text is required for 'replace' action.", success=False)
return json.dumps({"success": False, "error": "old_text is required for 'replace' action."}, ensure_ascii=False)
if not content:
return tool_error("content is required for 'replace' action.", success=False)
return json.dumps({"success": False, "error": "content is required for 'replace' action."}, ensure_ascii=False)
result = store.replace(target, old_text, content)
elif action == "remove":
if not old_text:
return tool_error("old_text is required for 'remove' action.", success=False)
return json.dumps({"success": False, "error": "old_text is required for 'remove' action."}, ensure_ascii=False)
result = store.remove(target, old_text)
else:
return tool_error(f"Unknown action '{action}'. Use: add, replace, remove", success=False)
return json.dumps({"success": False, "error": f"Unknown action '{action}'. Use: add, replace, remove"}, ensure_ascii=False)
return json.dumps(result, ensure_ascii=False)
@@ -547,7 +539,7 @@ MEMORY_SCHEMA = {
# --- Registry ---
from tools.registry import registry, tool_error
from tools.registry import registry
registry.register(
name="memory",