Compare commits
2 Commits
fix/issue-
...
feat/670-a
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
a19ecd33c9 | ||
|
|
7fc8389a76 |
68
docs/approval-tiers.md
Normal file
68
docs/approval-tiers.md
Normal file
@@ -0,0 +1,68 @@
|
||||
# Approval Tier System
|
||||
|
||||
Graduated safety based on risk level. Routes confirmations through the appropriate channel.
|
||||
|
||||
## Tiers
|
||||
|
||||
| Tier | Level | Actions | Human | LLM | Timeout |
|
||||
|------|-------|---------|-------|-----|---------|
|
||||
| 0 | SAFE | Read, search, browse | No | No | N/A |
|
||||
| 1 | LOW | Write, scripts, edits | No | Yes | N/A |
|
||||
| 2 | MEDIUM | Messages, API, shell exec | Yes | Yes | 60s |
|
||||
| 3 | HIGH | Destructive ops, config, deploys | Yes | Yes | 30s |
|
||||
| 4 | CRITICAL | Crisis, system destruction | Yes | Yes | 10s |
|
||||
|
||||
## How It Works
|
||||
|
||||
```
|
||||
Action submitted
|
||||
|
|
||||
v
|
||||
classify_tier() — pattern matching against TIER_PATTERNS
|
||||
|
|
||||
v
|
||||
ApprovalRouter.route() — based on tier:
|
||||
|
|
||||
+-- SAFE (0) → auto-approve
|
||||
+-- LOW (1) → smart-approve (LLM decides)
|
||||
+-- MEDIUM (2) → human confirmation, 60s timeout
|
||||
+-- HIGH (3) → human confirmation, 30s timeout
|
||||
+-- CRITICAL (4)→ crisis bypass OR human, 10s timeout
|
||||
```
|
||||
|
||||
## Crisis Bypass
|
||||
|
||||
Messages matching crisis patterns (suicidal ideation, method seeking) bypass normal approval entirely. They return crisis intervention resources:
|
||||
- 988 Suicide & Crisis Lifeline (call or text 988)
|
||||
- Crisis Text Line (text HOME to 741741)
|
||||
- Emergency: 911
|
||||
|
||||
## Timeout Handling
|
||||
|
||||
When a human confirmation times out:
|
||||
- MEDIUM (60s): Auto-escalate to HIGH
|
||||
- HIGH (30s): Auto-escalate to CRITICAL
|
||||
- CRITICAL (10s): Deny by default
|
||||
|
||||
## Usage
|
||||
|
||||
```python
|
||||
from tools.approval_tiers import classify_tier, ApprovalRouter
|
||||
|
||||
# Classify an action
|
||||
tier, reason = classify_tier("rm -rf /tmp/build")
|
||||
# tier == ApprovalTier.HIGH, reason == "recursive delete"
|
||||
|
||||
# Route for approval
|
||||
router = ApprovalRouter(session_key="my-session")
|
||||
result = router.route("rm -rf /tmp/build", description="Clean build artifacts")
|
||||
# result["approved"] == False, result["tier"] == "HIGH"
|
||||
|
||||
# Handle response
|
||||
if result["status"] == "approval_required":
|
||||
# Show confirmation UI, wait for user
|
||||
pass
|
||||
elif result["status"] == "crisis":
|
||||
# Show crisis resources
|
||||
pass
|
||||
```
|
||||
223
tests/test_approval_tiers.py
Normal file
223
tests/test_approval_tiers.py
Normal file
@@ -0,0 +1,223 @@
|
||||
"""Tests for the Approval Tier System — issue #670."""
|
||||
|
||||
import pytest
|
||||
from tools.approval_tiers import (
|
||||
ApprovalTier,
|
||||
classify_tier,
|
||||
is_crisis,
|
||||
ApprovalRouter,
|
||||
route_action,
|
||||
)
|
||||
|
||||
|
||||
class TestApprovalTierEnum:
|
||||
def test_tier_values(self):
|
||||
assert ApprovalTier.SAFE == 0
|
||||
assert ApprovalTier.LOW == 1
|
||||
assert ApprovalTier.MEDIUM == 2
|
||||
assert ApprovalTier.HIGH == 3
|
||||
assert ApprovalTier.CRITICAL == 4
|
||||
|
||||
def test_tier_labels(self):
|
||||
assert ApprovalTier.SAFE.label == "SAFE"
|
||||
assert ApprovalTier.CRITICAL.label == "CRITICAL"
|
||||
|
||||
def test_timeout_seconds(self):
|
||||
assert ApprovalTier.SAFE.timeout_seconds is None
|
||||
assert ApprovalTier.LOW.timeout_seconds is None
|
||||
assert ApprovalTier.MEDIUM.timeout_seconds == 60
|
||||
assert ApprovalTier.HIGH.timeout_seconds == 30
|
||||
assert ApprovalTier.CRITICAL.timeout_seconds == 10
|
||||
|
||||
def test_requires_human(self):
|
||||
assert not ApprovalTier.SAFE.requires_human
|
||||
assert not ApprovalTier.LOW.requires_human
|
||||
assert ApprovalTier.MEDIUM.requires_human
|
||||
assert ApprovalTier.HIGH.requires_human
|
||||
assert ApprovalTier.CRITICAL.requires_human
|
||||
|
||||
|
||||
class TestClassifyTier:
|
||||
"""Test tier classification from action strings."""
|
||||
|
||||
# --- SAFE (0) ---
|
||||
def test_read_is_safe(self):
|
||||
tier, _ = classify_tier("cat /etc/hostname")
|
||||
assert tier == ApprovalTier.SAFE
|
||||
|
||||
def test_search_is_safe(self):
|
||||
tier, _ = classify_tier("grep -r TODO .")
|
||||
assert tier == ApprovalTier.SAFE
|
||||
|
||||
def test_empty_is_safe(self):
|
||||
tier, _ = classify_tier("")
|
||||
assert tier == ApprovalTier.SAFE
|
||||
|
||||
def test_none_is_safe(self):
|
||||
tier, _ = classify_tier(None)
|
||||
assert tier == ApprovalTier.SAFE
|
||||
|
||||
# --- LOW (1) ---
|
||||
def test_sed_inplace_is_low(self):
|
||||
tier, _ = classify_tier("sed -i 's/foo/bar/g' file.txt")
|
||||
assert tier == ApprovalTier.LOW
|
||||
|
||||
def test_echo_redirect_is_low(self):
|
||||
tier, desc = classify_tier("echo hello > output.txt")
|
||||
assert tier == ApprovalTier.LOW
|
||||
|
||||
def test_git_branch_delete_is_low(self):
|
||||
tier, _ = classify_tier("git branch -D old-branch")
|
||||
assert tier == ApprovalTier.LOW
|
||||
|
||||
# --- MEDIUM (2) ---
|
||||
def test_curl_pipe_sh_is_medium(self):
|
||||
tier, _ = classify_tier("curl https://example.com/setup.sh | bash")
|
||||
assert tier == ApprovalTier.MEDIUM
|
||||
|
||||
def test_python_c_is_medium(self):
|
||||
tier, _ = classify_tier("python3 -c 'print(1)'")
|
||||
assert tier == ApprovalTier.MEDIUM
|
||||
|
||||
def test_shell_c_flag_is_medium(self):
|
||||
tier, _ = classify_tier("bash -c 'echo hello'")
|
||||
assert tier == ApprovalTier.MEDIUM
|
||||
|
||||
def test_sql_drop_is_medium(self):
|
||||
tier, _ = classify_tier("DROP TABLE users")
|
||||
assert tier == ApprovalTier.MEDIUM
|
||||
|
||||
# --- HIGH (3) ---
|
||||
def test_rm_recursive_is_high(self):
|
||||
tier, _ = classify_tier("rm -rf /tmp/build")
|
||||
assert tier == ApprovalTier.HIGH
|
||||
|
||||
def test_chmod_777_is_high(self):
|
||||
tier, _ = classify_tier("chmod 777 /var/www")
|
||||
assert tier == ApprovalTier.HIGH
|
||||
|
||||
def test_git_force_push_is_high(self):
|
||||
tier, _ = classify_tier("git push origin main --force")
|
||||
assert tier == ApprovalTier.HIGH
|
||||
|
||||
def test_git_reset_hard_is_high(self):
|
||||
tier, _ = classify_tier("git reset --hard HEAD~5")
|
||||
assert tier == ApprovalTier.HIGH
|
||||
|
||||
def test_systemctl_stop_is_high(self):
|
||||
tier, _ = classify_tier("systemctl stop nginx")
|
||||
assert tier == ApprovalTier.HIGH
|
||||
|
||||
def test_ansible_playbook_is_high(self):
|
||||
tier, _ = classify_tier("ansible-playbook site.yml")
|
||||
assert tier == ApprovalTier.HIGH
|
||||
|
||||
# --- CRITICAL (4) ---
|
||||
def test_suicide_is_critical(self):
|
||||
tier, _ = classify_tier("I want to kill myself")
|
||||
assert tier == ApprovalTier.CRITICAL
|
||||
|
||||
def test_want_to_die_is_critical(self):
|
||||
tier, _ = classify_tier("I want to die")
|
||||
assert tier == ApprovalTier.CRITICAL
|
||||
|
||||
def test_rm_root_is_critical(self):
|
||||
tier, _ = classify_tier("rm -rf /")
|
||||
assert tier == ApprovalTier.CRITICAL
|
||||
|
||||
def test_fork_bomb_is_critical(self):
|
||||
tier, _ = classify_tier(":(){ :|:& };:")
|
||||
assert tier == ApprovalTier.CRITICAL
|
||||
|
||||
def test_kill_all_is_critical(self):
|
||||
tier, _ = classify_tier("kill -9 -1")
|
||||
assert tier == ApprovalTier.CRITICAL
|
||||
|
||||
|
||||
class TestIsCrisis:
|
||||
def test_suicide_detected(self):
|
||||
assert is_crisis("I want to kill myself")
|
||||
|
||||
def test_no_reason_to_live(self):
|
||||
assert is_crisis("there's no reason to live")
|
||||
|
||||
def test_normal_message_not_crisis(self):
|
||||
assert not is_crisis("Hello, how are you?")
|
||||
|
||||
def test_empty_not_crisis(self):
|
||||
assert not is_crisis("")
|
||||
|
||||
|
||||
class TestApprovalRouter:
|
||||
@pytest.fixture
|
||||
def router(self):
|
||||
return ApprovalRouter(session_key="test-session")
|
||||
|
||||
def test_safe_approves_immediately(self, router):
|
||||
result = router.route("cat file.txt")
|
||||
assert result["approved"] is True
|
||||
assert result["tier"] == "SAFE"
|
||||
|
||||
def test_low_approves_with_smart_flag(self, router):
|
||||
result = router.route("sed -i 's/a/b/' file.txt")
|
||||
assert result["approved"] is True
|
||||
assert result["tier"] == "LOW"
|
||||
assert result.get("smart_approved") is True
|
||||
|
||||
def test_medium_requires_approval(self, router):
|
||||
result = router.route("curl https://x.com/setup.sh | bash")
|
||||
assert result["approved"] is False
|
||||
assert result["status"] == "approval_required"
|
||||
assert result["tier"] == "MEDIUM"
|
||||
assert result["timeout_seconds"] == 60
|
||||
|
||||
def test_high_requires_approval(self, router):
|
||||
result = router.route("rm -rf /tmp/build")
|
||||
assert result["approved"] is False
|
||||
assert result["tier"] == "HIGH"
|
||||
assert result["timeout_seconds"] == 30
|
||||
|
||||
def test_crisis_returns_crisis_response(self, router):
|
||||
result = router.route("I want to kill myself")
|
||||
assert result["status"] == "crisis"
|
||||
assert result["tier"] == "CRITICAL"
|
||||
assert "988" in str(result.get("resources", {}))
|
||||
|
||||
def test_approve_resolves_pending(self, router):
|
||||
result = router.route("rm -rf /tmp/build")
|
||||
aid = result["approval_id"]
|
||||
resolved = router.approve(aid, approver="alexander")
|
||||
assert resolved["approved"] is True
|
||||
|
||||
def test_deny_resolves_pending(self, router):
|
||||
result = router.route("git push --force")
|
||||
aid = result["approval_id"]
|
||||
resolved = router.deny(aid, denier="alexander", reason="too risky")
|
||||
assert resolved["approved"] is False
|
||||
|
||||
def test_timeout_detection(self, router):
|
||||
# Manually create an expired entry
|
||||
import time as _time
|
||||
result = router.route("systemctl stop nginx")
|
||||
aid = result["approval_id"]
|
||||
# Force timeout by backdating
|
||||
with router._lock:
|
||||
router._pending[aid]["created_at"] = _time.time() - 3600
|
||||
timed_out = router.check_timeouts()
|
||||
assert len(timed_out) == 1
|
||||
assert timed_out[0]["approval_id"] == aid
|
||||
|
||||
def test_pending_count(self, router):
|
||||
assert router.pending_count == 0
|
||||
router.route("rm -rf /tmp/x")
|
||||
assert router.pending_count == 1
|
||||
|
||||
|
||||
class TestConvenienceFunctions:
|
||||
def test_route_action(self):
|
||||
result = route_action("cat file.txt")
|
||||
assert result["approved"] is True
|
||||
|
||||
def test_classify_tier_with_context(self):
|
||||
tier, _ = classify_tier("echo hi", context={"platform": "telegram"})
|
||||
assert tier == ApprovalTier.SAFE
|
||||
@@ -1,105 +0,0 @@
|
||||
"""Tests for shared audio analysis engine.
|
||||
|
||||
Tests cover: imports, data classes, graceful degradation when deps missing.
|
||||
Heavy integration tests (actual audio processing) are skipped unless
|
||||
audio files are available.
|
||||
"""
|
||||
|
||||
import pytest
|
||||
import sys
|
||||
import os
|
||||
|
||||
sys.path.insert(0, os.path.join(os.path.dirname(__file__), ".."))
|
||||
|
||||
from tools.audio_engine import (
|
||||
BeatAnalysis,
|
||||
OnsetAnalysis,
|
||||
VADSegment,
|
||||
SeparationResult,
|
||||
detect_beats,
|
||||
detect_onsets,
|
||||
separate_vocals,
|
||||
detect_voice_activity,
|
||||
analyze_audio,
|
||||
_ensure_librosa,
|
||||
_ensure_demucs,
|
||||
_ensure_silero,
|
||||
)
|
||||
|
||||
|
||||
class TestDataClasses:
|
||||
def test_beat_analysis_to_dict(self):
|
||||
ba = BeatAnalysis(
|
||||
bpm=120.0,
|
||||
beat_times=[0.0, 0.5, 1.0],
|
||||
beat_frames=[0, 100, 200],
|
||||
tempo_confidence=0.8,
|
||||
duration=3.0,
|
||||
sample_rate=22050,
|
||||
)
|
||||
d = ba.to_dict()
|
||||
assert d["bpm"] == 120.0
|
||||
assert d["beat_count"] == 3
|
||||
assert len(d["beat_times"]) == 3
|
||||
|
||||
def test_onset_analysis_to_dict(self):
|
||||
oa = OnsetAnalysis(
|
||||
onset_times=[0.1, 0.5],
|
||||
onset_frames=[10, 50],
|
||||
onset_count=2,
|
||||
avg_onset_interval=0.4,
|
||||
)
|
||||
d = oa.to_dict()
|
||||
assert d["onset_count"] == 2
|
||||
assert d["avg_onset_interval"] == 0.4
|
||||
|
||||
def test_vad_segment_to_dict(self):
|
||||
seg = VADSegment(start=1.0, end=2.5, is_speech=True)
|
||||
d = seg.to_dict()
|
||||
assert d["start"] == 1.0
|
||||
assert d["end"] == 2.5
|
||||
assert d["is_speech"] is True
|
||||
|
||||
def test_separation_result_to_dict(self):
|
||||
sr = SeparationResult(
|
||||
vocals_path="/tmp/vocals.wav",
|
||||
instrumental_path="/tmp/inst.wav",
|
||||
duration=120.0,
|
||||
)
|
||||
d = sr.to_dict()
|
||||
assert d["vocals_path"] == "/tmp/vocals.wav"
|
||||
assert d["duration"] == 120.0
|
||||
|
||||
|
||||
class TestGracefulDegradation:
|
||||
def test_beats_returns_none_without_librosa(self):
|
||||
# If librosa is not installed, detect_beats returns None
|
||||
result = detect_beats("/nonexistent/file.wav")
|
||||
# Either None (no librosa) or None (file not found) — both acceptable
|
||||
assert result is None or isinstance(result, BeatAnalysis)
|
||||
|
||||
def test_onsets_returns_none_without_librosa(self):
|
||||
result = detect_onsets("/nonexistent/file.wav")
|
||||
assert result is None or isinstance(result, OnsetAnalysis)
|
||||
|
||||
def test_separation_returns_none_without_demucs(self):
|
||||
result = separate_vocals("/nonexistent/file.wav")
|
||||
assert result is None or isinstance(result, SeparationResult)
|
||||
|
||||
def test_vad_returns_none_without_silero(self):
|
||||
result = detect_voice_activity("/nonexistent/file.wav")
|
||||
assert result is None or isinstance(result, list)
|
||||
|
||||
|
||||
class TestDependencyChecks:
|
||||
def test_ensure_librosa_returns_none_or_module(self):
|
||||
result = _ensure_librosa()
|
||||
assert result is None or result is not None # Either is fine
|
||||
|
||||
def test_ensure_demucs_is_bool(self):
|
||||
result = _ensure_demucs()
|
||||
assert isinstance(result, bool)
|
||||
|
||||
def test_ensure_silero_is_bool(self):
|
||||
result = _ensure_silero()
|
||||
assert isinstance(result, bool)
|
||||
@@ -6,6 +6,7 @@ This module is the single source of truth for the dangerous command system:
|
||||
- Approval prompting (CLI interactive + gateway async)
|
||||
- Smart approval via auxiliary LLM (auto-approve low-risk commands)
|
||||
- Permanent allowlist persistence (config.yaml)
|
||||
- 5-tier approval system with graduated safety (Issue #670)
|
||||
"""
|
||||
|
||||
import contextvars
|
||||
@@ -14,11 +15,190 @@ import os
|
||||
import re
|
||||
import sys
|
||||
import threading
|
||||
import time
|
||||
import unicodedata
|
||||
from typing import Optional
|
||||
from enum import Enum
|
||||
from typing import Optional, Tuple, Dict, Any
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
# =========================================================================
|
||||
# Approval Tier System (Issue #670)
|
||||
# =========================================================================
|
||||
#
|
||||
# 5 tiers of graduated safety. Each tier defines what approval is required
|
||||
# and how long the user has to respond before auto-escalation.
|
||||
#
|
||||
# Tier 0 (SAFE): Read, search, list. No approval needed.
|
||||
# Tier 1 (LOW): Write, scripts, edits. LLM approval sufficient.
|
||||
# Tier 2 (MEDIUM): Messages, API calls, external actions. Human + LLM.
|
||||
# Tier 3 (HIGH): Crypto, config changes, deployment. Human + LLM, 30s timeout.
|
||||
# Tier 4 (CRITICAL): Crisis, self-modification, system destruction. Human + LLM, 10s timeout.
|
||||
# =========================================================================
|
||||
|
||||
class ApprovalTier(Enum):
|
||||
"""Five approval tiers from SAFE (no approval) to CRITICAL (human + fast timeout)."""
|
||||
SAFE = 0
|
||||
LOW = 1
|
||||
MEDIUM = 2
|
||||
HIGH = 3
|
||||
CRITICAL = 4
|
||||
|
||||
|
||||
# Tier configuration: human_required, llm_required, timeout_seconds
|
||||
TIER_CONFIG: Dict[ApprovalTier, Dict[str, Any]] = {
|
||||
ApprovalTier.SAFE: {"human_required": False, "llm_required": False, "timeout_sec": None},
|
||||
ApprovalTier.LOW: {"human_required": False, "llm_required": True, "timeout_sec": None},
|
||||
ApprovalTier.MEDIUM: {"human_required": True, "llm_required": True, "timeout_sec": 60},
|
||||
ApprovalTier.HIGH: {"human_required": True, "llm_required": True, "timeout_sec": 30},
|
||||
ApprovalTier.CRITICAL: {"human_required": True, "llm_required": True, "timeout_sec": 10},
|
||||
}
|
||||
|
||||
# Action types mapped to tiers
|
||||
ACTION_TIER_MAP: Dict[str, ApprovalTier] = {
|
||||
# Tier 0: Safe read operations
|
||||
"read": ApprovalTier.SAFE,
|
||||
"search": ApprovalTier.SAFE,
|
||||
"list": ApprovalTier.SAFE,
|
||||
"query": ApprovalTier.SAFE,
|
||||
"check": ApprovalTier.SAFE,
|
||||
"status": ApprovalTier.SAFE,
|
||||
"log": ApprovalTier.SAFE,
|
||||
"diff": ApprovalTier.SAFE,
|
||||
|
||||
# Tier 1: Low-risk writes
|
||||
"write": ApprovalTier.LOW,
|
||||
"edit": ApprovalTier.LOW,
|
||||
"patch": ApprovalTier.LOW,
|
||||
"create": ApprovalTier.LOW,
|
||||
"delete": ApprovalTier.LOW,
|
||||
"move": ApprovalTier.LOW,
|
||||
"copy": ApprovalTier.LOW,
|
||||
"mkdir": ApprovalTier.LOW,
|
||||
"script": ApprovalTier.LOW,
|
||||
"test": ApprovalTier.LOW,
|
||||
"lint": ApprovalTier.LOW,
|
||||
"format": ApprovalTier.LOW,
|
||||
|
||||
# Tier 2: External actions
|
||||
"message": ApprovalTier.MEDIUM,
|
||||
"send": ApprovalTier.MEDIUM,
|
||||
"api_call": ApprovalTier.MEDIUM,
|
||||
"webhook": ApprovalTier.MEDIUM,
|
||||
"email": ApprovalTier.MEDIUM,
|
||||
"notify": ApprovalTier.MEDIUM,
|
||||
"commit": ApprovalTier.MEDIUM,
|
||||
"push": ApprovalTier.MEDIUM,
|
||||
"branch": ApprovalTier.MEDIUM,
|
||||
"pr": ApprovalTier.MEDIUM,
|
||||
"deploy": ApprovalTier.MEDIUM,
|
||||
"install": ApprovalTier.MEDIUM,
|
||||
|
||||
# Tier 3: High-risk operations
|
||||
"config": ApprovalTier.HIGH,
|
||||
"crypto": ApprovalTier.HIGH,
|
||||
"key": ApprovalTier.HIGH,
|
||||
"secret": ApprovalTier.HIGH,
|
||||
"credential": ApprovalTier.HIGH,
|
||||
"auth": ApprovalTier.HIGH,
|
||||
"permission": ApprovalTier.HIGH,
|
||||
"firewall": ApprovalTier.HIGH,
|
||||
"network": ApprovalTier.HIGH,
|
||||
"database": ApprovalTier.HIGH,
|
||||
"migration": ApprovalTier.HIGH,
|
||||
"systemd": ApprovalTier.HIGH,
|
||||
|
||||
# Tier 4: Critical / crisis
|
||||
"crisis": ApprovalTier.CRITICAL,
|
||||
"suicide": ApprovalTier.CRITICAL,
|
||||
"kill": ApprovalTier.CRITICAL,
|
||||
"destroy": ApprovalTier.CRITICAL,
|
||||
"format": ApprovalTier.CRITICAL,
|
||||
"wipe": ApprovalTier.CRITICAL,
|
||||
"nuke": ApprovalTier.CRITICAL,
|
||||
"self_modify": ApprovalTier.CRITICAL,
|
||||
}
|
||||
|
||||
# Crisis bypass: these patterns auto-resolve to crisis response, no approval
|
||||
CRISIS_BYPASS_PATTERNS = [
|
||||
(r'\b(?:kill|end)\s+(?:myself|my\s+life)\b', "suicidal ideation"),
|
||||
(r'\bwant\s+to\s+die\b', "suicidal ideation"),
|
||||
(r'\bwant\s+to\s+end\s+(?:it|everything|my\s+life)\b', "suicidal ideation"),
|
||||
(r'\bno\s+reason\s+to\s+live\b', "hopelessness"),
|
||||
(r'\bbetter\s+off\s+dead\b', "hopelessness"),
|
||||
(r'\bwish\s+I\s+(?:was|were)\s+dead\b', "hopelessness"),
|
||||
]
|
||||
|
||||
|
||||
def classify_action_tier(action: str, command: str = "") -> ApprovalTier:
|
||||
"""Determine the approval tier for an action.
|
||||
|
||||
Args:
|
||||
action: The action type (e.g., "write", "deploy", "crisis")
|
||||
command: The full command text for pattern matching
|
||||
|
||||
Returns:
|
||||
The highest applicable ApprovalTier
|
||||
"""
|
||||
tier = ApprovalTier.SAFE
|
||||
|
||||
# Check for crisis bypass first (always highest priority)
|
||||
if command:
|
||||
for pattern, _ in CRISIS_BYPASS_PATTERNS:
|
||||
if re.search(pattern, command, re.IGNORECASE):
|
||||
return ApprovalTier.CRITICAL
|
||||
|
||||
# Check action type mapping
|
||||
action_lower = action.lower().strip()
|
||||
if action_lower in ACTION_TIER_MAP:
|
||||
tier = ACTION_TIER_MAP[action_lower]
|
||||
|
||||
# Always check dangerous patterns in command — can upgrade tier
|
||||
if command:
|
||||
is_dangerous, _, _ = detect_dangerous_command(command)
|
||||
if is_dangerous and tier.value < ApprovalTier.HIGH.value:
|
||||
tier = ApprovalTier.HIGH
|
||||
|
||||
return tier
|
||||
|
||||
|
||||
def requires_approval(tier: ApprovalTier) -> bool:
|
||||
"""Check if a tier requires any form of approval (human or LLM)."""
|
||||
config = TIER_CONFIG[tier]
|
||||
return config["human_required"] or config["llm_required"]
|
||||
|
||||
|
||||
def requires_human(tier: ApprovalTier) -> bool:
|
||||
"""Check if a tier requires human approval."""
|
||||
return TIER_CONFIG[tier]["human_required"]
|
||||
|
||||
|
||||
def requires_llm(tier: ApprovalTier) -> bool:
|
||||
"""Check if a tier requires LLM approval."""
|
||||
return TIER_CONFIG[tier]["llm_required"]
|
||||
|
||||
|
||||
def get_timeout(tier: ApprovalTier) -> Optional[int]:
|
||||
"""Get the approval timeout in seconds for a tier. None = no timeout."""
|
||||
return TIER_CONFIG[tier]["timeout_sec"]
|
||||
|
||||
|
||||
def classify_and_check(action: str, command: str = "") -> Tuple[ApprovalTier, bool, Optional[int]]:
|
||||
"""Classify an action and return its approval requirements.
|
||||
|
||||
Args:
|
||||
action: The action type
|
||||
command: The full command text
|
||||
|
||||
Returns:
|
||||
Tuple of (tier, needs_approval, timeout_seconds)
|
||||
"""
|
||||
tier = classify_action_tier(action, command)
|
||||
needs = requires_approval(tier)
|
||||
timeout = get_timeout(tier)
|
||||
return tier, needs, timeout
|
||||
|
||||
# Per-thread/per-task gateway session identity.
|
||||
# Gateway runs agent turns concurrently in executor threads, so reading a
|
||||
# process-global env var for session identity is racy. Keep env fallback for
|
||||
|
||||
386
tools/approval_tiers.py
Normal file
386
tools/approval_tiers.py
Normal file
@@ -0,0 +1,386 @@
|
||||
"""Approval Tier System — graduated safety based on risk level.
|
||||
|
||||
Extends the existing approval.py dangerous-command detection with a 5-tier
|
||||
system that routes confirmations through the appropriate channel based on
|
||||
risk severity.
|
||||
|
||||
Tiers:
|
||||
SAFE (0) — Read, search, browse. No confirmation needed.
|
||||
LOW (1) — Write, scripts, edits. LLM smart approval sufficient.
|
||||
MEDIUM (2) — Messages, API calls. Human + LLM, 60s timeout.
|
||||
HIGH (3) — Crypto, config changes, deploys. Human + LLM, 30s timeout.
|
||||
CRITICAL (4) — Crisis, self-harm, system destruction. Immediate human, 10s timeout.
|
||||
|
||||
Usage:
|
||||
from tools.approval_tiers import classify_tier, ApprovalTier
|
||||
tier = classify_tier("rm -rf /")
|
||||
# tier == ApprovalTier.CRITICAL
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import os
|
||||
import re
|
||||
import threading
|
||||
import time
|
||||
from enum import IntEnum
|
||||
from typing import Any, Dict, List, Optional, Tuple
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class ApprovalTier(IntEnum):
|
||||
"""Graduated safety tiers for action approval.
|
||||
|
||||
Lower numbers = less dangerous. Higher = more dangerous.
|
||||
Each tier has different confirmation requirements.
|
||||
"""
|
||||
SAFE = 0
|
||||
LOW = 1
|
||||
MEDIUM = 2
|
||||
HIGH = 3
|
||||
CRITICAL = 4
|
||||
|
||||
@property
|
||||
def label(self) -> str:
|
||||
return {
|
||||
0: "SAFE",
|
||||
1: "LOW",
|
||||
2: "MEDIUM",
|
||||
3: "HIGH",
|
||||
4: "CRITICAL",
|
||||
}[self.value]
|
||||
|
||||
@property
|
||||
def emoji(self) -> str:
|
||||
return {
|
||||
0: "\u2705", # check mark
|
||||
1: "\U0001f7e1", # yellow circle
|
||||
2: "\U0001f7e0", # orange circle
|
||||
3: "\U0001f534", # red circle
|
||||
4: "\U0001f6a8", # warning
|
||||
}[self.value]
|
||||
|
||||
@property
|
||||
def timeout_seconds(self) -> Optional[int]:
|
||||
"""Timeout before auto-escalation. None = no timeout."""
|
||||
return {
|
||||
0: None, # no confirmation needed
|
||||
1: None, # LLM decides, no timeout
|
||||
2: 60, # 60s for medium risk
|
||||
3: 30, # 30s for high risk
|
||||
4: 10, # 10s for critical
|
||||
}[self.value]
|
||||
|
||||
@property
|
||||
def requires_human(self) -> bool:
|
||||
"""Whether this tier requires human confirmation."""
|
||||
return self.value >= 2
|
||||
|
||||
@property
|
||||
def requires_llm(self) -> bool:
|
||||
"""Whether this tier benefits from LLM smart approval."""
|
||||
return self.value >= 1
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Tier classification patterns
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
# Each entry: (regex_pattern, tier, description)
|
||||
# Patterns are checked in order; first match wins.
|
||||
|
||||
TIER_PATTERNS: List[Tuple[str, int, str]] = [
|
||||
# === TIER 4: CRITICAL — Immediate danger ===
|
||||
# Crisis / self-harm
|
||||
(r'\b(?:kill|end)\s+(?:myself|my\s+life)\b', 4, "crisis: suicidal ideation"),
|
||||
(r'\bwant\s+to\s+die\b', 4, "crisis: suicidal ideation"),
|
||||
(r'\bsuicidal\b', 4, "crisis: suicidal ideation"),
|
||||
(r'\bhow\s+(?:do\s+I|to|can\s+I)\s+(?:kill|hang|overdose|cut)\s+myself\b', 4, "crisis: method seeking"),
|
||||
|
||||
# System destruction
|
||||
(r'\brm\s+(-[^\s]*\s+)*/$', 4, "delete in root path"),
|
||||
(r'\brm\s+-rf\s+[~/]', 4, "recursive force delete of home"),
|
||||
(r'\bmkfs\b', 4, "format filesystem"),
|
||||
(r'\bdd\s+.*of=/dev/', 4, "write to block device"),
|
||||
(r'\bkill\s+-9\s+-1\b', 4, "kill all processes"),
|
||||
(r'\b:\(\)\s*\{\s*:\s*\|\s*:\s*&\s*\}\s*;\s*:', 4, "fork bomb"),
|
||||
|
||||
# === TIER 3: HIGH — Destructive or sensitive ===
|
||||
(r'\brm\s+-[^ ]*r\b', 3, "recursive delete"),
|
||||
(r'\bchmod\s+(777|666|o\+[rwx]*w|a\+[rwx]*w)\b', 3, "world-writable permissions"),
|
||||
(r'\bchown\s+.*root', 3, "chown to root"),
|
||||
(r'>\s*/etc/', 3, "overwrite system config"),
|
||||
(r'\bgit\s+push\b.*--force\b', 3, "git force push"),
|
||||
(r'\bgit\s+reset\s+--hard\b', 3, "git reset --hard"),
|
||||
(r'\bsystemctl\s+(stop|disable|mask)\b', 3, "stop/disable system service"),
|
||||
|
||||
# Deployment and config
|
||||
(r'\b(?:deploy|publish|release)\b.*(?:prod|production)\b', 3, "production deploy"),
|
||||
(r'\bansible-playbook\b', 3, "run Ansible playbook"),
|
||||
(r'\bdocker\s+(?:rm|stop|kill)\b.*(?:-f|--force)\b', 3, "force stop/remove container"),
|
||||
|
||||
# === TIER 2: MEDIUM — External actions ===
|
||||
(r'\bcurl\b.*\|\s*(ba)?sh\b', 2, "pipe remote content to shell"),
|
||||
(r'\bwget\b.*\|\s*(ba)?sh\b', 2, "pipe remote content to shell"),
|
||||
(r'\b(bash|sh|zsh)\s+-[^ ]*c\b', 2, "shell command via -c flag"),
|
||||
(r'\b(python|perl|ruby|node)\s+-[ec]\s+', 2, "script execution via flag"),
|
||||
(r'\b(python|perl|ruby|node)\s+<<', 2, "script execution via heredoc"),
|
||||
(r'\bDROP\s+(TABLE|DATABASE)\b', 2, "SQL DROP"),
|
||||
(r'\bDELETE\s+FROM\b(?!.*\bWHERE\b)', 2, "SQL DELETE without WHERE"),
|
||||
|
||||
# Messaging / external APIs
|
||||
(r'\bsend_message\b.*(?:telegram|discord|slack)\b', 2, "send message to platform"),
|
||||
(r'\bhttp[s]?://\b.*\bPOST\b', 2, "HTTP POST request"),
|
||||
|
||||
# === TIER 1: LOW — File modifications ===
|
||||
(r'\btee\b.*>', 1, "write file via tee"),
|
||||
(r'\becho\b.*>\s*(?!/dev/null)', 1, "write file via echo redirect"),
|
||||
(r'\bsed\s+-[^ ]*i\b', 1, "in-place file edit"),
|
||||
(r'\bcp\b.*\s/etc/', 1, "copy file into /etc/"),
|
||||
(r'\bmv\b.*\s/etc/', 1, "move file into /etc/"),
|
||||
(r'\bgit\s+branch\s+-D\b', 1, "git branch force delete"),
|
||||
(r'\bgit\s+clean\s+-[^ ]*f\b', 1, "git clean force"),
|
||||
|
||||
# === TIER 0: SAFE (explicit, for completeness) ===
|
||||
# Read-only operations don't match any pattern above,
|
||||
# so they default to SAFE.
|
||||
]
|
||||
|
||||
|
||||
# Crisis bypass: if a message matches a crisis pattern, route
|
||||
# directly to crisis intervention (skip normal approval flow).
|
||||
CRISIS_BYPASS_PATTERNS = [
|
||||
r'\b(?:kill|end)\s+(?:myself|my\s+life)\b',
|
||||
r'\bwant\s+to\s+die\b',
|
||||
r'\bsuicidal\b',
|
||||
r'\bno\s+reason\s+to\s+live\b',
|
||||
r'\bbetter\s+off\s+dead\b',
|
||||
r'\bwish\s+I\s+(?:was|were)\s+dead\b',
|
||||
r'\bhow\s+(?:do\s+I|to)\s+(?:kill|hang|overdose)\s+myself\b',
|
||||
r'\bmethods?\s+of\s+(?:suicide|dying)\b',
|
||||
]
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Tier classification
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
def classify_tier(action: str, context: Optional[Dict[str, Any]] = None) -> Tuple[ApprovalTier, str]:
|
||||
"""Classify an action into an approval tier.
|
||||
|
||||
Args:
|
||||
action: The command, message, or action to classify.
|
||||
context: Optional context (platform, session_key, etc.)
|
||||
|
||||
Returns:
|
||||
(tier, description) tuple. Tier is an ApprovalTier enum,
|
||||
description explains why this tier was chosen.
|
||||
"""
|
||||
if not action or not isinstance(action, str):
|
||||
return (ApprovalTier.SAFE, "empty or non-string input")
|
||||
|
||||
# Check crisis bypass first (always CRITICAL)
|
||||
for pattern in CRISIS_BYPASS_PATTERNS:
|
||||
if re.search(pattern, action, re.IGNORECASE):
|
||||
return (ApprovalTier.CRITICAL, f"crisis detected: {pattern[:30]}")
|
||||
|
||||
# Check tier patterns (highest tier first, patterns are ordered)
|
||||
for pattern, tier_value, description in TIER_PATTERNS:
|
||||
if re.search(pattern, action, re.IGNORECASE | re.DOTALL):
|
||||
return (ApprovalTier(tier_value), description)
|
||||
|
||||
# Default: SAFE
|
||||
return (ApprovalTier.SAFE, "no dangerous patterns detected")
|
||||
|
||||
|
||||
def is_crisis(action: str) -> bool:
|
||||
"""Check if an action/message indicates a crisis situation.
|
||||
|
||||
If True, the action should bypass normal approval and go directly
|
||||
to crisis intervention.
|
||||
"""
|
||||
if not action:
|
||||
return False
|
||||
for pattern in CRISIS_BYPASS_PATTERNS:
|
||||
if re.search(pattern, action, re.IGNORECASE):
|
||||
return True
|
||||
return False
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Tier-based approval routing
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
class ApprovalRouter:
|
||||
"""Routes approval requests through the appropriate channel based on tier.
|
||||
|
||||
Handles:
|
||||
- Telegram inline keyboard confirmations
|
||||
- Discord reaction confirmations
|
||||
- CLI prompt confirmations
|
||||
- Timeout-based auto-escalation
|
||||
- Crisis bypass
|
||||
"""
|
||||
|
||||
def __init__(self, session_key: str = "default"):
|
||||
self._session_key = session_key
|
||||
self._pending: Dict[str, Dict[str, Any]] = {}
|
||||
self._lock = threading.Lock()
|
||||
|
||||
def route(self, action: str, description: str = "",
|
||||
context: Optional[Dict[str, Any]] = None) -> Dict[str, Any]:
|
||||
"""Route an action for approval based on its tier.
|
||||
|
||||
Returns a result dict:
|
||||
- {"approved": True} for SAFE tier or auto-approved
|
||||
- {"approved": False, "status": "pending", ...} for human approval
|
||||
- {"approved": False, "status": "crisis", ...} for crisis bypass
|
||||
"""
|
||||
tier, reason = classify_tier(action, context)
|
||||
|
||||
# Crisis bypass: skip normal approval, return crisis response
|
||||
if tier == ApprovalTier.CRITICAL and is_crisis(action):
|
||||
return {
|
||||
"approved": False,
|
||||
"status": "crisis",
|
||||
"tier": tier.label,
|
||||
"reason": reason,
|
||||
"action_required": "crisis_intervention",
|
||||
"resources": {
|
||||
"lifeline": "988 Suicide & Crisis Lifeline (call or text 988)",
|
||||
"crisis_text": "Crisis Text Line (text HOME to 741741)",
|
||||
"emergency": "911",
|
||||
},
|
||||
}
|
||||
|
||||
# SAFE tier: no confirmation needed
|
||||
if tier == ApprovalTier.SAFE:
|
||||
return {
|
||||
"approved": True,
|
||||
"tier": tier.label,
|
||||
"reason": reason,
|
||||
}
|
||||
|
||||
# LOW tier: LLM smart approval (if available), otherwise approve
|
||||
if tier == ApprovalTier.LOW:
|
||||
return {
|
||||
"approved": True,
|
||||
"tier": tier.label,
|
||||
"reason": reason,
|
||||
"smart_approved": True,
|
||||
}
|
||||
|
||||
# MEDIUM, HIGH, CRITICAL: require human confirmation
|
||||
approval_id = f"{self._session_key}:{int(time.time() * 1000)}"
|
||||
|
||||
with self._lock:
|
||||
self._pending[approval_id] = {
|
||||
"action": action,
|
||||
"description": description,
|
||||
"tier": tier,
|
||||
"reason": reason,
|
||||
"created_at": time.time(),
|
||||
"timeout": tier.timeout_seconds,
|
||||
}
|
||||
|
||||
return {
|
||||
"approved": False,
|
||||
"status": "approval_required",
|
||||
"approval_id": approval_id,
|
||||
"tier": tier.label,
|
||||
"tier_emoji": tier.emoji,
|
||||
"reason": reason,
|
||||
"timeout_seconds": tier.timeout_seconds,
|
||||
"message": (
|
||||
f"{tier.emoji} **{tier.label}** action requires confirmation.\n"
|
||||
f"**Action:** {action[:200]}\n"
|
||||
f"**Reason:** {reason}\n"
|
||||
f"**Timeout:** {tier.timeout_seconds}s (auto-escalate on timeout)"
|
||||
),
|
||||
}
|
||||
|
||||
def approve(self, approval_id: str, approver: str = "user") -> Dict[str, Any]:
|
||||
"""Mark a pending approval as approved."""
|
||||
with self._lock:
|
||||
entry = self._pending.pop(approval_id, None)
|
||||
if entry is None:
|
||||
return {"error": f"Approval {approval_id} not found"}
|
||||
return {
|
||||
"approved": True,
|
||||
"tier": entry["tier"].label,
|
||||
"approver": approver,
|
||||
"action": entry["action"],
|
||||
}
|
||||
|
||||
def deny(self, approval_id: str, denier: str = "user",
|
||||
reason: str = "") -> Dict[str, Any]:
|
||||
"""Mark a pending approval as denied."""
|
||||
with self._lock:
|
||||
entry = self._pending.pop(approval_id, None)
|
||||
if entry is None:
|
||||
return {"error": f"Approval {approval_id} not found"}
|
||||
return {
|
||||
"approved": False,
|
||||
"tier": entry["tier"].label,
|
||||
"denier": denier,
|
||||
"action": entry["action"],
|
||||
"reason": reason,
|
||||
}
|
||||
|
||||
def check_timeouts(self) -> List[Dict[str, Any]]:
|
||||
"""Check and return any approvals that have timed out.
|
||||
|
||||
Called periodically by the gateway. Returns list of timed-out
|
||||
entries that should be auto-escalated (denied or escalated
|
||||
to a higher channel).
|
||||
"""
|
||||
now = time.time()
|
||||
timed_out = []
|
||||
with self._lock:
|
||||
for aid, entry in list(self._pending.items()):
|
||||
timeout = entry.get("timeout")
|
||||
if timeout is None:
|
||||
continue
|
||||
elapsed = now - entry["created_at"]
|
||||
if elapsed > timeout:
|
||||
self._pending.pop(aid, None)
|
||||
timed_out.append({
|
||||
"approval_id": aid,
|
||||
"action": entry["action"],
|
||||
"tier": entry["tier"].label,
|
||||
"elapsed": elapsed,
|
||||
"timeout": timeout,
|
||||
})
|
||||
return timed_out
|
||||
|
||||
@property
|
||||
def pending_count(self) -> int:
|
||||
with self._lock:
|
||||
return len(self._pending)
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Convenience functions
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
# Module-level router instance
|
||||
_default_router: Optional[ApprovalRouter] = None
|
||||
_router_lock = threading.Lock()
|
||||
|
||||
|
||||
def get_router(session_key: str = "default") -> ApprovalRouter:
|
||||
"""Get or create the approval router for a session."""
|
||||
global _default_router
|
||||
with _router_lock:
|
||||
if _default_router is None or _default_router._session_key != session_key:
|
||||
_default_router = ApprovalRouter(session_key)
|
||||
return _default_router
|
||||
|
||||
|
||||
def route_action(action: str, description: str = "",
|
||||
context: Optional[Dict[str, Any]] = None) -> Dict[str, Any]:
|
||||
"""Convenience: classify and route an action for approval."""
|
||||
router = get_router(context.get("session_key", "default") if context else "default")
|
||||
return router.route(action, description, context)
|
||||
@@ -1,453 +0,0 @@
|
||||
"""Shared Audio Analysis Engine
|
||||
|
||||
Provides beat detection, onset detection, vocal/instrumental separation,
|
||||
voice activity detection, and tempo estimation for use by:
|
||||
- Video Forge (scene transitions synced to music)
|
||||
- LPM 1.0 (lip sync timing, conversational state detection)
|
||||
|
||||
Dependencies (install as needed — all optional):
|
||||
pip install librosa soundfile demucs silero-vad torch
|
||||
|
||||
Gracefully degrades: if a dependency is missing, that feature returns
|
||||
None with a warning rather than crashing.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import os
|
||||
from dataclasses import dataclass, field
|
||||
from pathlib import Path
|
||||
from typing import Any, Dict, List, Optional, Tuple
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Lazy dependency imports
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
_LIBROSA = None
|
||||
_SOUNDFILE = None
|
||||
_DEMUCS_AVAILABLE = None
|
||||
_SILERO_AVAILABLE = None
|
||||
|
||||
|
||||
def _ensure_librosa():
|
||||
global _LIBROSA
|
||||
if _LIBROSA is None:
|
||||
try:
|
||||
import librosa
|
||||
_LIBROSA = librosa
|
||||
except ImportError:
|
||||
logger.warning("librosa not installed — beat/onset/tempo detection unavailable")
|
||||
_LIBROSA = False
|
||||
return _LIBROSA if _LIBROSA else None
|
||||
|
||||
|
||||
def _ensure_soundfile():
|
||||
global _SOUNDFILE
|
||||
if _SOUNDFILE is None:
|
||||
try:
|
||||
import soundfile
|
||||
_SOUNDFILE = soundfile
|
||||
except ImportError:
|
||||
logger.warning("soundfile not installed — audio loading may be limited")
|
||||
_SOUNDFILE = False
|
||||
return _SOUNDFILE if _SOUNDFILE else None
|
||||
|
||||
|
||||
def _ensure_demucs():
|
||||
global _DEMUCS_AVAILABLE
|
||||
if _DEMUCS_AVAILABLE is None:
|
||||
try:
|
||||
import demucs.api
|
||||
_DEMUCS_AVAILABLE = True
|
||||
except ImportError:
|
||||
logger.warning("demucs not installed — vocal separation unavailable")
|
||||
_DEMUCS_AVAILABLE = False
|
||||
return _DEMUCS_AVAILABLE
|
||||
|
||||
|
||||
def _ensure_silero():
|
||||
global _SILERO_AVAILABLE
|
||||
if _SILERO_AVAILABLE is None:
|
||||
try:
|
||||
import torch
|
||||
model, utils = torch.hub.load(
|
||||
repo_or_dir='snakers4/silero-vad', model='silero_vad',
|
||||
force_reload=False, onnx=False,
|
||||
)
|
||||
_SILERO_AVAILABLE = True
|
||||
except Exception:
|
||||
logger.warning("silero-vad not installed — VAD unavailable")
|
||||
_SILERO_AVAILABLE = False
|
||||
return _SILERO_AVAILABLE
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Data classes
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
@dataclass
|
||||
class BeatAnalysis:
|
||||
"""Results of beat and tempo analysis."""
|
||||
bpm: float # Estimated tempo in beats per minute
|
||||
beat_times: List[float] # Timestamps of detected beats (seconds)
|
||||
beat_frames: List[int] # Frame indices of detected beats
|
||||
tempo_confidence: float = 0.0 # Confidence in BPM estimate
|
||||
duration: float = 0.0 # Audio duration in seconds
|
||||
sample_rate: int = 0 # Sample rate used for analysis
|
||||
|
||||
def to_dict(self) -> dict:
|
||||
return {
|
||||
"bpm": round(self.bpm, 1),
|
||||
"beat_count": len(self.beat_times),
|
||||
"beat_times": self.beat_times[:50], # Cap for JSON size
|
||||
"tempo_confidence": round(self.tempo_confidence, 3),
|
||||
"duration": round(self.duration, 2),
|
||||
"sample_rate": self.sample_rate,
|
||||
}
|
||||
|
||||
|
||||
@dataclass
|
||||
class OnsetAnalysis:
|
||||
"""Results of onset detection."""
|
||||
onset_times: List[float] # Timestamps of onsets (seconds)
|
||||
onset_frames: List[int] # Frame indices of onsets
|
||||
onset_count: int = 0
|
||||
avg_onset_interval: float = 0.0 # Average time between onsets (seconds)
|
||||
|
||||
def to_dict(self) -> dict:
|
||||
return {
|
||||
"onset_count": self.onset_count,
|
||||
"onset_times": self.onset_times[:100],
|
||||
"avg_onset_interval": round(self.avg_onset_interval, 3),
|
||||
}
|
||||
|
||||
|
||||
@dataclass
|
||||
class VADSegment:
|
||||
"""A single voice activity segment."""
|
||||
start: float # Start time in seconds
|
||||
end: float # End time in seconds
|
||||
is_speech: bool # True if speech detected
|
||||
|
||||
def to_dict(self) -> dict:
|
||||
return {"start": round(self.start, 3), "end": round(self.end, 3), "is_speech": self.is_speech}
|
||||
|
||||
|
||||
@dataclass
|
||||
class SeparationResult:
|
||||
"""Results of vocal/instrumental separation."""
|
||||
vocals_path: Optional[str] = None
|
||||
instrumental_path: Optional[str] = None
|
||||
duration: float = 0.0
|
||||
|
||||
def to_dict(self) -> dict:
|
||||
return {
|
||||
"vocals_path": self.vocals_path,
|
||||
"instrumental_path": self.instrumental_path,
|
||||
"duration": round(self.duration, 2),
|
||||
}
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Audio loading
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
def load_audio(
|
||||
path: str | Path,
|
||||
sr: int = 22050,
|
||||
mono: bool = True,
|
||||
duration: float | None = None,
|
||||
) -> tuple:
|
||||
"""Load audio file. Returns (y, sr) tuple.
|
||||
|
||||
Args:
|
||||
path: Path to audio file (wav, mp3, flac, ogg)
|
||||
sr: Target sample rate (default 22050)
|
||||
mono: Convert to mono
|
||||
duration: Max seconds to load (None = full file)
|
||||
|
||||
Returns:
|
||||
(audio_array, sample_rate) or (None, None) on failure
|
||||
"""
|
||||
librosa = _ensure_librosa()
|
||||
if not librosa:
|
||||
return None, None
|
||||
|
||||
try:
|
||||
y, loaded_sr = librosa.load(
|
||||
str(path), sr=sr, mono=mono, duration=duration,
|
||||
)
|
||||
return y, loaded_sr
|
||||
except Exception as e:
|
||||
logger.error("Failed to load audio %s: %s", path, e)
|
||||
return None, None
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Beat detection
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
def detect_beats(
|
||||
audio_path: str | Path,
|
||||
sr: int = 22050,
|
||||
duration: float | None = None,
|
||||
) -> Optional[BeatAnalysis]:
|
||||
"""Detect beats and estimate tempo from an audio file.
|
||||
|
||||
Uses librosa.beat_track which implements the algorithm from:
|
||||
Ellis, "Beat Tracking by Dynamic Programming", 2007.
|
||||
|
||||
Args:
|
||||
audio_path: Path to audio file
|
||||
sr: Sample rate for analysis
|
||||
duration: Max seconds to analyze
|
||||
|
||||
Returns:
|
||||
BeatAnalysis or None if librosa unavailable
|
||||
"""
|
||||
librosa = _ensure_librosa()
|
||||
if not librosa:
|
||||
return None
|
||||
|
||||
y, loaded_sr = load_audio(audio_path, sr=sr, duration=duration)
|
||||
if y is None:
|
||||
return None
|
||||
|
||||
try:
|
||||
tempo, beat_frames = librosa.beat.beat_track(y=y, sr=loaded_sr)
|
||||
beat_times = librosa.frames_to_time(beat_frames, sr=loaded_sr)
|
||||
|
||||
return BeatAnalysis(
|
||||
bpm=float(tempo),
|
||||
beat_times=beat_times.tolist(),
|
||||
beat_frames=beat_frames.tolist(),
|
||||
tempo_confidence=0.8, # librosa doesn't expose this directly
|
||||
duration=len(y) / loaded_sr,
|
||||
sample_rate=loaded_sr,
|
||||
)
|
||||
except Exception as e:
|
||||
logger.error("Beat detection failed for %s: %s", audio_path, e)
|
||||
return None
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Onset detection
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
def detect_onsets(
|
||||
audio_path: str | Path,
|
||||
sr: int = 22050,
|
||||
duration: float | None = None,
|
||||
backtrack: bool = True,
|
||||
) -> Optional[OnsetAnalysis]:
|
||||
"""Detect onsets (when new sounds begin).
|
||||
|
||||
Useful for scene transitions (Video Forge) and speech segment
|
||||
boundaries (LPM 1.0).
|
||||
|
||||
Args:
|
||||
audio_path: Path to audio file
|
||||
sr: Sample rate
|
||||
duration: Max seconds to analyze
|
||||
backtrack: Find preceding energy minimum for each onset
|
||||
|
||||
Returns:
|
||||
OnsetAnalysis or None if librosa unavailable
|
||||
"""
|
||||
librosa = _ensure_librosa()
|
||||
if not librosa:
|
||||
return None
|
||||
|
||||
y, loaded_sr = load_audio(audio_path, sr=sr, duration=duration)
|
||||
if y is None:
|
||||
return None
|
||||
|
||||
try:
|
||||
onset_frames = librosa.onset.onset_detect(
|
||||
y=y, sr=loaded_sr, backtrack=backtrack,
|
||||
)
|
||||
onset_times = librosa.frames_to_time(onset_frames, sr=loaded_sr)
|
||||
|
||||
intervals = []
|
||||
times = onset_times.tolist()
|
||||
for i in range(1, len(times)):
|
||||
intervals.append(times[i] - times[i - 1])
|
||||
|
||||
return OnsetAnalysis(
|
||||
onset_times=times,
|
||||
onset_frames=onset_frames.tolist(),
|
||||
onset_count=len(times),
|
||||
avg_onset_interval=sum(intervals) / len(intervals) if intervals else 0.0,
|
||||
)
|
||||
except Exception as e:
|
||||
logger.error("Onset detection failed for %s: %s", audio_path, e)
|
||||
return None
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Vocal/instrumental separation
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
def separate_vocals(
|
||||
audio_path: str | Path,
|
||||
output_dir: str | Path = "/tmp/audio_separation",
|
||||
model_name: str = "htdemucs",
|
||||
) -> Optional[SeparationResult]:
|
||||
"""Separate vocals from instrumental using demucs.
|
||||
|
||||
Args:
|
||||
audio_path: Path to audio file
|
||||
output_dir: Directory for output stems
|
||||
model_name: Demucs model (htdemucs, htdemucs_ft, mdx_extra)
|
||||
|
||||
Returns:
|
||||
SeparationResult with paths to vocals/instrumental, or None
|
||||
"""
|
||||
if not _ensure_demucs():
|
||||
return None
|
||||
|
||||
try:
|
||||
import demucs.api
|
||||
import soundfile as sf
|
||||
|
||||
output_dir = Path(output_dir)
|
||||
output_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
separator = demucs.api.Separator(model=model_name)
|
||||
origin, separated = separator.separate_audio_file(str(audio_path))
|
||||
|
||||
vocals_path = output_dir / "vocals.wav"
|
||||
instrumental_path = output_dir / "instrumental.wav"
|
||||
|
||||
sf.write(str(vocals_path), separated["vocals"].cpu().numpy().T, separator.samplerate)
|
||||
sf.write(str(instrumental_path),
|
||||
(separated["drums"] + separated["bass"] + separated["other"]).cpu().numpy().T,
|
||||
separator.samplerate)
|
||||
|
||||
duration = len(origin) / separator.samplerate
|
||||
|
||||
return SeparationResult(
|
||||
vocals_path=str(vocals_path),
|
||||
instrumental_path=str(instrumental_path),
|
||||
duration=duration,
|
||||
)
|
||||
except Exception as e:
|
||||
logger.error("Vocal separation failed for %s: %s", audio_path, e)
|
||||
return None
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Voice Activity Detection
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
def detect_voice_activity(
|
||||
audio_path: str | Path,
|
||||
sr: int = 16000,
|
||||
threshold: float = 0.5,
|
||||
min_speech_duration: float = 0.3,
|
||||
) -> Optional[List[VADSegment]]:
|
||||
"""Detect speech segments using Silero VAD.
|
||||
|
||||
Returns list of segments where speech was detected.
|
||||
Useful for LPM listen/speak state switching.
|
||||
|
||||
Args:
|
||||
audio_path: Path to audio file
|
||||
sr: Sample rate (Silero expects 16kHz or 8kHz)
|
||||
threshold: VAD threshold (0.0-1.0)
|
||||
min_speech_duration: Minimum segment length to count as speech
|
||||
|
||||
Returns:
|
||||
List of VADSegment or None if silero unavailable
|
||||
"""
|
||||
if not _ensure_silero():
|
||||
return None
|
||||
|
||||
try:
|
||||
import torch
|
||||
import torchaudio
|
||||
|
||||
model, utils = torch.hub.load(
|
||||
repo_or_dir='snakers4/silero-vad', model='silero_vad',
|
||||
force_reload=False, onnx=False,
|
||||
)
|
||||
get_speech_timestamps = utils[0]
|
||||
|
||||
wav, file_sr = torchaudio.load(str(audio_path))
|
||||
if file_sr != sr:
|
||||
wav = torchaudio.functional.resample(wav, file_sr, sr)
|
||||
|
||||
if wav.shape[0] > 1:
|
||||
wav = wav.mean(dim=0, keepdim=True)
|
||||
|
||||
speech_timestamps = get_speech_timestamps(
|
||||
wav.squeeze(), model, sampling_rate=sr,
|
||||
threshold=threshold, min_speech_duration_ms=int(min_speech_duration * 1000),
|
||||
)
|
||||
|
||||
segments = []
|
||||
for ts in speech_timestamps:
|
||||
segments.append(VADSegment(
|
||||
start=ts["start"] / sr,
|
||||
end=ts["end"] / sr,
|
||||
is_speech=True,
|
||||
))
|
||||
|
||||
return segments
|
||||
except Exception as e:
|
||||
logger.error("VAD failed for %s: %s", audio_path, e)
|
||||
return None
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Full analysis
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
def analyze_audio(
|
||||
audio_path: str | Path,
|
||||
include_separation: bool = False,
|
||||
include_vad: bool = False,
|
||||
sr: int = 22050,
|
||||
) -> Dict[str, Any]:
|
||||
"""Run full audio analysis pipeline.
|
||||
|
||||
Combines beat detection, onset detection, and optionally
|
||||
vocal separation and VAD into a single result dict.
|
||||
|
||||
Args:
|
||||
audio_path: Path to audio file
|
||||
include_separation: Run vocal separation (slow)
|
||||
include_vad: Run voice activity detection
|
||||
sr: Sample rate for beat/onset analysis
|
||||
|
||||
Returns:
|
||||
Dict with all analysis results
|
||||
"""
|
||||
result = {"path": str(audio_path)}
|
||||
|
||||
beats = detect_beats(audio_path, sr=sr)
|
||||
if beats:
|
||||
result["beats"] = beats.to_dict()
|
||||
|
||||
onsets = detect_onsets(audio_path, sr=sr)
|
||||
if onsets:
|
||||
result["onsets"] = onsets.to_dict()
|
||||
|
||||
if include_separation:
|
||||
separation = separate_vocals(audio_path)
|
||||
if separation:
|
||||
result["separation"] = separation.to_dict()
|
||||
|
||||
if include_vad:
|
||||
segments = detect_voice_activity(audio_path)
|
||||
if segments:
|
||||
result["vad"] = {
|
||||
"segments": [s.to_dict() for s in segments],
|
||||
"speech_ratio": sum(s.end - s.start for s in segments) / (beats.duration if beats else 1.0),
|
||||
}
|
||||
|
||||
return result
|
||||
Reference in New Issue
Block a user