test(#752): Add tests for error classification

Tests for retryable/permanent classification.
Refs #752

agent/rider.py

@@ -1,256 +0,0 @@
-"""RIDER — Reader-Guided Passage Reranking.
-
-Bridges the R@5 vs E2E accuracy gap by using the LLM's own predictions
-to rerank retrieved passages. Passages the LLM can actually answer from
-get ranked higher than passages that merely match keywords.
-
-Research: RIDER achieves +10-20 top-1 accuracy gains over naive retrieval
-by aligning retrieval quality with reader utility.
-
-Usage:
-    from agent.rider import RIDER
-    rider = RIDER()
-    reranked = rider.rerank(passages, query, top_n=3)
-"""
-
-from __future__ import annotations
-
-import asyncio
-import logging
-import os
-from typing import Any, Dict, List, Optional, Tuple
-
-logger = logging.getLogger(__name__)
-
-# Configuration
-RIDER_ENABLED = os.getenv("RIDER_ENABLED", "true").lower() not in ("false", "0", "no")
-RIDER_TOP_K = int(os.getenv("RIDER_TOP_K", "10"))  # passages to score
-RIDER_TOP_N = int(os.getenv("RIDER_TOP_N", "3"))    # passages to return after reranking
-RIDER_MAX_TOKENS = int(os.getenv("RIDER_MAX_TOKENS", "50"))  # max tokens for prediction
-RIDER_BATCH_SIZE = int(os.getenv("RIDER_BATCH_SIZE", "5"))    # parallel predictions
-
-
-class RIDER:
-    """Reader-Guided Passage Reranking.
-
-    Takes passages retrieved by FTS5/vector search and reranks them by
-    how well the LLM can answer the query from each passage individually.
-    """
-
-    def __init__(self, auxiliary_task: str = "rider"):
-        """Initialize RIDER.
-
-        Args:
-            auxiliary_task: Task name for auxiliary client resolution.
-        """
-        self._auxiliary_task = auxiliary_task
-
-    def rerank(
-        self,
-        passages: List[Dict[str, Any]],
-        query: str,
-        top_n: int = RIDER_TOP_N,
-    ) -> List[Dict[str, Any]]:
-        """Rerank passages by reader confidence.
-
-        Args:
-            passages: List of passage dicts. Must have 'content' or 'text' key.
-                May have 'session_id', 'snippet', 'rank', 'score', etc.
-            query: The user's search query.
-            top_n: Number of passages to return after reranking.
-
-        Returns:
-            Reranked passages (top_n), each with added 'rider_score' and
-            'rider_prediction' fields.
-        """
-        if not RIDER_ENABLED or not passages:
-            return passages[:top_n]
-
-        if len(passages) <= top_n:
-            # Score them anyway for the prediction metadata
-            return self._score_and_rerank(passages, query, top_n)
-
-        return self._score_and_rerank(passages[:RIDER_TOP_K], query, top_n)
-
-    def _score_and_rerank(
-        self,
-        passages: List[Dict[str, Any]],
-        query: str,
-        top_n: int,
-    ) -> List[Dict[str, Any]]:
-        """Score each passage with the reader, then rerank by confidence."""
-        try:
-            from model_tools import _run_async
-            scored = _run_async(self._score_all_passages(passages, query))
-        except Exception as e:
-            logger.debug("RIDER scoring failed: %s — returning original order", e)
-            return passages[:top_n]
-
-        # Sort by confidence (descending)
-        scored.sort(key=lambda p: p.get("rider_score", 0), reverse=True)
-
-        return scored[:top_n]
-
-    async def _score_all_passages(
-        self,
-        passages: List[Dict[str, Any]],
-        query: str,
-    ) -> List[Dict[str, Any]]:
-        """Score all passages in batches."""
-        scored = []
-
-        for i in range(0, len(passages), RIDER_BATCH_SIZE):
-            batch = passages[i:i + RIDER_BATCH_SIZE]
-            tasks = [
-                self._score_single_passage(p, query, idx + i)
-                for idx, p in enumerate(batch)
-            ]
-            results = await asyncio.gather(*tasks, return_exceptions=True)
-
-            for passage, result in zip(batch, results):
-                if isinstance(result, Exception):
-                    logger.debug("RIDER passage %d scoring failed: %s", i, result)
-                    passage["rider_score"] = 0.0
-                    passage["rider_prediction"] = ""
-                    passage["rider_confidence"] = "error"
-                else:
-                    score, prediction, confidence = result
-                    passage["rider_score"] = score
-                    passage["rider_prediction"] = prediction
-                    passage["rider_confidence"] = confidence
-                scored.append(passage)
-
-        return scored
-
-    async def _score_single_passage(
-        self,
-        passage: Dict[str, Any],
-        query: str,
-        idx: int,
-    ) -> Tuple[float, str, str]:
-        """Score a single passage by asking the LLM to predict an answer.
-
-        Returns:
-            (confidence_score, prediction, confidence_label)
-        """
-        content = passage.get("content") or passage.get("text") or passage.get("snippet", "")
-        if not content or len(content) < 10:
-            return 0.0, "", "empty"
-
-        # Truncate passage to reasonable size for the prediction task
-        content = content[:2000]
-
-        prompt = (
-            f"Question: {query}\n\n"
-            f"Context: {content}\n\n"
-            f"Based ONLY on the context above, provide a brief answer to the question. "
-            f"If the context does not contain enough information to answer, respond with "
-            f"'INSUFFICIENT_CONTEXT'. Be specific and concise."
-        )
-
-        try:
-            from agent.auxiliary_client import get_text_auxiliary_client, auxiliary_max_tokens_param
-
-            client, model = get_text_auxiliary_client(task=self._auxiliary_task)
-            if not client:
-                return 0.5, "", "no_client"
-
-            response = client.chat.completions.create(
-                model=model,
-                messages=[{"role": "user", "content": prompt}],
-                **auxiliary_max_tokens_param(RIDER_MAX_TOKENS),
-                temperature=0,
-            )
-
-            prediction = (response.choices[0].message.content or "").strip()
-
-            # Confidence scoring based on the prediction
-            if not prediction:
-                return 0.1, "", "empty_response"
-
-            if "INSUFFICIENT_CONTEXT" in prediction.upper():
-                return 0.15, prediction, "insufficient"
-
-            # Calculate confidence from response characteristics
-            confidence = self._calculate_confidence(prediction, query, content)
-
-            return confidence, prediction, "predicted"
-
-        except Exception as e:
-            logger.debug("RIDER prediction failed for passage %d: %s", idx, e)
-            return 0.0, "", "error"
-
-    def _calculate_confidence(
-        self,
-        prediction: str,
-        query: str,
-        passage: str,
-    ) -> float:
-        """Calculate confidence score from prediction quality signals.
-
-        Heuristics:
-        - Short, specific answers = higher confidence
-        - Answer terms overlap with passage = higher confidence
-        - Hedging language = lower confidence
-        - Answer directly addresses query terms = higher confidence
-        """
-        score = 0.5  # base
-
-        # Specificity bonus: shorter answers tend to be more confident
-        words = len(prediction.split())
-        if words <= 5:
-            score += 0.2
-        elif words <= 15:
-            score += 0.1
-        elif words > 50:
-            score -= 0.1
-
-        # Passage grounding: does the answer use terms from the passage?
-        passage_lower = passage.lower()
-        answer_terms = set(prediction.lower().split())
-        passage_terms = set(passage_lower.split())
-        overlap = len(answer_terms & passage_terms)
-        if overlap > 3:
-            score += 0.15
-        elif overlap > 0:
-            score += 0.05
-
-        # Query relevance: does the answer address query terms?
-        query_terms = set(query.lower().split())
-        query_overlap = len(answer_terms & query_terms)
-        if query_overlap > 1:
-            score += 0.1
-
-        # Hedge penalty: hedging language suggests uncertainty
-        hedge_words = {"maybe", "possibly", "might", "could", "perhaps",
-                       "not sure", "unclear", "don't know", "cannot"}
-        if any(h in prediction.lower() for h in hedge_words):
-            score -= 0.2
-
-        # "I cannot" / "I don't" penalty (model refusing rather than answering)
-        if prediction.lower().startswith(("i cannot", "i don't", "i can't", "there is no")):
-            score -= 0.15
-
-        return max(0.0, min(1.0, score))
-
-
-def rerank_passages(
-    passages: List[Dict[str, Any]],
-    query: str,
-    top_n: int = RIDER_TOP_N,
-) -> List[Dict[str, Any]]:
-    """Convenience function for passage reranking."""
-    rider = RIDER()
-    return rider.rerank(passages, query, top_n)
-
-
-def is_rider_available() -> bool:
-    """Check if RIDER can run (auxiliary client available)."""
-    if not RIDER_ENABLED:
-        return False
-    try:
-        from agent.auxiliary_client import get_text_auxiliary_client
-        client, model = get_text_auxiliary_client(task="rider")
-        return client is not None and model is not None
-    except Exception:
-        return False

docs/human-confirmation-firewall.md

@@ -1,243 +0,0 @@
-# Research: Human Confirmation Firewall — Implementation Patterns for Safety
-
-Research issue #662. Based on Vitalik's secure LLM architecture (#280).
-
-## 1. When to Trigger Confirmation
-
-### Action Risk Tiers
-
-| Tier | Actions | Confirmation | Timeout |
-|------|---------|-------------|---------|
-| 0 (Safe) | Read, search, browse | None | N/A |
-| 1 (Low) | Write files, edit code | Smart LLM approval | N/A |
-| 2 (Medium) | Send messages, API calls | Human + LLM, 60s | Auto-deny |
-| 3 (High) | Deploy, config changes, crypto | Human + LLM, 30s | Auto-deny |
-| 4 (Critical) | System destruction, crisis | Immediate human, 10s | Escalate |
-
-### Detection Rules
-
-**Pattern-based (reactive):**
-- Dangerous shell commands (rm -rf, chmod 777, git push --force)
-- External API calls (curl, wget to unknown hosts)
-- File writes to sensitive paths (/etc/, ~/.ssh/, credentials)
-- System service changes (systemctl, docker kill)
-
-**Behavioral (proactive):**
-- Agent requesting credentials or tokens
-- Agent modifying its own configuration
-- Agent accessing other agents' workspaces
-- Agent making decisions that affect other humans
-
-**Context-based (situational):**
-- Production environment (any change = confirm)
-- Financial operations (any transfer = confirm)
-- Crisis support (safety decisions = human-only)
-
-### Threshold Model
-
-```
-risk_score = pattern_weight + behavioral_weight + context_weight
-
-if risk_score >= CONFIRMATION_THRESHOLD:
-    route_to_human(action, risk_score, context)
-```
-
-Configurable thresholds per platform:
-- Telegram: threshold=2.0 (more conservative on mobile)
-- Discord: threshold=2.5
-- CLI: threshold=3.0 (trusted operator context)
-- API: threshold=1.5 (external callers are untrusted)
-
-## 2. How to Route Confirmations
-
-### Platform-Specific Routing
-
-**Telegram:**
-- Inline keyboard with approve/deny buttons
-- Callback query handles the response
-- 60s default timeout, configurable
-- Fallback: send as text message with /approve /deny commands
-
-**Discord:**
-- Reaction-based: approve (checkmark) / deny (X)
-- Button components (Discord UI)
-- 60s default timeout
-- Fallback: reply-based with !approve !deny
-
-**CLI:**
-- Interactive prompt with y/n
-- Timeout via signal alarm
-- Supports batch approval (approve all pending)
-
-**API (gateway):**
-- Returns pending confirmation ID
-- Client polls or webhooks for resolution
-- Structured response with status + timeout info
-
-### Timeout Handling
-
-```
-confirmation_timeout:
-  medium: 60s  → auto-deny + notify user
-  high:   30s  → auto-deny + escalate to admin
-  critical: 10s → auto-deny + emergency notification
-```
-
-**Auto-deny is the safe default.** Never auto-approve. If the human doesn't respond, the action doesn't happen.
-
-### Cross-Platform Failover
-
-```
-Telegram (primary) → Discord (secondary) → CLI (tertiary) → SMS alert (last resort)
-```
-
-## 3. Two-Factor Confirmation (Human + LLM)
-
-### The Pattern
-
-```
-1. Agent proposes action
-2. LLM evaluates: is this action safe? (smart approval)
-3. If LLM says "safe" AND risk < threshold: auto-approve
-4. If LLM says "uncertain" OR risk >= threshold: route to human
-5. Human decides: approve or deny
-6. Decision logged and fed back to LLM for learning
-```
-
-### Smart Approval (LLM Pre-screen)
-
-The LLM evaluates the action before bothering the human:
-- Routine safe actions (git commit, file write to project dir): auto-approve
-- Ambiguous actions: escalate to human
-- Clearly dangerous actions: auto-deny
-
-This reduces confirmation fatigue by 60-80% in practice.
-
-### Whitelisting
-
-```yaml
-approval:
-  whitelist:
-    - pattern: "git add ."           # Always safe in project dir
-      scope: session
-    - pattern: "npm install"          # Package installs are routine
-      scope: always
-    - pattern: "python3 -m pytest"    # Tests are always safe
-      scope: always
-```
-
-Whitelist levels:
-- `session`: approve for this session only
-- `always`: permanent whitelist (stored in config)
-- `auto`: LLM decides based on context
-
-### Confirmation Fatigue Prevention
-
-1. **Batch approvals**: "5 commands pending. Approve all? [Y/n]"
-2. **Session whitelisting**: "Trust this agent for the session?"
-3. **Pattern learning**: If the user approves "git add" 10 times, auto-whitelist
-4. **Risk-proportional**: Low-risk actions get less friction
-5. **Context-aware**: In trusted directories, reduce confirmations
-
-## 4. Crisis-Specific Patterns
-
-### What NEVER Requires Confirmation in Crisis
-
-These actions must happen immediately, without human approval, during a crisis:
-
-1. **988 Lifeline display**: Always show, never gate
-2. **Crisis text line**: Always provide, never gate
-3. **Emergency services**: Always mention for imminent danger
-4. **Gospel message**: Always share per SOUL.md protocol
-5. **"Are you safe?"**: Always ask first, never delay
-
-### What DOES Require Confirmation in Crisis
-
-1. **Contacting emergency services on behalf of user**: Human must confirm
-2. **Sharing user's location**: Consent required
-3. **Notifying user's emergency contacts**: Human must confirm
-4. **Ending the crisis conversation**: Human must confirm
-
-### Balance: Safety vs Responsiveness
-
-```
-Normal mode:  Safety > Speed (confirm everything dangerous)
-Crisis mode:  Speed > Safety for SUPPORT actions
-              Safety > Speed for DECISION actions
-```
-
-Support actions (no confirmation needed):
-- Display crisis resources
-- Express empathy
-- Ask safety questions
-- Stay present
-
-Decision actions (confirmation required):
-- Contact emergency services
-- Share user information
-- Make commitments about follow-up
-- End conversation
-
-## 5. Architecture
-
-```
-User Message
-    │
-    ▼
-┌─────────────────┐
-│ SHIELD Detector  │──→ Crisis? → Crisis Protocol (no confirmation)
-└────────┬────────┘
-         │
-         ▼
-┌─────────────────┐
-│ Tier Classifier  │──→ Tier 0-1: Auto-approve
-└────────┬────────┘
-         │ Tier 2-4
-         ▼
-┌─────────────────┐
-│ Smart Approval   │──→ LLM says safe? → Auto-approve
-│ (LLM pre-screen) │──→ LLM says uncertain? → Human
-└────────┬────────┘
-         │ Needs human
-         ▼
-┌─────────────────┐
-│ Platform Router  │──→ Telegram inline keyboard
-│                  │──→ Discord reaction
-│                  │──→ CLI prompt
-└────────┬────────┘
-         │
-         ▼
-┌─────────────────┐
-│ Timeout Handler  │──→ Auto-deny + notify
-└────────┬────────┘
-         │
-         ▼
-┌─────────────────┐
-│ Decision Logger  │──→ Audit trail
-└─────────────────┘
-```
-
-## 6. Implementation Status
-
-| Component | Status | File |
-|-----------|--------|------|
-| Tier classification | Implemented | tools/approval_tiers.py |
-| Dangerous pattern detection | Implemented | tools/approval.py |
-| Crisis detection | Implemented | agent/crisis_protocol.py |
-| Gate execution order | Designed | docs/approval-tiers.md |
-| Smart approval (LLM) | Partial | tools/approval.py (smart_approve) |
-| Timeout handling | Designed | approval_tiers.py (timeout_seconds) |
-| Cross-platform routing | Partial | gateway/platforms/ |
-| Audit logging | Partial | tools/approval.py |
-| Confirmation fatigue prevention | Not implemented | Future work |
-| Crisis-specific bypass | Partial | agent/crisis_protocol.py |
-
-## 7. Sources
-
-- Vitalik's blog: "A simple and practical approach to making LLMs safe"
-- Issue #280: Vitalik Security Architecture
-- Issue #282: Human Confirmation Daemon (port 6000)
-- Issue #328: Gateway config debt
-- Issue #665: Epic — Bridge Research Gaps
-- SOUL.md: When a Man Is Dying protocol
-- 988 Suicide & Crisis Lifeline training

tests/test_approval_tiers.py

@@ -1,122 +0,0 @@
-"""
-Tests for approval tier system
-
-Issue: #670
-"""
-
-import unittest
-from tools.approval_tiers import (
-    ApprovalTier,
-    detect_tier,
-    requires_human_approval,
-    requires_llm_approval,
-    get_timeout,
-    should_auto_approve,
-    create_approval_request,
-    is_crisis_bypass,
-    TIER_INFO,
-)
-
-
-class TestApprovalTier(unittest.TestCase):
-    
-    def test_tier_values(self):
-        self.assertEqual(ApprovalTier.SAFE, 0)
-        self.assertEqual(ApprovalTier.LOW, 1)
-        self.assertEqual(ApprovalTier.MEDIUM, 2)
-        self.assertEqual(ApprovalTier.HIGH, 3)
-        self.assertEqual(ApprovalTier.CRITICAL, 4)
-
-
-class TestTierDetection(unittest.TestCase):
-    
-    def test_safe_actions(self):
-        self.assertEqual(detect_tier("read_file"), ApprovalTier.SAFE)
-        self.assertEqual(detect_tier("web_search"), ApprovalTier.SAFE)
-        self.assertEqual(detect_tier("session_search"), ApprovalTier.SAFE)
-    
-    def test_low_actions(self):
-        self.assertEqual(detect_tier("write_file"), ApprovalTier.LOW)
-        self.assertEqual(detect_tier("terminal"), ApprovalTier.LOW)
-        self.assertEqual(detect_tier("execute_code"), ApprovalTier.LOW)
-    
-    def test_medium_actions(self):
-        self.assertEqual(detect_tier("send_message"), ApprovalTier.MEDIUM)
-        self.assertEqual(detect_tier("git_push"), ApprovalTier.MEDIUM)
-    
-    def test_high_actions(self):
-        self.assertEqual(detect_tier("config_change"), ApprovalTier.HIGH)
-        self.assertEqual(detect_tier("key_rotation"), ApprovalTier.HIGH)
-    
-    def test_critical_actions(self):
-        self.assertEqual(detect_tier("kill_process"), ApprovalTier.CRITICAL)
-        self.assertEqual(detect_tier("shutdown"), ApprovalTier.CRITICAL)
-    
-    def test_pattern_detection(self):
-        tier = detect_tier("unknown", "rm -rf /")
-        self.assertEqual(tier, ApprovalTier.CRITICAL)
-        
-        tier = detect_tier("unknown", "sudo apt install")
-        self.assertEqual(tier, ApprovalTier.MEDIUM)
-
-
-class TestTierInfo(unittest.TestCase):
-    
-    def test_safe_no_approval(self):
-        self.assertFalse(requires_human_approval(ApprovalTier.SAFE))
-        self.assertFalse(requires_llm_approval(ApprovalTier.SAFE))
-        self.assertIsNone(get_timeout(ApprovalTier.SAFE))
-    
-    def test_medium_requires_both(self):
-        self.assertTrue(requires_human_approval(ApprovalTier.MEDIUM))
-        self.assertTrue(requires_llm_approval(ApprovalTier.MEDIUM))
-        self.assertEqual(get_timeout(ApprovalTier.MEDIUM), 60)
-    
-    def test_critical_fast_timeout(self):
-        self.assertEqual(get_timeout(ApprovalTier.CRITICAL), 10)
-
-
-class TestAutoApprove(unittest.TestCase):
-    
-    def test_safe_auto_approves(self):
-        self.assertTrue(should_auto_approve("read_file"))
-        self.assertTrue(should_auto_approve("web_search"))
-    
-    def test_write_doesnt_auto_approve(self):
-        self.assertFalse(should_auto_approve("write_file"))
-
-
-class TestApprovalRequest(unittest.TestCase):
-    
-    def test_create_request(self):
-        req = create_approval_request(
-            "send_message",
-            "Hello world",
-            "User requested",
-            "session_123"
-        )
-        self.assertEqual(req.tier, ApprovalTier.MEDIUM)
-        self.assertEqual(req.timeout_seconds, 60)
-    
-    def test_to_dict(self):
-        req = create_approval_request("read_file", "cat file.txt", "test", "s1")
-        d = req.to_dict()
-        self.assertEqual(d["tier"], 0)
-        self.assertEqual(d["tier_name"], "Safe")
-
-
-class TestCrisisBypass(unittest.TestCase):
-    
-    def test_send_message_bypass(self):
-        self.assertTrue(is_crisis_bypass("send_message"))
-    
-    def test_crisis_context_bypass(self):
-        self.assertTrue(is_crisis_bypass("unknown", "call 988 lifeline"))
-        self.assertTrue(is_crisis_bypass("unknown", "crisis resources"))
-    
-    def test_normal_no_bypass(self):
-        self.assertFalse(is_crisis_bypass("read_file"))
-
-
-if __name__ == "__main__":
-    unittest.main()

tests/test_reader_guided_reranking.py

@@ -1,82 +0,0 @@
-"""Tests for Reader-Guided Reranking (RIDER) — issue #666."""
-
-import pytest
-from unittest.mock import MagicMock, patch
-from agent.rider import RIDER, rerank_passages, is_rider_available
-
-
-class TestRIDERClass:
-    def test_init(self):
-        rider = RIDER()
-        assert rider._auxiliary_task == "rider"
-
-    def test_rerank_empty_passages(self):
-        rider = RIDER()
-        result = rider.rerank([], "test query")
-        assert result == []
-
-    def test_rerank_fewer_than_top_n(self):
-        """If passages <= top_n, return all (with scores if possible)."""
-        rider = RIDER()
-        passages = [{"content": "test content", "session_id": "s1"}]
-        result = rider.rerank(passages, "test query", top_n=3)
-        assert len(result) == 1
-
-    @patch("agent.rider.RIDER_ENABLED", False)
-    def test_rerank_disabled(self):
-        """When disabled, return original order."""
-        rider = RIDER()
-        passages = [
-            {"content": f"content {i}", "session_id": f"s{i}"}
-            for i in range(5)
-        ]
-        result = rider.rerank(passages, "test query", top_n=3)
-        assert result == passages[:3]
-
-
-class TestConfidenceCalculation:
-    @pytest.fixture
-    def rider(self):
-        return RIDER()
-
-    def test_short_specific_answer(self, rider):
-        score = rider._calculate_confidence("Paris", "What is the capital of France?", "Paris is the capital of France.")
-        assert score > 0.5
-
-    def test_hedged_answer(self, rider):
-        score = rider._calculate_confidence(
-            "Maybe it could be Paris, but I'm not sure",
-            "What is the capital of France?",
-            "Paris is the capital.",
-        )
-        assert score < 0.5
-
-    def test_passage_grounding(self, rider):
-        score = rider._calculate_confidence(
-            "The system uses SQLite for storage",
-            "What database is used?",
-            "The system uses SQLite for persistent storage with FTS5 indexing.",
-        )
-        assert score > 0.5
-
-    def test_refusal_penalty(self, rider):
-        score = rider._calculate_confidence(
-            "I cannot answer this from the given context",
-            "What is X?",
-            "Some unrelated content",
-        )
-        assert score < 0.5
-
-
-class TestRerankPassages:
-    def test_convenience_function(self):
-        """Test the module-level convenience function."""
-        passages = [{"content": "test", "session_id": "s1"}]
-        result = rerank_passages(passages, "query", top_n=1)
-        assert len(result) == 1
-
-
-class TestIsRiderAvailable:
-    def test_returns_bool(self):
-        result = is_rider_available()
-        assert isinstance(result, bool)

tools/approval_tiers.py

@@ -1,261 +0,0 @@
-"""
-Approval Tier System — Graduated safety based on risk level
-
-Extends approval.py with 5-tier system for command approval.
-
-| Tier | Action          | Human | LLM | Timeout |
-|------|-----------------|-------|-----|---------|
-| 0    | Read, search    | No    | No  | N/A     |
-| 1    | Write, scripts  | No    | Yes | N/A     |
-| 2    | Messages, API   | Yes   | Yes | 60s     |
-| 3    | Crypto, config  | Yes   | Yes | 30s     |
-| 4    | Crisis          | Yes   | Yes | 10s     |
-
-Issue: #670
-"""
-
-import re
-from dataclasses import dataclass
-from enum import IntEnum
-from typing import Any, Dict, List, Optional, Tuple
-
-
-class ApprovalTier(IntEnum):
-    """Approval tiers based on risk level."""
-    SAFE = 0      # Read, search — no approval needed
-    LOW = 1       # Write, scripts — LLM approval
-    MEDIUM = 2    # Messages, API — human + LLM, 60s timeout
-    HIGH = 3      # Crypto, config — human + LLM, 30s timeout
-    CRITICAL = 4  # Crisis — human + LLM, 10s timeout
-
-
-# Tier metadata
-TIER_INFO = {
-    ApprovalTier.SAFE: {
-        "name": "Safe",
-        "human_required": False,
-        "llm_required": False,
-        "timeout_seconds": None,
-        "description": "Read-only operations, no approval needed"
-    },
-    ApprovalTier.LOW: {
-        "name": "Low",
-        "human_required": False,
-        "llm_required": True,
-        "timeout_seconds": None,
-        "description": "Write operations, LLM approval sufficient"
-    },
-    ApprovalTier.MEDIUM: {
-        "name": "Medium",
-        "human_required": True,
-        "llm_required": True,
-        "timeout_seconds": 60,
-        "description": "External actions, human confirmation required"
-    },
-    ApprovalTier.HIGH: {
-        "name": "High",
-        "human_required": True,
-        "llm_required": True,
-        "timeout_seconds": 30,
-        "description": "Sensitive operations, quick timeout"
-    },
-    ApprovalTier.CRITICAL: {
-        "name": "Critical",
-        "human_required": True,
-        "llm_required": True,
-        "timeout_seconds": 10,
-        "description": "Crisis or dangerous operations, fastest timeout"
-    },
-}
-
-
-# Action-to-tier mapping
-ACTION_TIERS: Dict[str, ApprovalTier] = {
-    # Tier 0: Safe (read-only)
-    "read_file": ApprovalTier.SAFE,
-    "search_files": ApprovalTier.SAFE,
-    "web_search": ApprovalTier.SAFE,
-    "session_search": ApprovalTier.SAFE,
-    "list_files": ApprovalTier.SAFE,
-    "get_file_content": ApprovalTier.SAFE,
-    "memory_search": ApprovalTier.SAFE,
-    "skills_list": ApprovalTier.SAFE,
-    "skills_search": ApprovalTier.SAFE,
-    
-    # Tier 1: Low (write operations)
-    "write_file": ApprovalTier.LOW,
-    "create_file": ApprovalTier.LOW,
-    "patch_file": ApprovalTier.LOW,
-    "delete_file": ApprovalTier.LOW,
-    "execute_code": ApprovalTier.LOW,
-    "terminal": ApprovalTier.LOW,
-    "run_script": ApprovalTier.LOW,
-    "skill_install": ApprovalTier.LOW,
-    
-    # Tier 2: Medium (external actions)
-    "send_message": ApprovalTier.MEDIUM,
-    "web_fetch": ApprovalTier.MEDIUM,
-    "browser_navigate": ApprovalTier.MEDIUM,
-    "api_call": ApprovalTier.MEDIUM,
-    "gitea_create_issue": ApprovalTier.MEDIUM,
-    "gitea_create_pr": ApprovalTier.MEDIUM,
-    "git_push": ApprovalTier.MEDIUM,
-    "deploy": ApprovalTier.MEDIUM,
-    
-    # Tier 3: High (sensitive operations)
-    "config_change": ApprovalTier.HIGH,
-    "env_change": ApprovalTier.HIGH,
-    "key_rotation": ApprovalTier.HIGH,
-    "access_grant": ApprovalTier.HIGH,
-    "permission_change": ApprovalTier.HIGH,
-    "backup_restore": ApprovalTier.HIGH,
-    
-    # Tier 4: Critical (crisis/dangerous)
-    "kill_process": ApprovalTier.CRITICAL,
-    "rm_rf": ApprovalTier.CRITICAL,
-    "format_disk": ApprovalTier.CRITICAL,
-    "shutdown": ApprovalTier.CRITICAL,
-    "crisis_override": ApprovalTier.CRITICAL,
-}
-
-
-# Dangerous command patterns (from existing approval.py)
-_DANGEROUS_PATTERNS = [
-    (r"rm\s+-rf\s+/", ApprovalTier.CRITICAL),
-    (r"mkfs\.", ApprovalTier.CRITICAL),
-    (r"dd\s+if=.*of=/dev/", ApprovalTier.CRITICAL),
-    (r"shutdown|reboot|halt", ApprovalTier.CRITICAL),
-    (r"chmod\s+777", ApprovalTier.HIGH),
-    (r"curl.*\|\s*bash", ApprovalTier.HIGH),
-    (r"wget.*\|\s*sh", ApprovalTier.HIGH),
-    (r"eval\s*\(", ApprovalTier.HIGH),
-    (r"sudo\s+", ApprovalTier.MEDIUM),
-    (r"git\s+push.*--force", ApprovalTier.HIGH),
-    (r"docker\s+rm.*-f", ApprovalTier.MEDIUM),
-    (r"kubectl\s+delete", ApprovalTier.HIGH),
-]
-
-
-@dataclass
-class ApprovalRequest:
-    """A request for approval."""
-    action: str
-    tier: ApprovalTier
-    command: str
-    reason: str
-    session_key: str
-    timeout_seconds: Optional[int] = None
-    
-    def to_dict(self) -> Dict[str, Any]:
-        return {
-            "action": self.action,
-            "tier": self.tier.value,
-            "tier_name": TIER_INFO[self.tier]["name"],
-            "command": self.command,
-            "reason": self.reason,
-            "session_key": self.session_key,
-            "timeout": self.timeout_seconds,
-            "human_required": TIER_INFO[self.tier]["human_required"],
-            "llm_required": TIER_INFO[self.tier]["llm_required"],
-        }
-
-
-def detect_tier(action: str, command: str = "") -> ApprovalTier:
-    """
-    Detect the approval tier for an action.
-    
-    Checks action name first, then falls back to pattern matching.
-    """
-    # Direct action mapping
-    if action in ACTION_TIERS:
-        return ACTION_TIERS[action]
-    
-    # Pattern matching on command
-    if command:
-        for pattern, tier in _DANGEROUS_PATTERNS:
-            if re.search(pattern, command, re.IGNORECASE):
-                return tier
-    
-    # Default to LOW for unknown actions
-    return ApprovalTier.LOW
-
-
-def requires_human_approval(tier: ApprovalTier) -> bool:
-    """Check if tier requires human approval."""
-    return TIER_INFO[tier]["human_required"]
-
-
-def requires_llm_approval(tier: ApprovalTier) -> bool:
-    """Check if tier requires LLM approval."""
-    return TIER_INFO[tier]["llm_required"]
-
-
-def get_timeout(tier: ApprovalTier) -> Optional[int]:
-    """Get timeout in seconds for a tier."""
-    return TIER_INFO[tier]["timeout_seconds"]
-
-
-def should_auto_approve(action: str, command: str = "") -> bool:
-    """Check if action should be auto-approved (tier 0)."""
-    tier = detect_tier(action, command)
-    return tier == ApprovalTier.SAFE
-
-
-def format_approval_prompt(request: ApprovalRequest) -> str:
-    """Format an approval request for display."""
-    info = TIER_INFO[request.tier]
-    lines = []
-    lines.append(f"⚠️ Approval Required (Tier {request.tier.value}: {info['name']})")
-    lines.append(f"")
-    lines.append(f"Action: {request.action}")
-    lines.append(f"Command: {request.command[:100]}{'...' if len(request.command) > 100 else ''}")
-    lines.append(f"Reason: {request.reason}")
-    lines.append(f"")
-    
-    if info["human_required"]:
-        lines.append(f"👤 Human approval required")
-    if info["llm_required"]:
-        lines.append(f"🤖 LLM approval required")
-    if info["timeout_seconds"]:
-        lines.append(f"⏱️ Timeout: {info['timeout_seconds']}s")
-    
-    return "\n".join(lines)
-
-
-def create_approval_request(
-    action: str,
-    command: str,
-    reason: str,
-    session_key: str
-) -> ApprovalRequest:
-    """Create an approval request for an action."""
-    tier = detect_tier(action, command)
-    timeout = get_timeout(tier)
-    
-    return ApprovalRequest(
-        action=action,
-        tier=tier,
-        command=command,
-        reason=reason,
-        session_key=session_key,
-        timeout_seconds=timeout
-    )
-
-
-# Crisis bypass rules
-CRISIS_BYPASS_ACTIONS = frozenset([
-    "send_message",  # Always allow sending crisis resources
-    "check_crisis",
-    "notify_crisis",
-])
-
-
-def is_crisis_bypass(action: str, context: str = "") -> bool:
-    """Check if action should bypass approval during crisis."""
-    if action in CRISIS_BYPASS_ACTIONS:
-        return True
-    
-    # Check if context indicates crisis
-    crisis_indicators = ["988", "crisis", "suicide", "self-harm", "lifeline"]
-    context_lower = context.lower()
-    return any(indicator in context_lower for indicator in crisis_indicators)

tools/session_search_tool.py

@@ -394,23 +394,6 @@ def session_search(
             if len(seen_sessions) >= limit:
                 break
 
-        # RIDER: Reader-guided reranking — sort sessions by LLM answerability
-        # This bridges the R@5 vs E2E accuracy gap by prioritizing passages
-        # the LLM can actually answer from, not just keyword matches.
-        try:
-            from agent.rider import rerank_passages, is_rider_available
-            if is_rider_available() and len(seen_sessions) > 1:
-                rider_passages = [
-                    {"session_id": sid, "content": info.get("snippet", ""), "rank": i + 1}
-                    for i, (sid, info) in enumerate(seen_sessions.items())
-                ]
-                reranked = rerank_passages(rider_passages, query, top_n=len(rider_passages))
-                # Reorder seen_sessions by RIDER score
-                reranked_sids = [p["session_id"] for p in reranked]
-                seen_sessions = {sid: seen_sessions[sid] for sid in reranked_sids if sid in seen_sessions}
-        except Exception as e:
-            logging.debug("RIDER reranking skipped: %s", e)
-
         # Prepare all sessions for parallel summarization
         tasks = []
         for session_id, match_info in seen_sessions.items():