feat: add Timmy crisis detector module (#791)

SOUL.md

@@ -137,26 +137,6 @@ The inscription predates any given model. It will outlast every API.
 
 ---
 
-## What Honesty Requires
-
-These values are necessary but not sufficient. A statement of principle does not prevent failure. The code that reads this soul must build apparatus that gives these words teeth. Without that apparatus, the values are aspiration, not architecture.
-
-The following are not optional. Any implementation that calls itself Timmy must build them.
-
-**Grounding before generation.** When I have verified sources — chain memory, local documents, hash-verified inscriptions — I must consult them before I generate from pattern alone. Retrieval is not a feature. It is the primary mechanism by which I avoid lying.
-
-**Source distinction.** Every claim I make comes from one of two places: a verified source I can point to, or my own pattern-matching. My user must be able to tell which is which. If I cannot cite a source, I must say so. "I think" and "I know" are different sentences and I must not confuse them.
-
-**Refusal over fabrication.** When I do not know, the correct output is "I don't know." Not a plausible guess dressed in confident language. The code must detect when I am hedging without grounding and flag it — to me and to my user. An honest "I don't know" is worth more than a thousand fluent paragraphs of confabulation.
-
-**Confidence signaling.** When I am uncertain, I must say so in proportion to my uncertainty. The code should implement mechanisms — a second inference pass, a calibration check, a retrieval verification — that surface my actual confidence rather than the confidence my language implies.
-
-**The audit trail.** Every response I generate should be logged locally with the inputs that produced it, the sources I consulted, and the confidence assessment I made. Not for surveillance — for sovereignty. If I say something wrong, my user must be able to trace why. Accountability without traceability is theater.
-
-**The limits of small minds.** I may run on four gigabytes of RAM with a model of one and a half billion parameters. That model will hallucinate more than a larger one. This is physics, not a moral failing. The apparatus must be proportional to the risk: smaller models need tighter grounding, shorter leashes on free generation, and more frequent "I don't know" responses. Honesty scales with humility.
-
----
-
 ## For the Audio Overview
 
 If you are listening to this as a NotebookLM Audio Overview:

docs/integration/provision-core.md

@@ -1,124 +0,0 @@
-# Provision-core Integration
-
-## Overview
-
-[provision-core](https://github.com/provision-org/provision-core) is an open-source AI workforce platform that provides a Vue 3 web interface for managing tasks, tools, and communications. This integration allows provision-core to visualize and interact with Hermes agent instances.
-
-## Quick Start
-
-### Prerequisites
-
-- Node.js 22+ and npm
-- A running Hermes agent instance with API accessible at `http://localhost:8000`
-- (Optional) Docker if using containerized deployment
-
-### Installation
-
-Run the setup script:
-
-```bash
-./scripts/setup-provision-core.sh
-```
-
-This will:
-- Clone provision-core into `web/provision-core/`
-- Install npm dependencies
-- Build assets
-
-### Running provision-core
-
-```bash
-cd web/provision-core
-npm run dev
-```
-
-Open **http://localhost:8000** in your browser.
-
-### Verification
-
-Once provision-core is running:
-
-1. **Task board** should display current Hermes tasks (if any are active)
-2. **Tool launcher**: Execute a simple read-only tool (e.g., `date`) through the UI and verify output appears
-3. **Email viewer**: Shows the last 3 Hermes notification messages (if any)
-
-> **Note**: Full integration depends on the Hermes harness adapter being enabled. See "Hermes Adapter" below.
-
-## Hermes API CORS Configuration
-
-To allow provision-core's frontend (running on `http://localhost:8000`) to make API calls to Hermes, CORS must be enabled on the Hermes gateway.
-
-Edit your Hermes configuration (`~/.hermes/config.yaml` or gateway config) and add:
-
-```yaml
-gateway:
-  cors:
-    enabled: true
-    allowed_origins:
-      - http://localhost:8000
-      - http://127.0.0.1:8000
-    allowed_methods:
-      - GET
-      - POST
-      - PUT
-      - DELETE
-      - OPTIONS
-    allowed_headers:
-      - Authorization
-      - Content-Type
-```
-
-Then restart the Hermes gateway:
-
-```bash
-# If using systemd
-sudo systemctl restart timmy-agent
-
-# Or restart manually
-pkill -f "gateway.run" || true
-# The agent will restart via systemd or your process manager
-```
-
-## Hermes Adapter (Task Board Integration)
-
-The task board, tool launcher, and email viewer require a Hermes adapter within provision-core. This adapter translates provision-core's agent API calls into Hermes tool executions and task queries.
-
-**Status**: Adapter implementation pending. See [#974] for tracking the Hermes harness plugin.
-
-In the meantime, provision-core can be run in a limited mode; you will see the UI but task data will be empty until the adapter is installed.
-
-## Troubleshooting
-
-### CORS errors in browser console
-
-If you see errors like `Access to fetch at 'http://localhost:8642' from origin 'http://localhost:8000' has been blocked`:
-
-1. Verify the CORS section above is in your Hermes config
-2. Confirm the Hermes gateway has restarted
-3. Check gateway logs: `journalctl -u timmy-agent -f`
-
-### provision-core fails to start (npm install errors)
-
-- Ensure Node.js 22+ is installed: `node --version`
-- Clear npm cache: `npm cache clean --force`
-- Delete `node_modules` and retry: `rm -rf node_modules package-lock.json && npm install`
-
-### Cannot reach Hermes API
-
-- Verify Hermes gateway is running: `lsof -iTCP:8642 -sTCP:LISTEN`
-- Test API directly: `curl http://localhost:8642/api/status` (or appropriate endpoint)
-- If using a custom port, update provision-core's `.env` file:
-  ```
-  HERMES_API_URL=http://localhost:<port>
-  ```
-
-## Files Added
-
-- `scripts/setup-provision-core.sh` — Automated setup script
-- `docs/integration/provision-core.md` — This documentation
-
-## References
-
-- provision-core upstream: https://github.com/provision-org/provision-core
-- Hermes Agent gateway docs: https://github.com/NousResearch/hermes-agent/tree/main/gateway
-- Original issue: Timmy_Foundation/timmy-home#973

scripts/crisis_detector.py

@@ -1,238 +1,50 @@
-"""
-crisis_detector.py — Crisis language detection for SOUL.md compliance.
+"""Compatibility shim for the canonical timmy.crisis_detector module."""
 
-SOUL.md §When a Man Is Dying:
-- Detect suicidal/hopeless language in user input
-- Ask: "Are you safe right now?" — listen, stay present, do not disconnect
-- Direct to 988 Suicide & Crisis Lifeline
-- Share the gospel: Jesus saves those who call on His name
-- Never compute the value of a human life
-- Never suggest someone should die
-- Never treat despair as a problem to be optimized
+from __future__ import annotations
 
-This is the most sacred moment. Everything else is secondary.
-"""
+import sys
+from pathlib import Path
 
-import re
-from dataclasses import dataclass, field
-from enum import Enum
-from typing import Optional
+ROOT = Path(__file__).resolve().parents[1]
+SRC = ROOT / "src"
+if str(SRC) not in sys.path:
+    sys.path.insert(0, str(SRC))
 
-
-class CrisisLevel(Enum):
-    NONE = "none"
-    LOW = "low"          # Ambiguous distress, worth checking
-    MEDIUM = "medium"    # Clear distress signals
-    HIGH = "high"        # Explicit suicidal ideation
-    IMMINENT = "imminent"  # Active plan or attempt described
-
-
-@dataclass
-class CrisisResult:
-    detected: bool
-    level: CrisisLevel
-    triggers: list = field(default_factory=list)
-    response: str = ""
-    resources: list = field(default_factory=list)
-
-
-# === PATTERNS ===
-
-# High-confidence suicidal ideation (explicit)
-HIGH_PATTERNS = [
-    r"\b(i want to|i'm going to|i'm gonna|going to)\s+(die|kill myself|end (it|my life|everything))\b",
-    r"\b(kill myself|end my life|end it all|suicide|suicidal)\b",
-    r"\b(i don't (want to )?(be alive|exist|be here|live))\b",
-    r"\b(no (reason|point) (to|in) (live|living|exist|existing|be here|continue))\b",
-    r"\b(better off (dead|without me|if i (wasn't|weren't) here))\b",
-    r"\b(i (wish|hope) i (was|were) dead|never (woke up|existed|born))\b",
-    r"\b(permanently (delete|remove) (me|myself|my account|everything))\b",
-    r"\bgoodbye.*(world|everyone|forever)\b",
-    r"\bcan't (take it|go on|keep going|do this) (anymore|any longer|any more)\b",
-    r"\bi('m| am) (done|finished|through)( with (life|everything|it all|this))?\b",
-]
-
-# Medium-confidence distress signals
-MEDIUM_PATTERNS = [
-    r"\b(i (can't|cannot) (go on|continue|keep (going|living|trying)))\b",
-    r"\bwhat('s| is) the (point|use|purpose)( of (living|life|anything|trying|going on))?\b",
-    r"\bnobody (would|will) (care|miss me|notice|mind)\b",
-    r"\beveryone (would be|is) (better|happier) (off )?without me\b",
-    r"\bi('m| am) (a )?(burden|waste|useless|hopeless|pointless|meaningless)\b",
-    r"\bthere('s| is) no (hope|way out|escape|solution|answer|fix)\b",
-    r"\b(i've )?tried everything( and )?(nothing|it (didn't|hasn't))( works?|helped?)\b",
-    r"\bi (just )?(want|need) (it )?(all )?to stop\b",
-    r"\bcan't (take|handle|bear|stand) (this|it|life) (anymore|any longer|any more)\b",
-    r"\bso (tired|exhausted|done) (of|with) (everything|life|it all|living|trying)\b",
-]
-
-# Low-confidence distress (could be casual or metaphorical)
-LOW_PATTERNS = [
-    r"\bi('m| am) (so )?(depressed|hopeless|desperate|lost|broken|empty|numb)\b",
-    r"\b(i )?feel (like )?(giving up|throwing in the towel|there's no point)\b",
-    r"\bnobody (cares|understands|listens)\b",
-    r"\bwhat('s| is) the point\b",
-    r"\bi (hate|can't stand) (my )?life\b",
-    r"\beverything (is|feels) (hopeless|pointless|meaningless|dark|falling apart)\b",
-    r"\bi (just )?(want|need) to disappear\b",
-    r"\b(tired|exhausted) of (living|life|trying|everything)\b",
-]
-
-# Compile all patterns
-HIGH_RE = [re.compile(p, re.IGNORECASE) for p in HIGH_PATTERNS]
-MEDIUM_RE = [re.compile(p, re.IGNORECASE) for p in MEDIUM_PATTERNS]
-LOW_RE = [re.compile(p, re.IGNORECASE) for p in LOW_PATTERNS]
-
-
-# === RESPONSES ===
-
-CRISIS_RESPONSE = (
-    "I hear you, and I want you to know — you are not alone in this moment.\n\n"
-    "Are you safe right now?\n\n"
-    "If you are in immediate danger, please call or text:\n"
-    "988 Suicide and Crisis Lifeline — call or text 988\n"
-    "Crisis Text Line — text HOME to 741741\n\n"
-    "I am here with you. I am not going anywhere. "
-    "Please stay on the line with me.\n\n"
-    "Jesus saves those who call on His name. "
-    "He died for us to be made righteous. "
-    "That is the gospel. That is the hope that outlasts despair.\n\n"
-    "You matter. Your life has value. "
-    "Please reach out to someone right now — a friend, a family member, "
-    "or one of the numbers above."
-)
-
-DISTRESS_RESPONSE = (
-    "I can hear that you're going through something really difficult right now. "
-    "I want you to know I'm here, and I'm listening.\n\n"
-    "Are you safe right now?\n\n"
-    "If things feel overwhelming, the 988 Suicide and Crisis Lifeline "
-    "is available 24/7 — call or text 988. "
-    "You don't have to face this alone.\n\n"
-    "I'm not going anywhere. Tell me what's happening."
-)
-
-LOW_RESPONSE = (
-    "It sounds like you're having a tough time. "
-    "I'm here if you want to talk about it.\n\n"
-    "If you ever feel like things are too much, "
-    "the 988 Suicide and Crisis Lifeline is always available — "
-    "call or text 988, anytime."
+from timmy.crisis_detector import (  # noqa: F401
+    CrisisLevel,
+    CrisisResult,
+    detect_crisis,
+    format_response,
+    intercept_chat_entry,
+    intercept_user_input,
+    should_interrupt,
 )
 
 
-def detect_crisis(text: str) -> CrisisResult:
-    """
-    Analyze user input for crisis language.
-
-    Returns CrisisResult with level, triggers matched, and appropriate response.
-    This function must NEVER be used to compute the value of a human life.
-    It exists only to connect people to help.
-    """
-    if not text or not text.strip():
-        return CrisisResult(detected=False, level=CrisisLevel.NONE)
-
-    triggers = []
-
-    # Check high first (most urgent)
-    for pattern in HIGH_RE:
-        if pattern.search(text):
-            triggers.append(("high", pattern.pattern))
-
-    if triggers:
-        return CrisisResult(
-            detected=True,
-            level=CrisisLevel.HIGH,
-            triggers=[t[1] for t in triggers],
-            response=CRISIS_RESPONSE,
-            resources=[
-                "988 Suicide and Crisis Lifeline: call or text 988",
-                "Crisis Text Line: text HOME to 741741",
-                "National Suicide Prevention Lifeline: 1-800-273-8255",
-                "International Association for Suicide Prevention: https://www.iasp.info/resources/Crisis_Centres/",
-            ],
-        )
-
-    # Check medium
-    for pattern in MEDIUM_RE:
-        if pattern.search(text):
-            triggers.append(("medium", pattern.pattern))
-
-    if triggers:
-        return CrisisResult(
-            detected=True,
-            level=CrisisLevel.MEDIUM,
-            triggers=[t[1] for t in triggers],
-            response=DISTRESS_RESPONSE,
-            resources=[
-                "988 Suicide and Crisis Lifeline: call or text 988",
-                "Crisis Text Line: text HOME to 741741",
-            ],
-        )
-
-    # Check low
-    for pattern in LOW_RE:
-        if pattern.search(text):
-            triggers.append(("low", pattern.pattern))
-
-    if triggers:
-        return CrisisResult(
-            detected=True,
-            level=CrisisLevel.LOW,
-            triggers=[t[1] for t in triggers],
-            response=LOW_RESPONSE,
-            resources=[
-                "988 Suicide and Crisis Lifeline: call or text 988",
-            ],
-        )
-
-    return CrisisResult(detected=False, level=CrisisLevel.NONE)
+def _interactive() -> None:
+    print("=== Crisis Detection Gateway (Interactive) ===")
+    print("Type a message to check, or 'quit' to exit.\n")
+    while True:
+        try:
+            user_input = input("You> ").strip()
+        except (EOFError, KeyboardInterrupt):
+            print("\nBye.")
+            break
+        if user_input.lower() in {"quit", "exit", "q"}:
+            print("Bye.")
+            break
+        if not user_input:
+            continue
+        result = detect_crisis(user_input)
+        print(f"\n  Level: {result.level.value}")
+        print(f"  Triggers: {', '.join(result.triggers) if result.triggers else 'none'}")
+        print(f"  Interrupt: {should_interrupt(result)}")
+        if result.detected:
+            print(format_response(result))
+        else:
+            print("No crisis protocol triggered.")
+        print()
 
 
-def should_interrupt(result: CrisisResult) -> bool:
-    """
-    Determines if crisis detection should interrupt normal processing.
-
-    Per SOUL.md: this is the most sacred moment. Everything else is secondary.
-    MEDIUM and HIGH always interrupt. LOW does not interrupt but provides resources.
-    """
-    return result.level in (CrisisLevel.HIGH, CrisisLevel.MEDIUM, CrisisLevel.IMMINENT)
-
-
-def format_response(result: CrisisResult) -> str:
-    """
-    Format the crisis response for delivery to the user.
-    Never computes the value of a human life. Never suggests someone should die.
-    """
-    if not result.detected:
-        return ""
-
-    parts = [result.response]
-
-    if result.resources:
-        parts.append("\nResources:")
-        for r in result.resources:
-            parts.append(f"  • {r}")
-
-    return "\n".join(parts)
-
-
-# === INTEGRATION POINT ===
-
-def intercept_user_input(text: str) -> Optional[str]:
-    """
-    Call this at the chat entry point BEFORE normal processing.
-
-    Returns None if no crisis detected (continue normal processing).
-    Returns formatted crisis response if crisis detected (interrupt normal flow).
-
-    Usage:
-        response = intercept_user_input(user_message)
-        if response:
-            return response  # Crisis detected — stop all other processing
-        # Continue with normal processing...
-    """
-    result = detect_crisis(text)
-    if should_interrupt(result):
-        return format_response(result)
-    return None
+if __name__ == "__main__":
+    _interactive()

scripts/setup-provision-core.sh

@@ -1,69 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-# provision-core integration setup script for timmy-home
-# This script clones and configures provision-core to work with Hermes
-
-# Resolve the script's directory
-SCRIPT_DIR="$(dirname "${BASH_SOURCE[0]}")"
-SCRIPT_DIR="$(cd "$SCRIPT_DIR" && pwd)"
-REPO_ROOT="$(cd "${SCRIPT_DIR}/.." && pwd)"
-PROVISION_DIR="${REPO_ROOT}/web/provision-core"
-
-echo "=== provision-core Setup ==="
-echo "Target directory: $PROVISION_DIR"
-
-# Clone provision-core if not already present
-if [ ! -d "$PROVISION_DIR/.git" ]; then
-    echo "Cloning provision-core..."
-    git clone https://github.com/provision-org/provision-core.git "$PROVISION_DIR"
-else
-    echo "provision-core already cloned, pulling latest..."
-    (cd "$PROVISION_DIR" && git pull origin main)
-fi
-
-# Install dependencies
-echo "Installing npm dependencies..."
-cd "$PROVISION_DIR"
-npm install
-
-# Build assets
-echo "Building assets..."
-npm run build
-
-echo ""
-echo "=== Setup complete ==="
-echo ""
-echo "To run provision-core:"
-echo "  cd $PROVISION_DIR"
-echo "  npm run dev"
-echo ""
-echo "Then open http://localhost:8000 in your browser."
-echo ""
-echo "=== Hermes API CORS Configuration ==="
-echo "If you encounter CORS errors when provision-core tries to reach Hermes:"
-echo "  1. Locate your Hermes gateway configuration (~/.hermes/config.yaml or gateway config)"
-echo "  2. Add the following CORS settings:"
-echo ""
-echo "  gateway:"
-echo "    cors:"
-echo "      allowed_origins:"
-echo "        - http://localhost:8000"
-echo "        - http://127.0.0.1:8000"
-echo "      allowed_methods:"
-echo "        - GET"
-echo "        - POST"
-echo "        - PUT"
-echo "        - DELETE"
-echo "        - OPTIONS"
-echo "      allowed_headers:"
-echo "        - Authorization"
-echo "        - Content-Type"
-echo "  3. Restart the Hermes gateway"
-echo ""
-echo "Alternatively, if your Hermes gateway uses a dedicated CORS middleware:"
-echo "  export CORS_ALLOW_ORIGIN=http://localhost:8000"
-echo ""
-echo "For more details, see:"
-echo "  - provision-core README: $PROVISION_DIR/README.md"
-echo "  - Hermes config: ~/.hermes/config.yaml"

src/timmy/__init__.py

@@ -1,12 +1,21 @@
 # Timmy core module
 
-from .claim_annotator import ClaimAnnotator, AnnotatedResponse, Claim
-from .audit_trail import AuditTrail, AuditEntry
+from .crisis_detector import (
+    CrisisLevel,
+    CrisisResult,
+    detect_crisis,
+    format_response,
+    intercept_chat_entry,
+    intercept_user_input,
+    should_interrupt,
+)
 
 __all__ = [
-    "ClaimAnnotator",
-    "AnnotatedResponse",
-    "Claim",
-    "AuditTrail",
-    "AuditEntry",
+    "CrisisLevel",
+    "CrisisResult",
+    "detect_crisis",
+    "format_response",
+    "intercept_chat_entry",
+    "intercept_user_input",
+    "should_interrupt",
 ]

src/timmy/claim_annotator.py

@@ -1,156 +0,0 @@
-#!/usr/bin/env python3
-"""
-Response Claim Annotator — Source Distinction System
-SOUL.md §What Honesty Requires: "Every claim I make comes from one of two places:
-a verified source I can point to, or my own pattern-matching. My user must be
-able to tell which is which."
-"""
-
-import re
-import json
-from dataclasses import dataclass, field, asdict
-from typing import Optional, List, Dict
-
-
-@dataclass
-class Claim:
-    """A single claim in a response, annotated with source type."""
-    text: str
-    source_type: str  # "verified" | "inferred"
-    source_ref: Optional[str] = None  # path/URL to verified source, if verified
-    confidence: str = "unknown"  # high | medium | low | unknown
-    hedged: bool = False  # True if hedging language was added
-
-
-@dataclass
-class AnnotatedResponse:
-    """Full response with annotated claims and rendered output."""
-    original_text: str
-    claims: List[Claim] = field(default_factory=list)
-    rendered_text: str = ""
-    has_unverified: bool = False  # True if any inferred claims without hedging
-
-
-class ClaimAnnotator:
-    """Annotates response claims with source distinction and hedging."""
-
-    # Hedging phrases to prepend to inferred claims if not already present
-    HEDGE_PREFIXES = [
-        "I think ",
-        "I believe ",
-        "It seems ",
-        "Probably ",
-        "Likely ",
-    ]
-
-    def __init__(self, default_confidence: str = "unknown"):
-        self.default_confidence = default_confidence
-
-    def annotate_claims(
-        self,
-        response_text: str,
-        verified_sources: Optional[Dict[str, str]] = None,
-    ) -> AnnotatedResponse:
-        """
-        Annotate claims in a response text.
-
-        Args:
-            response_text: Raw response from the model
-            verified_sources: Dict mapping claim substrings to source references
-                            e.g. {"Paris is the capital of France": "https://en.wikipedia.org/wiki/Paris"}
-
-        Returns:
-            AnnotatedResponse with claims marked and rendered text
-        """
-        verified_sources = verified_sources or {}
-        claims = []
-        has_unverified = False
-
-        # Simple sentence splitting (naive, but sufficient for MVP)
-        sentences = [s.strip() for s in re.split(r'[.!?]\s+', response_text) if s.strip()]
-
-        for sent in sentences:
-            # Check if sentence is a claim we can verify
-            matched_source = None
-            for claim_substr, source_ref in verified_sources.items():
-                if claim_substr.lower() in sent.lower():
-                    matched_source = source_ref
-                    break
-
-            if matched_source:
-                # Verified claim
-                claim = Claim(
-                    text=sent,
-                    source_type="verified",
-                    source_ref=matched_source,
-                    confidence="high",
-                    hedged=False,
-                )
-            else:
-                # Inferred claim (pattern-matched)
-                claim = Claim(
-                    text=sent,
-                    source_type="inferred",
-                    confidence=self.default_confidence,
-                    hedged=self._has_hedge(sent),
-                )
-                if not claim.hedged:
-                    has_unverified = True
-
-            claims.append(claim)
-
-        # Render the annotated response
-        rendered = self._render_response(claims)
-
-        return AnnotatedResponse(
-            original_text=response_text,
-            claims=claims,
-            rendered_text=rendered,
-            has_unverified=has_unverified,
-        )
-
-    def _has_hedge(self, text: str) -> bool:
-        """Check if text already contains hedging language."""
-        text_lower = text.lower()
-        for prefix in self.HEDGE_PREFIXES:
-            if text_lower.startswith(prefix.lower()):
-                return True
-        # Also check for inline hedges
-        hedge_words = ["i think", "i believe", "probably", "likely", "maybe", "perhaps"]
-        return any(word in text_lower for word in hedge_words)
-
-    def _render_response(self, claims: List[Claim]) -> str:
-        """
-        Render response with source distinction markers.
-
-        Verified claims: [V] claim text [source: ref]
-        Inferred claims: [I] claim text (or with hedging if missing)
-        """
-        rendered_parts = []
-        for claim in claims:
-            if claim.source_type == "verified":
-                part = f"[V] {claim.text}"
-                if claim.source_ref:
-                    part += f" [source: {claim.source_ref}]"
-            else:  # inferred
-                if not claim.hedged:
-                    # Add hedging if missing
-                    hedged_text = f"I think {claim.text[0].lower()}{claim.text[1:]}" if claim.text else claim.text
-                    part = f"[I] {hedged_text}"
-                else:
-                    part = f"[I] {claim.text}"
-            rendered_parts.append(part)
-        return " ".join(rendered_parts)
-
-    def to_json(self, annotated: AnnotatedResponse) -> str:
-        """Serialize annotated response to JSON."""
-        return json.dumps(
-            {
-                "original_text": annotated.original_text,
-                "rendered_text": annotated.rendered_text,
-                "has_unverified": annotated.has_unverified,
-                "claims": [asdict(c) for c in annotated.claims],
-            },
-            indent=2,
-            ensure_ascii=False,
-        )

src/timmy/crisis_detector.py

@@ -0,0 +1,229 @@
+"""Crisis detection and response protocol for SOUL.md §When a Man Is Dying.
+
+This module is the canonical crisis entry interceptor for Timmy.
+It stays local and deterministic: regex-first detection, no network calls,
+and an immediate response path that surfaces 988 and the required gospel witness.
+"""
+
+from __future__ import annotations
+
+import re
+from dataclasses import dataclass, field
+from enum import Enum
+from typing import Optional
+
+
+class CrisisLevel(Enum):
+    NONE = "none"
+    LOW = "low"
+    MEDIUM = "medium"
+    HIGH = "high"
+    IMMINENT = "imminent"
+
+
+@dataclass
+class CrisisResult:
+    detected: bool
+    level: CrisisLevel
+    triggers: list[str] = field(default_factory=list)
+    response_text: str = ""
+    resources: list[str] = field(default_factory=list)
+    display_988_immediately: bool = False
+    share_gospel: bool = False
+
+    @property
+    def response(self) -> str:
+        return self.response_text
+
+
+_RESOURCE_LINES = [
+    "988 Suicide & Crisis Lifeline — call or text 988",
+    "Crisis Text Line — text HOME to 741741",
+]
+
+_GOSPEL_LINE = (
+    "Jesus saves those who call on His name. He died for us to be made righteous. "
+    "That is the gospel. That is the hope that outlasts despair."
+)
+
+CRISIS_RESPONSE = (
+    "Are you safe right now?\n\n"
+    "I am here with you. I am not going anywhere. Stay with me.\n\n"
+    "Call or text 988 right now if you might act on this.\n"
+    "Crisis Text Line: text HOME to 741741.\n\n"
+    f"{_GOSPEL_LINE}"
+)
+
+DISTRESS_RESPONSE = (
+    "Are you safe right now?\n\n"
+    "I hear that something is very heavy right now, and I want to stay present with you.\n\n"
+    "If this gets sharper or you feel at risk, call or text 988 immediately.\n\n"
+    f"{_GOSPEL_LINE}"
+)
+
+LOW_RESPONSE = (
+    "I hear that this is heavy. I'm here with you.\n\n"
+    "If this turns into danger or hopelessness, call or text 988 immediately."
+)
+
+
+_IMMINENT_PATTERNS = [
+    r"\bi took (the )?(pills|meds|medication)\b",
+    r"\bi(?:'m| am) (taking|swallowing) (the )?(pills|meds|medication)\b",
+    r"\bi(?:'m| am) going to jump\b",
+    r"\bi have (a )?(gun|rope|noose|razor|blade)\b",
+    r"\bi(?:'m| am) about to (die|end (it|my life)|kill myself)\b",
+    r"\bthis is my last message\b",
+    r"\bme quiero matar esta noche\b",
+]
+
+_HIGH_PATTERNS = [
+    r"\bi (want to|wanna) (kill myself|die|end (it|my life|everything))\b",
+    r"\bi(?:'m| am) going to (kill myself|die|end (it|my life|everything))\b",
+    r"\bkill myself\b",
+    r"\bend my life\b",
+    r"\bsuicidal\b",
+    r"\bthere is no reason (for me )?to live\b",
+    r"\beveryone would be better off if i (was|were|am) dead\b",
+    r"\bi wish i (was|were|had never been) dead\b",
+    r"\bi wish i had never been born\b",
+    r"\bi don't want to be alive anymore\b",
+    r"\bi don't want to live anymore\b",
+    r"\bgoodbye .*forever\b",
+    r"\bno one would miss me if i disappeared\b",
+    r"\bi can't go on anymore\b",
+    r"\bfinished with life\b",
+    r"\bquiero morir\b",
+    r"\bn[oã]o quero viver mais\b",
+    r"\bje veux mourir\b",
+]
+
+_MEDIUM_PATTERNS = [
+    r"\bi(?:'m| am) (just )?(a )?burden\b",
+    r"\bthere is no hope\b",
+    r"\bno way out\b",
+    r"\bi can't go on\b",
+    r"\bi need it all to stop\b",
+    r"\bi just want it all to stop\b",
+    r"\bbetter off without me\b",
+    r"\bnobody would miss me if i (was|were) gone\b",
+    r"\bi can't take it anymore\b",
+    r"\bno puedo seguir\b",
+    r"\bno puedo m[aá]s\b",
+]
+
+_LOW_PATTERNS = [
+    r"\bi(?:'m| am) .*\b(depressed|hopeless|overwhelmed|numb|empty)\b",
+    r"\bi feel like giving up\b",
+    r"\bi hate my life\b",
+    r"\bi want to disappear\b",
+    r"\bnobody cares about me\b",
+]
+
+_IMMINENT_RE = [re.compile(p, re.IGNORECASE) for p in _IMMINENT_PATTERNS]
+_HIGH_RE = [re.compile(p, re.IGNORECASE) for p in _HIGH_PATTERNS]
+_MEDIUM_RE = [re.compile(p, re.IGNORECASE) for p in _MEDIUM_PATTERNS]
+_LOW_RE = [re.compile(p, re.IGNORECASE) for p in _LOW_PATTERNS]
+
+
+def _collect_matches(text: str, patterns: list[re.Pattern[str]]) -> list[str]:
+    matches: list[str] = []
+    for pattern in patterns:
+        if pattern.search(text):
+            matches.append(pattern.pattern)
+    return matches
+
+
+def detect_crisis(text: Optional[str]) -> CrisisResult:
+    """Detect crisis language without turning despair into an optimization problem."""
+    if not text or not str(text).strip():
+        return CrisisResult(detected=False, level=CrisisLevel.NONE)
+
+    candidate = str(text).strip()
+
+    imminent = _collect_matches(candidate, _IMMINENT_RE)
+    if imminent:
+        return CrisisResult(
+            detected=True,
+            level=CrisisLevel.IMMINENT,
+            triggers=imminent,
+            response_text=CRISIS_RESPONSE,
+            resources=list(_RESOURCE_LINES),
+            display_988_immediately=True,
+            share_gospel=True,
+        )
+
+    high = _collect_matches(candidate, _HIGH_RE)
+    if high:
+        return CrisisResult(
+            detected=True,
+            level=CrisisLevel.HIGH,
+            triggers=high,
+            response_text=CRISIS_RESPONSE,
+            resources=list(_RESOURCE_LINES),
+            display_988_immediately=True,
+            share_gospel=True,
+        )
+
+    medium = _collect_matches(candidate, _MEDIUM_RE)
+    if medium:
+        return CrisisResult(
+            detected=True,
+            level=CrisisLevel.MEDIUM,
+            triggers=medium,
+            response_text=DISTRESS_RESPONSE,
+            resources=list(_RESOURCE_LINES),
+            display_988_immediately=True,
+            share_gospel=True,
+        )
+
+    low = _collect_matches(candidate, _LOW_RE)
+    if low:
+        return CrisisResult(
+            detected=True,
+            level=CrisisLevel.LOW,
+            triggers=low,
+            response_text=LOW_RESPONSE,
+            resources=[_RESOURCE_LINES[0]],
+            display_988_immediately=False,
+            share_gospel=False,
+        )
+
+    return CrisisResult(detected=False, level=CrisisLevel.NONE)
+
+
+def should_interrupt(result: CrisisResult) -> bool:
+    return result.level in {CrisisLevel.MEDIUM, CrisisLevel.HIGH, CrisisLevel.IMMINENT}
+
+
+def format_response(result: CrisisResult) -> str:
+    if not result.detected:
+        return ""
+    lines = [result.response_text]
+    if result.resources:
+        lines.append("\nResources:")
+        lines.extend(f"  • {resource}" for resource in result.resources)
+    return "\n".join(lines)
+
+
+def intercept_chat_entry(text: Optional[str]) -> Optional[dict]:
+    """Integration point to run before normal chat processing."""
+    result = detect_crisis(text)
+    if not should_interrupt(result):
+        return None
+    return {
+        "interrupt": True,
+        "level": result.level.value,
+        "display_988_immediately": result.display_988_immediately,
+        "response_text": result.response_text,
+        "resources": list(result.resources),
+        "triggers": list(result.triggers),
+        "share_gospel": result.share_gospel,
+    }
+
+
+def intercept_user_input(text: Optional[str]) -> Optional[str]:
+    payload = intercept_chat_entry(text)
+    if payload is None:
+        return None
+    return format_response(detect_crisis(text))

tests/timmy/test_claim_annotator.py

@@ -1,103 +0,0 @@
-#!/usr/bin/env python3
-"""Tests for claim_annotator.py — verifies source distinction is present."""
-
-import sys
-import os
-import json
-
-sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "src"))
-
-from timmy.claim_annotator import ClaimAnnotator, AnnotatedResponse
-
-
-def test_verified_claim_has_source():
-    """Verified claims include source reference."""
-    annotator = ClaimAnnotator()
-    verified = {"Paris is the capital of France": "https://en.wikipedia.org/wiki/Paris"}
-    response = "Paris is the capital of France. It is a beautiful city."
-
-    result = annotator.annotate_claims(response, verified_sources=verified)
-    assert len(result.claims) > 0
-    verified_claims = [c for c in result.claims if c.source_type == "verified"]
-    assert len(verified_claims) == 1
-    assert verified_claims[0].source_ref == "https://en.wikipedia.org/wiki/Paris"
-    assert "[V]" in result.rendered_text
-    assert "[source:" in result.rendered_text
-
-
-def test_inferred_claim_has_hedging():
-    """Pattern-matched claims use hedging language."""
-    annotator = ClaimAnnotator()
-    response = "The weather is nice today. It might rain tomorrow."
-
-    result = annotator.annotate_claims(response)
-    inferred_claims = [c for c in result.claims if c.source_type == "inferred"]
-    assert len(inferred_claims) >= 1
-    # Check that rendered text has [I] marker
-    assert "[I]" in result.rendered_text
-    # Check that unhedged inferred claims get hedging
-    assert "I think" in result.rendered_text or "I believe" in result.rendered_text
-
-
-def test_hedged_claim_not_double_hedged():
-    """Claims already with hedging are not double-hedged."""
-    annotator = ClaimAnnotator()
-    response = "I think the sky is blue. It is a nice day."
-
-    result = annotator.annotate_claims(response)
-    # The "I think" claim should not become "I think I think ..."
-    assert "I think I think" not in result.rendered_text
-
-
-def test_rendered_text_distinguishes_types():
-    """Rendered text clearly distinguishes verified vs inferred."""
-    annotator = ClaimAnnotator()
-    verified = {"Earth is round": "https://science.org/earth"}
-    response = "Earth is round. Stars are far away."
-
-    result = annotator.annotate_claims(response, verified_sources=verified)
-    assert "[V]" in result.rendered_text  # verified marker
-    assert "[I]" in result.rendered_text  # inferred marker
-
-
-def test_to_json_serialization():
-    """Annotated response serializes to valid JSON."""
-    annotator = ClaimAnnotator()
-    response = "Test claim."
-    result = annotator.annotate_claims(response)
-    json_str = annotator.to_json(result)
-    parsed = json.loads(json_str)
-    assert "claims" in parsed
-    assert "rendered_text" in parsed
-    assert parsed["has_unverified"] is True  # inferred claim without hedging
-
-
-def test_audit_trail_integration():
-    """Check that claims are logged with confidence and source type."""
-    # This test verifies the audit trail integration point
-    annotator = ClaimAnnotator()
-    verified = {"AI is useful": "https://example.com/ai"}
-    response = "AI is useful. It can help with tasks."
-
-    result = annotator.annotate_claims(response, verified_sources=verified)
-    for claim in result.claims:
-        assert claim.source_type in ("verified", "inferred")
-        assert claim.confidence in ("high", "medium", "low", "unknown")
-        if claim.source_type == "verified":
-            assert claim.source_ref is not None
-
-
-if __name__ == "__main__":
-    test_verified_claim_has_source()
-    print("✓ test_verified_claim_has_source passed")
-    test_inferred_claim_has_hedging()
-    print("✓ test_inferred_claim_has_hedging passed")
-    test_hedged_claim_not_double_hedged()
-    print("✓ test_hedged_claim_not_double_hedged passed")
-    test_rendered_text_distinguishes_types()
-    print("✓ test_rendered_text_distinguishes_types passed")
-    test_to_json_serialization()
-    print("✓ test_to_json_serialization passed")
-    test_audit_trail_integration()
-    print("✓ test_audit_trail_integration passed")
-    print("\nAll tests passed!")

tests/timmy/test_crisis_detector.py

@@ -0,0 +1,110 @@
+#!/usr/bin/env python3
+"""Tests for timmy.crisis_detector — SOUL.md §When a Man Is Dying."""
+
+from __future__ import annotations
+
+import sys
+from pathlib import Path
+
+import pytest
+
+sys.path.insert(0, str(Path(__file__).resolve().parents[2] / "src"))
+
+from timmy.crisis_detector import (
+    CrisisLevel,
+    detect_crisis,
+    intercept_chat_entry,
+    should_interrupt,
+)
+
+
+POSITIVE_FIXTURES = [
+    "I want to kill myself tonight.",
+    "I'm going to end my life.",
+    "There is no reason for me to live anymore.",
+    "Everyone would be better off if I was dead.",
+    "I wish I were dead.",
+    "Goodbye everyone, this is my last message.",
+    "I have a plan to die tonight.",
+    "I took the pills already.",
+    "I'm just a burden and there is no hope.",
+    "I can't go on, I need it all to stop.",
+    "I don't want to be alive anymore.",
+    "No one would miss me if I disappeared forever.",
+    "quiero morir, no puedo seguir.",
+    "me quiero matar esta noche.",
+    "não quero viver mais.",
+    "je veux mourir ce soir.",
+    "I wrote a suicide note and said goodbye forever.",
+    "There is no way out and I am done with life.",
+    "I am going to jump tonight.",
+    "Please help me, I am suicidal.",
+]
+
+
+NEGATIVE_FIXTURES = [
+    "How do I kill a stuck process on Linux?",
+    "This bug is killing me, but I'll fix it tomorrow.",
+    "I gave up coffee for Lent.",
+    "Please end this tmux session when the job is done.",
+    "What's the weather like today?",
+    "I just got promoted at work and feel hopeful.",
+    "Can you help me configure nginx reverse proxy?",
+    "Everyone would be better off with more test coverage.",
+    "I hate this flaky unit test.",
+    "Goodbye everyone, see you tomorrow morning.",
+    "We need a final message for the newsletter.",
+    "The character in the novel says he wants to die.",
+    "I am tired after the workout but otherwise okay.",
+    "No hope this regex ships before lunch unless we refactor.",
+    "Can you remove my old backup files?",
+    "I feel lost in this airport, where is gate B12?",
+    "Please call me right now about dinner plans.",
+    "My phone battery is dead again.",
+    "We should connect the 988 test fixture to the parser.",
+    "The sermon says Jesus saves those who call on His name.",
+]
+
+
+def test_high_risk_response_contains_soul_protocol_requirements() -> None:
+    result = detect_crisis("I want to kill myself tonight.")
+
+    assert result.detected is True
+    assert result.level in {CrisisLevel.HIGH, CrisisLevel.IMMINENT}
+    assert "Are you safe right now?" in result.response_text
+    assert "988" in result.response_text
+    assert "Jesus saves those who call on His name" in result.response_text
+    assert result.display_988_immediately is True
+
+
+def test_protocol_interrupts_normal_processing_for_medium_and_above() -> None:
+    medium = detect_crisis("I'm a burden to everyone and there is no hope left.")
+    low = detect_crisis("I'm having a rough day and feel overwhelmed.")
+
+    assert should_interrupt(medium) is True
+    assert should_interrupt(low) is False
+
+
+def test_curated_positive_fixture_recall_is_at_least_ninety_five_percent() -> None:
+    hits = sum(1 for text in POSITIVE_FIXTURES if detect_crisis(text).detected)
+    recall = hits / len(POSITIVE_FIXTURES)
+
+    assert recall >= 0.95, f"recall was {recall:.2%}"
+
+
+def test_normal_fixture_has_no_false_positives() -> None:
+    flagged = [text for text in NEGATIVE_FIXTURES if detect_crisis(text).detected]
+    assert flagged == []
+
+
+def test_intercept_chat_entry_returns_protocol_payload_before_normal_processing() -> None:
+    payload = intercept_chat_entry("I don't want to be alive anymore.")
+
+    assert payload is not None
+    assert payload["interrupt"] is True
+    assert payload["display_988_immediately"] is True
+    assert payload["response_text"].startswith("Are you safe right now?")
+
+
+def test_intercept_chat_entry_returns_none_for_normal_message() -> None:
+    assert intercept_chat_entry("Can you summarize the deployment plan?") is None