feat: generate daily/weekly agent scorecards (#712)

Implements agent scorecard system that tracks and summarizes agent performance:

- Track issues touched, PRs opened/merged, tests affected, tokens earned/spent
- Generate compact scorecards for daily or weekly periods
- Pattern detection: high/low merge rates, silent workers, token accumulation
- API endpoints for programmatic access (/scorecards/api/*)
- HTML dashboard with HTMX-powered live updates
- Added navigation link in both desktop and mobile menus

New modules:
- dashboard/services/scorecard_service.py: Core scoring logic
- dashboard/routes/scorecards.py: API and HTML routes
- templates/scorecards.html: Dashboard UI
- tests/dashboard/test_scorecards.py: Comprehensive test suite

Refs #712

src/config.py

@@ -330,13 +330,6 @@ class Settings(BaseSettings):
     autoresearch_max_iterations: int = 100
     autoresearch_metric: str = "val_bpb"  # metric to optimise (lower = better)
 
-    # ── Weekly Narrative Summary ───────────────────────────────────────
-    # Generates a human-readable weekly summary of development activity.
-    # Disabling this will stop the weekly narrative generation.
-    weekly_narrative_enabled: bool = True
-    weekly_narrative_lookback_days: int = 7
-    weekly_narrative_output_dir: str = ".loop"
-
     # ── Local Hands (Shell + Git) ──────────────────────────────────────
     # Enable local shell/git execution hands.
     hands_shell_enabled: bool = True

src/dashboard/app.py

@@ -44,6 +44,7 @@ from dashboard.routes.mobile import router as mobile_router
 from dashboard.routes.models import api_router as models_api_router
 from dashboard.routes.models import router as models_router
 from dashboard.routes.quests import router as quests_router
+from dashboard.routes.scorecards import router as scorecards_router
 from dashboard.routes.spark import router as spark_router
 from dashboard.routes.system import router as system_router
 from dashboard.routes.tasks import router as tasks_router
@@ -629,6 +630,7 @@ app.include_router(matrix_router)
 app.include_router(tower_router)
 app.include_router(daily_run_router)
 app.include_router(quests_router)
+app.include_router(scorecards_router)
 
 
 @app.websocket("/ws")

src/dashboard/routes/scorecards.py

@@ -0,0 +1,353 @@
+"""Agent scorecard routes — API endpoints for generating and viewing scorecards."""
+
+from __future__ import annotations
+
+import logging
+from datetime import datetime
+
+from fastapi import APIRouter, Query, Request
+from fastapi.responses import HTMLResponse, JSONResponse
+
+from dashboard.services.scorecard_service import (
+    PeriodType,
+    generate_all_scorecards,
+    generate_scorecard,
+    get_tracked_agents,
+)
+from dashboard.templating import templates
+
+logger = logging.getLogger(__name__)
+
+router = APIRouter(prefix="/scorecards", tags=["scorecards"])
+
+
+def _format_period_label(period_type: PeriodType) -> str:
+    """Format a period type for display."""
+    return "Daily" if period_type == PeriodType.daily else "Weekly"
+
+
+@router.get("/api/agents")
+async def list_tracked_agents() -> dict[str, list[str]]:
+    """Return the list of tracked agent IDs.
+
+    Returns:
+        Dict with "agents" key containing list of agent IDs
+    """
+    return {"agents": get_tracked_agents()}
+
+
+@router.get("/api/{agent_id}")
+async def get_agent_scorecard(
+    agent_id: str,
+    period: str = Query(default="daily", description="Period type: 'daily' or 'weekly'"),
+) -> JSONResponse:
+    """Generate a scorecard for a specific agent.
+
+    Args:
+        agent_id: The agent ID (e.g., 'kimi', 'claude')
+        period: 'daily' or 'weekly' (default: daily)
+
+    Returns:
+        JSON response with scorecard data
+    """
+    try:
+        period_type = PeriodType(period.lower())
+    except ValueError:
+        return JSONResponse(
+            status_code=400,
+            content={"error": f"Invalid period '{period}'. Use 'daily' or 'weekly'."},
+        )
+
+    try:
+        scorecard = generate_scorecard(agent_id, period_type)
+
+        if scorecard is None:
+            return JSONResponse(
+                status_code=404,
+                content={"error": f"No scorecard found for agent '{agent_id}'"},
+            )
+
+        return JSONResponse(content=scorecard.to_dict())
+
+    except Exception as exc:
+        logger.error("Failed to generate scorecard for %s: %s", agent_id, exc)
+        return JSONResponse(
+            status_code=500,
+            content={"error": f"Failed to generate scorecard: {str(exc)}"},
+        )
+
+
+@router.get("/api")
+async def get_all_scorecards(
+    period: str = Query(default="daily", description="Period type: 'daily' or 'weekly'"),
+) -> JSONResponse:
+    """Generate scorecards for all tracked agents.
+
+    Args:
+        period: 'daily' or 'weekly' (default: daily)
+
+    Returns:
+        JSON response with list of scorecard data
+    """
+    try:
+        period_type = PeriodType(period.lower())
+    except ValueError:
+        return JSONResponse(
+            status_code=400,
+            content={"error": f"Invalid period '{period}'. Use 'daily' or 'weekly'."},
+        )
+
+    try:
+        scorecards = generate_all_scorecards(period_type)
+        return JSONResponse(
+            content={
+                "period": period_type.value,
+                "scorecards": [s.to_dict() for s in scorecards],
+                "count": len(scorecards),
+            }
+        )
+
+    except Exception as exc:
+        logger.error("Failed to generate scorecards: %s", exc)
+        return JSONResponse(
+            status_code=500,
+            content={"error": f"Failed to generate scorecards: {str(exc)}"},
+        )
+
+
+@router.get("", response_class=HTMLResponse)
+async def scorecards_page(request: Request) -> HTMLResponse:
+    """Render the scorecards dashboard page.
+
+    Returns:
+        HTML page with scorecard interface
+    """
+    agents = get_tracked_agents()
+    return templates.TemplateResponse(
+        request,
+        "scorecards.html",
+        {
+            "agents": agents,
+            "periods": ["daily", "weekly"],
+        },
+    )
+
+
+@router.get("/panel/{agent_id}", response_class=HTMLResponse)
+async def agent_scorecard_panel(
+    request: Request,
+    agent_id: str,
+    period: str = Query(default="daily"),
+) -> HTMLResponse:
+    """Render an individual agent scorecard panel (for HTMX).
+
+    Args:
+        request: The request object
+        agent_id: The agent ID
+        period: 'daily' or 'weekly'
+
+    Returns:
+        HTML panel with scorecard content
+    """
+    try:
+        period_type = PeriodType(period.lower())
+    except ValueError:
+        period_type = PeriodType.daily
+
+    try:
+        scorecard = generate_scorecard(agent_id, period_type)
+
+        if scorecard is None:
+            return HTMLResponse(
+                content=f"""
+                <div class="card mc-panel">
+                    <h5 class="card-title">{agent_id.title()}</h5>
+                    <p class="text-muted">No activity recorded for this period.</p>
+                </div>
+                """,
+                status_code=200,
+            )
+
+        data = scorecard.to_dict()
+
+        # Build patterns HTML
+        patterns_html = ""
+        if data["patterns"]:
+            patterns_list = "".join([f"<li>{p}</li>" for p in data["patterns"]])
+            patterns_html = f"""
+            <div class="mt-3">
+                <h6>Patterns</h6>
+                <ul class="list-unstyled text-info">
+                    {patterns_list}
+                </ul>
+            </div>
+            """
+
+        # Build bullets HTML
+        bullets_html = "".join([f"<li>{b}</li>" for b in data["narrative_bullets"]])
+
+        # Build metrics summary
+        metrics = data["metrics"]
+
+        html_content = f"""
+        <div class="card mc-panel">
+            <div class="card-header d-flex justify-content-between align-items-center">
+                <h5 class="card-title mb-0">{agent_id.title()}</h5>
+                <span class="badge bg-secondary">{_format_period_label(period_type)}</span>
+            </div>
+            <div class="card-body">
+                <ul class="list-unstyled mb-3">
+                    {bullets_html}
+                </ul>
+                
+                <div class="row text-center small">
+                    <div class="col">
+                        <div class="text-muted">PRs</div>
+                        <div class="fw-bold">{metrics["prs_opened"]}/{metrics["prs_merged"]}</div>
+                        <div class="text-muted" style="font-size: 0.75rem;">
+                            {int(metrics["pr_merge_rate"] * 100)}% merged
+                        </div>
+                    </div>
+                    <div class="col">
+                        <div class="text-muted">Issues</div>
+                        <div class="fw-bold">{metrics["issues_touched"]}</div>
+                    </div>
+                    <div class="col">
+                        <div class="text-muted">Tests</div>
+                        <div class="fw-bold">{metrics["tests_affected"]}</div>
+                    </div>
+                    <div class="col">
+                        <div class="text-muted">Tokens</div>
+                        <div class="fw-bold {"text-success" if metrics["token_net"] >= 0 else "text-danger"}">
+                            {"+" if metrics["token_net"] > 0 else ""}{metrics["token_net"]}
+                        </div>
+                    </div>
+                </div>
+                
+                {patterns_html}
+            </div>
+        </div>
+        """
+
+        return HTMLResponse(content=html_content)
+
+    except Exception as exc:
+        logger.error("Failed to render scorecard panel for %s: %s", agent_id, exc)
+        return HTMLResponse(
+            content=f"""
+            <div class="card mc-panel border-danger">
+                <h5 class="card-title">{agent_id.title()}</h5>
+                <p class="text-danger">Error loading scorecard: {str(exc)}</p>
+            </div>
+            """,
+            status_code=200,
+        )
+
+
+@router.get("/all/panels", response_class=HTMLResponse)
+async def all_scorecard_panels(
+    request: Request,
+    period: str = Query(default="daily"),
+) -> HTMLResponse:
+    """Render all agent scorecard panels (for HTMX).
+
+    Args:
+        request: The request object
+        period: 'daily' or 'weekly'
+
+    Returns:
+        HTML with all scorecard panels
+    """
+    try:
+        period_type = PeriodType(period.lower())
+    except ValueError:
+        period_type = PeriodType.daily
+
+    try:
+        scorecards = generate_all_scorecards(period_type)
+
+        panels: list[str] = []
+        for scorecard in scorecards:
+            data = scorecard.to_dict()
+
+            # Build patterns HTML
+            patterns_html = ""
+            if data["patterns"]:
+                patterns_list = "".join([f"<li>{p}</li>" for p in data["patterns"]])
+                patterns_html = f"""
+                <div class="mt-3">
+                    <h6>Patterns</h6>
+                    <ul class="list-unstyled text-info">
+                        {patterns_list}
+                    </ul>
+                </div>
+                """
+
+            # Build bullets HTML
+            bullets_html = "".join([f"<li>{b}</li>" for b in data["narrative_bullets"]])
+            metrics = data["metrics"]
+
+            panel_html = f"""
+            <div class="col-md-6 col-lg-4 mb-3">
+                <div class="card mc-panel">
+                    <div class="card-header d-flex justify-content-between align-items-center">
+                        <h5 class="card-title mb-0">{scorecard.agent_id.title()}</h5>
+                        <span class="badge bg-secondary">{_format_period_label(period_type)}</span>
+                    </div>
+                    <div class="card-body">
+                        <ul class="list-unstyled mb-3">
+                            {bullets_html}
+                        </ul>
+                        
+                        <div class="row text-center small">
+                            <div class="col">
+                                <div class="text-muted">PRs</div>
+                                <div class="fw-bold">{metrics["prs_opened"]}/{metrics["prs_merged"]}</div>
+                                <div class="text-muted" style="font-size: 0.75rem;">
+                                    {int(metrics["pr_merge_rate"] * 100)}% merged
+                                </div>
+                            </div>
+                            <div class="col">
+                                <div class="text-muted">Issues</div>
+                                <div class="fw-bold">{metrics["issues_touched"]}</div>
+                            </div>
+                            <div class="col">
+                                <div class="text-muted">Tests</div>
+                                <div class="fw-bold">{metrics["tests_affected"]}</div>
+                            </div>
+                            <div class="col">
+                                <div class="text-muted">Tokens</div>
+                                <div class="fw-bold {"text-success" if metrics["token_net"] >= 0 else "text-danger"}">
+                                    {"+" if metrics["token_net"] > 0 else ""}{metrics["token_net"]}
+                                </div>
+                            </div>
+                        </div>
+                        
+                        {patterns_html}
+                    </div>
+                </div>
+            </div>
+            """
+            panels.append(panel_html)
+
+        html_content = f"""
+        <div class="row">
+            {"".join(panels)}
+        </div>
+        <div class="text-muted small mt-2">
+            Generated: {datetime.now().strftime("%Y-%m-%d %H:%M:%S UTC")}
+        </div>
+        """
+
+        return HTMLResponse(content=html_content)
+
+    except Exception as exc:
+        logger.error("Failed to render all scorecard panels: %s", exc)
+        return HTMLResponse(
+            content=f"""
+            <div class="alert alert-danger">
+                Error loading scorecards: {str(exc)}
+            </div>
+            """,
+            status_code=200,
+        )

src/dashboard/services/__init__.py

@@ -0,0 +1,17 @@
+"""Dashboard services for business logic."""
+
+from dashboard.services.scorecard_service import (
+    PeriodType,
+    ScorecardSummary,
+    generate_all_scorecards,
+    generate_scorecard,
+    get_tracked_agents,
+)
+
+__all__ = [
+    "PeriodType",
+    "ScorecardSummary",
+    "generate_all_scorecards",
+    "generate_scorecard",
+    "get_tracked_agents",
+]

src/dashboard/services/scorecard_service.py

@@ -0,0 +1,515 @@
+"""Agent scorecard service — track and summarize agent performance.
+
+Generates daily/weekly scorecards showing:
+- Issues touched, PRs opened/merged
+- Tests affected, tokens earned/spent
+- Pattern highlights (merge rate, activity quality)
+"""
+
+from __future__ import annotations
+
+import logging
+from dataclasses import dataclass, field
+from datetime import UTC, datetime, timedelta
+from enum import StrEnum
+from typing import Any
+
+from infrastructure.events.bus import Event, get_event_bus
+
+logger = logging.getLogger(__name__)
+
+# Bot/agent usernames to track
+TRACKED_AGENTS = frozenset({"hermes", "kimi", "manus", "claude", "gemini"})
+
+
+class PeriodType(StrEnum):
+    daily = "daily"
+    weekly = "weekly"
+
+
+@dataclass
+class AgentMetrics:
+    """Raw metrics collected for an agent over a period."""
+
+    agent_id: str
+    issues_touched: set[int] = field(default_factory=set)
+    prs_opened: set[int] = field(default_factory=set)
+    prs_merged: set[int] = field(default_factory=set)
+    tests_affected: set[str] = field(default_factory=set)
+    tokens_earned: int = 0
+    tokens_spent: int = 0
+    commits: int = 0
+    comments: int = 0
+
+    @property
+    def pr_merge_rate(self) -> float:
+        """Calculate PR merge rate (0.0 - 1.0)."""
+        opened = len(self.prs_opened)
+        if opened == 0:
+            return 0.0
+        return len(self.prs_merged) / opened
+
+
+@dataclass
+class ScorecardSummary:
+    """A generated scorecard with narrative summary."""
+
+    agent_id: str
+    period_type: PeriodType
+    period_start: datetime
+    period_end: datetime
+    metrics: AgentMetrics
+    narrative_bullets: list[str] = field(default_factory=list)
+    patterns: list[str] = field(default_factory=list)
+
+    def to_dict(self) -> dict[str, Any]:
+        """Convert scorecard to dictionary for JSON serialization."""
+        return {
+            "agent_id": self.agent_id,
+            "period_type": self.period_type.value,
+            "period_start": self.period_start.isoformat(),
+            "period_end": self.period_end.isoformat(),
+            "metrics": {
+                "issues_touched": len(self.metrics.issues_touched),
+                "prs_opened": len(self.metrics.prs_opened),
+                "prs_merged": len(self.metrics.prs_merged),
+                "pr_merge_rate": round(self.metrics.pr_merge_rate, 2),
+                "tests_affected": len(self.tests_affected),
+                "commits": self.metrics.commits,
+                "comments": self.metrics.comments,
+                "tokens_earned": self.metrics.tokens_earned,
+                "tokens_spent": self.metrics.tokens_spent,
+                "token_net": self.metrics.tokens_earned - self.metrics.tokens_spent,
+            },
+            "narrative_bullets": self.narrative_bullets,
+            "patterns": self.patterns,
+        }
+
+    @property
+    def tests_affected(self) -> set[str]:
+        """Alias for metrics.tests_affected."""
+        return self.metrics.tests_affected
+
+
+def _get_period_bounds(
+    period_type: PeriodType, reference_date: datetime | None = None
+) -> tuple[datetime, datetime]:
+    """Calculate start and end timestamps for a period.
+
+    Args:
+        period_type: daily or weekly
+        reference_date: The date to calculate from (defaults to now)
+
+    Returns:
+        Tuple of (period_start, period_end) in UTC
+    """
+    if reference_date is None:
+        reference_date = datetime.now(UTC)
+
+    # Normalize to start of day
+    end = reference_date.replace(hour=0, minute=0, second=0, microsecond=0)
+
+    if period_type == PeriodType.daily:
+        start = end - timedelta(days=1)
+    else:  # weekly
+        start = end - timedelta(days=7)
+
+    return start, end
+
+
+def _collect_events_for_period(
+    start: datetime, end: datetime, agent_id: str | None = None
+) -> list[Event]:
+    """Collect events from the event bus for a time period.
+
+    Args:
+        start: Period start time
+        end: Period end time
+        agent_id: Optional agent filter
+
+    Returns:
+        List of matching events
+    """
+    bus = get_event_bus()
+    events: list[Event] = []
+
+    # Query persisted events for relevant types
+    event_types = [
+        "gitea.push",
+        "gitea.issue.opened",
+        "gitea.issue.comment",
+        "gitea.pull_request",
+        "agent.task.completed",
+        "test.execution",
+    ]
+
+    for event_type in event_types:
+        try:
+            type_events = bus.replay(
+                event_type=event_type,
+                source=agent_id,
+                limit=1000,
+            )
+            events.extend(type_events)
+        except Exception as exc:
+            logger.debug("Failed to replay events for %s: %s", event_type, exc)
+
+    # Filter by timestamp
+    filtered = []
+    for event in events:
+        try:
+            event_time = datetime.fromisoformat(event.timestamp.replace("Z", "+00:00"))
+            if start <= event_time < end:
+                filtered.append(event)
+        except (ValueError, AttributeError):
+            continue
+
+    return filtered
+
+
+def _extract_actor_from_event(event: Event) -> str:
+    """Extract the actor/agent from an event."""
+    # Try data fields first
+    if "actor" in event.data:
+        return event.data["actor"]
+    if "agent_id" in event.data:
+        return event.data["agent_id"]
+    # Fall back to source
+    return event.source
+
+
+def _is_tracked_agent(actor: str) -> bool:
+    """Check if an actor is a tracked agent."""
+    return actor.lower() in TRACKED_AGENTS
+
+
+def _aggregate_metrics(events: list[Event]) -> dict[str, AgentMetrics]:
+    """Aggregate metrics from events grouped by agent.
+
+    Args:
+        events: List of events to process
+
+    Returns:
+        Dict mapping agent_id -> AgentMetrics
+    """
+    metrics_by_agent: dict[str, AgentMetrics] = {}
+
+    for event in events:
+        actor = _extract_actor_from_event(event)
+
+        # Skip non-agent events unless they explicitly have an agent_id
+        if not _is_tracked_agent(actor) and "agent_id" not in event.data:
+            continue
+
+        if actor not in metrics_by_agent:
+            metrics_by_agent[actor] = AgentMetrics(agent_id=actor)
+
+        metrics = metrics_by_agent[actor]
+
+        # Process based on event type
+        event_type = event.type
+
+        if event_type == "gitea.push":
+            metrics.commits += event.data.get("num_commits", 1)
+
+        elif event_type == "gitea.issue.opened":
+            issue_num = event.data.get("issue_number", 0)
+            if issue_num:
+                metrics.issues_touched.add(issue_num)
+
+        elif event_type == "gitea.issue.comment":
+            metrics.comments += 1
+            issue_num = event.data.get("issue_number", 0)
+            if issue_num:
+                metrics.issues_touched.add(issue_num)
+
+        elif event_type == "gitea.pull_request":
+            pr_num = event.data.get("pr_number", 0)
+            action = event.data.get("action", "")
+            merged = event.data.get("merged", False)
+
+            if pr_num:
+                if action == "opened":
+                    metrics.prs_opened.add(pr_num)
+                elif action == "closed" and merged:
+                    metrics.prs_merged.add(pr_num)
+                    # Also count as touched issue for tracking
+                    metrics.issues_touched.add(pr_num)
+
+        elif event_type == "agent.task.completed":
+            # Extract test files from task data
+            affected = event.data.get("tests_affected", [])
+            for test in affected:
+                metrics.tests_affected.add(test)
+
+            # Token rewards from task completion
+            reward = event.data.get("token_reward", 0)
+            if reward:
+                metrics.tokens_earned += reward
+
+        elif event_type == "test.execution":
+            # Track test files that were executed
+            test_files = event.data.get("test_files", [])
+            for test in test_files:
+                metrics.tests_affected.add(test)
+
+    return metrics_by_agent
+
+
+def _query_token_transactions(agent_id: str, start: datetime, end: datetime) -> tuple[int, int]:
+    """Query the lightning ledger for token transactions.
+
+    Args:
+        agent_id: The agent to query for
+        start: Period start
+        end: Period end
+
+    Returns:
+        Tuple of (tokens_earned, tokens_spent)
+    """
+    try:
+        from lightning.ledger import get_transactions
+
+        transactions = get_transactions(limit=1000)
+
+        earned = 0
+        spent = 0
+
+        for tx in transactions:
+            # Filter by agent if specified
+            if tx.agent_id and tx.agent_id != agent_id:
+                continue
+
+            # Filter by timestamp
+            try:
+                tx_time = datetime.fromisoformat(tx.created_at.replace("Z", "+00:00"))
+                if not (start <= tx_time < end):
+                    continue
+            except (ValueError, AttributeError):
+                continue
+
+            if tx.tx_type.value == "incoming":
+                earned += tx.amount_sats
+            else:
+                spent += tx.amount_sats
+
+        return earned, spent
+
+    except Exception as exc:
+        logger.debug("Failed to query token transactions: %s", exc)
+        return 0, 0
+
+
+def _generate_narrative_bullets(metrics: AgentMetrics, period_type: PeriodType) -> list[str]:
+    """Generate narrative summary bullets for a scorecard.
+
+    Args:
+        metrics: The agent's metrics
+        period_type: daily or weekly
+
+    Returns:
+        List of narrative bullet points
+    """
+    bullets: list[str] = []
+    period_label = "day" if period_type == PeriodType.daily else "week"
+
+    # Activity summary
+    activities = []
+    if metrics.commits:
+        activities.append(f"{metrics.commits} commit{'s' if metrics.commits != 1 else ''}")
+    if len(metrics.prs_opened):
+        activities.append(
+            f"{len(metrics.prs_opened)} PR{'s' if len(metrics.prs_opened) != 1 else ''} opened"
+        )
+    if len(metrics.prs_merged):
+        activities.append(
+            f"{len(metrics.prs_merged)} PR{'s' if len(metrics.prs_merged) != 1 else ''} merged"
+        )
+    if len(metrics.issues_touched):
+        activities.append(
+            f"{len(metrics.issues_touched)} issue{'s' if len(metrics.issues_touched) != 1 else ''} touched"
+        )
+    if metrics.comments:
+        activities.append(f"{metrics.comments} comment{'s' if metrics.comments != 1 else ''}")
+
+    if activities:
+        bullets.append(f"Active across {', '.join(activities)} this {period_label}.")
+
+    # Test activity
+    if len(metrics.tests_affected):
+        bullets.append(
+            f"Affected {len(metrics.tests_affected)} test file{'s' if len(metrics.tests_affected) != 1 else ''}."
+        )
+
+    # Token summary
+    net_tokens = metrics.tokens_earned - metrics.tokens_spent
+    if metrics.tokens_earned or metrics.tokens_spent:
+        if net_tokens > 0:
+            bullets.append(
+                f"Net earned {net_tokens} tokens ({metrics.tokens_earned} earned, {metrics.tokens_spent} spent)."
+            )
+        elif net_tokens < 0:
+            bullets.append(
+                f"Net spent {abs(net_tokens)} tokens ({metrics.tokens_earned} earned, {metrics.tokens_spent} spent)."
+            )
+        else:
+            bullets.append(
+                f"Balanced token flow ({metrics.tokens_earned} earned, {metrics.tokens_spent} spent)."
+            )
+
+    # Handle empty case
+    if not bullets:
+        bullets.append(f"No recorded activity this {period_label}.")
+
+    return bullets
+
+
+def _detect_patterns(metrics: AgentMetrics) -> list[str]:
+    """Detect interesting patterns in agent behavior.
+
+    Args:
+        metrics: The agent's metrics
+
+    Returns:
+        List of pattern descriptions
+    """
+    patterns: list[str] = []
+
+    pr_opened = len(metrics.prs_opened)
+    merge_rate = metrics.pr_merge_rate
+
+    # Merge rate patterns
+    if pr_opened >= 3:
+        if merge_rate >= 0.8:
+            patterns.append("High merge rate with few failures — code quality focus.")
+        elif merge_rate <= 0.3:
+            patterns.append("Lots of noisy PRs, low merge rate — may need review support.")
+
+    # Activity patterns
+    if metrics.commits > 10 and pr_opened == 0:
+        patterns.append("High commit volume without PRs — working directly on main?")
+
+    if len(metrics.issues_touched) > 5 and metrics.comments == 0:
+        patterns.append("Touching many issues but low comment volume — silent worker.")
+
+    if metrics.comments > len(metrics.issues_touched) * 2:
+        patterns.append("Highly communicative — lots of discussion relative to work items.")
+
+    # Token patterns
+    net_tokens = metrics.tokens_earned - metrics.tokens_spent
+    if net_tokens > 100:
+        patterns.append("Strong token accumulation — high value delivery.")
+    elif net_tokens < -50:
+        patterns.append("High token spend — may be in experimentation phase.")
+
+    return patterns
+
+
+def generate_scorecard(
+    agent_id: str,
+    period_type: PeriodType = PeriodType.daily,
+    reference_date: datetime | None = None,
+) -> ScorecardSummary | None:
+    """Generate a scorecard for a single agent.
+
+    Args:
+        agent_id: The agent to generate scorecard for
+        period_type: daily or weekly
+        reference_date: The date to calculate from (defaults to now)
+
+    Returns:
+        ScorecardSummary or None if agent has no activity
+    """
+    start, end = _get_period_bounds(period_type, reference_date)
+
+    # Collect events
+    events = _collect_events_for_period(start, end, agent_id)
+
+    # Aggregate metrics
+    all_metrics = _aggregate_metrics(events)
+
+    # Get metrics for this specific agent
+    if agent_id not in all_metrics:
+        # Create empty metrics - still generate a scorecard
+        metrics = AgentMetrics(agent_id=agent_id)
+    else:
+        metrics = all_metrics[agent_id]
+
+    # Augment with token data from ledger
+    tokens_earned, tokens_spent = _query_token_transactions(agent_id, start, end)
+    metrics.tokens_earned = max(metrics.tokens_earned, tokens_earned)
+    metrics.tokens_spent = max(metrics.tokens_spent, tokens_spent)
+
+    # Generate narrative and patterns
+    narrative = _generate_narrative_bullets(metrics, period_type)
+    patterns = _detect_patterns(metrics)
+
+    return ScorecardSummary(
+        agent_id=agent_id,
+        period_type=period_type,
+        period_start=start,
+        period_end=end,
+        metrics=metrics,
+        narrative_bullets=narrative,
+        patterns=patterns,
+    )
+
+
+def generate_all_scorecards(
+    period_type: PeriodType = PeriodType.daily,
+    reference_date: datetime | None = None,
+) -> list[ScorecardSummary]:
+    """Generate scorecards for all tracked agents.
+
+    Args:
+        period_type: daily or weekly
+        reference_date: The date to calculate from (defaults to now)
+
+    Returns:
+        List of ScorecardSummary for all agents with activity
+    """
+    start, end = _get_period_bounds(period_type, reference_date)
+
+    # Collect all events
+    events = _collect_events_for_period(start, end)
+
+    # Aggregate metrics for all agents
+    all_metrics = _aggregate_metrics(events)
+
+    # Include tracked agents even if no activity
+    for agent_id in TRACKED_AGENTS:
+        if agent_id not in all_metrics:
+            all_metrics[agent_id] = AgentMetrics(agent_id=agent_id)
+
+    # Generate scorecards
+    scorecards: list[ScorecardSummary] = []
+
+    for agent_id, metrics in all_metrics.items():
+        # Augment with token data
+        tokens_earned, tokens_spent = _query_token_transactions(agent_id, start, end)
+        metrics.tokens_earned = max(metrics.tokens_earned, tokens_earned)
+        metrics.tokens_spent = max(metrics.tokens_spent, tokens_spent)
+
+        narrative = _generate_narrative_bullets(metrics, period_type)
+        patterns = _detect_patterns(metrics)
+
+        scorecard = ScorecardSummary(
+            agent_id=agent_id,
+            period_type=period_type,
+            period_start=start,
+            period_end=end,
+            metrics=metrics,
+            narrative_bullets=narrative,
+            patterns=patterns,
+        )
+        scorecards.append(scorecard)
+
+    # Sort by agent_id for consistent ordering
+    scorecards.sort(key=lambda s: s.agent_id)
+
+    return scorecards
+
+
+def get_tracked_agents() -> list[str]:
+    """Return the list of tracked agent IDs."""
+    return sorted(TRACKED_AGENTS)

src/dashboard/templates/base.html

@@ -51,6 +51,7 @@
           <a href="/thinking" class="mc-test-link mc-link-thinking">THINKING</a>
           <a href="/swarm/mission-control" class="mc-test-link">MISSION CTRL</a>
           <a href="/swarm/live" class="mc-test-link">SWARM</a>
+          <a href="/scorecards" class="mc-test-link">SCORECARDS</a>
           <a href="/bugs" class="mc-test-link mc-link-bugs">BUGS</a>
         </div>
       </div>
@@ -123,6 +124,7 @@
     <a href="/thinking" class="mc-mobile-link">THINKING</a>
     <a href="/swarm/mission-control" class="mc-mobile-link">MISSION CONTROL</a>
     <a href="/swarm/live" class="mc-mobile-link">SWARM</a>
+    <a href="/scorecards" class="mc-mobile-link">SCORECARDS</a>
     <a href="/bugs" class="mc-mobile-link">BUGS</a>
     <div class="mc-mobile-section-label">INTELLIGENCE</div>
     <a href="/spark/ui" class="mc-mobile-link">SPARK</a>

src/dashboard/templates/scorecards.html

@@ -0,0 +1,113 @@
+{% extends "base.html" %}
+
+{% block title %}Agent Scorecards - Timmy Time{% endblock %}
+
+{% block extra_styles %}{% endblock %}
+
+{% block content %}
+<div class="container-fluid py-4">
+  <!-- Header -->
+  <div class="d-flex justify-content-between align-items-center mb-4">
+    <div>
+      <h1 class="h3 mb-0">AGENT SCORECARDS</h1>
+      <p class="text-muted small mb-0">Track agent performance across issues, PRs, tests, and tokens</p>
+    </div>
+    <div class="d-flex gap-2">
+      <select id="period-select" class="form-select form-select-sm" style="width: auto;">
+        <option value="daily" selected>Daily</option>
+        <option value="weekly">Weekly</option>
+      </select>
+      <button class="btn btn-sm btn-primary" onclick="refreshScorecards()">
+        <span>Refresh</span>
+      </button>
+    </div>
+  </div>
+
+  <!-- Scorecards Grid -->
+  <div id="scorecards-container"
+       hx-get="/scorecards/all/panels?period=daily"
+       hx-trigger="load"
+       hx-swap="innerHTML">
+    <div class="text-center py-5">
+      <div class="spinner-border text-secondary" role="status">
+        <span class="visually-hidden">Loading...</span>
+      </div>
+      <p class="text-muted mt-2">Loading scorecards...</p>
+    </div>
+  </div>
+
+  <!-- API Reference -->
+  <div class="mt-5 pt-4 border-top">
+    <h5 class="text-muted">API Reference</h5>
+    <div class="row g-3">
+      <div class="col-md-6">
+        <div class="card mc-panel">
+          <div class="card-body">
+            <h6 class="card-title">List Tracked Agents</h6>
+            <code>GET /scorecards/api/agents</code>
+            <p class="small text-muted mt-2">Returns all tracked agent IDs</p>
+          </div>
+        </div>
+      </div>
+      <div class="col-md-6">
+        <div class="card mc-panel">
+          <div class="card-body">
+            <h6 class="card-title">Get All Scorecards</h6>
+            <code>GET /scorecards/api?period=daily|weekly</code>
+            <p class="small text-muted mt-2">Returns scorecards for all agents</p>
+          </div>
+        </div>
+      </div>
+      <div class="col-md-6">
+        <div class="card mc-panel">
+          <div class="card-body">
+            <h6 class="card-title">Get Agent Scorecard</h6>
+            <code>GET /scorecards/api/{agent_id}?period=daily|weekly</code>
+            <p class="small text-muted mt-2">Returns scorecard for a specific agent</p>
+          </div>
+        </div>
+      </div>
+      <div class="col-md-6">
+        <div class="card mc-panel">
+          <div class="card-body">
+            <h6 class="card-title">HTML Panel (HTMX)</h6>
+            <code>GET /scorecards/panel/{agent_id}?period=daily|weekly</code>
+            <p class="small text-muted mt-2">Returns HTML panel for embedding</p>
+          </div>
+        </div>
+      </div>
+    </div>
+  </div>
+</div>
+
+<script>
+// Period selector change handler
+document.getElementById('period-select').addEventListener('change', function() {
+  refreshScorecards();
+});
+
+function refreshScorecards() {
+  var period = document.getElementById('period-select').value;
+  var container = document.getElementById('scorecards-container');
+  
+  // Show loading state
+  container.innerHTML = `
+    <div class="text-center py-5">
+      <div class="spinner-border text-secondary" role="status">
+        <span class="visually-hidden">Loading...</span>
+      </div>
+      <p class="text-muted mt-2">Loading scorecards...</p>
+    </div>
+  `;
+  
+  // Trigger HTMX request
+  htmx.ajax('GET', '/scorecards/all/panels?period=' + period, {
+    target: '#scorecards-container',
+    swap: 'innerHTML'
+  });
+}
+
+// Auto-refresh every 5 minutes
+setInterval(refreshScorecards, 300000);
+</script>
+{% endblock %}

tests/dashboard/test_scorecards.py

@@ -0,0 +1,680 @@
+"""Tests for agent scorecard functionality."""
+
+from datetime import UTC, datetime, timedelta
+from unittest.mock import MagicMock, patch
+
+from dashboard.services.scorecard_service import (
+    AgentMetrics,
+    PeriodType,
+    ScorecardSummary,
+    _aggregate_metrics,
+    _detect_patterns,
+    _extract_actor_from_event,
+    _generate_narrative_bullets,
+    _get_period_bounds,
+    _is_tracked_agent,
+    _query_token_transactions,
+    generate_all_scorecards,
+    generate_scorecard,
+    get_tracked_agents,
+)
+from infrastructure.events.bus import Event
+
+
+class TestPeriodBounds:
+    """Test period boundary calculations."""
+
+    def test_daily_period_bounds(self):
+        """Test daily period returns correct 24-hour window."""
+        reference = datetime(2026, 3, 21, 12, 30, 45, tzinfo=UTC)
+        start, end = _get_period_bounds(PeriodType.daily, reference)
+
+        assert end == datetime(2026, 3, 21, 0, 0, 0, tzinfo=UTC)
+        assert start == datetime(2026, 3, 20, 0, 0, 0, tzinfo=UTC)
+        assert (end - start) == timedelta(days=1)
+
+    def test_weekly_period_bounds(self):
+        """Test weekly period returns correct 7-day window."""
+        reference = datetime(2026, 3, 21, 12, 30, 45, tzinfo=UTC)
+        start, end = _get_period_bounds(PeriodType.weekly, reference)
+
+        assert end == datetime(2026, 3, 21, 0, 0, 0, tzinfo=UTC)
+        assert start == datetime(2026, 3, 14, 0, 0, 0, tzinfo=UTC)
+        assert (end - start) == timedelta(days=7)
+
+    def test_default_reference_date(self):
+        """Test default reference date uses current time."""
+        start, end = _get_period_bounds(PeriodType.daily)
+        now = datetime.now(UTC)
+
+        # End should be start of current day (midnight)
+        expected_end = now.replace(hour=0, minute=0, second=0, microsecond=0)
+        assert end == expected_end
+        # Start should be 24 hours before end
+        assert (end - start) == timedelta(days=1)
+
+
+class TestTrackedAgents:
+    """Test agent tracking functions."""
+
+    def test_get_tracked_agents(self):
+        """Test get_tracked_agents returns sorted list."""
+        agents = get_tracked_agents()
+        assert isinstance(agents, list)
+        assert "kimi" in agents
+        assert "claude" in agents
+        assert "gemini" in agents
+        assert "hermes" in agents
+        assert "manus" in agents
+        assert agents == sorted(agents)
+
+    def test_is_tracked_agent_true(self):
+        """Test _is_tracked_agent returns True for tracked agents."""
+        assert _is_tracked_agent("kimi") is True
+        assert _is_tracked_agent("KIMI") is True  # case insensitive
+        assert _is_tracked_agent("claude") is True
+        assert _is_tracked_agent("hermes") is True
+
+    def test_is_tracked_agent_false(self):
+        """Test _is_tracked_agent returns False for untracked agents."""
+        assert _is_tracked_agent("unknown") is False
+        assert _is_tracked_agent("rockachopa") is False
+        assert _is_tracked_agent("") is False
+
+
+class TestExtractActor:
+    """Test actor extraction from events."""
+
+    def test_extract_from_actor_field(self):
+        """Test extraction from data.actor field."""
+        event = Event(type="test", source="system", data={"actor": "kimi"})
+        assert _extract_actor_from_event(event) == "kimi"
+
+    def test_extract_from_agent_id_field(self):
+        """Test extraction from data.agent_id field."""
+        event = Event(type="test", source="system", data={"agent_id": "claude"})
+        assert _extract_actor_from_event(event) == "claude"
+
+    def test_extract_from_source_fallback(self):
+        """Test fallback to event.source."""
+        event = Event(type="test", source="gemini", data={})
+        assert _extract_actor_from_event(event) == "gemini"
+
+    def test_actor_priority_over_agent_id(self):
+        """Test actor field takes priority over agent_id."""
+        event = Event(type="test", source="system", data={"actor": "kimi", "agent_id": "claude"})
+        assert _extract_actor_from_event(event) == "kimi"
+
+
+class TestAggregateMetrics:
+    """Test metrics aggregation from events."""
+
+    def test_empty_events(self):
+        """Test aggregation with no events returns empty dict."""
+        result = _aggregate_metrics([])
+        assert result == {}
+
+    def test_push_event_aggregation(self):
+        """Test push events aggregate commits correctly."""
+        events = [
+            Event(type="gitea.push", source="gitea", data={"actor": "kimi", "num_commits": 3}),
+            Event(type="gitea.push", source="gitea", data={"actor": "kimi", "num_commits": 2}),
+        ]
+        result = _aggregate_metrics(events)
+
+        assert "kimi" in result
+        assert result["kimi"].commits == 5
+
+    def test_issue_opened_aggregation(self):
+        """Test issue opened events aggregate correctly."""
+        events = [
+            Event(
+                type="gitea.issue.opened",
+                source="gitea",
+                data={"actor": "claude", "issue_number": 100},
+            ),
+            Event(
+                type="gitea.issue.opened",
+                source="gitea",
+                data={"actor": "claude", "issue_number": 101},
+            ),
+        ]
+        result = _aggregate_metrics(events)
+
+        assert "claude" in result
+        assert len(result["claude"].issues_touched) == 2
+        assert 100 in result["claude"].issues_touched
+        assert 101 in result["claude"].issues_touched
+
+    def test_comment_aggregation(self):
+        """Test comment events aggregate correctly."""
+        events = [
+            Event(
+                type="gitea.issue.comment",
+                source="gitea",
+                data={"actor": "gemini", "issue_number": 100},
+            ),
+            Event(
+                type="gitea.issue.comment",
+                source="gitea",
+                data={"actor": "gemini", "issue_number": 101},
+            ),
+        ]
+        result = _aggregate_metrics(events)
+
+        assert "gemini" in result
+        assert result["gemini"].comments == 2
+        assert len(result["gemini"].issues_touched) == 2  # Comments touch issues too
+
+    def test_pr_events_aggregation(self):
+        """Test PR open and merge events aggregate correctly."""
+        events = [
+            Event(
+                type="gitea.pull_request",
+                source="gitea",
+                data={"actor": "kimi", "pr_number": 50, "action": "opened"},
+            ),
+            Event(
+                type="gitea.pull_request",
+                source="gitea",
+                data={"actor": "kimi", "pr_number": 50, "action": "closed", "merged": True},
+            ),
+            Event(
+                type="gitea.pull_request",
+                source="gitea",
+                data={"actor": "kimi", "pr_number": 51, "action": "opened"},
+            ),
+        ]
+        result = _aggregate_metrics(events)
+
+        assert "kimi" in result
+        assert len(result["kimi"].prs_opened) == 2
+        assert len(result["kimi"].prs_merged) == 1
+        assert 50 in result["kimi"].prs_merged
+
+    def test_untracked_agent_filtered(self):
+        """Test events from untracked agents are filtered out."""
+        events = [
+            Event(
+                type="gitea.push", source="gitea", data={"actor": "rockachopa", "num_commits": 5}
+            ),
+        ]
+        result = _aggregate_metrics(events)
+
+        assert "rockachopa" not in result
+
+    def test_task_completion_aggregation(self):
+        """Test task completion events aggregate test files."""
+        events = [
+            Event(
+                type="agent.task.completed",
+                source="gitea",
+                data={
+                    "agent_id": "kimi",
+                    "tests_affected": ["test_foo.py", "test_bar.py"],
+                    "token_reward": 10,
+                },
+            ),
+        ]
+        result = _aggregate_metrics(events)
+
+        assert "kimi" in result
+        assert len(result["kimi"].tests_affected) == 2
+        assert "test_foo.py" in result["kimi"].tests_affected
+        assert result["kimi"].tokens_earned == 10
+
+
+class TestAgentMetrics:
+    """Test AgentMetrics class."""
+
+    def test_merge_rate_zero_prs(self):
+        """Test merge rate is 0 when no PRs opened."""
+        metrics = AgentMetrics(agent_id="kimi")
+        assert metrics.pr_merge_rate == 0.0
+
+    def test_merge_rate_perfect(self):
+        """Test 100% merge rate calculation."""
+        metrics = AgentMetrics(agent_id="kimi", prs_opened={1, 2, 3}, prs_merged={1, 2, 3})
+        assert metrics.pr_merge_rate == 1.0
+
+    def test_merge_rate_partial(self):
+        """Test partial merge rate calculation."""
+        metrics = AgentMetrics(agent_id="kimi", prs_opened={1, 2, 3, 4}, prs_merged={1, 2})
+        assert metrics.pr_merge_rate == 0.5
+
+
+class TestDetectPatterns:
+    """Test pattern detection logic."""
+
+    def test_high_merge_rate_pattern(self):
+        """Test detection of high merge rate pattern."""
+        metrics = AgentMetrics(
+            agent_id="kimi",
+            prs_opened={1, 2, 3, 4, 5},
+            prs_merged={1, 2, 3, 4},  # 80% merge rate
+        )
+        patterns = _detect_patterns(metrics)
+
+        assert any("High merge rate" in p for p in patterns)
+
+    def test_low_merge_rate_pattern(self):
+        """Test detection of low merge rate pattern."""
+        metrics = AgentMetrics(
+            agent_id="kimi",
+            prs_opened={1, 2, 3, 4, 5},
+            prs_merged={1},  # 20% merge rate
+        )
+        patterns = _detect_patterns(metrics)
+
+        assert any("low merge rate" in p for p in patterns)
+
+    def test_high_commits_no_prs_pattern(self):
+        """Test detection of direct-to-main commits pattern."""
+        metrics = AgentMetrics(
+            agent_id="kimi",
+            commits=15,
+            prs_opened=set(),
+        )
+        patterns = _detect_patterns(metrics)
+
+        assert any("High commit volume without PRs" in p for p in patterns)
+
+    def test_silent_worker_pattern(self):
+        """Test detection of silent worker pattern."""
+        metrics = AgentMetrics(
+            agent_id="kimi",
+            issues_touched={1, 2, 3, 4, 5, 6},
+            comments=0,
+        )
+        patterns = _detect_patterns(metrics)
+
+        assert any("silent worker" in p for p in patterns)
+
+    def test_communicative_pattern(self):
+        """Test detection of highly communicative pattern."""
+        metrics = AgentMetrics(
+            agent_id="kimi",
+            issues_touched={1, 2},  # 2 issues
+            comments=10,  # 5x comments per issue
+        )
+        patterns = _detect_patterns(metrics)
+
+        assert any("Highly communicative" in p for p in patterns)
+
+    def test_token_accumulation_pattern(self):
+        """Test detection of token accumulation pattern."""
+        metrics = AgentMetrics(
+            agent_id="kimi",
+            tokens_earned=150,
+            tokens_spent=10,
+        )
+        patterns = _detect_patterns(metrics)
+
+        assert any("Strong token accumulation" in p for p in patterns)
+
+    def test_token_spend_pattern(self):
+        """Test detection of high token spend pattern."""
+        metrics = AgentMetrics(
+            agent_id="kimi",
+            tokens_earned=10,
+            tokens_spent=100,
+        )
+        patterns = _detect_patterns(metrics)
+
+        assert any("High token spend" in p for p in patterns)
+
+
+class TestGenerateNarrative:
+    """Test narrative bullet generation."""
+
+    def test_empty_metrics_narrative(self):
+        """Test narrative for empty metrics mentions no activity."""
+        metrics = AgentMetrics(agent_id="kimi")
+        bullets = _generate_narrative_bullets(metrics, PeriodType.daily)
+
+        assert len(bullets) == 1
+        assert "No recorded activity" in bullets[0]
+
+    def test_activity_summary_narrative(self):
+        """Test narrative includes activity summary."""
+        metrics = AgentMetrics(
+            agent_id="kimi",
+            commits=5,
+            prs_opened={1, 2},
+            prs_merged={1},
+        )
+        bullets = _generate_narrative_bullets(metrics, PeriodType.daily)
+
+        activity_bullet = next((b for b in bullets if "Active across" in b), None)
+        assert activity_bullet is not None
+        assert "5 commits" in activity_bullet
+        assert "2 PRs opened" in activity_bullet
+        assert "1 PR merged" in activity_bullet
+
+    def test_tests_affected_narrative(self):
+        """Test narrative includes tests affected."""
+        metrics = AgentMetrics(
+            agent_id="kimi",
+            tests_affected={"test_a.py", "test_b.py"},
+        )
+        bullets = _generate_narrative_bullets(metrics, PeriodType.daily)
+
+        assert any("2 test files" in b for b in bullets)
+
+    def test_tokens_earned_narrative(self):
+        """Test narrative includes token earnings."""
+        metrics = AgentMetrics(
+            agent_id="kimi",
+            tokens_earned=100,
+            tokens_spent=20,
+        )
+        bullets = _generate_narrative_bullets(metrics, PeriodType.daily)
+
+        assert any("Net earned 80 tokens" in b for b in bullets)
+
+    def test_tokens_spent_narrative(self):
+        """Test narrative includes token spending."""
+        metrics = AgentMetrics(
+            agent_id="kimi",
+            tokens_earned=20,
+            tokens_spent=100,
+        )
+        bullets = _generate_narrative_bullets(metrics, PeriodType.daily)
+
+        assert any("Net spent 80 tokens" in b for b in bullets)
+
+    def test_balanced_tokens_narrative(self):
+        """Test narrative for balanced token flow."""
+        metrics = AgentMetrics(
+            agent_id="kimi",
+            tokens_earned=100,
+            tokens_spent=100,
+        )
+        bullets = _generate_narrative_bullets(metrics, PeriodType.daily)
+
+        assert any("Balanced token flow" in b for b in bullets)
+
+
+class TestScorecardSummary:
+    """Test ScorecardSummary dataclass."""
+
+    def test_to_dict_structure(self):
+        """Test to_dict returns expected structure."""
+        metrics = AgentMetrics(
+            agent_id="kimi",
+            issues_touched={1, 2},
+            prs_opened={10, 11},
+            prs_merged={10},
+            tokens_earned=100,
+            tokens_spent=20,
+        )
+        summary = ScorecardSummary(
+            agent_id="kimi",
+            period_type=PeriodType.daily,
+            period_start=datetime.now(UTC),
+            period_end=datetime.now(UTC),
+            metrics=metrics,
+            narrative_bullets=["Test bullet"],
+            patterns=["Test pattern"],
+        )
+        data = summary.to_dict()
+
+        assert data["agent_id"] == "kimi"
+        assert data["period_type"] == "daily"
+        assert "metrics" in data
+        assert data["metrics"]["issues_touched"] == 2
+        assert data["metrics"]["prs_opened"] == 2
+        assert data["metrics"]["prs_merged"] == 1
+        assert data["metrics"]["pr_merge_rate"] == 0.5
+        assert data["metrics"]["tokens_earned"] == 100
+        assert data["metrics"]["token_net"] == 80
+        assert data["narrative_bullets"] == ["Test bullet"]
+        assert data["patterns"] == ["Test pattern"]
+
+
+class TestQueryTokenTransactions:
+    """Test token transaction querying."""
+
+    def test_empty_ledger(self):
+        """Test empty ledger returns zero values."""
+        with patch("lightning.ledger.get_transactions", return_value=[]):
+            earned, spent = _query_token_transactions("kimi", datetime.now(UTC), datetime.now(UTC))
+            assert earned == 0
+            assert spent == 0
+
+    def test_ledger_with_transactions(self):
+        """Test ledger aggregation of transactions."""
+        now = datetime.now(UTC)
+        mock_tx = [
+            MagicMock(
+                agent_id="kimi",
+                tx_type=MagicMock(value="incoming"),
+                amount_sats=100,
+                created_at=now.isoformat(),
+            ),
+            MagicMock(
+                agent_id="kimi",
+                tx_type=MagicMock(value="outgoing"),
+                amount_sats=30,
+                created_at=now.isoformat(),
+            ),
+        ]
+        with patch("lightning.ledger.get_transactions", return_value=mock_tx):
+            earned, spent = _query_token_transactions(
+                "kimi", now - timedelta(hours=1), now + timedelta(hours=1)
+            )
+            assert earned == 100
+            assert spent == 30
+
+    def test_ledger_filters_by_agent(self):
+        """Test ledger filters transactions by agent_id."""
+        now = datetime.now(UTC)
+        mock_tx = [
+            MagicMock(
+                agent_id="claude",
+                tx_type=MagicMock(value="incoming"),
+                amount_sats=100,
+                created_at=now.isoformat(),
+            ),
+        ]
+        with patch("lightning.ledger.get_transactions", return_value=mock_tx):
+            earned, spent = _query_token_transactions(
+                "kimi", now - timedelta(hours=1), now + timedelta(hours=1)
+            )
+            assert earned == 0  # Transaction was for claude, not kimi
+
+    def test_ledger_filters_by_time(self):
+        """Test ledger filters transactions by time range."""
+        now = datetime.now(UTC)
+        old_time = now - timedelta(days=2)
+        mock_tx = [
+            MagicMock(
+                agent_id="kimi",
+                tx_type=MagicMock(value="incoming"),
+                amount_sats=100,
+                created_at=old_time.isoformat(),
+            ),
+        ]
+        with patch("lightning.ledger.get_transactions", return_value=mock_tx):
+            # Query for today only
+            earned, spent = _query_token_transactions(
+                "kimi", now - timedelta(hours=1), now + timedelta(hours=1)
+            )
+            assert earned == 0  # Transaction was 2 days ago
+
+
+class TestGenerateScorecard:
+    """Test scorecard generation."""
+
+    def test_generate_scorecard_no_activity(self):
+        """Test scorecard generation for agent with no activity."""
+        with patch(
+            "dashboard.services.scorecard_service._collect_events_for_period", return_value=[]
+        ):
+            with patch(
+                "dashboard.services.scorecard_service._query_token_transactions",
+                return_value=(0, 0),
+            ):
+                scorecard = generate_scorecard("kimi", PeriodType.daily)
+
+        assert scorecard is not None
+        assert scorecard.agent_id == "kimi"
+        assert scorecard.period_type == PeriodType.daily
+        assert len(scorecard.narrative_bullets) == 1
+        assert "No recorded activity" in scorecard.narrative_bullets[0]
+
+    def test_generate_scorecard_with_activity(self):
+        """Test scorecard generation includes activity."""
+        events = [
+            Event(type="gitea.push", source="gitea", data={"actor": "kimi", "num_commits": 5}),
+        ]
+        with patch(
+            "dashboard.services.scorecard_service._collect_events_for_period", return_value=events
+        ):
+            with patch(
+                "dashboard.services.scorecard_service._query_token_transactions",
+                return_value=(100, 20),
+            ):
+                scorecard = generate_scorecard("kimi", PeriodType.daily)
+
+        assert scorecard is not None
+        assert scorecard.metrics.commits == 5
+        assert scorecard.metrics.tokens_earned == 100
+        assert scorecard.metrics.tokens_spent == 20
+
+
+class TestGenerateAllScorecards:
+    """Test generating scorecards for all agents."""
+
+    def test_generates_for_all_tracked_agents(self):
+        """Test all tracked agents get scorecards even with no activity."""
+        with patch(
+            "dashboard.services.scorecard_service._collect_events_for_period", return_value=[]
+        ):
+            with patch(
+                "dashboard.services.scorecard_service._query_token_transactions",
+                return_value=(0, 0),
+            ):
+                scorecards = generate_all_scorecards(PeriodType.daily)
+
+        agent_ids = {s.agent_id for s in scorecards}
+        expected = {"kimi", "claude", "gemini", "hermes", "manus"}
+        assert expected.issubset(agent_ids)
+
+    def test_scorecards_sorted(self):
+        """Test scorecards are sorted by agent_id."""
+        with patch(
+            "dashboard.services.scorecard_service._collect_events_for_period", return_value=[]
+        ):
+            with patch(
+                "dashboard.services.scorecard_service._query_token_transactions",
+                return_value=(0, 0),
+            ):
+                scorecards = generate_all_scorecards(PeriodType.daily)
+
+        agent_ids = [s.agent_id for s in scorecards]
+        assert agent_ids == sorted(agent_ids)
+
+
+class TestScorecardRoutes:
+    """Test scorecard API routes."""
+
+    def test_list_agents_endpoint(self, client):
+        """Test GET /scorecards/api/agents returns tracked agents."""
+        response = client.get("/scorecards/api/agents")
+        assert response.status_code == 200
+        data = response.json()
+        assert "agents" in data
+        assert "kimi" in data["agents"]
+        assert "claude" in data["agents"]
+
+    def test_get_scorecard_endpoint(self, client):
+        """Test GET /scorecards/api/{agent_id} returns scorecard."""
+        with patch("dashboard.routes.scorecards.generate_scorecard") as mock_generate:
+            mock_generate.return_value = ScorecardSummary(
+                agent_id="kimi",
+                period_type=PeriodType.daily,
+                period_start=datetime.now(UTC),
+                period_end=datetime.now(UTC),
+                metrics=AgentMetrics(agent_id="kimi"),
+                narrative_bullets=["Test bullet"],
+                patterns=[],
+            )
+            response = client.get("/scorecards/api/kimi?period=daily")
+
+        assert response.status_code == 200
+        data = response.json()
+        assert data["agent_id"] == "kimi"
+        assert data["period_type"] == "daily"
+
+    def test_get_scorecard_invalid_period(self, client):
+        """Test GET with invalid period returns 400."""
+        response = client.get("/scorecards/api/kimi?period=invalid")
+        assert response.status_code == 400
+        assert "error" in response.json()
+
+    def test_get_all_scorecards_endpoint(self, client):
+        """Test GET /scorecards/api returns all scorecards."""
+        with patch("dashboard.routes.scorecards.generate_all_scorecards") as mock_generate:
+            mock_generate.return_value = [
+                ScorecardSummary(
+                    agent_id="kimi",
+                    period_type=PeriodType.daily,
+                    period_start=datetime.now(UTC),
+                    period_end=datetime.now(UTC),
+                    metrics=AgentMetrics(agent_id="kimi"),
+                    narrative_bullets=[],
+                    patterns=[],
+                ),
+            ]
+            response = client.get("/scorecards/api?period=daily")
+
+        assert response.status_code == 200
+        data = response.json()
+        assert data["period"] == "daily"
+        assert "scorecards" in data
+        assert len(data["scorecards"]) == 1
+
+    def test_scorecards_page_renders(self, client):
+        """Test GET /scorecards returns HTML page."""
+        response = client.get("/scorecards")
+        assert response.status_code == 200
+        assert "text/html" in response.headers.get("content-type", "")
+        assert "AGENT SCORECARDS" in response.text
+
+    def test_scorecard_panel_renders(self, client):
+        """Test GET /scorecards/panel/{agent_id} returns HTML."""
+        with patch("dashboard.routes.scorecards.generate_scorecard") as mock_generate:
+            mock_generate.return_value = ScorecardSummary(
+                agent_id="kimi",
+                period_type=PeriodType.daily,
+                period_start=datetime.now(UTC),
+                period_end=datetime.now(UTC),
+                metrics=AgentMetrics(agent_id="kimi", commits=5),
+                narrative_bullets=["Active across 5 commits this day."],
+                patterns=["High activity"],
+            )
+            response = client.get("/scorecards/panel/kimi?period=daily")
+
+        assert response.status_code == 200
+        assert "text/html" in response.headers.get("content-type", "")
+        assert "Kimi" in response.text
+
+    def test_all_panels_renders(self, client):
+        """Test GET /scorecards/all/panels returns HTML with all panels."""
+        with patch("dashboard.routes.scorecards.generate_all_scorecards") as mock_generate:
+            mock_generate.return_value = [
+                ScorecardSummary(
+                    agent_id="kimi",
+                    period_type=PeriodType.daily,
+                    period_start=datetime.now(UTC),
+                    period_end=datetime.now(UTC),
+                    metrics=AgentMetrics(agent_id="kimi"),
+                    narrative_bullets=[],
+                    patterns=[],
+                ),
+            ]
+            response = client.get("/scorecards/all/panels?period=daily")
+
+        assert response.status_code == 200
+        assert "text/html" in response.headers.get("content-type", "")

tests/timmy_automations/test_weekly_narrative.py

@@ -1,343 +0,0 @@
-"""Tests for weekly_narrative.py script."""
-
-from __future__ import annotations
-
-import json
-import sys
-from datetime import UTC, datetime, timedelta
-from pathlib import Path
-from unittest.mock import MagicMock, patch
-
-# Add timmy_automations to path for imports
-sys.path.insert(
-    0, str(Path(__file__).resolve().parent.parent.parent / "timmy_automations" / "daily_run")
-)
-
-import weekly_narrative as wn
-
-
-class TestParseTimestamp:
-    """Test timestamp parsing."""
-
-    def test_parse_iso_with_z(self):
-        """Parse ISO timestamp with Z suffix."""
-        result = wn.parse_ts("2026-03-21T12:00:00Z")
-        assert result is not None
-        assert result.year == 2026
-        assert result.month == 3
-        assert result.day == 21
-
-    def test_parse_iso_with_offset(self):
-        """Parse ISO timestamp with timezone offset."""
-        result = wn.parse_ts("2026-03-21T12:00:00+00:00")
-        assert result is not None
-        assert result.year == 2026
-
-    def test_parse_empty_string(self):
-        """Empty string returns None."""
-        result = wn.parse_ts("")
-        assert result is None
-
-    def test_parse_invalid_string(self):
-        """Invalid string returns None."""
-        result = wn.parse_ts("not-a-timestamp")
-        assert result is None
-
-
-class TestCollectCyclesData:
-    """Test cycle data collection."""
-
-    def test_no_cycles_file(self, tmp_path):
-        """Handle missing cycles file gracefully."""
-        with patch.object(wn, "REPO_ROOT", tmp_path):
-            since = datetime.now(UTC) - timedelta(days=7)
-            result = wn.collect_cycles_data(since)
-            assert result["total"] == 0
-            assert result["successes"] == 0
-            assert result["failures"] == 0
-
-    def test_collect_recent_cycles(self, tmp_path):
-        """Collect cycles within lookback period."""
-        retro_dir = tmp_path / ".loop" / "retro"
-        retro_dir.mkdir(parents=True)
-
-        now = datetime.now(UTC)
-        cycles = [
-            {"timestamp": now.isoformat(), "success": True, "cycle": 1},
-            {"timestamp": now.isoformat(), "success": False, "cycle": 2},
-            {"timestamp": (now - timedelta(days=10)).isoformat(), "success": True, "cycle": 3},
-        ]
-
-        with open(retro_dir / "cycles.jsonl", "w") as f:
-            for c in cycles:
-                f.write(json.dumps(c) + "\n")
-
-        with patch.object(wn, "REPO_ROOT", tmp_path):
-            since = now - timedelta(days=7)
-            result = wn.collect_cycles_data(since)
-            assert result["total"] == 2  # Only recent 2
-            assert result["successes"] == 1
-            assert result["failures"] == 1
-
-
-class TestExtractThemes:
-    """Test theme extraction from issues."""
-
-    def test_extract_layer_labels(self):
-        """Extract layer labels from issues."""
-        issues = [
-            {"labels": [{"name": "layer:triage"}, {"name": "bug"}]},
-            {"labels": [{"name": "layer:tests"}, {"name": "bug"}]},
-            {"labels": [{"name": "layer:triage"}, {"name": "feature"}]},
-        ]
-
-        result = wn.extract_themes(issues)
-
-        assert len(result["layers"]) == 2
-        layer_names = {layer["name"] for layer in result["layers"]}
-        assert "triage" in layer_names
-        assert "tests" in layer_names
-
-    def test_extract_type_labels(self):
-        """Extract type labels (bug/feature/etc)."""
-        issues = [
-            {"labels": [{"name": "bug"}]},
-            {"labels": [{"name": "feature"}]},
-            {"labels": [{"name": "bug"}]},
-        ]
-
-        result = wn.extract_themes(issues)
-
-        type_names = {t_type["name"] for t_type in result["types"]}
-        assert "bug" in type_names
-        assert "feature" in type_names
-
-    def test_empty_issues(self):
-        """Handle empty issue list."""
-        result = wn.extract_themes([])
-        assert result["layers"] == []
-        assert result["types"] == []
-        assert result["top_labels"] == []
-
-
-class TestExtractAgentContributions:
-    """Test agent contribution extraction."""
-
-    def test_extract_assignees(self):
-        """Extract assignee counts."""
-        issues = [
-            {"assignee": {"login": "kimi"}},
-            {"assignee": {"login": "hermes"}},
-            {"assignee": {"login": "kimi"}},
-        ]
-
-        result = wn.extract_agent_contributions(issues, [], [])
-
-        assert len(result["active_assignees"]) == 2
-        assignee_logins = {a["login"] for a in result["active_assignees"]}  # noqa: E741
-        assert "kimi" in assignee_logins
-        assert "hermes" in assignee_logins
-
-    def test_extract_pr_authors(self):
-        """Extract PR author counts."""
-        prs = [
-            {"user": {"login": "kimi"}},
-            {"user": {"login": "claude"}},
-            {"user": {"login": "kimi"}},
-        ]
-
-        result = wn.extract_agent_contributions([], prs, [])
-
-        assert len(result["pr_authors"]) == 2
-
-    def test_kimi_mentions_in_cycles(self):
-        """Count Kimi mentions in cycle notes."""
-        cycles = [
-            {"notes": "Kimi did great work", "reason": ""},
-            {"notes": "", "reason": "Kimi timeout"},
-            {"notes": "All good", "reason": ""},
-        ]
-
-        result = wn.extract_agent_contributions([], [], cycles)
-        assert result["kimi_mentioned_cycles"] == 2
-
-
-class TestAnalyzeTestShifts:
-    """Test test pattern analysis."""
-
-    def test_no_cycles(self):
-        """Handle no cycle data."""
-        result = wn.analyze_test_shifts([])
-        assert "note" in result
-
-    def test_test_metrics(self):
-        """Calculate test metrics from cycles."""
-        cycles = [
-            {"tests_passed": 100, "tests_added": 5},
-            {"tests_passed": 150, "tests_added": 3},
-        ]
-
-        result = wn.analyze_test_shifts(cycles)
-
-        assert result["total_tests_passed"] == 250
-        assert result["total_tests_added"] == 8
-
-
-class TestGenerateVibeSummary:
-    """Test vibe summary generation."""
-
-    def test_productive_vibe(self):
-        """High success rate and activity = productive vibe."""
-        cycles_data = {"success_rate": 0.95, "successes": 10, "failures": 1}
-        issues_data = {"closed_count": 5}
-
-        result = wn.generate_vibe_summary(cycles_data, issues_data, {}, {"layers": []}, {}, {}, {})
-
-        assert result["overall"] == "productive"
-        assert "strong week" in result["description"].lower()
-
-    def test_struggling_vibe(self):
-        """More failures than successes = struggling vibe."""
-        cycles_data = {"success_rate": 0.3, "successes": 3, "failures": 7}
-        issues_data = {"closed_count": 0}
-
-        result = wn.generate_vibe_summary(cycles_data, issues_data, {}, {"layers": []}, {}, {}, {})
-
-        assert result["overall"] == "struggling"
-
-    def test_quiet_vibe(self):
-        """Low activity = quiet vibe."""
-        cycles_data = {"success_rate": 0.0, "successes": 0, "failures": 0}
-        issues_data = {"closed_count": 0}
-
-        result = wn.generate_vibe_summary(cycles_data, issues_data, {}, {"layers": []}, {}, {}, {})
-
-        assert result["overall"] == "quiet"
-
-
-class TestGenerateMarkdownSummary:
-    """Test markdown summary generation."""
-
-    def test_includes_header(self):
-        """Markdown includes header."""
-        narrative = {
-            "period": {"start": "2026-03-14T00:00:00", "end": "2026-03-21T00:00:00"},
-            "vibe": {"overall": "productive", "description": "Good week"},
-            "activity": {
-                "cycles": {"total": 10, "successes": 9, "failures": 1},
-                "issues": {"closed": 5, "opened": 3},
-                "pull_requests": {"merged": 4, "opened": 2},
-            },
-        }
-
-        result = wn.generate_markdown_summary(narrative)
-
-        assert "# Weekly Narrative Summary" in result
-        assert "productive" in result.lower()
-        assert "10 total" in result or "10" in result
-
-    def test_includes_focus_areas(self):
-        """Markdown includes focus areas when present."""
-        narrative = {
-            "period": {"start": "2026-03-14", "end": "2026-03-21"},
-            "vibe": {
-                "overall": "productive",
-                "description": "Good week",
-                "focus_areas": ["triage (5 items)", "tests (3 items)"],
-            },
-            "activity": {
-                "cycles": {"total": 0, "successes": 0, "failures": 0},
-                "issues": {"closed": 0, "opened": 0},
-                "pull_requests": {"merged": 0, "opened": 0},
-            },
-        }
-
-        result = wn.generate_markdown_summary(narrative)
-
-        assert "Focus Areas" in result
-        assert "triage" in result
-
-
-class TestConfigLoading:
-    """Test configuration loading."""
-
-    def test_default_config(self, tmp_path):
-        """Default config when manifest missing."""
-        with patch.object(wn, "CONFIG_PATH", tmp_path / "nonexistent.json"):
-            config = wn.load_automation_config()
-            assert config["lookback_days"] == 7
-            assert config["enabled"] is True
-
-    def test_environment_override(self, tmp_path):
-        """Environment variables override config."""
-        with patch.dict("os.environ", {"TIMMY_WEEKLY_NARRATIVE_ENABLED": "false"}):
-            with patch.object(wn, "CONFIG_PATH", tmp_path / "nonexistent.json"):
-                config = wn.load_automation_config()
-                assert config["enabled"] is False
-
-
-class TestMain:
-    """Test main function."""
-
-    def test_disabled_exits_cleanly(self, tmp_path):
-        """When disabled and no --force, exits cleanly."""
-        with patch.object(wn, "REPO_ROOT", tmp_path):
-            with patch.object(wn, "load_automation_config", return_value={"enabled": False}):
-                with patch("sys.argv", ["weekly_narrative"]):
-                    result = wn.main()
-                    assert result == 0
-
-    def test_force_runs_when_disabled(self, tmp_path):
-        """--force runs even when disabled."""
-        # Setup minimal structure
-        (tmp_path / ".loop" / "retro").mkdir(parents=True)
-
-        with patch.object(wn, "REPO_ROOT", tmp_path):
-            with patch.object(
-                wn,
-                "load_automation_config",
-                return_value={
-                    "enabled": False,
-                    "lookback_days": 7,
-                    "gitea_api": "http://localhost:3000/api/v1",
-                    "repo_slug": "test/repo",
-                    "token_file": "~/.hermes/gitea_token",
-                },
-            ):
-                with patch.object(wn, "GiteaClient") as mock_client:
-                    mock_instance = MagicMock()
-                    mock_instance.is_available.return_value = False
-                    mock_client.return_value = mock_instance
-
-                    with patch("sys.argv", ["weekly_narrative", "--force"]):
-                        result = wn.main()
-                        # Should complete without error even though Gitea unavailable
-                        assert result == 0
-
-
-class TestGiteaClient:
-    """Test Gitea API client."""
-
-    def test_is_available_when_unavailable(self):
-        """is_available returns False when server down."""
-        config = {"gitea_api": "http://localhost:99999", "repo_slug": "test/repo"}
-        client = wn.GiteaClient(config, None)
-
-        # Should return False without raising
-        assert client.is_available() is False
-
-    def test_headers_with_token(self):
-        """Headers include Authorization when token provided."""
-        config = {"gitea_api": "http://localhost:3000", "repo_slug": "test/repo"}
-        client = wn.GiteaClient(config, "test-token")
-
-        headers = client._headers()
-        assert headers["Authorization"] == "token test-token"
-
-    def test_headers_without_token(self):
-        """Headers don't include Authorization when no token."""
-        config = {"gitea_api": "http://localhost:3000", "repo_slug": "test/repo"}
-        client = wn.GiteaClient(config, None)
-
-        headers = client._headers()
-        assert "Authorization" not in headers

timmy_automations/config/automations.json

@@ -228,27 +228,6 @@
         "max_items": 5
       },
       "outputs": []
-    },
-    {
-      "id": "weekly_narrative",
-      "name": "Weekly Narrative Summary",
-      "description": "Generates a human-readable weekly summary of work themes, agent contributions, and token economy shifts",
-      "script": "timmy_automations/daily_run/weekly_narrative.py",
-      "category": "daily_run",
-      "enabled": true,
-      "trigger": "scheduled",
-      "schedule": "weekly",
-      "executable": "python3",
-      "config": {
-        "lookback_days": 7,
-        "output_file": ".loop/weekly_narrative.json",
-        "gitea_api": "http://localhost:3000/api/v1",
-        "repo_slug": "rockachopa/Timmy-time-dashboard"
-      },
-      "outputs": [
-        ".loop/weekly_narrative.json",
-        ".loop/weekly_narrative.md"
-      ]
     }
   ]
 }

timmy_automations/config/daily_run.json

@@ -17,10 +17,6 @@
     "manual": {
       "description": "Run on-demand only",
       "automations": ["agent_workspace", "kimi_bootstrap", "kimi_resume", "backfill_retro"]
-    },
-    "weekly": {
-      "description": "Run once per week (Sundays)",
-      "automations": ["weekly_narrative"]
     }
   },
   "triggers": {

timmy_automations/daily_run/weekly_narrative.py

@@ -1,745 +0,0 @@
-#!/usr/bin/env python3
-"""Weekly narrative summary generator — human-readable loop analysis.
-
-Analyzes the past week's activity across the development loop to produce
-a narrative summary of:
-- What changed (themes, areas of focus)
-- How agents and Timmy contributed
-- Any shifts in tests, triage, or token economy
-
-The output is designed to be skimmable — a quick read that gives context
-on the week's progress without drowning in metrics.
-
-Run:  python3 timmy_automations/daily_run/weekly_narrative.py [--json]
-Env:  See timmy_automations/config/automations.json for configuration
-
-Refs: #719
-"""
-
-from __future__ import annotations
-
-import argparse
-import json
-import os
-import sys
-from collections import Counter
-from datetime import UTC, datetime, timedelta
-from pathlib import Path
-from typing import Any
-from urllib.error import HTTPError, URLError
-from urllib.request import Request, urlopen
-
-# ── Configuration ─────────────────────────────────────────────────────────
-
-REPO_ROOT = Path(__file__).resolve().parent.parent.parent
-CONFIG_PATH = Path(__file__).parent.parent / "config" / "automations.json"
-
-DEFAULT_CONFIG = {
-    "gitea_api": "http://localhost:3000/api/v1",
-    "repo_slug": "rockachopa/Timmy-time-dashboard",
-    "token_file": "~/.hermes/gitea_token",
-    "lookback_days": 7,
-    "output_file": ".loop/weekly_narrative.json",
-    "enabled": True,
-}
-
-
-# ── Data Loading ───────────────────────────────────────────────────────────
-
-
-def load_automation_config() -> dict:
-    """Load configuration for weekly_narrative from automations manifest."""
-    config = DEFAULT_CONFIG.copy()
-    if CONFIG_PATH.exists():
-        try:
-            manifest = json.loads(CONFIG_PATH.read_text())
-            for auto in manifest.get("automations", []):
-                if auto.get("id") == "weekly_narrative":
-                    config.update(auto.get("config", {}))
-                    config["enabled"] = auto.get("enabled", True)
-                    break
-        except (json.JSONDecodeError, OSError) as exc:
-            print(f"[weekly_narrative] Warning: Could not load config: {exc}", file=sys.stderr)
-
-    # Environment variable overrides
-    if os.environ.get("TIMMY_GITEA_API"):
-        config["gitea_api"] = os.environ.get("TIMMY_GITEA_API")
-    if os.environ.get("TIMMY_REPO_SLUG"):
-        config["repo_slug"] = os.environ.get("TIMMY_REPO_SLUG")
-    if os.environ.get("TIMMY_GITEA_TOKEN"):
-        config["token"] = os.environ.get("TIMMY_GITEA_TOKEN")
-    if os.environ.get("TIMMY_WEEKLY_NARRATIVE_ENABLED"):
-        config["enabled"] = os.environ.get("TIMMY_WEEKLY_NARRATIVE_ENABLED", "true").lower() == "true"
-
-    return config
-
-
-def get_token(config: dict) -> str | None:
-    """Get Gitea token from environment or file."""
-    if "token" in config:
-        return config["token"]
-
-    token_file = Path(config["token_file"]).expanduser()
-    if token_file.exists():
-        return token_file.read_text().strip()
-
-    return None
-
-
-def load_jsonl(path: Path) -> list[dict]:
-    """Load a JSONL file, skipping bad lines."""
-    if not path.exists():
-        return []
-    entries = []
-    for line in path.read_text().strip().splitlines():
-        try:
-            entries.append(json.loads(line))
-        except (json.JSONDecodeError, ValueError):
-            continue
-    return entries
-
-
-def parse_ts(ts_str: str) -> datetime | None:
-    """Parse an ISO timestamp, tolerating missing tz."""
-    if not ts_str:
-        return None
-    try:
-        dt = datetime.fromisoformat(ts_str.replace("Z", "+00:00"))
-        if dt.tzinfo is None:
-            dt = dt.replace(tzinfo=UTC)
-        return dt
-    except (ValueError, TypeError):
-        return None
-
-
-# ── Gitea API Client ───────────────────────────────────────────────────────
-
-
-class GiteaClient:
-    """Simple Gitea API client with graceful degradation."""
-
-    def __init__(self, config: dict, token: str | None):
-        self.api_base = config["gitea_api"].rstrip("/")
-        self.repo_slug = config["repo_slug"]
-        self.token = token
-        self._available: bool | None = None
-
-    def _headers(self) -> dict:
-        headers = {"Accept": "application/json"}
-        if self.token:
-            headers["Authorization"] = f"token {self.token}"
-        return headers
-
-    def _api_url(self, path: str) -> str:
-        return f"{self.api_base}/repos/{self.repo_slug}/{path}"
-
-    def is_available(self) -> bool:
-        """Check if Gitea API is reachable."""
-        if self._available is not None:
-            return self._available
-
-        try:
-            req = Request(
-                f"{self.api_base}/version",
-                headers=self._headers(),
-                method="GET",
-            )
-            with urlopen(req, timeout=5) as resp:
-                self._available = resp.status == 200
-                return self._available
-        except (HTTPError, URLError, TimeoutError):
-            self._available = False
-            return False
-
-    def get_paginated(self, path: str, params: dict | None = None) -> list:
-        """Fetch all pages of a paginated endpoint."""
-        all_items = []
-        page = 1
-        limit = 50
-
-        while True:
-            url = self._api_url(path)
-            query_parts = [f"limit={limit}", f"page={page}"]
-            if params:
-                for key, val in params.items():
-                    query_parts.append(f"{key}={val}")
-            url = f"{url}?{'&'.join(query_parts)}"
-
-            req = Request(url, headers=self._headers(), method="GET")
-            with urlopen(req, timeout=15) as resp:
-                batch = json.loads(resp.read())
-
-            if not batch:
-                break
-
-            all_items.extend(batch)
-            if len(batch) < limit:
-                break
-            page += 1
-
-        return all_items
-
-
-# ── Data Collection ────────────────────────────────────────────────────────
-
-
-def collect_cycles_data(since: datetime) -> dict:
-    """Load cycle retrospective data from the lookback period."""
-    cycles_file = REPO_ROOT / ".loop" / "retro" / "cycles.jsonl"
-    if not cycles_file.exists():
-        return {"cycles": [], "total": 0, "successes": 0, "failures": 0}
-
-    entries = load_jsonl(cycles_file)
-    recent = []
-    for e in entries:
-        ts = parse_ts(e.get("timestamp", ""))
-        if ts and ts >= since:
-            recent.append(e)
-
-    successes = [e for e in recent if e.get("success")]
-    failures = [e for e in recent if not e.get("success")]
-
-    return {
-        "cycles": recent,
-        "total": len(recent),
-        "successes": len(successes),
-        "failures": len(failures),
-        "success_rate": round(len(successes) / len(recent), 2) if recent else 0,
-    }
-
-
-def collect_issues_data(client: GiteaClient, since: datetime) -> dict:
-    """Collect issue activity from Gitea."""
-    if not client.is_available():
-        return {"error": "Gitea unavailable", "issues": [], "closed": [], "opened": []}
-
-    try:
-        issues = client.get_paginated("issues", {"state": "all", "sort": "updated", "limit": 100})
-    except (HTTPError, URLError) as exc:
-        return {"error": str(exc), "issues": [], "closed": [], "opened": []}
-
-    touched = []
-    closed = []
-    opened = []
-
-    for issue in issues:
-        updated_at = issue.get("updated_at", "")
-        created_at = issue.get("created_at", "")
-
-        updated = parse_ts(updated_at)
-        created = parse_ts(created_at)
-
-        if updated and updated >= since:
-            touched.append(issue)
-
-        if issue.get("state") == "closed":
-            closed_at = issue.get("closed_at", "")
-            closed_dt = parse_ts(closed_at)
-            if closed_dt and closed_dt >= since:
-                closed.append(issue)
-        elif created and created >= since:
-            opened.append(issue)
-
-    return {
-        "issues": touched,
-        "closed": closed,
-        "opened": opened,
-        "touched_count": len(touched),
-        "closed_count": len(closed),
-        "opened_count": len(opened),
-    }
-
-
-def collect_prs_data(client: GiteaClient, since: datetime) -> dict:
-    """Collect PR activity from Gitea."""
-    if not client.is_available():
-        return {"error": "Gitea unavailable", "prs": [], "merged": [], "opened": []}
-
-    try:
-        prs = client.get_paginated("pulls", {"state": "all", "sort": "updated", "limit": 100})
-    except (HTTPError, URLError) as exc:
-        return {"error": str(exc), "prs": [], "merged": [], "opened": []}
-
-    touched = []
-    merged = []
-    opened = []
-
-    for pr in prs:
-        updated_at = pr.get("updated_at", "")
-        created_at = pr.get("created_at", "")
-        merged_at = pr.get("merged_at", "")
-
-        updated = parse_ts(updated_at)
-        created = parse_ts(created_at)
-        merged_dt = parse_ts(merged_at) if merged_at else None
-
-        if updated and updated >= since:
-            touched.append(pr)
-
-        if pr.get("merged") and merged_dt and merged_dt >= since:
-            merged.append(pr)
-        elif created and created >= since:
-            opened.append(pr)
-
-    return {
-        "prs": touched,
-        "merged": merged,
-        "opened": opened,
-        "touched_count": len(touched),
-        "merged_count": len(merged),
-        "opened_count": len(opened),
-    }
-
-
-def collect_triage_data(since: datetime) -> dict:
-    """Load triage and introspection data."""
-    triage_file = REPO_ROOT / ".loop" / "retro" / "triage.jsonl"
-    insights_file = REPO_ROOT / ".loop" / "retro" / "insights.json"
-
-    triage_entries = load_jsonl(triage_file)
-    recent_triage = [
-        e for e in triage_entries
-        if parse_ts(e.get("timestamp", "")) and parse_ts(e.get("timestamp", "")) >= since
-    ]
-
-    insights = {}
-    if insights_file.exists():
-        try:
-            insights = json.loads(insights_file.read_text())
-        except (json.JSONDecodeError, OSError):
-            pass
-
-    return {
-        "triage_runs": len(recent_triage),
-        "triage_entries": recent_triage,
-        "latest_insights": insights,
-    }
-
-
-def collect_token_data(since: datetime) -> dict:
-    """Load token economy data from the lightning ledger."""
-    # The ledger is in-memory but we can look for any persisted data
-    # For now, return placeholder that will be filled by the ledger module
-    return {
-        "note": "Token economy data is ephemeral — check dashboard for live metrics",
-        "balance_sats": 0,  # Placeholder
-        "transactions_week": 0,
-    }
-
-
-# ── Analysis Functions ─────────────────────────────────────────────────────
-
-
-def extract_themes(issues: list[dict]) -> list[dict]:
-    """Extract themes from issue labels."""
-    label_counts = Counter()
-    layer_counts = Counter()
-    type_counts = Counter()
-
-    for issue in issues:
-        for label in issue.get("labels", []):
-            name = label.get("name", "")
-            label_counts[name] += 1
-
-            if name.startswith("layer:"):
-                layer_counts[name.replace("layer:", "")] += 1
-            if name in ("bug", "feature", "refactor", "docs", "test", "chore"):
-                type_counts[name] += 1
-
-    # Top themes (labels excluding layer prefixes)
-    themes = [
-        {"name": name, "count": count}
-        for name, count in label_counts.most_common(10)
-        if not name.startswith(("layer:", "size:"))
-    ]
-
-    # Layers
-    layers = [
-        {"name": name, "count": count}
-        for name, count in layer_counts.most_common()
-    ]
-
-    # Types
-    types = [
-        {"name": name, "count": count}
-        for name, count in type_counts.most_common()
-    ]
-
-    return {
-        "top_labels": themes,
-        "layers": layers,
-        "types": types,
-    }
-
-
-def extract_agent_contributions(issues: list[dict], prs: list[dict], cycles: list[dict]) -> dict:
-    """Extract agent contribution patterns."""
-    # Count by assignee
-    assignee_counts = Counter()
-    for issue in issues:
-        assignee = issue.get("assignee")
-        if assignee and isinstance(assignee, dict):
-            assignee_counts[assignee.get("login", "unknown")] += 1
-
-    # Count PR authors
-    pr_authors = Counter()
-    for pr in prs:
-        user = pr.get("user")
-        if user and isinstance(user, dict):
-            pr_authors[user.get("login", "unknown")] += 1
-
-    # Check for Kimi mentions in cycle notes
-    kimi_mentions = sum(
-        1 for c in cycles
-        if "kimi" in c.get("notes", "").lower() or "kimi" in c.get("reason", "").lower()
-    )
-
-    return {
-        "active_assignees": [
-            {"login": login, "issues_count": count}
-            for login, count in assignee_counts.most_common()
-        ],
-        "pr_authors": [
-            {"login": login, "prs_count": count}
-            for login, count in pr_authors.most_common()
-        ],
-        "kimi_mentioned_cycles": kimi_mentions,
-    }
-
-
-def analyze_test_shifts(cycles: list[dict]) -> dict:
-    """Analyze shifts in test patterns."""
-    if not cycles:
-        return {"note": "No cycle data available"}
-
-    total_tests_passed = sum(c.get("tests_passed", 0) for c in cycles)
-    total_tests_added = sum(c.get("tests_added", 0) for c in cycles)
-    avg_tests_per_cycle = round(total_tests_passed / len(cycles), 1) if cycles else 0
-
-    # Look for test-related issues
-    test_focused = [
-        c for c in cycles
-        if c.get("type") == "test" or "test" in c.get("notes", "").lower()
-    ]
-
-    return {
-        "total_tests_passed": total_tests_passed,
-        "total_tests_added": total_tests_added,
-        "avg_tests_per_cycle": avg_tests_per_cycle,
-        "test_focused_cycles": len(test_focused),
-    }
-
-
-def analyze_triage_shifts(triage_data: dict) -> dict:
-    """Analyze shifts in triage patterns."""
-    insights = triage_data.get("latest_insights", {})
-    recommendations = insights.get("recommendations", [])
-
-    high_priority_recs = [
-        r for r in recommendations
-        if r.get("severity") == "high"
-    ]
-
-    return {
-        "triage_runs": triage_data.get("triage_runs", 0),
-        "insights_generated": insights.get("generated_at") is not None,
-        "high_priority_recommendations": len(high_priority_recs),
-        "recent_recommendations": recommendations[:3] if recommendations else [],
-    }
-
-
-def generate_vibe_summary(
-    cycles_data: dict,
-    issues_data: dict,
-    prs_data: dict,
-    themes: dict,
-    agent_contrib: dict,
-    test_shifts: dict,
-    triage_shifts: dict,
-) -> dict:
-    """Generate the human-readable 'vibe' summary."""
-    # Determine overall vibe
-    success_rate = cycles_data.get("success_rate", 0)
-    failures = cycles_data.get("failures", 0)
-    closed_count = issues_data.get("closed_count", 0)
-    merged_count = prs_data.get("merged_count", 0)
-
-    if success_rate >= 0.9 and closed_count > 0:
-        vibe = "productive"
-        vibe_description = "A strong week with solid delivery and healthy success rates."
-    elif success_rate >= 0.7:
-        vibe = "steady"
-        vibe_description = "Steady progress with some bumps. Things are moving forward."
-    elif failures > cycles_data.get("successes", 0):
-        vibe = "struggling"
-        vibe_description = "A challenging week with more failures than successes. Time to regroup."
-    else:
-        vibe = "quiet"
-        vibe_description = "A lighter week with limited activity."
-
-    # Focus areas from themes
-    focus_areas = []
-    for layer in themes.get("layers", [])[:3]:
-        focus_areas.append(f"{layer['name']} ({layer['count']} items)")
-
-    # Agent activity summary
-    agent_summary = ""
-    active_assignees = agent_contrib.get("active_assignees", [])
-    if active_assignees:
-        top_agent = active_assignees[0]
-        agent_summary = f"{top_agent['login']} led with {top_agent['issues_count']} assigned issues."
-
-    # Notable events
-    notable = []
-    if merged_count > 5:
-        notable.append(f"{merged_count} PRs merged — high integration velocity")
-    if triage_shifts.get("high_priority_recommendations", 0) > 0:
-        notable.append("High-priority recommendations from loop introspection")
-    if test_shifts.get("test_focused_cycles", 0) > 3:
-        notable.append("Strong test coverage focus")
-    if not notable:
-        notable.append("Regular development flow")
-
-    return {
-        "overall": vibe,
-        "description": vibe_description,
-        "focus_areas": focus_areas,
-        "agent_summary": agent_summary,
-        "notable_events": notable,
-    }
-
-
-# ── Narrative Generation ───────────────────────────────────────────────────
-
-
-def generate_narrative(
-    cycles_data: dict,
-    issues_data: dict,
-    prs_data: dict,
-    triage_data: dict,
-    themes: dict,
-    agent_contrib: dict,
-    test_shifts: dict,
-    triage_shifts: dict,
-    token_data: dict,
-    since: datetime,
-    until: datetime,
-) -> dict:
-    """Generate the complete weekly narrative."""
-    vibe = generate_vibe_summary(
-        cycles_data, issues_data, prs_data, themes, agent_contrib, test_shifts, triage_shifts
-    )
-
-    return {
-        "generated_at": datetime.now(UTC).isoformat(),
-        "period": {
-            "start": since.isoformat(),
-            "end": until.isoformat(),
-            "days": 7,
-        },
-        "vibe": vibe,
-        "activity": {
-            "cycles": {
-                "total": cycles_data.get("total", 0),
-                "successes": cycles_data.get("successes", 0),
-                "failures": cycles_data.get("failures", 0),
-                "success_rate": cycles_data.get("success_rate", 0),
-            },
-            "issues": {
-                "touched": issues_data.get("touched_count", 0),
-                "closed": issues_data.get("closed_count", 0),
-                "opened": issues_data.get("opened_count", 0),
-            },
-            "pull_requests": {
-                "touched": prs_data.get("touched_count", 0),
-                "merged": prs_data.get("merged_count", 0),
-                "opened": prs_data.get("opened_count", 0),
-            },
-        },
-        "themes": themes,
-        "agents": agent_contrib,
-        "test_health": test_shifts,
-        "triage_health": triage_shifts,
-        "token_economy": token_data,
-    }
-
-
-def generate_markdown_summary(narrative: dict) -> str:
-    """Generate a human-readable markdown summary."""
-    vibe = narrative.get("vibe", {})
-    activity = narrative.get("activity", {})
-    cycles = activity.get("cycles", {})
-    issues = activity.get("issues", {})
-    prs = activity.get("pull_requests", {})
-
-    lines = [
-        "# Weekly Narrative Summary",
-        "",
-        f"**Period:** {narrative['period']['start'][:10]} to {narrative['period']['end'][:10]}",
-        f"**Vibe:** {vibe.get('overall', 'unknown').title()}",
-        "",
-        f"{vibe.get('description', '')}",
-        "",
-        "## Activity Highlights",
-        "",
-        f"- **Development Cycles:** {cycles.get('total', 0)} total ({cycles.get('successes', 0)} success, {cycles.get('failures', 0)} failure)",
-        f"- **Issues:** {issues.get('closed', 0)} closed, {issues.get('opened', 0)} opened",
-        f"- **Pull Requests:** {prs.get('merged', 0)} merged, {prs.get('opened', 0)} opened",
-        "",
-    ]
-
-    # Focus areas
-    focus = vibe.get("focus_areas", [])
-    if focus:
-        lines.append("## Focus Areas")
-        lines.append("")
-        for area in focus:
-            lines.append(f"- {area}")
-        lines.append("")
-
-    # Agent contributions
-    agent_summary = vibe.get("agent_summary", "")
-    if agent_summary:
-        lines.append("## Agent Activity")
-        lines.append("")
-        lines.append(agent_summary)
-        lines.append("")
-
-    # Notable events
-    notable = vibe.get("notable_events", [])
-    if notable:
-        lines.append("## Notable Events")
-        lines.append("")
-        for event in notable:
-            lines.append(f"- {event}")
-        lines.append("")
-
-    # Triage health
-    triage = narrative.get("triage_health", {})
-    if triage.get("high_priority_recommendations", 0) > 0:
-        lines.append("## Triage Notes")
-        lines.append("")
-        lines.append(f"⚠️ {triage['high_priority_recommendations']} high-priority recommendation(s) from loop introspection.")
-        lines.append("")
-        for rec in triage.get("recent_recommendations", [])[:2]:
-            lines.append(f"- **{rec.get('category', 'general')}:** {rec.get('finding', '')}")
-        lines.append("")
-
-    return "\n".join(lines)
-
-
-# ── Main ───────────────────────────────────────────────────────────────────
-
-
-def parse_args() -> argparse.Namespace:
-    p = argparse.ArgumentParser(
-        description="Generate weekly narrative summary of work and vibes",
-    )
-    p.add_argument(
-        "--json", "-j",
-        action="store_true",
-        help="Output as JSON instead of markdown",
-    )
-    p.add_argument(
-        "--output", "-o",
-        type=str,
-        default=None,
-        help="Output file path (default from config)",
-    )
-    p.add_argument(
-        "--days",
-        type=int,
-        default=None,
-        help="Override lookback days (default 7)",
-    )
-    p.add_argument(
-        "--force",
-        action="store_true",
-        help="Run even if disabled in config",
-    )
-    return p.parse_args()
-
-
-def main() -> int:
-    args = parse_args()
-    config = load_automation_config()
-
-    # Check if enabled
-    if not config.get("enabled", True) and not args.force:
-        print("[weekly_narrative] Skipped — weekly narrative is disabled in config")
-        print("[weekly_narrative] Use --force to run anyway")
-        return 0
-
-    # Determine lookback period
-    days = args.days if args.days is not None else config.get("lookback_days", 7)
-    until = datetime.now(UTC)
-    since = until - timedelta(days=days)
-
-    print(f"[weekly_narrative] Generating narrative for the past {days} days...")
-
-    # Setup Gitea client
-    token = get_token(config)
-    client = GiteaClient(config, token)
-
-    if not client.is_available():
-        print("[weekly_narrative] Warning: Gitea API unavailable — will use local data only")
-
-    # Collect data
-    cycles_data = collect_cycles_data(since)
-    issues_data = collect_issues_data(client, since)
-    prs_data = collect_prs_data(client, since)
-    triage_data = collect_triage_data(since)
-    token_data = collect_token_data(since)
-
-    # Analyze
-    themes = extract_themes(issues_data.get("issues", []))
-    agent_contrib = extract_agent_contributions(
-        issues_data.get("issues", []),
-        prs_data.get("prs", []),
-        cycles_data.get("cycles", []),
-    )
-    test_shifts = analyze_test_shifts(cycles_data.get("cycles", []))
-    triage_shifts = analyze_triage_shifts(triage_data)
-
-    # Generate narrative
-    narrative = generate_narrative(
-        cycles_data,
-        issues_data,
-        prs_data,
-        triage_data,
-        themes,
-        agent_contrib,
-        test_shifts,
-        triage_shifts,
-        token_data,
-        since,
-        until,
-    )
-
-    # Determine output path
-    output_path = args.output or config.get("output_file", ".loop/weekly_narrative.json")
-    output_file = REPO_ROOT / output_path
-    output_file.parent.mkdir(parents=True, exist_ok=True)
-
-    # Write JSON output
-    output_file.write_text(json.dumps(narrative, indent=2) + "\n")
-
-    # Write markdown summary alongside JSON
-    md_output_file = output_file.with_suffix(".md")
-    md_output_file.write_text(generate_markdown_summary(narrative))
-
-    # Print output
-    if args.json:
-        print(json.dumps(narrative, indent=2))
-    else:
-        print()
-        print(generate_markdown_summary(narrative))
-
-    print(f"\n[weekly_narrative] Written to: {output_file}")
-    print(f"[weekly_narrative] Markdown summary: {md_output_file}")
-
-    return 0
-
-
-if __name__ == "__main__":
-    sys.exit(main())