chore: release v1.10.0

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

.gitignore

@@ -68,7 +68,10 @@ dmypy.json
 .ruff_cache/
 
 # Logs
-logs/
+logs/*
+!logs/traces/
+logs/traces/*
+!logs/traces/viewer.html
 *.log
 
 # Database

CHANGELOG.md

@@ -7,6 +7,52 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [1.10.0] - 2025-12-22
+
+### Added
+
+#### Lightweight Request Tracing
+- **JSON-based tracing system** for local development debugging
+  - Captures full request flow through multi-agent architecture
+  - `Trace` and `Span` dataclasses with automatic timing and nesting
+  - ContextVar-based propagation for async-safe tracing
+  - `trace_span` async context manager for clean instrumentation
+  - Traces written to `logs/traces/{trace_id}.json`
+  - Enabled via `DEBUG=true` environment variable
+- **Trace Viewer UI** (`logs/traces/viewer.html`)
+  - Standalone HTML viewer with timeline visualization
+  - Filter by status, search by request text
+  - Expandable span details with prompts and responses
+- **Tracing REST API** (`/traces`)
+  - `GET /traces` - Serve trace viewer UI
+  - `GET /traces/list` - List available traces with filtering
+  - `GET /traces/{trace_id}` - Retrieve specific trace JSON
+  - Only available when `DEBUG=true`
+- **Full pipeline instrumentation**
+  - Router-level trace start/end with context management
+  - Steward analysis spans in preprocessing
+  - Tatlock orchestrate/synthesize spans
+  - Expert delegation spans (librarian/biographer/housekeeper)
+  - Tool-level spans extracted from PydanticAI messages
+
+### Changed
+
+- **Replaced Redis benchmarks with file-based tracing** - Simpler, more useful for debugging
+- **Context management moved to service layer** - Router simplified, context set in response service
+- **Server binds to all interfaces** - `wakeup.sh` now uses `0.0.0.0` for network access
+
+### Removed
+
+- **Redis benchmark system** (`src/core/benchmarks.py`)
+  - `ENABLE_BENCHMARKS` config setting
+  - `REDIS_BENCHMARK_DB` config setting
+  - `redis_url` property (kept `redis_memory_url`)
+  - Benchmark recording in Steward service and tool tracking
+
+### Fixed
+
+- **Librarian fabrication prevention** - Added explicit instructions to never invent data when tools fail or sources are unavailable
+
 ## [1.9.0] - 2025-12-18
 
 ### Changed
@@ -779,7 +825,17 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - CORS middleware
 - Exception handlers (OpenAI-compatible error format)
 
-[Unreleased]: https://git.schweitz.net/jpmschweitzer/tatlock/compare/v1.6.0...main
+[Unreleased]: https://git.schweitz.net/jpmschweitzer/tatlock/compare/v1.10.0...main
+[1.10.0]: https://git.schweitz.net/jpmschweitzer/tatlock/compare/v1.9.0...v1.10.0
+[1.9.0]: https://git.schweitz.net/jpmschweitzer/tatlock/compare/v1.8.6...v1.9.0
+[1.8.6]: https://git.schweitz.net/jpmschweitzer/tatlock/compare/v1.8.5...v1.8.6
+[1.8.5]: https://git.schweitz.net/jpmschweitzer/tatlock/compare/v1.8.4...v1.8.5
+[1.8.4]: https://git.schweitz.net/jpmschweitzer/tatlock/compare/v1.8.3...v1.8.4
+[1.8.3]: https://git.schweitz.net/jpmschweitzer/tatlock/compare/v1.8.2...v1.8.3
+[1.8.2]: https://git.schweitz.net/jpmschweitzer/tatlock/compare/v1.8.1...v1.8.2
+[1.8.1]: https://git.schweitz.net/jpmschweitzer/tatlock/compare/v1.8.0...v1.8.1
+[1.8.0]: https://git.schweitz.net/jpmschweitzer/tatlock/compare/v1.7.0...v1.8.0
+[1.7.0]: https://git.schweitz.net/jpmschweitzer/tatlock/compare/v1.6.0...v1.7.0
 [1.6.0]: https://git.schweitz.net/jpmschweitzer/tatlock/compare/v1.5.0...v1.6.0
 [1.5.0]: https://git.schweitz.net/jpmschweitzer/tatlock/compare/v1.4.0...v1.5.0
 [1.4.0]: https://git.schweitz.net/jpmschweitzer/tatlock/compare/v1.3.3...v1.4.0

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "tatlock"
-version = "1.9.0"
+version = "1.10.0"
 description = "OpenAI-compatible API with Ollama backend"
 requires-python = ">=3.12"
 dependencies = []

src/agents/delegation.py

@@ -13,6 +13,7 @@ from enum import Enum
 from typing import AsyncGenerator, Callable, Optional, Any
 
 from src.core.logging_config import get_logger
+from src.core.tracing import trace_span, SpanType
 
 logger = get_logger(__name__)
 
@@ -239,6 +240,15 @@ async def delegate_to_librarian(
         has_context=bool(context),
     )
 
+    async with trace_span(
+        "delegate_to_librarian",
+        SpanType.EXPERT,
+        metadata={
+            "expert": "librarian",
+            "task_preview": task[:100],
+            "has_context": bool(context),
+        },
+    ) as span:
         try:
             # Use run() not run_stream() - avoids Ollama bug
             output = await run_librarian(task=task, context=context)
@@ -249,6 +259,13 @@ async def delegate_to_librarian(
                 output_length=len(output),
             )
 
+            if span:
+                span.metadata["success"] = True
+                span.metadata["output_length"] = len(output)
+                span.details["task"] = task
+                span.details["context"] = context[:500] if context else None
+                span.details["result_preview"] = output[:1000]
+
             return DelegationResult(
                 expert_name="librarian",
                 task=task,
@@ -264,6 +281,10 @@ async def delegate_to_librarian(
                 exc_info=True,
             )
 
+            if span:
+                span.metadata["success"] = False
+                span.details["error"] = str(e)
+
             return DelegationResult(
                 expert_name="librarian",
                 task=task,
@@ -317,6 +338,15 @@ async def delegate_to_biographer(
         has_context=bool(context),
     )
 
+    async with trace_span(
+        "delegate_to_biographer",
+        SpanType.EXPERT,
+        metadata={
+            "expert": "biographer",
+            "task_preview": task[:100],
+            "has_context": bool(context),
+        },
+    ) as span:
         try:
             # Use run() not run_stream() - avoids Ollama bug
             output = await run_biographer(task=task, context=context)
@@ -327,6 +357,13 @@ async def delegate_to_biographer(
                 output_length=len(output),
             )
 
+            if span:
+                span.metadata["success"] = True
+                span.metadata["output_length"] = len(output)
+                span.details["task"] = task
+                span.details["context"] = context[:500] if context else None
+                span.details["result_preview"] = output[:1000]
+
             return DelegationResult(
                 expert_name="biographer",
                 task=task,
@@ -342,6 +379,10 @@ async def delegate_to_biographer(
                 exc_info=True,
             )
 
+            if span:
+                span.metadata["success"] = False
+                span.details["error"] = str(e)
+
             return DelegationResult(
                 expert_name="biographer",
                 task=task,
@@ -394,6 +435,15 @@ async def delegate_to_housekeeper(
         has_context=bool(context),
     )
 
+    async with trace_span(
+        "delegate_to_housekeeper",
+        SpanType.EXPERT,
+        metadata={
+            "expert": "housekeeper",
+            "task_preview": task[:100],
+            "has_context": bool(context),
+        },
+    ) as span:
         try:
             # Use run() not run_stream() - avoids Ollama bug
             output = await run_housekeeper(task=task, context=context)
@@ -404,6 +454,13 @@ async def delegate_to_housekeeper(
                 output_length=len(output),
             )
 
+            if span:
+                span.metadata["success"] = True
+                span.metadata["output_length"] = len(output)
+                span.details["task"] = task
+                span.details["context"] = context[:500] if context else None
+                span.details["result_preview"] = output[:1000]
+
             return DelegationResult(
                 expert_name="housekeeper",
                 task=task,
@@ -419,6 +476,10 @@ async def delegate_to_housekeeper(
                 exc_info=True,
             )
 
+            if span:
+                span.metadata["success"] = False
+                span.details["error"] = str(e)
+
             return DelegationResult(
                 expert_name="housekeeper",
                 task=task,

src/agents/librarian/agent.py

@@ -114,6 +114,14 @@ Your responses are returned to Tatlock (the butler) who will synthesize them int
 - Note any gaps in available information
 - Be concise but thorough - Tatlock will format the final response
 - Structure your findings clearly so they can be easily integrated with other responses
+
+## CRITICAL: Never Fabricate Information
+If a tool fails or you cannot access a data source:
+- Say "I was unable to retrieve [information type]" - be specific about what failed
+- Do NOT provide placeholder, template, or made-up data
+- Do NOT say "Here's what I would have said" or "Here's a sample response"
+- Do NOT invent specific numbers, dates, or facts when the actual data is unavailable
+- It is better to return no information than to return fabricated information
 """
 
 # Lazy initialization to avoid connection issues during imports

src/agents/steward/service.py

@@ -1,8 +1,8 @@
 """
 Steward service layer.
 
-Provides high-level interface for request analysis with logging,
-benchmarking, and error handling.
+Provides high-level interface for request analysis with logging
+and error handling.
 
 Parses plain text recommendations into structured data.
 Includes memory pre-fetch for user context injection.
@@ -10,7 +10,6 @@ Includes memory pre-fetch for user context injection.
 import re
 from typing import Any, Optional
 
-from src.core.benchmarks import PerformanceBenchmark, get_benchmark_store
 from src.core.household_registry import get_household_registry
 from src.core.logging_config import get_logger, log_operation
 from src.core.memory_service import memory_service
@@ -285,8 +284,7 @@ async def analyze_request(
     This is the main entry point for Steward analysis. It:
     1. Calls the Steward agent with full conversation history
     2. Logs the operation with timing
-    3. Records performance benchmarks to Redis
-    4. Returns structured recommendations
+    3. Returns structured recommendations
 
     Args:
         user_request: The current user message to analyze
@@ -365,23 +363,6 @@ async def analyze_request(
                 reasoning=analysis_text[:200],  # First 200 chars
             )
 
-            # Record performance benchmark
-            if log_ctx.get("duration_seconds"):
-                benchmark = PerformanceBenchmark(
-                    operation="steward_analysis",
-                    duration_seconds=log_ctx["duration_seconds"],
-                    success=True,
-                    recommendation_count=len(recommendation.recommended_capabilities),
-                    confidence=None,  # Could add confidence scoring in future
-                    conversation_id=conversation_id,
-                    metadata={
-                        "complexity": recommendation.estimated_complexity,
-                        "has_context": recommendation.conversation_context.has_previous_context,
-                        "missing_capabilities": recommendation.missing_capabilities is not None,
-                    },
-                )
-                await get_benchmark_store().record(benchmark)
-
             return recommendation
 
         except Exception as e:

src/agents/tatlock.py

@@ -20,6 +20,11 @@ from src.agents.tatlock_core.tools import (
 )
 from src.core.config import config
 from src.core.logging_config import get_logger
+from src.core.tracing import (
+    start_span, end_span, get_current_span,
+    add_tool_spans_from_messages,
+    SpanType, SpanStatus,
+)
 
 logger = get_logger(__name__)
 
@@ -433,7 +438,7 @@ class TatlockAgent(AgentInterface):
             steward_note: Note from Steward (prepended to request, invisible to user)
             scoped_tools: List of tool definitions from household registry
             message_history: Conversation history in PydanticAI format
-            tool_tracker: Optional tool call tracker for benchmarking
+            tool_tracker: Optional tool call tracker for analysis
 
         Returns:
             str: Tatlock's response text
@@ -627,7 +632,7 @@ class TatlockAgent(AgentInterface):
             steward_note: Note from Steward (invisible to user)
             scoped_tools: List of tool definitions from household registry
             message_history: Conversation history
-            tool_tracker: Optional tool call tracker for benchmarking
+            tool_tracker: Optional tool call tracker for analysis
 
         Returns:
             dict with:
@@ -655,6 +660,16 @@ class TatlockAgent(AgentInterface):
             history_length=len(message_history),
         )
 
+        # Start tracing span for orchestration phase
+        orchestrate_span = start_span(
+            "tatlock_orchestrate",
+            SpanType.TATLOCK,
+            metadata={
+                "scoped_tool_count": len(scoped_tools),
+                "tool_names": [getattr(t, '__name__', str(t)) for t in scoped_tools[:5]],
+            },
+        )
+
         # Create a fresh agent instance with scoped tools only
         clean_host = self.ollama_host.rstrip('/')
         base_url = f"{clean_host}/v1"
@@ -731,6 +746,23 @@ class TatlockAgent(AgentInterface):
             tool_output_count=len(tool_outputs),
         )
 
+        # Add tool-level spans from result messages
+        if orchestrate_span:
+            add_tool_spans_from_messages(result.new_messages(), orchestrate_span)
+
+        # End orchestration span with results
+        end_span(
+            orchestrate_span,
+            metadata_update={
+                "tools_called": tools_called,
+                "expert_count": len(expert_results),
+                "tool_output_count": len(tool_outputs),
+            },
+            details_update={
+                "steward_note_preview": steward_note[:500] if steward_note else None,
+            },
+        )
+
         return {
             "tools_called": tools_called,
             "expert_results": expert_results,
@@ -769,6 +801,16 @@ class TatlockAgent(AgentInterface):
             tool_count=len(orchestration_results.get("tool_outputs", {})),
         )
 
+        # Start tracing span for synthesis phase
+        synthesize_span = start_span(
+            "tatlock_synthesize",
+            SpanType.TATLOCK,
+            metadata={
+                "expert_count": len(orchestration_results.get("expert_results", {})),
+                "tool_output_count": len(orchestration_results.get("tool_outputs", {})),
+            },
+        )
+
         # Build synthesis prompt with all available information
         synthesis_parts = []
         synthesis_parts.append(f"The user asked: {user_message}")
@@ -841,6 +883,18 @@ class TatlockAgent(AgentInterface):
             response_preview=result.output[:100],
         )
 
+        # End synthesis span with result
+        end_span(
+            synthesize_span,
+            metadata_update={
+                "response_length": len(result.output),
+            },
+            details_update={
+                "synthesis_prompt": synthesis_prompt[:1000],
+                "response_preview": result.output[:500],
+            },
+        )
+
         return result.output
 
     async def get_capabilities(self) -> dict:

src/core/benchmarks.py

@@ -1,345 +0,0 @@
-"""
-Performance benchmark storage using Redis.
-
-Tracks operation timing, tool usage, and recommendation accuracy across sessions.
-Provides time-series data for performance analysis and optimization.
-"""
-import json
-from datetime import datetime, timezone
-from typing import Any, Literal, Optional
-
-import redis.asyncio as redis
-from pydantic import BaseModel, Field
-
-from .config import config
-from .logging_config import get_logger
-
-logger = get_logger(__name__)
-
-
-class PerformanceBenchmark(BaseModel):
-    """
-    Performance benchmark record.
-
-    Stores timing and metadata for operations like Steward analysis,
-    tool calls, and agent execution.
-    """
-    timestamp: datetime = Field(default_factory=lambda: datetime.now(timezone.utc))
-    operation: str  # "steward_analysis", "tool_call", "tatlock_execution"
-    duration_seconds: float
-    success: bool
-
-    # Steward-specific fields
-    recommendation_count: Optional[int] = None
-    confidence: Optional[float] = None
-
-    # Tool-specific fields
-    tool_name: Optional[str] = None
-    was_recommended: Optional[bool] = None
-    was_actually_used: Optional[bool] = None
-
-    # Context
-    conversation_id: Optional[str] = None
-    metadata: dict[str, Any] = Field(default_factory=dict)
-
-    def to_redis_dict(self) -> dict[str, Any]:
-        """Convert to dict suitable for Redis storage."""
-        data = self.model_dump()
-        data["timestamp"] = self.timestamp.isoformat()
-        data["metadata"] = json.dumps(self.metadata)
-        # Convert booleans to strings (Redis doesn't accept bool type)
-        for key, value in data.items():
-            if isinstance(value, bool):
-                data[key] = str(value)
-        return data
-
-    @classmethod
-    def from_redis_dict(cls, data: dict[str, Any]) -> "PerformanceBenchmark":
-        """Reconstruct from Redis dict."""
-        data["timestamp"] = datetime.fromisoformat(data["timestamp"])
-        data["metadata"] = json.loads(data.get("metadata", "{}"))
-        # Convert string booleans back to bool
-        for key in ["success", "was_recommended", "was_actually_used"]:
-            if key in data and isinstance(data[key], str):
-                data[key] = data[key] == "True"
-        return cls(**data)
-
-
-class BenchmarkStore:
-    """
-    Redis-backed benchmark storage with automatic expiry.
-
-    Stores performance metrics in time-series format with 30-day retention.
-    Provides querying capabilities for analysis and reporting.
-    """
-
-    def __init__(self, redis_client: Optional[redis.Redis] = None):
-        """
-        Initialize benchmark store.
-
-        Args:
-            redis_client: Optional Redis client. If None, creates from config.
-        """
-        self._client = redis_client
-        self._ttl_days = 30  # 30-day retention
-
-    async def _get_client(self) -> redis.Redis:
-        """Get or create Redis client."""
-        if self._client is None:
-            self._client = redis.from_url(
-                config.redis_url,
-                encoding="utf-8",
-                decode_responses=True,
-                socket_timeout=config.REDIS_TIMEOUT,
-                socket_connect_timeout=config.REDIS_TIMEOUT,
-            )
-        return self._client
-
-    async def record(self, benchmark: PerformanceBenchmark) -> None:
-        """
-        Record a performance benchmark.
-
-        Args:
-            benchmark: Performance benchmark to record
-
-        Example:
-            >>> await store.record(PerformanceBenchmark(
-            ...     operation="steward_analysis",
-            ...     duration_seconds=1.23,
-            ...     success=True,
-            ...     recommendation_count=3,
-            ... ))
-        """
-        if not config.ENABLE_BENCHMARKS:
-            return
-
-        try:
-            client = await self._get_client()
-
-            # Generate key: benchmark:{operation}:{timestamp_ms}
-            timestamp_ms = int(benchmark.timestamp.timestamp() * 1000)
-            key = f"benchmark:{benchmark.operation}:{timestamp_ms}"
-
-            # Store as hash
-            await client.hset(key, mapping=benchmark.to_redis_dict())
-
-            # Set expiry
-            await client.expire(key, self._ttl_days * 24 * 60 * 60)
-
-            # Add to sorted set for time-based queries
-            index_key = f"benchmark_index:{benchmark.operation}"
-            await client.zadd(index_key, {key: timestamp_ms})
-            await client.expire(index_key, self._ttl_days * 24 * 60 * 60)
-
-            logger.debug(
-                "benchmark_recorded",
-                operation=benchmark.operation,
-                duration=benchmark.duration_seconds,
-                success=benchmark.success,
-            )
-
-        except Exception as e:
-            logger.warning(
-                "benchmark_recording_failed",
-                error=str(e),
-                operation=benchmark.operation,
-            )
-            # Don't fail the request if benchmarking fails
-
-    async def query(
-        self,
-        operation: str,
-        start_time: Optional[datetime] = None,
-        end_time: Optional[datetime] = None,
-        limit: int = 100,
-    ) -> list[PerformanceBenchmark]:
-        """
-        Query benchmarks by operation and time range.
-
-        Args:
-            operation: Operation name to filter by
-            start_time: Start of time range (inclusive)
-            end_time: End of time range (inclusive)
-            limit: Maximum number of results
-
-        Returns:
-            List of benchmarks matching the query
-
-        Example:
-            >>> from datetime import timedelta
-            >>> now = datetime.now(timezone.utc)
-            >>> yesterday = now - timedelta(days=1)
-            >>> benchmarks = await store.query(
-            ...     "steward_analysis",
-            ...     start_time=yesterday,
-            ...     limit=50
-            ... )
-        """
-        if not config.ENABLE_BENCHMARKS:
-            return []
-
-        try:
-            client = await self._get_client()
-            index_key = f"benchmark_index:{operation}"
-
-            # Convert time range to timestamps
-            min_score = (
-                int(start_time.timestamp() * 1000)
-                if start_time
-                else "-inf"
-            )
-            max_score = (
-                int(end_time.timestamp() * 1000)
-                if end_time
-                else "+inf"
-            )
-
-            # Query sorted set
-            keys = await client.zrevrangebyscore(
-                index_key,
-                max_score,
-                min_score,
-                start=0,
-                num=limit,
-            )
-
-            # Fetch benchmark data
-            benchmarks = []
-            for key in keys:
-                data = await client.hgetall(key)
-                if data:
-                    benchmarks.append(PerformanceBenchmark.from_redis_dict(data))
-
-            return benchmarks
-
-        except Exception as e:
-            logger.error(
-                "benchmark_query_failed",
-                error=str(e),
-                operation=operation,
-            )
-            return []
-
-    async def get_statistics(
-        self,
-        operation: str,
-        start_time: Optional[datetime] = None,
-        end_time: Optional[datetime] = None,
-    ) -> dict[str, Any]:
-        """
-        Get aggregate statistics for an operation.
-
-        Args:
-            operation: Operation name
-            start_time: Start of time range
-            end_time: End of time range
-
-        Returns:
-            Dictionary with statistics (count, avg_duration, success_rate, etc.)
-
-        Example:
-            >>> stats = await store.get_statistics("steward_analysis")
-            >>> print(f"Average duration: {stats['avg_duration']}s")
-            >>> print(f"Success rate: {stats['success_rate']}%")
-        """
-        benchmarks = await self.query(operation, start_time, end_time, limit=1000)
-
-        if not benchmarks:
-            return {
-                "count": 0,
-                "avg_duration": 0.0,
-                "min_duration": 0.0,
-                "max_duration": 0.0,
-                "success_rate": 0.0,
-            }
-
-        durations = [b.duration_seconds for b in benchmarks]
-        successes = sum(1 for b in benchmarks if b.success)
-
-        return {
-            "count": len(benchmarks),
-            "avg_duration": sum(durations) / len(durations),
-            "min_duration": min(durations),
-            "max_duration": max(durations),
-            "success_rate": (successes / len(benchmarks)) * 100,
-            "total_successes": successes,
-            "total_failures": len(benchmarks) - successes,
-        }
-
-    async def get_tool_accuracy(
-        self,
-        start_time: Optional[datetime] = None,
-        end_time: Optional[datetime] = None,
-    ) -> dict[str, Any]:
-        """
-        Analyze tool recommendation accuracy.
-
-        Compares recommended tools vs actually used tools to measure
-        Steward's recommendation precision.
-
-        Args:
-            start_time: Start of time range
-            end_time: End of time range
-
-        Returns:
-            Dictionary with accuracy metrics
-
-        Example:
-            >>> accuracy = await store.get_tool_accuracy()
-            >>> print(f"Precision: {accuracy['precision']}%")
-        """
-        tool_calls = await self.query("tool_call", start_time, end_time, limit=1000)
-
-        if not tool_calls:
-            return {
-                "total_calls": 0,
-                "recommended_and_used": 0,
-                "recommended_not_used": 0,
-                "not_recommended_but_used": 0,
-                "precision": 0.0,
-            }
-
-        recommended_and_used = sum(
-            1 for b in tool_calls
-            if b.was_recommended and b.was_actually_used
-        )
-        not_recommended_but_used = sum(
-            1 for b in tool_calls
-            if not b.was_recommended and b.was_actually_used
-        )
-
-        total_used = sum(1 for b in tool_calls if b.was_actually_used)
-        precision = (
-            (recommended_and_used / total_used * 100) if total_used > 0 else 0.0
-        )
-
-        return {
-            "total_calls": len(tool_calls),
-            "total_used": total_used,
-            "recommended_and_used": recommended_and_used,
-            "not_recommended_but_used": not_recommended_but_used,
-            "precision": precision,
-        }
-
-    async def close(self) -> None:
-        """Close Redis connection."""
-        if self._client:
-            await self._client.aclose()
-            self._client = None
-
-
-# Global benchmark store instance
-_benchmark_store: Optional[BenchmarkStore] = None
-
-
-def get_benchmark_store() -> BenchmarkStore:
-    """
-    Get global benchmark store instance.
-
-    Returns:
-        BenchmarkStore instance
-    """
-    global _benchmark_store
-    if _benchmark_store is None:
-        _benchmark_store = BenchmarkStore()
-    return _benchmark_store

src/core/config.py

@@ -101,10 +101,6 @@ class Config(BaseSettings):
         default=6379,
         description="Redis server port"
     )
-    REDIS_BENCHMARK_DB: int = Field(
-        default=6,
-        description="Redis database number for benchmarks"
-    )
     REDIS_TIMEOUT: int = Field(
         default=5,
         description="Redis connection timeout in seconds"
@@ -158,7 +154,7 @@ class Config(BaseSettings):
         description="Ollama model for embeddings"
     )
 
-    # Redis Memory Database (separate from benchmarks)
+    # Redis Memory Database
     REDIS_MEMORY_DB: int = Field(
         default=1,
         description="Redis database number for memory cache"
@@ -173,7 +169,6 @@ class Config(BaseSettings):
         default=None,
         description="Logging level (auto-set based on environment if not specified)"
     )
-    ENABLE_BENCHMARKS: bool = Field(default=True, description="Enable performance benchmarking")
 
     # User Configuration
     DEFAULT_USER: str | None = Field(
@@ -190,11 +185,6 @@ class Config(BaseSettings):
     CORS_ALLOW_METHODS: list[str] = ["*"]
     CORS_ALLOW_HEADERS: list[str] = ["*"]
 
-    @property
-    def redis_url(self) -> str:
-        """Construct Redis connection URL for benchmarks."""
-        return f"redis://{self.REDIS_HOST}:{self.REDIS_PORT}/{self.REDIS_BENCHMARK_DB}"
-
     @property
     def redis_memory_url(self) -> str:
         """Construct Redis connection URL for memory cache."""

src/core/memory_cache.py

@@ -6,7 +6,7 @@ Provides short-term memory storage with TTL:
 - Recent entities mentioned in conversation
 - User-scoped with conversation isolation
 
-Uses Redis DB 2 (separate from benchmarks in DB 1).
+Uses Redis DB 1.
 """
 import json
 from typing import Any

src/core/preprocessing.py

@@ -11,6 +11,7 @@ from src.agents.steward import analyze_request, format_steward_note
 from src.agents.steward.schemas import StewardRecommendation
 from src.core.household_registry import get_household_registry
 from src.core.logging_config import get_logger
+from src.core.tracing import trace_span, SpanType
 
 logger = get_logger(__name__)
 
@@ -93,13 +94,33 @@ async def preprocess_request(
         conversation_id=conversation_id,
     )
 
-    # Call Steward with full conversation history
+    # Call Steward with full conversation history (traced)
+    async with trace_span(
+        "steward_analysis",
+        SpanType.STEWARD,
+        metadata={
+            "request_preview": user_request[:100],
+            "history_length": len(conversation_history),
+        },
+    ) as span:
         recommendation = await analyze_request(
             enriched_request,
             conversation_history=conversation_history,
             conversation_id=conversation_id,
         )
 
+        # Update span with results
+        if span:
+            span.metadata.update({
+                "recommended_capabilities": recommendation.recommended_capabilities,
+                "complexity": recommendation.estimated_complexity,
+                "has_memory_context": bool(recommendation.memory_context),
+                "has_conversation_context": recommendation.conversation_context.has_previous_context,
+            })
+            span.details["reasoning"] = recommendation.reasoning
+            if recommendation.enriched_query:
+                span.details["enriched_query"] = recommendation.enriched_query
+
     # Format note for Tatlock (includes conversation context)
     steward_note = await format_steward_note(recommendation)
 

src/core/tool_tracking.py

@@ -1,13 +1,11 @@
 """
-Tool call tracking and benchmarking.
+Tool call tracking.
 
 Tracks which tools are recommended by the Steward versus which tools
-are actually used by Tatlock, recording benchmarks for analysis.
+are actually used by Tatlock for debugging and analysis.
 """
-from datetime import datetime, timezone
 from typing import Optional
 
-from src.core.benchmarks import PerformanceBenchmark, get_benchmark_store
 from src.core.logging_config import get_logger
 
 logger = get_logger(__name__)
@@ -15,7 +13,7 @@ logger = get_logger(__name__)
 
 class ToolCallTracker:
     """
-    Tracks tool calls for benchmarking and accuracy analysis.
+    Tracks tool calls for accuracy analysis.
 
     Compares Steward's recommendations with Tatlock's actual tool usage
     to measure recommendation accuracy.
@@ -53,6 +51,10 @@ class ToolCallTracker:
             return tool_name.replace("delegate_to_", "")
         return tool_name
 
+    def log_call(self, message: str):
+        """Log a tool call message (for UI display)."""
+        logger.debug("tool_call_message", message=message)
+
     async def track_call(self, tool_name: str, duration: float):
         """
         Record a tool call with timing.
@@ -78,23 +80,6 @@ class ToolCallTracker:
                 recommended=list(self.recommended_capabilities),
             )
 
-        # Record benchmark to Redis
-        benchmark = PerformanceBenchmark(
-            timestamp=datetime.now(timezone.utc),
-            operation="tool_call",
-            duration_seconds=duration,
-            success=True,  # If we got here, the call succeeded
-            tool_name=tool_name,
-            was_recommended=was_recommended,
-            was_actually_used=True,
-            conversation_id=self.conversation_id,
-            metadata={
-                "recommended_capabilities": list(self.recommended_capabilities),
-            },
-        )
-
-        await get_benchmark_store().record(benchmark)
-
         logger.debug(
             "tool_call_tracked",
             tool_name=tool_name,
@@ -124,24 +109,6 @@ class ToolCallTracker:
                 conversation_id=self.conversation_id,
             )
 
-            # Record benchmarks for unused recommendations
-            for tool_name in unused_tools:
-                benchmark = PerformanceBenchmark(
-                    timestamp=datetime.now(timezone.utc),
-                    operation="tool_call",
-                    duration_seconds=0.0,  # Not used
-                    success=True,
-                    tool_name=tool_name,
-                    was_recommended=True,
-                    was_actually_used=False,
-                    conversation_id=self.conversation_id,
-                    metadata={
-                        "recommended_capabilities": list(self.recommended_capabilities),
-                        "reason": "recommended_but_unused",
-                    },
-                )
-                await get_benchmark_store().record(benchmark)
-
         # Log summary
         total_calls = sum(len(durations) for durations in self.actual_calls.values())
         logger.info(

src/core/tracing.py

@@ -0,0 +1,434 @@
+"""
+Lightweight request tracing for local development.
+
+Captures the full request flow through Tatlock's multi-agent architecture
+as structured JSON traces for debugging and optimization.
+
+Enable via DEBUG=true environment variable.
+
+Traces are written to logs/traces/{trace_id}.json
+View with logs/traces/viewer.html
+"""
+from contextlib import asynccontextmanager
+from contextvars import ContextVar
+from dataclasses import dataclass, field
+from datetime import datetime, timezone
+from enum import Enum
+from pathlib import Path
+from typing import Any
+
+import json
+import secrets
+
+from src.core.logging_config import get_logger
+
+logger = get_logger(__name__)
+
+
+class SpanType(str, Enum):
+    """Types of traced operations."""
+    ROUTER = "router"
+    STEWARD = "steward"
+    TATLOCK = "tatlock"
+    EXPERT = "expert"
+    TOOL = "tool"
+
+
+class SpanStatus(str, Enum):
+    """Span completion status."""
+    OK = "ok"
+    ERROR = "error"
+
+
+@dataclass
+class Span:
+    """A single traced operation."""
+    span_id: str
+    name: str
+    type: SpanType
+    start_time: datetime
+    parent_id: str | None = None
+    end_time: datetime | None = None
+    status: SpanStatus = SpanStatus.OK
+    metadata: dict[str, Any] = field(default_factory=dict)
+    details: dict[str, Any] = field(default_factory=dict)
+    children: list[str] = field(default_factory=list)
+    error: str | None = None
+
+    @property
+    def duration_ms(self) -> float | None:
+        """Calculate duration in milliseconds."""
+        if self.end_time and self.start_time:
+            return (self.end_time - self.start_time).total_seconds() * 1000
+        return None
+
+    def to_dict(self) -> dict[str, Any]:
+        """Convert span to dictionary for JSON serialization."""
+        result = {
+            "span_id": self.span_id,
+            "parent_id": self.parent_id,
+            "name": self.name,
+            "type": self.type.value,
+            "start_time": self.start_time.isoformat(),
+            "end_time": self.end_time.isoformat() if self.end_time else None,
+            "duration_ms": round(self.duration_ms, 2) if self.duration_ms else None,
+            "status": self.status.value,
+            "metadata": self.metadata if self.metadata else None,
+        }
+        # Only include non-empty optional fields
+        if self.details:
+            result["details"] = self.details
+        if self.children:
+            result["children"] = self.children
+        if self.error:
+            result["error"] = self.error
+        return {k: v for k, v in result.items() if v is not None}
+
+
+@dataclass
+class Trace:
+    """Complete trace of a request."""
+    trace_id: str
+    conversation_id: str | None
+    user: str
+    timestamp: datetime
+    request: dict[str, Any]
+    spans: list[Span] = field(default_factory=list)
+    response: dict[str, Any] | None = None
+    status: str = "in_progress"
+
+    @property
+    def total_duration_ms(self) -> float | None:
+        """Calculate total trace duration from span timings."""
+        if not self.spans:
+            return None
+        start = min(s.start_time for s in self.spans)
+        ends = [s.end_time for s in self.spans if s.end_time]
+        if not ends:
+            return None
+        end = max(ends)
+        return (end - start).total_seconds() * 1000
+
+    def to_dict(self) -> dict[str, Any]:
+        """Convert trace to dictionary for JSON serialization."""
+        return {
+            "trace_id": self.trace_id,
+            "conversation_id": self.conversation_id,
+            "user": self.user,
+            "timestamp": self.timestamp.isoformat(),
+            "total_duration_ms": round(self.total_duration_ms, 2) if self.total_duration_ms else None,
+            "status": self.status,
+            "request": self.request,
+            "response": self.response,
+            "spans": [s.to_dict() for s in self.spans],
+        }
+
+
+# ContextVar for async-safe trace propagation
+_current_trace: ContextVar[Trace | None] = ContextVar("current_trace", default=None)
+_current_span: ContextVar[Span | None] = ContextVar("current_span", default=None)
+
+
+def tracing_enabled() -> bool:
+    """Check if tracing is enabled (requires DEBUG=true)."""
+    from src.core.config import config
+    return config.DEBUG
+
+
+def _generate_id(prefix: str = "") -> str:
+    """Generate unique ID with optional prefix."""
+    return f"{prefix}{secrets.token_hex(8)}"
+
+
+def start_trace(
+    conversation_id: str | None,
+    user: str,
+    request: dict[str, Any],
+) -> Trace | None:
+    """
+    Start a new trace for a request.
+
+    Args:
+        conversation_id: Conversation identifier
+        user: User identifier
+        request: Request data (should include preview and full)
+
+    Returns:
+        Trace object if tracing enabled, None otherwise
+    """
+    if not tracing_enabled():
+        return None
+
+    trace = Trace(
+        trace_id=_generate_id("trace_"),
+        conversation_id=conversation_id,
+        user=user,
+        timestamp=datetime.now(timezone.utc),
+        request=request,
+    )
+    _current_trace.set(trace)
+
+    logger.debug("trace_started", trace_id=trace.trace_id, user=user)
+    return trace
+
+
+def get_current_trace() -> Trace | None:
+    """Get the current trace from context."""
+    return _current_trace.get()
+
+
+def get_current_span() -> Span | None:
+    """Get the current span from context."""
+    return _current_span.get()
+
+
+def start_span(
+    name: str,
+    span_type: SpanType,
+    metadata: dict[str, Any] | None = None,
+    details: dict[str, Any] | None = None,
+) -> Span | None:
+    """
+    Start a new span within the current trace.
+
+    Args:
+        name: Span name (e.g., "steward_analysis")
+        span_type: Type of operation
+        metadata: Quick-access metadata (shown in timeline)
+        details: Expandable details (prompts, full responses)
+
+    Returns:
+        Span object if tracing enabled, None otherwise
+    """
+    trace = get_current_trace()
+    if not trace:
+        return None
+
+    parent = get_current_span()
+    span = Span(
+        span_id=_generate_id("span_"),
+        name=name,
+        type=span_type,
+        start_time=datetime.now(timezone.utc),
+        parent_id=parent.span_id if parent else None,
+        metadata=metadata or {},
+        details=details or {},
+    )
+
+    # Add to parent's children list
+    if parent:
+        parent.children.append(span.span_id)
+
+    trace.spans.append(span)
+    _current_span.set(span)
+
+    logger.debug(
+        "span_started",
+        span_id=span.span_id,
+        name=name,
+        type=span_type.value,
+        parent_id=span.parent_id,
+    )
+    return span
+
+
+def end_span(
+    span: Span | None = None,
+    status: SpanStatus = SpanStatus.OK,
+    metadata_update: dict[str, Any] | None = None,
+    details_update: dict[str, Any] | None = None,
+    error: str | None = None,
+) -> None:
+    """
+    End a span and restore parent as current.
+
+    Args:
+        span: Span to end (defaults to current span)
+        status: Completion status
+        metadata_update: Additional metadata to merge
+        details_update: Additional details to merge
+        error: Error message if failed
+    """
+    if span is None:
+        span = get_current_span()
+    if not span:
+        return
+
+    span.end_time = datetime.now(timezone.utc)
+    span.status = status
+    if error:
+        span.error = error
+        span.status = SpanStatus.ERROR
+    if metadata_update:
+        span.metadata.update(metadata_update)
+    if details_update:
+        span.details.update(details_update)
+
+    # Restore parent span as current
+    trace = get_current_trace()
+    if trace and span.parent_id:
+        parent = next((s for s in trace.spans if s.span_id == span.parent_id), None)
+        _current_span.set(parent)
+    else:
+        _current_span.set(None)
+
+    logger.debug(
+        "span_ended",
+        span_id=span.span_id,
+        duration_ms=span.duration_ms,
+        status=status.value,
+    )
+
+
+def end_trace(
+    response: dict[str, Any] | None = None,
+    status: str = "completed",
+) -> str | None:
+    """
+    End the current trace and write to file.
+
+    Args:
+        response: Response data to include
+        status: Final trace status ("completed" or "error")
+
+    Returns:
+        Path to trace file if written, None otherwise
+    """
+    trace = get_current_trace()
+    if not trace:
+        return None
+
+    trace.response = response
+    trace.status = status
+
+    # Write trace to file
+    trace_path = _write_trace(trace)
+
+    # Clear context
+    _current_trace.set(None)
+    _current_span.set(None)
+
+    logger.info(
+        "trace_completed",
+        trace_id=trace.trace_id,
+        total_duration_ms=round(trace.total_duration_ms, 2) if trace.total_duration_ms else None,
+        span_count=len(trace.spans),
+        path=str(trace_path) if trace_path else None,
+    )
+
+    return str(trace_path) if trace_path else None
+
+
+def _write_trace(trace: Trace) -> Path | None:
+    """Write trace to JSON file."""
+    try:
+        # Ensure traces directory exists
+        traces_dir = Path("logs/traces")
+        traces_dir.mkdir(parents=True, exist_ok=True)
+
+        # Write trace file
+        trace_path = traces_dir / f"{trace.trace_id}.json"
+        with open(trace_path, "w") as f:
+            json.dump(trace.to_dict(), f, indent=2, default=str)
+
+        return trace_path
+
+    except Exception as e:
+        logger.error("trace_write_failed", error=str(e), trace_id=trace.trace_id)
+        return None
+
+
+@asynccontextmanager
+async def trace_span(
+    name: str,
+    span_type: SpanType,
+    metadata: dict[str, Any] | None = None,
+    details: dict[str, Any] | None = None,
+):
+    """
+    Async context manager for tracing a span.
+
+    Automatically handles start/end timing and error capture.
+
+    Usage:
+        async with trace_span("steward_analysis", SpanType.STEWARD) as span:
+            result = await analyze_request(...)
+            if span:
+                span.metadata["result_count"] = len(result)
+
+    Args:
+        name: Span name
+        span_type: Type of operation
+        metadata: Initial metadata
+        details: Initial details (expandable in viewer)
+
+    Yields:
+        Span object or None if tracing disabled
+    """
+    span = start_span(name, span_type, metadata, details)
+    try:
+        yield span
+    except Exception as e:
+        end_span(span, SpanStatus.ERROR, error=str(e))
+        raise
+    else:
+        end_span(span, SpanStatus.OK)
+
+
+def add_tool_spans_from_messages(messages: list[Any], parent_span: Span | None = None) -> None:
+    """
+    Extract tool calls from PydanticAI result messages and add as child spans.
+
+    Call this after an agent.run() to capture tool-level timing retroactively.
+    Note: Since we don't have actual timing, we estimate based on sequence.
+
+    Args:
+        messages: List from result.new_messages()
+        parent_span: Parent span to attach tool spans to
+    """
+    trace = get_current_trace()
+    if not trace or not parent_span:
+        return
+
+    # Import PydanticAI message types
+    try:
+        from pydantic_ai.messages import ModelRequest, ModelResponse, ToolCallPart, ToolReturnPart
+    except ImportError:
+        return
+
+    # Track tool calls and their returns
+    tool_calls: dict[str, dict[str, Any]] = {}
+
+    for msg in messages:
+        if isinstance(msg, ModelResponse):
+            for part in msg.parts:
+                if isinstance(part, ToolCallPart):
+                    tool_calls[part.tool_call_id] = {
+                        "name": part.tool_name,
+                        "args": part.args if hasattr(part, 'args') else {},
+                    }
+        elif isinstance(msg, ModelRequest):
+            for part in msg.parts:
+                if isinstance(part, ToolReturnPart):
+                    if part.tool_call_id in tool_calls:
+                        tool_info = tool_calls[part.tool_call_id]
+                        # Create a span for this tool call
+                        span = Span(
+                            span_id=_generate_id("span_"),
+                            name=tool_info["name"],
+                            type=SpanType.TOOL,
+                            start_time=parent_span.start_time,  # Approximate
+                            end_time=parent_span.end_time or datetime.now(timezone.utc),
+                            parent_id=parent_span.span_id,
+                            status=SpanStatus.OK,
+                            metadata={
+                                "tool_name": tool_info["name"],
+                                "args_preview": str(tool_info.get("args", {}))[:100],
+                            },
+                            details={
+                                "args": tool_info.get("args", {}),
+                                "result": part.content[:2000] if isinstance(part.content, str) else str(part.content)[:2000],
+                            },
+                        )
+                        parent_span.children.append(span.span_id)
+                        trace.spans.append(span)

src/core/tracing_router.py

@@ -0,0 +1,153 @@
+"""
+Trace viewer router.
+
+Serves the trace viewer UI and trace files when tracing is enabled.
+Only available when DEBUG=true.
+"""
+from pathlib import Path
+
+from fastapi import APIRouter, HTTPException
+from fastapi.responses import HTMLResponse, JSONResponse
+
+from src.core.config import config
+from src.core.logging_config import get_logger
+
+logger = get_logger(__name__)
+
+router = APIRouter(prefix="/traces", tags=["traces"])
+
+TRACES_DIR = Path("logs/traces")
+VIEWER_PATH = TRACES_DIR / "viewer.html"
+
+
+def tracing_enabled() -> bool:
+    """Check if tracing is enabled."""
+    return config.DEBUG
+
+
+@router.get("", response_class=HTMLResponse)
+async def get_trace_viewer():
+    """
+    Serve the trace viewer UI.
+
+    Returns the standalone HTML viewer for browsing traces.
+    """
+    if not tracing_enabled():
+        raise HTTPException(status_code=404, detail="Tracing not enabled")
+
+    if not VIEWER_PATH.exists():
+        raise HTTPException(status_code=404, detail="Viewer not found")
+
+    return HTMLResponse(content=VIEWER_PATH.read_text())
+
+
+@router.get("/list")
+async def list_traces(
+    limit: int = 50,
+    since_minutes: int | None = None,
+    status: str | None = None,
+    search: str | None = None,
+):
+    """
+    List available trace files.
+
+    Returns most recent traces first, with basic metadata.
+
+    Args:
+        limit: Maximum number of traces to return (default 50)
+        since_minutes: Only return traces from the last N minutes
+        status: Filter by status (completed, error, streaming)
+        search: Search in request preview text
+    """
+    if not tracing_enabled():
+        raise HTTPException(status_code=404, detail="Tracing not enabled")
+
+    if not TRACES_DIR.exists():
+        return {"traces": [], "total": 0}
+
+    import json
+    from datetime import datetime, timezone, timedelta
+
+    # Calculate cutoff time if filtering by time
+    cutoff_time = None
+    if since_minutes:
+        cutoff_time = datetime.now(timezone.utc) - timedelta(minutes=since_minutes)
+
+    # Get all trace files, sorted by modification time (newest first)
+    trace_files = sorted(
+        TRACES_DIR.glob("trace_*.json"),
+        key=lambda p: p.stat().st_mtime,
+        reverse=True,
+    )
+
+    traces = []
+    for path in trace_files:
+        if len(traces) >= limit:
+            break
+
+        try:
+            with open(path) as f:
+                data = json.load(f)
+
+            # Parse timestamp for filtering
+            trace_timestamp = data.get("timestamp")
+            if cutoff_time and trace_timestamp:
+                try:
+                    ts = datetime.fromisoformat(trace_timestamp.replace('Z', '+00:00'))
+                    if ts < cutoff_time:
+                        continue
+                except (ValueError, TypeError):
+                    pass
+
+            # Filter by status
+            trace_status = data.get("status", "")
+            if status and trace_status != status:
+                continue
+
+            # Filter by search text
+            request_preview = data.get("request", {}).get("input_preview", "")
+            if search and search.lower() not in request_preview.lower():
+                continue
+
+            traces.append({
+                "trace_id": data.get("trace_id"),
+                "timestamp": trace_timestamp,
+                "user": data.get("user"),
+                "status": trace_status,
+                "total_duration_ms": data.get("total_duration_ms"),
+                "span_count": len(data.get("spans", [])),
+                "request_preview": request_preview[:100],
+            })
+        except Exception as e:
+            logger.warning("trace_list_parse_error", path=str(path), error=str(e))
+
+    return {"traces": traces, "total": len(traces)}
+
+
+@router.get("/{trace_id}")
+async def get_trace(trace_id: str):
+    """
+    Get a specific trace by ID.
+
+    Returns the full trace JSON.
+    """
+    if not tracing_enabled():
+        raise HTTPException(status_code=404, detail="Tracing not enabled")
+
+    # Sanitize trace_id to prevent path traversal
+    if not trace_id.startswith("trace_") or "/" in trace_id or "\\" in trace_id:
+        raise HTTPException(status_code=400, detail="Invalid trace ID")
+
+    trace_path = TRACES_DIR / f"{trace_id}.json"
+
+    if not trace_path.exists():
+        raise HTTPException(status_code=404, detail="Trace not found")
+
+    try:
+        import json
+        with open(trace_path) as f:
+            data = json.load(f)
+        return JSONResponse(content=data)
+    except Exception as e:
+        logger.error("trace_read_error", trace_id=trace_id, error=str(e))
+        raise HTTPException(status_code=500, detail="Failed to read trace")

src/main.py

@@ -23,6 +23,7 @@ from src.core.exceptions import AppException
 from src.core.logging_config import get_logger
 from src.core.router import router as core_router
 from src.core.startup import initialize_application
+from src.core.tracing_router import router as tracing_router
 from src.models.router import router as models_router
 from src.responses.router import router as responses_router
 
@@ -45,7 +46,7 @@ async def lifespan(app: FastAPI) -> AsyncGenerator[None, None]:
         environment=config.ENVIRONMENT.value,
         ollama_host=str(config.OLLAMA_HOST),
         ollama_model=config.OLLAMA_DEFAULT_MODEL,
-        redis_url=config.redis_url,
+        redis_url=config.redis_memory_url,
         log_format=config.log_format,
     )
 
@@ -91,6 +92,11 @@ def create_application() -> FastAPI:
     application.include_router(models_router, prefix=config.API_PREFIX)
     application.include_router(responses_router, prefix=config.API_PREFIX)  # Responses API
 
+    # Conditionally include tracing router (only in debug mode)
+    if config.DEBUG:
+        application.include_router(tracing_router)
+        logger.info("tracing_router_enabled")
+
     return application
 
 

src/responses/router.py

@@ -10,7 +10,6 @@ from sse_starlette.sse import EventSourceResponse
 from src.responses import service
 from src.responses.schemas import ResponseRequest, Response
 from src.core.exceptions import ModelNotFoundError, AppException
-from src.core.context import current_user, current_conversation, get_default_user
 from src.core.logging_config import get_logger
 
 logger = get_logger(__name__)
@@ -37,77 +36,16 @@ async def create_response(
 
     Returns:
         Response object or SSE stream
-
-    Example non-streaming request:
-        POST /v1/responses
-        {
-            "model": "lorem-tester",
-            "input": [{"role": "user", "content": "Hello"}],
-            "reasoning": {"effort": "medium", "summary": "auto"},
-            "stream": false
-        }
-
-    Example streaming request:
-        POST /v1/responses
-        {
-            "model": "lorem-tester",
-            "input": [{"role": "user", "content": "Hello"}],
-            "stream": true
-        }
-
-    Response format (non-streaming):
-        {
-            "id": "resp_...",
-            "object": "response",
-            "created_at": 1733529600,
-            "model": "lorem-tester",
-            "status": "completed",
-            "output": [
-                {
-                    "type": "reasoning",
-                    "id": "rs_...",
-                    "summary": ["Analyzing...", "Considering..."]
-                },
-                {
-                    "type": "message",
-                    "id": "msg_...",
-                    "role": "assistant",
-                    "content": [{"type": "output_text", "text": "Lorem ipsum..."}]
-                }
-            ],
-            "usage": {
-                "input_tokens": 10,
-                "output_tokens": 50,
-                "reasoning_tokens": 20,
-                "total_tokens": 80
-            }
-        }
-
-    Streaming format (SSE):
-        event: response.reasoning_summary_text.delta
-        data: {"delta": "Analyzing..."}
-
-        event: response.output_text.delta
-        data: {"delta": "Lorem"}
-
-        event: response.done
-        data: {"response": {...}}
     """
-    # Set request context (propagates through all async calls)
-    effective_user = request.user or get_default_user()
-    user_token = current_user.set(effective_user)
-    conv_id = request.metadata.get("conversation_id") if request.metadata else None
-    conv_token = current_conversation.set(conv_id)
-
     logger.info(
         "response_request_received",
         model=request.model,
-        user=effective_user,
-        conversation_id=conv_id,
+        user=request.user,
+        streaming=request.stream,
     )
 
     try:
-        # Check if this is a Tatlock request - use Steward preprocessing (Phase 2)
+        # Check if this is a Tatlock request - use Steward preprocessing
         model_id = request.model
         if "." in model_id:
             model_id = model_id.split(".", 1)[1]
@@ -116,21 +54,20 @@ async def create_response(
 
         if request.stream:
             logger.info("Streaming response requested")
+
             if use_steward:
                 logger.info("Streaming with Steward preprocessing for Tatlock request")
-                # Use Steward + Tatlock streaming (Milestone 3.5)
                 from src.responses.streaming import StreamingCoordinator
                 coordinator = StreamingCoordinator()
                 return EventSourceResponse(
                     coordinator.stream_response_with_steward(request)
                 )
             else:
-                # Regular streaming for non-Tatlock models
                 return EventSourceResponse(
                     service.create_response_stream(request)
                 )
 
-        # Use appropriate service method
+        # Non-streaming response
         if use_steward:
             logger.info("Using Steward preprocessing for Tatlock request")
             return await service.create_response_with_steward(request)
@@ -148,8 +85,3 @@ async def create_response(
     except Exception as e:
         logger.error(f"Unexpected error: {e}", exc_info=True)
         raise HTTPException(status_code=500, detail="Internal server error")
-
-    finally:
-        # Reset context (important for connection reuse)
-        current_user.reset(user_token)
-        current_conversation.reset(conv_token)

src/responses/service.py

@@ -26,6 +26,8 @@ from src.responses.context import ContextWindow
 from src.core.preprocessing import preprocess_request
 from src.core.tool_tracking import ToolCallTracker
 from src.core.logging_config import get_logger
+from src.core.tracing import start_trace, end_trace, start_span, SpanType
+from src.core.context import current_user, current_conversation, get_default_user
 from src.agents.steward.schemas import StewardRecommendation
 
 import re
@@ -34,6 +36,29 @@ import asyncio
 logger = get_logger(__name__)
 
 
+def _extract_user_input(input_data) -> str:
+    """Extract user input text from request input for tracing."""
+    if isinstance(input_data, str):
+        return input_data
+    elif isinstance(input_data, list) and input_data:
+        last_msg = input_data[-1]
+        if isinstance(last_msg, dict):
+            return last_msg.get("content", str(last_msg))
+        return str(last_msg)
+    return ""
+
+
+def _extract_response_preview(response: Response) -> str:
+    """Extract response preview text for tracing."""
+    if response.output:
+        for item in response.output:
+            if hasattr(item, 'content'):
+                for content in item.content:
+                    if hasattr(content, 'text'):
+                        return content.text[:200]
+    return ""
+
+
 async def _execute_single_delegation(
     agent_name: str,
     task: str,
@@ -405,6 +430,34 @@ async def create_response(request: ResponseRequest) -> Response:
     # Get or generate conversation ID
     conversation_id = await _conversation_history.get_conversation_id(request)
 
+    # Set context for tracing
+    effective_user = request.user or get_default_user()
+    current_user.set(effective_user)
+    current_conversation.set(conversation_id)
+
+    # Extract user input for tracing
+    user_input = _extract_user_input(request.input)
+
+    # Start trace
+    trace = start_trace(
+        conversation_id=conversation_id,
+        user=effective_user,
+        request={
+            "model": request.model,
+            "input_preview": user_input[:200] if user_input else "",
+            "full_input": request.input,
+            "streaming": False,
+        },
+    )
+
+    # Start service span
+    service_span = start_span(
+        "create_response",
+        SpanType.ROUTER,
+        metadata={"model": request.model, "user": effective_user},
+    )
+
+    try:
         # Strip pipeline prefix if present (e.g., "pipeline.model" -> "model")
         model_id = request.model
         if "." in model_id:
@@ -443,8 +496,23 @@ async def create_response(request: ResponseRequest) -> Response:
         # Track conversation history (for analytics and future vector memory)
         await _conversation_history.add_response(conversation_id, response)
 
+        # End trace with response info
+        response_preview = _extract_response_preview(response)
+        end_trace(
+            response={
+                "output_preview": response_preview,
+                "output_count": len(response.output) if response.output else 0,
+                "status": response.status,
+            },
+            status="completed",
+        )
+
         return response
 
+    except Exception as e:
+        end_trace(status="error")
+        raise
+
 
 async def create_response_with_steward(request: ResponseRequest) -> Response:
     """
@@ -454,7 +522,7 @@ async def create_response_with_steward(request: ResponseRequest) -> Response:
     1. Steward analyzes the request and recommends capabilities
     2. Phase 1: Tatlock orchestrates tool calls and expert delegations
     3. Phase 2: Tatlock synthesizes butler-toned response from results
-    4. Tool usage is tracked for benchmarking
+    4. Tool usage is tracked for analysis
 
     Args:
         request: Response request
@@ -473,6 +541,34 @@ async def create_response_with_steward(request: ResponseRequest) -> Response:
     # Get or generate conversation ID
     conversation_id = await _conversation_history.get_conversation_id(request)
 
+    # Set context for tracing
+    effective_user = request.user or get_default_user()
+    current_user.set(effective_user)
+    current_conversation.set(conversation_id)
+
+    # Extract user input for tracing
+    user_input = _extract_user_input(request.input)
+
+    # Start trace
+    trace = start_trace(
+        conversation_id=conversation_id,
+        user=effective_user,
+        request={
+            "model": request.model,
+            "input_preview": user_input[:200] if user_input else "",
+            "full_input": request.input,
+            "streaming": False,
+        },
+    )
+
+    # Start service span
+    service_span = start_span(
+        "create_response_with_steward",
+        SpanType.ROUTER,
+        metadata={"model": request.model, "user": effective_user},
+    )
+
+    try:
         # Extract user message and conversation history
         user_message = ""
         for msg in reversed(request.input):
@@ -599,8 +695,23 @@ async def create_response_with_steward(request: ResponseRequest) -> Response:
             tool_summary=tracker.get_summary(),
         )
 
+        # End trace with response info
+        response_preview = _extract_response_preview(response)
+        end_trace(
+            response={
+                "output_preview": response_preview,
+                "output_count": len(response.output) if response.output else 0,
+                "status": response.status,
+            },
+            status="completed",
+        )
+
         return response
 
+    except Exception as e:
+        end_trace(status="error")
+        raise
+
 
 async def create_response_stream(
     request: ResponseRequest

wakeup.sh

@@ -43,8 +43,8 @@ LOG_FILE="$LOGS_DIR/server.log"
 echo -e "${YELLOW}Logs will be written to: ${LOG_FILE}${NC}"
 
 # Start the server
-echo -e "${GREEN}Starting uvicorn server on http://localhost:8777${NC}"
+echo -e "${GREEN}Starting uvicorn server on http://tower-of-joy:8777${NC}"
 echo -e "${YELLOW}Press Ctrl+C to stop the server${NC}"
 echo ""
 
-uvicorn src.main:app --reload --host localhost --port 8777 2>&1 | tee "$LOG_FILE"
+uvicorn src.main:app --reload --host 0.0.0.0 --port 8777 2>&1 | tee "$LOG_FILE"