feat: implement Phase 2 two-tier architecture with Steward

Add comprehensive two-tier architecture where Steward analyzes requests
and Tatlock executes with scoped tools. Includes full infrastructure for
request preprocessing, tool tracking, benchmarking, and streaming.

**Added:**
- Steward agent for request analysis and capability recommendation
- Household Registry for centralized capability management
- Request preprocessing pipeline (Steward → Tatlock flow)
- Tool usage tracking and benchmarking system
- Streaming transparency (Steward reasoning visible in streams)
- Structured logging with operation timing
- Redis benchmark storage with 30-day expiry
- Benchmark analysis CLI tools

**Infrastructure:**
- src/agents/steward/ - Steward agent implementation
- src/agents/tatlock_core/ - Tatlock capability domain
- src/core/preprocessing.py - Request preprocessing pipeline
- src/core/tool_tracking.py - Tool call tracking
- src/core/benchmarks.py - Benchmark recording system
- src/core/household_registry.py - Capability registry
- src/core/startup.py - Application startup coordination
- src/core/logging_config.py - Structured logging setup

**Integration:**
- Responses API uses Steward for Tatlock requests
- Chat Completions wraps Responses API for OpenAI compatibility
- Streaming coordinator supports Steward + Tatlock flow
- Tool scoping per request based on Steward recommendations

**Testing:**
- Integration tests for Steward-Tatlock flow
- Benchmark and registry unit tests
- Steward streaming tests

See PHASE2_PLAN.md and PHASE2_COMPLETE.md for detailed documentation.

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

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
This commit is contained in:
2025-12-07 15:39:20 +01:00
co-authored by Claude Sonnet 4.5
parent 2577730546
commit 6eed5f4d13
34 changed files with 6362 additions and 133 deletions
+88
View File
@@ -0,0 +1,88 @@
"""
PydanticAI toolset for Tatlock's core tools.
Converts the core tool functions into PydanticAI tool definitions
that can be registered with agents and the household registry.
"""
from pydantic_ai.tools import Tool
from . import tools
# Create tool definitions for PydanticAI
calculator_tool = Tool(
function=tools.calculate,
name="calculate",
description=(
"Safely evaluate mathematical expressions. "
"Supports basic arithmetic (+, -, *, /, %, **), "
"functions (sqrt, sin, cos, log, exp, etc.), "
"and constants (pi, e). "
"Use this for ALL mathematical calculations."
),
)
current_datetime_tool = Tool(
function=tools.get_current_datetime,
name="get_current_datetime",
description=(
"Get the current date and time. "
"Supports various formats: 'full' (datetime), 'date' (YYYY-MM-DD), "
"'time' (HH:MM:SS), 'iso' (ISO 8601), or custom strftime format. "
"Use this instead of guessing the current date/time."
),
)
time_offset_tool = Tool(
function=tools.calculate_time_offset,
name="calculate_time_offset",
description=(
"Calculate a date/time relative to now. "
"Accepts natural language like '1 week ago', '2 days from now', "
"'3 months ago', etc. "
"Use this for calculating past or future dates."
),
)
time_difference_tool = Tool(
function=tools.time_difference,
name="time_difference",
description=(
"Calculate the difference between two dates. "
"Accepts dates in YYYY-MM-DD or YYYY-MM-DD HH:MM:SS format. "
"Second date can be 'now'. "
"Returns human-readable difference (e.g., '5 days, 3 hours')."
),
)
web_search_tool = Tool(
function=tools.search_web,
name="search_web",
description=(
"Search the web using SearXNG for current information. "
"Use this to find recent events, current data, or verify facts. "
"Returns formatted results with titles, URLs, and snippets. "
"Useful for information that may have changed since training data."
),
takes_ctx=False,
)
# Combined toolset of all core tools
tatlock_core_tools = [
calculator_tool,
current_datetime_tool,
time_offset_tool,
time_difference_tool,
web_search_tool,
]
def get_core_tools():
"""
Get list of Tatlock's core tool definitions.
Returns:
List of PydanticAI Tool objects
"""
return tatlock_core_tools