1000411eb2
Frame Engine (v3-framed): - Tick-based deterministic pipeline: frames advance on completion, not timers - FrameRecord/FrameTrace dataclasses for structured per-message tracing - /api/frames endpoint: queryable frame trace history (last 20 messages) - frame_trace HUD event with full pipeline visibility - Reflex=2F, Director=4F, Director+Interpreter=5F deterministic frame counts Expert Architecture (v4-eras): - PA node (pa_v1): routes to domain experts, holds user context - ExpertNode base: stateless executor with plan+execute two-LLM-call pattern - ErasExpertNode: eras2_production DB specialist with DESCRIBE-first discipline - Schema caching: DESCRIBE results reused across queries within session - Progress streaming: PA streams thinking message, expert streams per-tool progress - PARouting type for structured routing decisions UI Controls Split: - Separate thinker_controls from machine controls (current_controls is now a property) - Machine buttons persist across Thinker responses - Machine state parser handles both dict and list formats from Director - Normalized button format with go/payload field mapping WebSocket Architecture: - /ws/test: dedicated debug socket for test runner progress - /ws/trace: dedicated debug socket for HUD/frame trace events - /ws (chat): cleaned up, only deltas/controls/done/cleared - WS survives graph switch (re-attaches to new runtime) - Pipeline result reset on clear Test Infrastructure: - Live test streaming: on_result callback fires per check during execution - Frontend polling fallback (500ms) for proxy-buffered WS - frame_trace-first trace assertion (fixes stale perceived event bug) - action_match supports "or" patterns and multi-pattern matching - Trace window increased to 40 events - Graph-agnostic assertions (has X or Y) Test Suites: - smoketest.md: 12 steps covering all categories (~2min) - fast.md: 10 quick checks (~1min) - fast_v4.md: 10 v4-eras specific checks - expert_eras.md: eras domain tests (routing, DB, schema, errors) - expert_progress.md: progress streaming tests Other: - Shared db.py extracted from thinker_v2 (reused by experts) - InputNode prompt: few-shot examples, history as context summary - Director prompt: full tool signatures for add_state/reset_machine/destroy_machine - nginx no-cache headers for static files during development - Cache-busted static file references Scores: v3 smoketest 39/40, v4-eras fast 28/28, expert_eras 23/23 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
89 lines
3.1 KiB
Python
89 lines
3.1 KiB
Python
"""Message types flowing between nodes."""
|
|
|
|
from dataclasses import dataclass, field, asdict
|
|
|
|
|
|
@dataclass
|
|
class Envelope:
|
|
"""What flows between nodes."""
|
|
text: str
|
|
user_id: str = "anon"
|
|
session_id: str = ""
|
|
timestamp: str = ""
|
|
|
|
|
|
@dataclass
|
|
class InputAnalysis:
|
|
"""Structured classification from Input node."""
|
|
who: str = "unknown"
|
|
language: str = "en"
|
|
intent: str = "request" # question | request | social | action | feedback
|
|
topic: str = ""
|
|
tone: str = "casual" # casual | frustrated | playful | urgent
|
|
complexity: str = "simple" # trivial | simple | complex
|
|
context: str = ""
|
|
|
|
|
|
@dataclass
|
|
class Command:
|
|
"""Input node's structured perception of what was heard."""
|
|
analysis: InputAnalysis
|
|
source_text: str
|
|
metadata: dict = field(default_factory=dict)
|
|
|
|
@property
|
|
def instruction(self) -> str:
|
|
"""Backward-compatible summary string for logging/thinker."""
|
|
a = self.analysis
|
|
return f"{a.who} ({a.intent}, {a.tone}): {a.topic}"
|
|
|
|
|
|
@dataclass
|
|
class DirectorPlan:
|
|
"""Director v2's output — tells Thinker exactly what to execute."""
|
|
goal: str = ""
|
|
steps: list = field(default_factory=list) # ["query_db('SHOW TABLES')", ...]
|
|
present_as: str = "summary" # table | summary | machine
|
|
tool_sequence: list = field(default_factory=list) # [{"tool": "query_db", "args": {...}}, ...]
|
|
reasoning: str = "" # Director's internal reasoning (for audit)
|
|
response_hint: str = "" # How to phrase the response if no tools needed
|
|
|
|
@property
|
|
def has_tools(self) -> bool:
|
|
return bool(self.tool_sequence)
|
|
|
|
@property
|
|
def is_direct_response(self) -> bool:
|
|
return not self.tool_sequence and bool(self.response_hint)
|
|
|
|
|
|
@dataclass
|
|
class InterpretedResult:
|
|
"""Interpreter's factual summary of tool output."""
|
|
summary: str # Factual text summary
|
|
row_count: int = 0 # Number of data rows (for DB)
|
|
key_facts: list = field(default_factory=list) # ["693 customers", "avg 5.2 devices"]
|
|
confidence: str = "high" # high | medium | low
|
|
|
|
|
|
@dataclass
|
|
class PARouting:
|
|
"""PA's routing decision — which expert handles this, what's the job."""
|
|
expert: str = "none" # "eras" | "plankiste" | "none"
|
|
job: str = "" # Self-contained task for the expert
|
|
thinking_message: str = "" # Shown to user while expert works
|
|
response_hint: str = "" # If expert="none", PA answers directly
|
|
language: str = "de" # Response language
|
|
|
|
|
|
@dataclass
|
|
class ThoughtResult:
|
|
"""Thinker node's output — either a direct answer or tool results."""
|
|
response: str
|
|
tool_used: str = ""
|
|
tool_output: str = ""
|
|
actions: list = field(default_factory=list) # [{label, action, payload?}]
|
|
state_updates: dict = field(default_factory=dict) # {key: value} from set_state
|
|
display_items: list = field(default_factory=list) # [{type, label, value?, style?}] from emit_display
|
|
machine_ops: list = field(default_factory=list) # [{op, id, ...}] from machine tools
|