2125_GCE/xic_ops.py

from dataclasses import dataclass, field
from typing import Dict, Any, Optional
from runtime_executor.runner import execute_gx, ExecutionError


@dataclass
class XICContext:
    model_path: Optional[str] = None
    mode: str = "chat"
    params: Dict[str, Any] = field(default_factory=dict)
    _state: Dict[str, Any] = field(default_factory=dict)
    symbolic_mode: bool = False


def op_LOAD_MODEL(ctx: XICContext, *args):
    """LOAD_MODEL <path>: Load a .gx model file."""
    if not args:
        raise ValueError("LOAD_MODEL requires a path argument")
    model_path = args[0]
    ctx.model_path = str(model_path)
    print(f"[XIC] Model loaded: {ctx.model_path}")


def op_SET_MODE(ctx: XICContext, *args):
    """SET_MODE <mode>: Set execution mode (chat, eval, benchmark, symbolic)."""
    if not args:
        raise ValueError("SET_MODE requires a mode argument")
    ctx.mode = str(args[0])
    if ctx.mode == "symbolic":
        ctx.symbolic_mode = True
    print(f"[XIC] Mode set to: {ctx.mode}")


def op_SET_PARAM(ctx: XICContext, *args):
    """SET_PARAM <key> <value>: Set a parameter."""
    if len(args) < 2:
        raise ValueError("SET_PARAM requires key and value arguments")
    key = str(args[0])
    value = args[1]
    ctx.params[key] = value
    print(f"[XIC] Parameter {key} = {value}")


def op_RUN_PROMPT(ctx: XICContext, *args):
    """RUN_PROMPT <prompt>: Execute prompt against loaded model or symbolic cognition.

    Symbolic behavior (ctx.symbolic_mode=True):
    - Routes through symbolic pipeline (run_symbolic_pipeline).
    - Uses ctx.params["context"] for execution context.
    - Stores full pipeline result in ctx._state["last_symbolic_pipeline"].

    Compressed behavior (ctx.symbolic_mode=False):
    - Requires model_path to be set via LOAD_MODEL.
    - Routes to execute_gx() for compressed execution.
    - Stores result in ctx._state["last_result"].
    """
    if not args:
        raise ValueError("RUN_PROMPT requires a prompt argument")

    prompt = str(args[0])

    if ctx.symbolic_mode:
        from glyphos.symbolic_pipeline import run_symbolic_pipeline
        pipeline_result = run_symbolic_pipeline(
            prompt=prompt,
            context=ctx.params.get("context")
        )
        print(f"[XIC-SYMBOLIC] {pipeline_result.output_text}")
        ctx._state["last_symbolic_result"] = pipeline_result.output_text
        ctx._state["last_symbolic_pipeline"] = pipeline_result
        return

    if not ctx.model_path:
        raise ValueError("No model loaded. Use LOAD_MODEL first.")

    try:
        execution_context = execute_gx(
            ctx.model_path,
            trace=ctx.params.get("trace", False),
            profile=ctx.params.get("profile", False)
        )

        print(f"[XIC] Execution complete")
        print(f"[XIC] Result: {getattr(execution_context, 'result', 'OK')}")
        ctx._state["last_result"] = execution_context

    except ExecutionError as e:
        print(f"[XIC] Execution error: {e}")
        raise
    except Exception as e:
        print(f"[XIC] Unexpected error: {e}")
        raise


def op_STREAM(ctx: XICContext, *args):
    """STREAM <prompt>: Execute and stream output line by line.

    Symbolic behavior (ctx.symbolic_mode=True):
    - Routes through symbolic pipeline.
    - Streams output_text line by line with [XIC-STREAM] prefix.
    - Stores pipeline result in ctx._state["last_symbolic_pipeline"].

    Compressed behavior (ctx.symbolic_mode=False):
    - Routes to execute_gx().
    - Streams result line by line with [XIC-STREAM] prefix.
    - Stores result in ctx._state["last_result"].
    """
    if not args:
        raise ValueError("STREAM requires a prompt argument")
    prompt = str(args[0])

    if ctx.symbolic_mode:
        from glyphos.symbolic_pipeline import run_symbolic_pipeline
        pipeline_result = run_symbolic_pipeline(
            prompt=prompt,
            context=ctx.params.get("context")
        )
        for chunk in str(pipeline_result.output_text).split("\n"):
            if chunk.strip():
                print(f"[XIC-STREAM] {chunk}")
        ctx._state["last_symbolic_result"] = pipeline_result.output_text
        ctx._state["last_symbolic_pipeline"] = pipeline_result
        return

    if not ctx.model_path:
        raise ValueError("No model loaded. Use LOAD_MODEL first.")

    try:
        exec_ctx = execute_gx(
            ctx.model_path,
            trace=ctx.params.get("trace", False),
            profile=ctx.params.get("profile", False),
        )
        result_text = str(getattr(exec_ctx, "result", "OK"))
        for chunk in result_text.split("\n"):
            if chunk.strip():
                print(f"[XIC-STREAM] {chunk}")
        ctx._state["last_result"] = exec_ctx
    except ExecutionError as e:
        print(f"[XIC] Execution error: {e}")
        raise
    except Exception as e:
        print(f"[XIC] Unexpected error: {e}")
        raise


def op_CHAIN(ctx: XICContext, *args):
    """CHAIN <label>: Mark start of a named chain; passes context forward."""
    if not args:
        raise ValueError("CHAIN requires a label argument")
    label = str(args[0])
    ctx.params["chain_label"] = label
    print(f"[XIC-CHAIN] Entering chain: {label}")


def op_CALL_GLYPH(ctx: XICContext, *args):
    """CALL_GLYPH <glyph_id> <payload>: Invoke glyph-aware cognition with resonance tracking.

    Routes through symbolic pipeline with explicit glyph_id parameter.
    The glyph_id is propagated into the pipeline context and used for
    glyph-aware symbolic transformations in the LAIN layer.

    Stores comprehensive result with key "glyph_{glyph_id}" containing:
    - output_text: Final text from cognition
    - fused_symbol: Fused symbolic representation with glyph_ids and resonance_map
    - resonance_metrics: Extracted per-glyph resonance scores (weight, lineage, contributor, etc.)
    - global_resonance_score: Overall resonance from LAIN
    - steps: List of symbolic pipeline steps
    """
    if not args:
        raise ValueError("CALL_GLYPH requires glyph_id argument")
    glyph_id = str(args[0])
    payload = str(args[1]) if len(args) > 1 else ""

    from glyphos.symbolic_pipeline import (
        run_symbolic_pipeline,
        extract_glyph_resonances,
        format_glyph_resonance_report,
    )

    glyph_context = dict(ctx.params.get("context", {}))
    glyph_context["glyph_id"] = glyph_id

    pipeline_result = run_symbolic_pipeline(
        prompt=payload,
        context=glyph_context,
        glyph_id=glyph_id,
    )

    print(f"[XIC-GLYPH] {pipeline_result.output_text}")

    # Extract resonance metrics
    resonance_metrics = extract_glyph_resonances(pipeline_result)
    global_resonance = 0.0
    if pipeline_result.fused_symbol:
        global_resonance = pipeline_result.fused_symbol.resonance_map.global_resonance_score

    # Store comprehensive result
    ctx._state[f"glyph_{glyph_id}"] = {
        "output_text": pipeline_result.output_text,
        "fused_symbol": {
            "summary": pipeline_result.fused_symbol.summary if pipeline_result.fused_symbol else None,
            "glyph_ids": pipeline_result.fused_symbol.glyph_ids if pipeline_result.fused_symbol else [],
        } if pipeline_result.fused_symbol else None,
        "resonance_metrics": resonance_metrics,
        "global_resonance_score": global_resonance,
        "steps": [{"name": s.name, "kind": s.kind, "payload": str(s.payload)[:100]}
                  for s in pipeline_result.steps],
    }

    # Also store for direct query access
    ctx._state[f"glyph_{glyph_id}_pipeline_result"] = pipeline_result


def op_SET_CONTEXT(ctx: XICContext, *args):
    """SET_CONTEXT <key> <value>: Set symbolic/cognitive context key."""
    if len(args) < 2:
        raise ValueError("SET_CONTEXT requires key and value")
    if "context" not in ctx.params:
        ctx.params["context"] = {}
    key = str(args[0])
    value = args[1]
    ctx.params["context"][key] = value
    print(f"[XIC] Context {key} = {value}")


def op_LOG(ctx: XICContext, *args):
    """LOG <message>: Structured log from XIC program."""
    message = str(args[0]) if args else ""
    print(f"[XIC-LOG] {message}")


def op_GET_GLYPH_RESONANCE(ctx: XICContext, *args):
    """GET_GLYPH_RESONANCE <glyph_id> [metric]: Query glyph resonance metrics from previous CALL_GLYPH.

    Retrieves resonance data stored by CALL_GLYPH and provides:
    - No metric arg: Returns formatted resonance report for the glyph
    - metric="weight" | "lineage" | "contributor" | "frequency" | "grammar": Returns specific metric for glyph
    - metric="global": Returns global resonance score
    - metric="dominant": Returns top 5 dominant glyphs by weight

    Results are printed and stored in ctx._state["resonance_query_<glyph_id>_<metric>"]
    """
    if not args:
        raise ValueError("GET_GLYPH_RESONANCE requires glyph_id argument")

    glyph_id = str(args[0])
    metric = str(args[1]) if len(args) > 1 else None

    # Try to find the stored glyph result
    glyph_key = f"glyph_{glyph_id}"
    if glyph_key not in ctx._state:
        print(f"[XIC-RESONANCE] No resonance data for glyph: {glyph_id}")
        ctx._state[f"resonance_query_{glyph_id}_notfound"] = None
        return

    glyph_data = ctx._state[glyph_key]

    # If we have the pipeline result object, use it to regenerate report
    pipeline_key = f"glyph_{glyph_id}_pipeline_result"
    if pipeline_key in ctx._state:
        from glyphos.symbolic_pipeline import (
            format_glyph_resonance_report,
            extract_glyph_resonances,
            get_dominant_glyphs,
        )
        pipeline_result = ctx._state[pipeline_key]

        if metric is None or metric == "report":
            report = format_glyph_resonance_report(pipeline_result)
            print(f"[XIC-RESONANCE] Report for {glyph_id}:\n{report}")
            ctx._state[f"resonance_query_{glyph_id}_report"] = report
        elif metric == "global":
            if pipeline_result.fused_symbol:
                score = pipeline_result.fused_symbol.resonance_map.global_resonance_score
                print(f"[XIC-RESONANCE] Global resonance for {glyph_id}: {score:.3f}")
                ctx._state[f"resonance_query_{glyph_id}_global"] = score
            else:
                print(f"[XIC-RESONANCE] No fused_symbol for {glyph_id}")
                ctx._state[f"resonance_query_{glyph_id}_global"] = None
        elif metric == "dominant":
            dominant = get_dominant_glyphs(pipeline_result, n=5)
            print(f"[XIC-RESONANCE] Dominant glyphs for {glyph_id}:")
            for glyph, weight in dominant:
                print(f"  {glyph}: {weight:.3f}")
            ctx._state[f"resonance_query_{glyph_id}_dominant"] = dominant
        elif metric in ["weight", "lineage", "contributor", "frequency", "grammar"]:
            resonances = extract_glyph_resonances(pipeline_result)
            if glyph_id in resonances:
                metric_val = resonances[glyph_id].get(
                    metric if metric != "lineage" else "lineage_score",
                    resonances[glyph_id].get(f"{metric}_score") if metric != "weight" else None
                )
                if metric == "lineage":
                    metric_val = resonances[glyph_id].get("lineage_score")
                elif metric == "contributor":
                    metric_val = resonances[glyph_id].get("contributor_score")
                elif metric == "frequency":
                    metric_val = resonances[glyph_id].get("frequency_score")
                elif metric == "grammar":
                    metric_val = resonances[glyph_id].get("grammar_score")

                if metric_val is not None:
                    print(f"[XIC-RESONANCE] {metric} for {glyph_id}: {metric_val:.3f}")
                    ctx._state[f"resonance_query_{glyph_id}_{metric}"] = metric_val
                else:
                    print(f"[XIC-RESONANCE] Metric '{metric}' not found for {glyph_id}")
                    ctx._state[f"resonance_query_{glyph_id}_{metric}"] = None
            else:
                print(f"[XIC-RESONANCE] Glyph {glyph_id} not in resonance data")
                ctx._state[f"resonance_query_{glyph_id}_{metric}"] = None
        else:
            print(f"[XIC-RESONANCE] Unknown metric: {metric}")
            ctx._state[f"resonance_query_{glyph_id}_{metric}"] = None
    else:
        # Fallback: use stored resonance_metrics if available
        if "resonance_metrics" in glyph_data:
            resonance_metrics = glyph_data["resonance_metrics"]
            if metric is None:
                print(f"[XIC-RESONANCE] Resonance metrics for {glyph_id}:")
                for glyph, metrics_dict in resonance_metrics.items():
                    print(f"  {glyph}: weight={metrics_dict.get('weight', 0):.3f}")
                ctx._state[f"resonance_query_{glyph_id}_report"] = resonance_metrics
            elif metric == "global":
                score = glyph_data.get("global_resonance_score", 0.0)
                print(f"[XIC-RESONANCE] Global resonance for {glyph_id}: {score:.3f}")
                ctx._state[f"resonance_query_{glyph_id}_global"] = score
            else:
                print(f"[XIC-RESONANCE] Specific metric query requires pipeline result")
                ctx._state[f"resonance_query_{glyph_id}_{metric}"] = None
        else:
            print(f"[XIC-RESONANCE] No resonance metrics available for {glyph_id}")
            ctx._state[f"resonance_query_{glyph_id}_notfound"] = None


# Operation dispatch table
OP_TABLE = {
    "LOAD_MODEL": op_LOAD_MODEL,
    "SET_MODE": op_SET_MODE,
    "SET_PARAM": op_SET_PARAM,
    "SET_CONTEXT": op_SET_CONTEXT,
    "RUN_PROMPT": op_RUN_PROMPT,
    "STREAM": op_STREAM,
    "CHAIN": op_CHAIN,
    "CALL_GLYPH": op_CALL_GLYPH,
    "GET_GLYPH_RESONANCE": op_GET_GLYPH_RESONANCE,
    "LOG": op_LOG,
}