core/generate/realizer.py
Shay c1e723f185 feat: integrate 3-core-language depth into PropositionGraph spine for bidirectional unification
- Add LexicalResolution dataclass + resolve_entry() in chat/pack_resolver.py
  that returns language, root, morphology_id, gloss, semantic_domains from
  he/grc/en packs (lru-cached, first-match, full depth support).

- Extend GraphNode (generate/graph_planner.py) with optional language/root/
  morphology_id fields (defaults preserve all call sites). Update as_dict()
  to include them conditionally. ground_graph() now propagates depth.

- Generalize enrichment in core/cognition/pipeline.py:
  - Per-subject resolution map using depth packs.
  - Enrich all matching nodes before ground (subject→node map).
  - Pass depth alongside recalled_words to ground_graph().

- Consume depth on articulation side:
  - realize_semantic() and render_semantic() now accept/use language+root
    for etymological/Logos framing on Hebrew/Greek nodes (e.g. "אמת (Hebrew
    root: א-מ-ן) is defined as..."). English unchanged.

- Enrich oov_geometric_context with node_depths for future geometric
  anti-unification using roots.

- Extend recognition/connector.py to forward depth from EpistemicNode
  paths into GraphNode.

- Add full Hebrew turn test under realizer_grounded_authority flag.
- Update related tests (semantic realizer, OOV context, surface resolution).
- Cleaned legacy type() hack immediately on discovery (hard-stop rule).

All targeted tests green (52+ in slices), broad relevant suite 581 passed.
Invariants preserved: versor only at owned boundaries, exact recall,
immutable updates, no new legacy parsers. 3 pillars upheld.

Work continues tomorrow from this checkpoint.
2026-07-06 09:01:43 -07:00

302 lines
10 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

"""ArticulationRealizerV2 — deterministic template-based realization.
Converts an ArticulationTarget (ordered rhetorical steps from the graph
planner) into a RealizedPlan: an ordered sequence of surface fragments
joined into a single deterministic surface string.
Design constraints:
- No LLM fallback
- No broad grammar engine
- Deterministic: same ArticulationTarget → same RealizedPlan, always
- Composable: does not replace the existing realize() path yet
"""
from __future__ import annotations
from dataclasses import dataclass
from core.physics.energy import EnergyClass
from generate.graph_planner import (
ArticulationStep,
ArticulationTarget,
PropositionGraph,
RhetoricalMove,
)
from generate.intent import IntentTag
from generate.semantic_templates import render_semantic
from generate.templates import render_step
_ENERGY_SURFACE_PREFIX: dict[EnergyClass, str] = {
EnergyClass.E0: "From memory: ",
EnergyClass.E1: "I seem to recall: ",
EnergyClass.E2: "I recall: ",
EnergyClass.E3: "",
EnergyClass.E4: "",
}
def energy_modulated_surface(base_surface: str, energy_class: EnergyClass) -> str:
"""Prepend energy-class framing per ADR-0006 §Integration Points."""
prefix = _ENERGY_SURFACE_PREFIX.get(energy_class, "")
if not prefix or not base_surface:
return base_surface
return prefix + base_surface
@dataclass(frozen=True, slots=True)
class RealizedFragment:
node_id: str
move: RhetoricalMove
surface: str
def as_dict(self) -> dict[str, str]:
return {
"node_id": self.node_id,
"move": self.move.value,
"surface": self.surface,
}
def _capitalize_sentence(s: str) -> str:
"""Capitalize the first alphabetic character of a sentence.
Skips leading whitespace/punctuation so fragments that start with
discourse markers ("next, knowledge…") still emit a capital first
letter ("Next, knowledge…") at the sentence boundary. Leaves the
rest of the string untouched — proper nouns and embedded all-caps
tokens are preserved.
"""
if not s:
return s
for i, ch in enumerate(s):
if ch.isalpha():
return s[:i] + ch.upper() + s[i + 1:]
return s
def _join_as_paragraph(fragments: list["RealizedFragment"]) -> str:
"""Join fragments into a paragraph with sentence-initial capitalization.
Each fragment becomes one sentence; sentence-initial letters are
capitalized; the paragraph ends with a single terminal period.
"""
if not fragments:
return ""
pieces: list[str] = []
for f in fragments:
s = f.surface.strip()
if not s:
continue
s = _capitalize_sentence(s)
pieces.append(s)
joined = ". ".join(pieces)
if joined and not joined.endswith("."):
joined += "."
return joined
@dataclass(frozen=True, slots=True)
class RealizedPlan:
fragments: tuple[RealizedFragment, ...]
surface: str
def as_dict(self) -> dict[str, object]:
return {
"fragments": tuple(f.as_dict() for f in self.fragments),
"surface": self.surface,
}
def realize_semantic(
target: ArticulationTarget,
graph: PropositionGraph | None = None,
) -> RealizedPlan:
"""Realize using intent-aware semantic templates.
Uses the source intent to select a template that produces structurally
better surfaces (e.g. "X is defined as Y" for definition intents)
rather than the generic rhetorical-move templates.
Returns an empty RealizedPlan for empty/None targets so the caller
can fall back to the older articulation path.
"""
if target is None or not target.steps:
return RealizedPlan(fragments=(), surface="")
intent = target.source_intent
fragments: list[RealizedFragment] = []
# Comb pass 2026-05-21 — O(1) object-slot lookup per step.
node_objs = _build_node_map(graph)
# Depth map for 3-language articulation enrichment (Hebrew roots, Greek precision).
# Consulted when realizing surfaces for higher-fidelity etymological/Logos framing.
depth_by_id: dict[str, tuple[str | None, str | None]] = {}
if graph:
for n in graph.nodes:
depth_by_id[n.node_id] = (getattr(n, "language", None), getattr(n, "root", None))
if intent is IntentTag.COMPARISON and len(target.steps) >= 2:
step_a = target.steps[0]
step_b = target.steps[1]
obj_a = node_objs.get(step_a.node_id, "...")
secondary = step_b.subject if step_b.subject != step_a.subject else obj_a
lang_a, root_a = depth_by_id.get(step_a.node_id, (None, None))
surface = render_semantic(
intent=intent,
subject=step_a.subject,
predicate=step_a.predicate,
obj=obj_a,
secondary=secondary,
language=lang_a,
root=root_a,
)
fragments.append(RealizedFragment(
node_id=step_a.node_id,
move=RhetoricalMove.CONTRAST,
surface=surface,
))
else:
for step in target.steps:
obj = node_objs.get(step.node_id, "...")
lang, rt = depth_by_id.get(step.node_id, (None, None))
surface = render_semantic(
intent=intent,
subject=step.subject,
predicate=step.predicate,
obj=obj,
language=lang,
root=rt,
)
move = step.move
if move is RhetoricalMove.ASSERT and intent is IntentTag.CORRECTION:
move = RhetoricalMove.CORRECT
fragments.append(RealizedFragment(
node_id=step.node_id,
move=move,
surface=surface,
))
joined = _join_as_paragraph(fragments)
return RealizedPlan(fragments=tuple(fragments), surface=joined)
def _build_node_map(graph: PropositionGraph | None) -> dict[str, str]:
"""Index graph nodes by node_id for O(1) ``obj`` lookup.
Comb pass 2026-05-21 — pre-fix ``_resolve_obj`` did an O(N) linear
scan of ``graph.nodes`` per step, so a target with S steps over an
N-node graph cost O(S × N). Building the map once in the realizer
and indexing into it makes the realizer linear in (S + N) overall.
Returns an empty mapping when the graph is None or empty.
"""
if graph is None:
return {}
return {node.node_id: node.obj for node in graph.nodes}
def _resolve_obj(step: ArticulationStep, graph: PropositionGraph | None) -> str:
"""Look up the object slot from the graph node matching this step.
Retained as the legacy single-step accessor for callers that do
not have a node_map handy. Hot paths in ``realize_semantic`` and
``realize_target`` build the map once and bypass this function.
"""
if graph is None:
return "..."
for node in graph.nodes:
if node.node_id == step.node_id:
return node.obj
return "..."
def realize_target(
target: ArticulationTarget,
graph: PropositionGraph | None = None,
) -> RealizedPlan:
"""Realize an ArticulationTarget into a deterministic surface plan.
Handles compound constructions (conjunction, disjunction, complement,
relative clause) by detecting graph edges and joining surfaces with
appropriate connectors rather than sentence-level punctuation.
Returns an empty-but-valid RealizedPlan for empty/None targets.
"""
from generate.graph_planner import Relation
if target is None or not target.steps:
return RealizedPlan(fragments=(), surface="")
edge_map: dict[str, tuple[str, Relation]] = {}
if graph is not None:
for edge in graph.edges:
edge_map[edge.source] = (edge.target, edge.relation)
step_by_id = {step.node_id: step for step in target.steps}
# Comb pass 2026-05-21 — O(1) object-slot lookup per step.
node_objs = _build_node_map(graph)
visited: set[str] = set()
fragments: list[RealizedFragment] = []
for step in target.steps:
if step.node_id in visited:
continue
visited.add(step.node_id)
obj = node_objs.get(step.node_id, "...")
move = step.move
if move is RhetoricalMove.ASSERT and target.source_intent is IntentTag.CORRECTION:
move = RhetoricalMove.CORRECT
surface = render_step(
move=move,
subject=step.subject,
predicate=step.predicate,
obj=obj,
negated=step.negated,
quantifier=step.quantifier,
tense=step.tense,
aspect=step.aspect,
)
if step.node_id in edge_map:
target_id, relation = edge_map[step.node_id]
target_step = step_by_id.get(target_id)
if target_step is not None and target_id not in visited:
match relation:
case Relation.CONJUNCTION | Relation.DISJUNCTION | Relation.COMPLEMENT | Relation.RELATIVE:
visited.add(target_id)
target_obj = node_objs.get(target_step.node_id, "...")
target_surface = render_step(
move=RhetoricalMove.ASSERT,
subject=target_step.subject,
predicate=target_step.predicate,
obj=target_obj,
negated=target_step.negated,
quantifier=target_step.quantifier,
tense=target_step.tense,
aspect=target_step.aspect,
)
match relation:
case Relation.CONJUNCTION:
surface = f"{surface} and {target_surface}"
case Relation.DISJUNCTION:
surface = f"{surface} or {target_surface}"
case Relation.COMPLEMENT:
surface = f"{step.subject} {step.predicate} that {target_surface}"
case Relation.RELATIVE:
surface = f"{step.subject}, which {target_step.predicate} {target_obj}, {step.predicate} {obj}"
case _:
pass
fragments.append(
RealizedFragment(
node_id=step.node_id,
move=move,
surface=surface,
)
)
joined = _join_as_paragraph(fragments)
return RealizedPlan(fragments=tuple(fragments), surface=joined)