ed7c809fd0
Pins the arc's original goal against the ACTUAL serving spine (ChatRuntime, the driver core chat constructs), not just the composer: a user asks a basic logic question -> CORE decides -> an articulated, deterministic, telemetered response comes back. Covers propositional + categorical, flag-off byte-identity across both bands, honest reader-refusal on out-of-regime input (INV-34), and the peripheral-systems wiring. Peripheral systems verified (nothing to build, all automatic): deduction turns are well-formed served turns (turn_log grows, _context.turn advances) so ADR-0255 discovery-yield counts them; they carry grounding_source= 'deduction' on ChatResponse + TurnEvent and an observable DispatchAttempt; they emit no discovery candidates (decided answer, not a would-have-grounded gap) so they lift the yield denominator without inflating the numerator. Scope-out doc (docs/research/deduction-serve-arc-completion-and-scope-outs- 2026-07-23.md) records the whole arc + everything deliberately deferred with rationale: multi-word English reader relaxation (risky, shared reader, its own pass), multi-step proof recap (Phase-6 core_logos), accrue_realized_ knowledge default, ADR-0246 s3.7 (blocked on research evidence not wiring), Tier-2 (waits for field reader), Hamiltonian compiler (eval-side), and the GroundingSource enum registration. New: tests/test_deduction_serve_e2e.py (5 tests through the real REPL path). [Verification]: core test --suite deductive 50 passed; smoke 180 passed; cognition 122 passed/1 skipped.
87 lines
3.4 KiB
Python
87 lines
3.4 KiB
Python
"""Deduction-serve arc, Phase 5 — end-to-end workflow through the real REPL path.
|
|
|
|
The arc's original goal, pinned against the ACTUAL serving spine (``ChatRuntime``,
|
|
the driver ``core chat`` constructs) rather than the composer in isolation:
|
|
|
|
a user asks a basic logic question -> CORE decides -> an articulated,
|
|
deterministic, telemetered response comes back.
|
|
|
|
Also pins the peripheral-systems wiring (Phase 5): deduction turns are
|
|
well-formed ``TurnEvent``s tagged ``grounding_source="deduction"``, they advance
|
|
the served-turn counter (so ADR-0255 discovery-yield counts them), and they
|
|
carry an observable ``DispatchAttempt`` — with the whole thing byte-identical
|
|
when the flag is off.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from chat.runtime import ChatRuntime
|
|
from core.config import RuntimeConfig
|
|
|
|
|
|
def _runtime(enabled: bool) -> ChatRuntime:
|
|
return ChatRuntime(
|
|
config=RuntimeConfig(deduction_serving_enabled=enabled), no_load_state=True,
|
|
)
|
|
|
|
|
|
def test_end_to_end_propositional_and_categorical_workflow() -> None:
|
|
rt = _runtime(True)
|
|
prop = rt.chat("If p then q. p. Therefore q.")
|
|
assert prop.grounding_source == "deduction"
|
|
assert "Your premises entail: q" in prop.surface
|
|
|
|
cat = rt.chat(
|
|
"All mammals are animals. All whales are mammals. "
|
|
"Therefore all whales are animals."
|
|
)
|
|
assert cat.grounding_source == "deduction"
|
|
assert "valid" in cat.surface and "follows" in cat.surface
|
|
|
|
|
|
def test_deduction_turns_are_well_formed_served_turns() -> None:
|
|
"""turn_log grows and the served-turn counter advances — so a deduction
|
|
conversation is real served traffic (ADR-0255 discovery-yield denominator)."""
|
|
rt = _runtime(True)
|
|
before = rt._context.turn
|
|
rt.chat("p or q. Not p. Therefore q.")
|
|
rt.chat("If a then b. If b then c. a. Therefore c.")
|
|
assert len(rt.turn_log) == 2
|
|
assert rt._context.turn == before + 2
|
|
last = rt.turn_log[-1]
|
|
assert last.grounding_source == "deduction"
|
|
|
|
|
|
def test_dispatch_trace_records_deduction_commit() -> None:
|
|
rt = _runtime(True)
|
|
resp = rt.chat("If p then q. p. Therefore q.")
|
|
assert resp.dispatch_trace is not None
|
|
assert resp.dispatch_trace.selected == "deduction"
|
|
committed = [
|
|
a for a in resp.dispatch_trace.attempts
|
|
if a.source == "deduction" and a.outcome == "admitted"
|
|
]
|
|
assert committed, "a committed deduction turn must record an admitted DispatchAttempt"
|
|
|
|
|
|
def test_flag_off_is_byte_identical_across_bands() -> None:
|
|
"""With the flag off, both a propositional and a categorical argument fall
|
|
through to the pre-arc pack-token-gloss surface, unchanged."""
|
|
rt = _runtime(False)
|
|
for text in [
|
|
"If p then q. p. Therefore q.",
|
|
"All mammals are animals. All whales are mammals. Therefore all whales are animals.",
|
|
]:
|
|
resp = rt.chat(text)
|
|
assert resp.grounding_source == "pack"
|
|
assert "Pack-resident tokens" in resp.surface
|
|
|
|
|
|
def test_out_of_regime_argument_refuses_honestly() -> None:
|
|
"""A 'therefore' argument the reader can't parse into either band gets an
|
|
honest committed refusal surface, never a fluent-but-ungrounded answer or a
|
|
silent fall-through (INV-34 fail-closed)."""
|
|
rt = _runtime(True)
|
|
resp = rt.chat("If it rains then the ground is wet. It rains. Therefore the ground is wet.")
|
|
assert resp.grounding_source == "deduction"
|
|
assert "can't parse" in resp.surface # honest reader-refusal disclosure
|