core/generate
Shay 401ae53328
chore(generate): make stop-tokens caller-overridable via RuntimeConfig (#87)
Closes audit Finding 6 (2026-05-20).

Pre-fix ``_STOP_TOKENS = frozenset({"it", "to", "word"})`` was
hardcoded inside ``generate.stream.generate()`` and inhibited those
three tokens unconditionally across every pack, every language, and
every domain.  If a pack legitimately needed one of them as a content
word — e.g. a philosophy pack where ``"word"`` maps to λόγος, or a
syntax pack where ``"to"`` is a content node — there was no override
path.  The ``_try_index`` guard handled the case where the token was
absent from the pack, but offered nothing for packs that contained
the token and meant it.

Changes:

  * ``generate.stream.generate`` accepts ``stop_tokens: frozenset[str]
    | None = None``.  ``None`` resolves to the historical
    ``_STOP_TOKENS`` constant, preserving byte-identity for every
    pre-Finding-6 caller.
  * ``RuntimeConfig.stop_tokens: tuple[str, ...] | None = None`` —
    operator-level override threaded through ``ChatRuntime`` into
    ``generate()``.
  * Default ``None`` preserves byte-identical behavior for every
    existing pack and every existing test.

Scope notes:

  * This PR delivers the *runtime override* surface.  Manifest-driven
    per-pack overrides (``generation_stop_tokens`` field in the pack
    manifest) are the natural next step but require a pack-schema
    ADR and re-ratification of every affected pack, so the wiring
    lands first and the manifest field follows on a separate ADR.
  * ``agenerate`` was identified as unreachable and is being deleted
    in a sibling PR (Finding 7); its hardcoded ``_STOP_TOKENS``
    reference disappears with it, so it is intentionally not touched
    here.

Verification:

  * 4 new tests in ``tests/test_stop_tokens_override.py``:
      - ``RuntimeConfig.stop_tokens`` defaults to ``None``
      - ``generate()`` signature exposes ``stop_tokens`` with default
        ``None``
      - the historical constant is unchanged
      - an explicit override flows through the runtime end-to-end
  * ``core eval cognition`` — public 100/100/91.7/100, byte-identical
    to the MEMORY baseline.
  * ``core test --suite cognition`` — 120/0/1.
  * ``core test --suite smoke`` — 67/0.
  * ``core test --suite runtime`` — 19/0.
2026-05-20 19:59:33 -07:00
..
__init__.py chore(generate): delete unreachable agenerate (#90) 2026-05-20 19:59:28 -07:00
admissibility.py feat(adr-0026): Phase 3 — ranked admissibility with margin 2026-05-17 15:03:03 -07:00
articulation.py Graceful fallback in realize() when slot versors are missing 2026-05-13 21:41:52 -07:00
articulation_legality.py feat(realizer): C1.5 — articulation legality at the realizer boundary 2026-05-20 11:11:28 -07:00
attention.py Add ADR-0008 salience attention 2026-05-13 22:40:36 -07:00
bridge_trace.py Phase 1 — bridge trace instrumentation (observation-only) 2026-05-18 18:04:57 -07:00
dialogue.py Fix test suite errors across core physics and generation 2026-05-14 13:02:32 -07:00
discourse_planner.py feat(intent): normalize confirmation-tag propositions (#45) 2026-05-19 22:55:28 -07:00
exhaustion.py feat(adr-0025): Phase 4 — rotor / frame admissibility at the seam 2026-05-17 15:16:32 -07:00
graph_constraint.py fix(adr-0046): make forward-graph-constraint branch mergeable 2026-05-18 05:57:46 -07:00
graph_planner.py feat(realizer): extend to all 13 English v1 constructions 2026-05-16 05:55:49 -07:00
grounding_accessors.py feat(grounding): structured GroundedFact accessors for discourse planner 2026-05-19 11:19:59 -07:00
intent.py feat(intent): normalize confirmation-tag propositions (#45) 2026-05-19 22:55:28 -07:00
intent_bridge.py Phase 2 — proposition-slot grounding for articulate_with_intent 2026-05-18 18:18:31 -07:00
intent_ratifier.py chore(ratifier): calibrate default ratification threshold 0.0 → 0.5 (#86) 2026-05-20 19:59:25 -07:00
morphology.py fix(gaps): close G1+G2+G3 + identity vocab + pipeline safety-stub honour 2026-05-16 21:21:06 -07:00
operators.py feat(compositionality): compose_relations operator lifts lane 68.8% → 100% 2026-05-16 22:44:06 -07:00
proposition.py feat(adr-0022): Forward Semantic Control — Accepted 2026-05-17 12:10:20 -07:00
realizer.py feat(benchmarks): discourse_paragraph lane + pipeline profiler + word-selection tracer 2026-05-16 21:53:46 -07:00
realizer_guard.py feat(coherence): ADR-0075 — realizer slot-type guard (C1) 2026-05-19 22:35:09 -07:00
render.py feat(generate): add render.py — default TextRenderer and Renderer protocol (ADR-0011) 2026-05-13 10:51:52 -07:00
result.py feat(adr-0023): Forward Semantic Control proof evidence — Accepted 2026-05-17 12:55:19 -07:00
rotor_admissibility.py feat(adr-0025): Phase 4 — rotor / frame admissibility at the seam 2026-05-17 15:16:32 -07:00
salience.py Implement core physics and pack validation 2026-05-14 12:35:19 -07:00
semantic_templates.py feat: vault recall index, Rust versor parity, cognitive pack expansion 2026-05-15 15:34:39 -07:00
stream.py chore(generate): make stop-tokens caller-overridable via RuntimeConfig (#87) 2026-05-20 19:59:33 -07:00
surface.py feat(surface): ADR-0031 — score-decomposition surface (per-axis hedges) 2026-05-17 20:16:22 -07:00
templates.py feat(realizer): C1.5 — articulation legality at the realizer boundary 2026-05-20 11:11:28 -07:00