Manage specialist token spend: bound the proposal set, stop discarding it, and name a stop condition

src/hyperloom/inference_optimizer/tests/test_coordinator_async_batch2_unit.py

@@ -1366,7 +1366,7 @@ async def test_compose_prompt_orchestration_all_advisory_blocks(
         assert token in out
 
 
-def test_research_scout_seed_block_keeps_all_rounds(coord: Coordinator) -> None:
+def test_research_scout_seed_block_keeps_findings_and_questions_only(coord: Coordinator) -> None:
     from hyperloom.orchestrator.knowledge import research_hints
 
     research_hints.append_hints(
@@ -1410,11 +1410,14 @@ def test_research_scout_seed_block_keeps_all_rounds(coord: Coordinator) -> None:
 
     assert "hint one" in block
     assert "hint two" in block
-    assert '"name": "first"' in block
-    assert '"name": "second"' in block
     assert "question one" in block
     assert "question two" in block
     assert "ignore-me" not in block
+    # Proposals moved to the shared untested-proposal queue, which also drops
+    # the ones already benched; rendering them here as well would double them.
+    assert "Untested executable proposals" not in block
+    assert '"name": "first"' not in block
+    assert '"name": "second"' not in block
 
 
 @pytest.mark.asyncio

src/hyperloom/inference_optimizer/tests/test_critic_verdict_map.py

@@ -2073,10 +2073,16 @@ def _build_specialist_prompt_text() -> str:
     return system_prompt + "\n" + user_prompt
 
 
-def test_specialist_prompt_renders_top_6_target():
+def test_specialist_prompt_renders_proposal_target_and_ceiling():
     text = _build_specialist_prompt_text()
-    assert "AT MOST **6** entries" in text
-    assert "top-6" in text
+    # Section 8 states both numbers; Section 1 repeats them so the target is
+    # visible before the specialist starts working, not only at exit time.
+    assert "**2 entries is the norm, 4 the hard cap.**" in text
+    assert "**2 proposals is the norm, 4 the hard" in text
+    # Both the padding and the keep-going pressures need a stated counterweight.
+    assert "``empty=true`` is better than one" in text
+    assert "stop once" in text and "not the only stop" in text
+    assert "a coin-flip proposal is worse than none" in text
     assert "reviews each surviving variant" in text
 
 

src/hyperloom/inference_optimizer/tests/test_grid_size_prompt_unit.py

@@ -0,0 +1,33 @@
+# SPDX-FileCopyrightText: 2026 Advanced Micro Devices, Inc.
+# SPDX-License-Identifier: MIT
+
+"""The grid author's two prompt surfaces agree on where a grid comes from and how big it gets."""
+
+from __future__ import annotations
+
+
+def _grid_prompt_surfaces() -> list[str]:
+    from hyperloom.orchestrator.prompts.prompt_builder import (
+        _idea_generation_lines,
+        _format_grid_injection_hint,
+    )
+
+    return [_format_grid_injection_hint("explore") or "", "\n".join(_idea_generation_lines())]
+
+
+def test_both_grid_surfaces_state_the_same_target_and_ceiling():
+    for surface in _grid_prompt_surfaces():
+        assert "4" in surface
+        assert "maximum 6" in surface
+    assert all("Untested proposals (current cycle)" in s for s in _grid_prompt_surfaces()[1:])
+
+
+def test_the_stale_proposal_set_wording_is_gone():
+    from pathlib import Path
+
+    from hyperloom.orchestrator.prompts import prompt_builder
+
+    stale = "proposal_set drives the next"
+    assert stale not in Path(prompt_builder.__file__).read_text(encoding="utf-8")
+    md = Path(prompt_builder.__file__).parent / "orchestration.md"
+    assert "specialist proposal_set" not in md.read_text(encoding="utf-8")

src/hyperloom/inference_optimizer/tests/test_proposal_identity_unit.py

@@ -0,0 +1,122 @@
+# SPDX-FileCopyrightText: 2026 Advanced Micro Devices, Inc.
+# SPDX-License-Identifier: MIT
+
+"""Shared proposal/variant identity.
+
+The fingerprints below were captured from the explore executor's own identity
+block before it was refactored onto this helper. They are pinned rather than
+recomputed: a change here re-keys ``explore_search["tested"]``, so every
+resumed session would re-bench its whole history.
+"""
+
+from __future__ import annotations
+
+import pytest
+
+from hyperloom.orchestrator.actions.executors._proposal_identity import (
+    controls_of,
+    effective_fingerprint,
+    is_executable,
+    normalize_proposal,
+)
+
+
+# (label, extra_args, extra_envs, variant controls, base controls, expected fingerprint)
+_GOLDEN = [
+    ("plain", "--max-num-seqs 128", {"A": "1"}, ([], [], "append"), ([], [], ""), "caacd6bf1da76201"),
+    ("variant-only", "--max-num-seqs 128", {"A": "1"}, (["--x"], ["E"], "append"), ([], [], ""), "39cfaf303d04885d"),
+    ("base-only", "--max-num-seqs 128", {"A": "1"}, ([], [], "append"), (["--b"], ["BE"], ""), "e85521a43890c743"),
+    ("both", "--max-num-seqs 128", {"A": "1"}, (["--x"], ["E"], "append"), (["--b"], ["BE"], ""), "1e630973fad523ab"),
+    ("overlap", "--max-num-seqs 128", {}, (["--b"], [], "append"), (["--b"], [], ""), "9cb8463804e7a11c"),
+    ("variant-replace", "", {"A": "1"}, ([], [], "replace"), ([], [], ""), "7f4d4d32a84df525"),
+    ("base-replace", "", {"A": "1"}, ([], [], "append"), ([], [], "replace"), "7f4d4d32a84df525"),
+    ("removal-only", "", {}, (["--enable-prefix-caching"], [], "append"), ([], [], ""), "ca4d2e9e9760543a"),
+    ("empty", "", {}, ([], [], "append"), ([], [], ""), "164374825086dc65"),
+]
+
+
+def _controls(remove_args, unset_envs, args_mode) -> dict:
+    return controls_of(
+        normalize_proposal({"remove_args": remove_args, "unset_envs": unset_envs, "args_mode": args_mode})
+    )
+
+
+@pytest.mark.parametrize(
+    "args,envs,variant,base,expected",
+    [row[1:] for row in _GOLDEN],
+    ids=[row[0] for row in _GOLDEN],
+)
+def test_effective_fingerprint_matches_the_pinned_executor_values(args, envs, variant, base, expected):
+    b_remove, b_unset, b_mode = base
+    assert (
+        effective_fingerprint(
+            args,
+            envs,
+            controls=_controls(*variant),
+            base_remove_args=b_remove,
+            base_unset_envs=b_unset,
+            base_args_mode=b_mode,
+        )
+        == expected
+    )
+
+
+def test_base_controls_change_the_fingerprint():
+    controls = _controls(["--x"], [], "append")
+    assert effective_fingerprint("--a 1", {}, controls=controls) != effective_fingerprint(
+        "--a 1", {}, controls=controls, base_remove_args=["--b"]
+    )
+
+
+def test_removal_union_is_base_first_and_deduped():
+    both = effective_fingerprint("", {}, controls=_controls(["--b", "--v"], [], "append"), base_remove_args=["--b"])
+    assert both == effective_fingerprint("", {}, controls=_controls(["--b", "--v"], [], "append"))
+
+
+@pytest.mark.parametrize(
+    "proposal,expected",
+    [
+        ({"extra_args": "--a 1"}, True),
+        ({"extra_server_args": "--a 1"}, True),
+        ({"extra_envs": {"A": "1"}}, True),
+        ({"remove_args": ["--a"]}, True),
+        ({"unset_envs": ["A"]}, True),
+        ({"args_mode": "replace"}, True),
+        ({"name": "research-only", "reason": "read the scheduler"}, False),
+        ({"extra_args": "  ", "extra_envs": {}}, False),
+    ],
+)
+def test_is_executable(proposal, expected):
+    assert is_executable(normalize_proposal(proposal)) is expected
+
+
+def test_normalize_resolves_the_args_alias_and_keeps_atomic():
+    fields = normalize_proposal(
+        {
+            "name": " coupled ",
+            "extra_server_args": " --a 1 ",
+            "extra_envs": {"A": 1},
+            "remove_args": "--drop",
+            "args_mode": "REPLACE",
+            "atomic": True,
+            "reason": "needs the paired headroom",
+        }
+    )
+    assert fields == {
+        "name": "coupled",
+        "extra_args": "--a 1",
+        "extra_envs": {"A": "1"},
+        "remove_args": ["--drop"],
+        "unset_envs": [],
+        "args_mode": "replace",
+        "atomic": True,
+        "reason": "needs the paired headroom",
+    }
+
+
+def test_controls_of_drops_defaults():
+    assert controls_of(normalize_proposal({"extra_args": "--a 1"})) == {}
+    assert controls_of(normalize_proposal({"remove_args": ["--x"], "args_mode": "replace"})) == {
+        "remove_args": ["--x"],
+        "args_mode": "replace",
+    }