Add advisory harness attribution and descriptor planner MVP

src/aituner/cli.py

@@ -1,10 +1,12 @@
 from __future__ import annotations
 
 import argparse
+import hashlib
 import json
 import sys
 from dataclasses import replace
 from pathlib import Path
+from typing import Any
 
 from .compare import run_compare
 from .config_signature import (
@@ -25,6 +27,7 @@ from .lca import (
 )
 from .llm import build_prompt, call_llm_for_proposal, load_capability_profile, parse_proposal_text
 from .spec import (
+    ConfigPatch,
     Proposal,
     SpecError,
     StudySpec,
@@ -68,6 +71,302 @@ def _reject_repeated_effective_config(
     )
 
 
+def _effective_config_fingerprint(signature: str) -> str:
+    return hashlib.sha256(signature.encode("utf-8")).hexdigest()
+
+
+def _proposal_effective_config_fingerprint(
+    *,
+    study: StudySpec,
+    state: StudyState,
+    proposal: Proposal,
+) -> str | None:
+    if proposal.should_stop:
+        return None
+    signature = materialized_effective_config_signature(
+        study=study,
+        state=state,
+        proposal=proposal,
+    )
+    return _effective_config_fingerprint(signature)
+
+
+def _visible_harness_candidates(
+    harness_context: dict[str, object] | None,
+) -> list[dict[str, Any]]:
+    if not isinstance(harness_context, dict):
+        return []
+    experiment_plan = harness_context.get("experiment_plan")
+    if not isinstance(experiment_plan, dict):
+        return []
+    candidate_set = experiment_plan.get("candidate_set")
+    if not isinstance(candidate_set, dict):
+        return []
+    candidates = candidate_set.get("eligible_candidates")
+    if not isinstance(candidates, list):
+        return []
+    return [item for item in candidates if isinstance(item, dict)]
+
+
+def _candidate_set_hash(harness_context: dict[str, object] | None) -> object:
+    if not isinstance(harness_context, dict):
+        return None
+    experiment_plan = harness_context.get("experiment_plan")
+    if not isinstance(experiment_plan, dict):
+        return None
+    candidate_set = experiment_plan.get("candidate_set")
+    if not isinstance(candidate_set, dict):
+        return None
+    return candidate_set.get("candidate_set_hash")
+
+
+def _match_visible_harness_candidate(
+    *,
+    proposal_fingerprint: str | None,
+    harness_context: dict[str, object] | None,
+) -> dict[str, Any] | None:
+    if proposal_fingerprint is None:
+        return None
+    for candidate in _visible_harness_candidates(harness_context):
+        if candidate.get("effective_config_fingerprint") == proposal_fingerprint:
+            return candidate
+    return None
+
+
+def _proposal_source_label(
+    *,
+    proposal_name: str,
+    proposal_source: Path | None,
+) -> str:
+    if proposal_name.startswith("baseline-"):
+        return "baseline"
+    if proposal_name.startswith("harness-stop-") or proposal_name.startswith("harness-proposal-"):
+        return "harness"
+    return str(proposal_source) if proposal_source else "llm"
+
+
+def _classify_proposal_attribution(
+    *,
+    study: StudySpec,
+    state: StudyState,
+    proposal: Proposal,
+    proposal_name: str,
+    proposal_source: Path | None,
+    harness_context: dict[str, object] | None,
+) -> dict[str, Any]:
+    source_label = _proposal_source_label(
+        proposal_name=proposal_name,
+        proposal_source=proposal_source,
+    )
+    fingerprint = _proposal_effective_config_fingerprint(
+        study=study,
+        state=state,
+        proposal=proposal,
+    )
+    matched = _match_visible_harness_candidate(
+        proposal_fingerprint=fingerprint,
+        harness_context=harness_context,
+    )
+    matched_candidate_id = matched.get("candidate_id") if matched else None
+    if proposal.should_stop:
+        origin = (
+            "harness_stop"
+            if proposal_name.startswith("harness-stop-")
+            else "proposal_file_stop"
+            if proposal_source is not None
+            else "llm_stop"
+        )
+    elif proposal_name.startswith("baseline-"):
+        origin = "baseline"
+    elif proposal_name.startswith("harness-proposal-"):
+        origin = "harness_top1"
+    elif proposal_source is not None:
+        origin = "proposal_file"
+    elif study.llm.use_harness and harness_context is not None:
+        origin = "llm_selected_harness_candidate" if matched else "llm_out_of_set"
+    else:
+        origin = "llm_no_harness"
+    return {
+        "schema_version": 1,
+        "proposal_name": proposal_name,
+        "proposal_source": source_label,
+        "proposal_origin": origin,
+        "harness_candidate_policy": study.llm.harness_candidate_policy,
+        "candidate_set_hash": _candidate_set_hash(harness_context),
+        "proposal_effective_config_fingerprint": fingerprint,
+        "matched_effective_config_signature": matched is not None,
+        "matched_candidate_id": matched_candidate_id,
+        "matched_candidate": _compact_candidate_for_attribution(matched),
+    }
+
+
+def _compact_candidate_for_attribution(candidate: dict[str, Any] | None) -> dict[str, Any] | None:
+    if not candidate:
+        return None
+    return {
+        "candidate_id": candidate.get("candidate_id"),
+        "action_id": candidate.get("action_id"),
+        "knob_family": candidate.get("knob_family"),
+        "score": candidate.get("score"),
+        "config_patch": candidate.get("config_patch"),
+    }
+
+
+def _validate_harness_candidate_policy(attribution: dict[str, Any]) -> None:
+    if (
+        attribution.get("harness_candidate_policy") == "strict"
+        and attribution.get("proposal_origin") == "llm_out_of_set"
+    ):
+        raise SpecError(
+            "LLM proposal is outside the visible harness eligible candidate set while "
+            "llm.harness_candidate_policy=strict. Use an eligible harness candidate, "
+            "switch to advisory mode, or disable harness context."
+        )
+
+
+def _config_patch_knob_keys(config_patch: object) -> set[str]:
+    if not isinstance(config_patch, dict):
+        return set()
+    keys: set[str] = set()
+    env_patch = config_patch.get("env_patch")
+    if isinstance(env_patch, dict):
+        keys.update(f"env:{key}" for key in env_patch)
+    flag_patch = config_patch.get("flag_patch")
+    if isinstance(flag_patch, dict):
+        keys.update(f"flag:{key}" for key in flag_patch)
+    return keys
+
+
+def _proposal_knob_keys(proposal: Proposal) -> set[str]:
+    return {
+        *{f"env:{key}" for key in proposal.config_patch.env_patch},
+        *{f"flag:{key}" for key in proposal.config_patch.flag_patch},
+    }
+
+
+def _nearest_visible_harness_candidates(
+    *,
+    proposal: Proposal,
+    harness_context: dict[str, object] | None,
+    limit: int = 3,
+) -> list[dict[str, Any]]:
+    proposal_keys = _proposal_knob_keys(proposal)
+    scored: list[tuple[int, float, dict[str, Any]]] = []
+    for candidate in _visible_harness_candidates(harness_context):
+        candidate_keys = _config_patch_knob_keys(candidate.get("config_patch"))
+        overlap = len(proposal_keys & candidate_keys)
+        score = candidate.get("score")
+        candidate_score = float(score) if isinstance(score, (int, float)) else 0.0
+        scored.append((overlap, candidate_score, candidate))
+    scored.sort(key=lambda item: (item[0], item[1]), reverse=True)
+    return [_compact_candidate_for_attribution(item[2]) or {} for item in scored[:limit]]
+
+
+def _candidate_family_gap_payload(
+    *,
+    study: StudySpec,
+    trial_id: str,
+    proposal_name: str,
+    proposal: Proposal,
+    attribution: dict[str, Any],
+    harness_context: dict[str, object] | None,
+    incumbent_rate_per_gpu: float,
+    result_rate_per_gpu: float,
+) -> dict[str, Any]:
+    nearest = _nearest_visible_harness_candidates(
+        proposal=proposal,
+        harness_context=harness_context,
+    )
+    proposal_keys = _proposal_knob_keys(proposal)
+    has_same_knob_candidate = any(
+        proposal_keys
+        & _config_patch_knob_keys(candidate.get("config_patch") if isinstance(candidate, dict) else None)
+        for candidate in nearest
+    )
+    return {
+        "schema_version": 1,
+        "study_id": study.study_id,
+        "trial_id": trial_id,
+        "proposal_name": proposal_name,
+        "proposal_origin": attribution.get("proposal_origin"),
+        "gap_type": "same_operator_new_step" if has_same_knob_candidate else "missing_operator",
+        "review_status": "pending",
+        "incumbent_request_rate_per_gpu": incumbent_rate_per_gpu,
+        "result_request_rate_per_gpu": result_rate_per_gpu,
+        "absolute_gain": result_rate_per_gpu - incumbent_rate_per_gpu,
+        "relative_gain": (
+            (result_rate_per_gpu - incumbent_rate_per_gpu) / incumbent_rate_per_gpu
+            if incumbent_rate_per_gpu > 0
+            else None
+        ),
+        "proposal_patch": {
+            "env_patch": dict(proposal.config_patch.env_patch),
+            "flag_patch": dict(proposal.config_patch.flag_patch),
+        },
+        "changed_knobs": sorted(proposal_keys),
+        "candidate_set_hash": attribution.get("candidate_set_hash"),
+        "nearest_harness_candidates": nearest,
+        "interpretation": (
+            "LLM changed a knob already present in the visible harness candidate set; "
+            "treat this as a step-size/acquisition gap until offline review accepts "
+            "a descriptor or operator change."
+            if has_same_knob_candidate
+            else "LLM changed knobs not represented by the visible harness candidates; "
+            "offline review should decide whether this is a missing operator, "
+            "descriptor, or mechanism."
+        ),
+    }
+
+
+def _result_request_rate_per_gpu(result: dict[str, object], parallel_size: int | None) -> float | None:
+    best_request_rate = result.get("best_request_rate")
+    if not isinstance(best_request_rate, (int, float)):
+        return None
+    if not isinstance(parallel_size, int) or parallel_size <= 0:
+        return None
+    return float(best_request_rate) / float(parallel_size)
+
+
+def _parse_parallel_int(value: object, *, default: int = 1) -> int:
+    if value is None:
+        return default
+    if isinstance(value, bool):
+        raise SpecError("Boolean values are not valid topology settings.")
+    if isinstance(value, int):
+        return value
+    if isinstance(value, float) and value.is_integer():
+        return int(value)
+    if isinstance(value, str) and value.strip():
+        return int(value.strip())
+    raise SpecError(f"Unable to parse topology setting from {value!r}.")
+
+
+def _parallel_size_for_config_patch(study: StudySpec, config_patch: object) -> int | None:
+    if not isinstance(config_patch, ConfigPatch):
+        return None
+    flags: dict[str, object] = dict(study.engine.base_flags)
+    flags.update(config_patch.flag_patch)
+    tp = _parse_parallel_int(flags.get("tensor-parallel-size"), default=1)
+    dp = _parse_parallel_int(flags.get("data-parallel-size"), default=1)
+    return tp * dp
+
+
+def _is_candidate_family_gap(
+    *,
+    attribution: dict[str, Any],
+    incumbent_rate_per_gpu: float | None,
+    result_rate_per_gpu: float | None,
+) -> bool:
+    if attribution.get("proposal_origin") != "llm_out_of_set":
+        return False
+    if not isinstance(incumbent_rate_per_gpu, (int, float)):
+        return False
+    if not isinstance(result_rate_per_gpu, (int, float)):
+        return False
+    min_gain = max(1e-6, float(incumbent_rate_per_gpu) * 0.01)
+    return float(result_rate_per_gpu) > float(incumbent_rate_per_gpu) + min_gain
+
+
 def _harness_snapshot_payload(
     *,
     study: StudySpec,
@@ -418,8 +717,23 @@ def cmd_study_tune(args: argparse.Namespace) -> int:
             proposal=proposal,
             proposal_name=proposal_name,
         )
+        proposal_attribution = _classify_proposal_attribution(
+            study=study,
+            state=state,
+            proposal=proposal,
+            proposal_name=proposal_name,
+            proposal_source=proposal_source,
+            harness_context=harness_context,
+        )
+        _validate_harness_candidate_policy(proposal_attribution)
         store.write_proposal(study.study_id, proposal_name, proposal)
         if proposal.should_stop:
+            proposal_attribution["stopped"] = True
+            store.write_proposal_attribution(
+                study.study_id,
+                proposal_name,
+                proposal_attribution,
+            )
             is_harness_stop = proposal_name.startswith("harness-stop-")
             is_llm_stop = not is_harness_stop and proposal_source is None
             stop_authority = (
@@ -498,21 +812,55 @@ def cmd_study_tune(args: argparse.Namespace) -> int:
             and not state.trials
             and _is_empty_config_patch(proposal)
         )
+        pre_trial_best_rate_per_gpu = state.best_request_rate_per_gpu
         trial, _ = store.materialize_trial(study=study, state=state, proposal=proposal)
+        proposal_attribution["trial_id"] = trial.trial_id
+        store.write_proposal_attribution(
+            study.study_id,
+            proposal_name,
+            proposal_attribution,
+        )
         trial_spec_path = Path(trial.artifact_dir) / "trial_spec.json"
         result = run_trial(trial_spec_path)
         state = store.ingest_trial_results(study.study_id)
+        trial_parallel_size = _parallel_size_for_config_patch(study, trial.config_patch)
+        result_rate_per_gpu = _result_request_rate_per_gpu(result, trial_parallel_size)
+        gap_path: Path | None = None
+        if _is_candidate_family_gap(
+            attribution=proposal_attribution,
+            incumbent_rate_per_gpu=pre_trial_best_rate_per_gpu,
+            result_rate_per_gpu=result_rate_per_gpu,
+        ):
+            gap_payload = _candidate_family_gap_payload(
+                study=study,
+                trial_id=trial.trial_id,
+                proposal_name=proposal_name,
+                proposal=proposal,
+                attribution=proposal_attribution,
+                harness_context=harness_context,
+                incumbent_rate_per_gpu=float(pre_trial_best_rate_per_gpu),
+                result_rate_per_gpu=float(result_rate_per_gpu),
+            )
+            gap_path = store.write_candidate_family_gap(
+                study.study_id,
+                trial.trial_id,
+                gap_payload,
+            )
         executed.append(
-                {
-                    "trial_id": trial.trial_id,
-                    "proposal_name": proposal_name,
-                    "proposal_source": (
-                        "harness"
-                        if proposal_name.startswith("harness-proposal-")
-                        else str(proposal_source) if proposal_source else "llm"
-                    ),
+            {
+                "trial_id": trial.trial_id,
+                "proposal_name": proposal_name,
+                "proposal_source": (
+                    "harness"
+                    if proposal_name.startswith("harness-proposal-")
+                    else str(proposal_source) if proposal_source else "llm"
+                ),
+                "proposal_origin": proposal_attribution.get("proposal_origin"),
+                "matched_candidate_id": proposal_attribution.get("matched_candidate_id"),
+                "candidate_family_gap_path": str(gap_path) if gap_path else None,
                 "best_sampling_u": result.get("best_sampling_u"),
                 "best_request_rate": result.get("best_request_rate"),
+                "best_request_rate_per_gpu": result_rate_per_gpu,
                 "best_pass_rate": result.get("best_pass_rate"),
                 "state_best_trial_id": state.best_trial_id,
                 "state_best_request_rate": state.best_request_rate,

src/aituner/engine_adapters/__init__.py

@@ -0,0 +1,2 @@
+from __future__ import annotations
+

src/aituner/engine_adapters/vllm.py

@@ -0,0 +1,82 @@
+from __future__ import annotations
+
+from collections.abc import Iterable
+
+from ..knob_descriptor import KnobConstraints, KnobDescriptor
+
+
+def default_vllm_descriptors(*, tunable_flags: Iterable[str]) -> tuple[KnobDescriptor, ...]:
+    tunable = set(tunable_flags)
+    descriptors: list[KnobDescriptor] = []
+    if "max-num-seqs" in tunable:
+        descriptors.append(
+            KnobDescriptor(
+                name="max-num-seqs",
+                location="flag",
+                value_type="int",
+                mechanisms=("admission_capacity", "kv_memory_pressure"),
+                search_geometry="positive_capacity",
+                operators=("coordinate_line_search", "frontier_delta_projection"),
+                constraints=KnobConstraints(min_value=1, integer=True, multiple_of=8),
+                directional_effects={
+                    "increase": ("admission_capacity",),
+                    "decrease": ("kv_memory_pressure",),
+                },
+                risk_effects={
+                    "increase": ("kv_memory_pressure", "decode_tail_latency"),
+                },
+            )
+        )
+    if "max-num-batched-tokens" in tunable:
+        descriptors.append(
+            KnobDescriptor(
+                name="max-num-batched-tokens",
+                location="flag",
+                value_type="int",
+                mechanisms=("prefill_scheduling", "decode_batching"),
+                search_geometry="positive_capacity",
+                operators=("coordinate_line_search", "frontier_delta_projection"),
+                constraints=KnobConstraints(min_value=1, integer=True, multiple_of=128),
+                directional_effects={
+                    "increase": ("prefill_scheduling", "decode_batching"),
+                    "decrease": ("prefill_tail_latency",),
+                },
+                risk_effects={
+                    "increase": ("prefill_tail_latency", "kv_memory_pressure"),
+                },
+            )
+        )
+    if "gpu-memory-utilization" in tunable:
+        descriptors.append(
+            KnobDescriptor(
+                name="gpu-memory-utilization",
+                location="flag",
+                value_type="float",
+                mechanisms=("kv_memory_capacity", "launch_feasibility"),
+                search_geometry="bounded_fraction",
+                operators=("coordinate_line_search", "frontier_delta_projection"),
+                constraints=KnobConstraints(min_value=0.0, max_value=1.0),
+                directional_effects={
+                    "increase": ("kv_memory_capacity",),
+                    "decrease": ("launch_feasibility",),
+                },
+                risk_effects={
+                    "increase": ("launch_feasibility",),
+                },
+            )
+        )
+    if "enable-chunked-prefill" in tunable:
+        descriptors.append(
+            KnobDescriptor(
+                name="enable-chunked-prefill",
+                location="flag",
+                value_type="bool",
+                mechanisms=("prefill_scheduling",),
+                search_geometry="toggle",
+                operators=("coordinate_line_search",),
+                directional_effects={
+                    "toggle": ("prefill_scheduling",),
+                },
+            )
+        )
+    return tuple(descriptors)

src/aituner/knob_descriptor.py

@@ -0,0 +1,40 @@
+from __future__ import annotations
+
+from dataclasses import dataclass, field
+from typing import Any, Literal, Mapping
+
+
+KnobLocation = Literal["flag", "env"]
+KnobValueType = Literal["int", "float", "bool", "enum", "str"]
+SearchGeometry = Literal["linear", "positive_capacity", "bounded_fraction", "toggle"]
+
+
+@dataclass(frozen=True)
+class KnobConstraints:
+    min_value: float | None = None
+    max_value: float | None = None
+    integer: bool = False
+    multiple_of: int | None = None
+
+
+@dataclass(frozen=True)
+class KnobDescriptor:
+    """Declarative serving-knob semantics used by generic planners.
+
+    The descriptor intentionally does not enumerate target values for continuous
+    or large integer knobs. It describes how a generic operator may perturb the
+    knob and which mechanism each direction is expected to affect.
+    """
+
+    name: str
+    location: KnobLocation
+    value_type: KnobValueType
+    mechanisms: tuple[str, ...]
+    search_geometry: SearchGeometry
+    operators: tuple[str, ...]
+    constraints: KnobConstraints = field(default_factory=KnobConstraints)
+    directional_effects: Mapping[str, tuple[str, ...]] = field(default_factory=dict)
+    risk_effects: Mapping[str, tuple[str, ...]] = field(default_factory=dict)
+
+    def current_value(self, config: Mapping[str, Any]) -> Any:
+        return config.get(self.name)

src/aituner/llm.py

@@ -317,6 +317,11 @@ def build_prompt(
             if parallel_candidates
             else "If TP/DP/EP are not tunable, focus on the remaining launch-safe runtime knobs."
         ),
+        (
+            "Harness candidate policy is advisory: prefer a high-scoring harness candidate when it matches your diagnosis, but you may propose an out-of-set config when the harness candidate family appears to miss the right step; such proposals are audited as candidate-family gaps."
+            if study.llm.harness_candidate_policy == "advisory"
+            else "Harness candidate policy is strict: your config_patch must match one of the harness eligible candidates after effective-config materialization."
+        ),
         "",
         "Study stack:",
         json.dumps(

src/aituner/mechanism_planner.py

@@ -0,0 +1,213 @@
+from __future__ import annotations
+
+import math
+from dataclasses import dataclass, field
+from typing import Any, Mapping
+
+from .knob_descriptor import KnobDescriptor
+
+
+@dataclass(frozen=True)
+class CoordinateSearchPolicy:
+    initial_relative_step: float = 1.0
+    initial_fraction_step: float = 0.05
+    grow_factor: float = 1.5
+    shrink_factor: float = 0.5
+    min_score: float = 0.0
+
+
+@dataclass(frozen=True)
+class CoordinateOperatorState:
+    knob: str
+    direction: str
+    trust_radius: float | None = None
+    last_good_value: Any | None = None
+    last_bad_value: Any | None = None
+    tested_values: tuple[Any, ...] = ()
+
+
+@dataclass(frozen=True)
+class MechanismCandidate:
+    action_id: str
+    knob: str
+    mechanism: str
+    operator: str
+    direction: str
+    patch: dict[str, Any]
+    score: float
+    score_factors: dict[str, float]
+    evidence_refs: tuple[str, ...] = ()
+
+
+def coordinate_line_search_candidates(
+    *,
+    current_config: Mapping[str, Any],
+    descriptors: tuple[KnobDescriptor, ...],
+    evidence_weights: Mapping[str, float],
+    states: Mapping[tuple[str, str], CoordinateOperatorState] | None = None,
+    policy: CoordinateSearchPolicy | None = None,
+) -> tuple[MechanismCandidate, ...]:
+    policy = policy or CoordinateSearchPolicy()
+    states = states or {}
+    candidates: list[MechanismCandidate] = []
+    for descriptor in descriptors:
+        if "coordinate_line_search" not in descriptor.operators:
+            continue
+        direction, mechanism, evidence = _choose_direction(descriptor, evidence_weights)
+        if direction is None or mechanism is None:
+            continue
+        if evidence < policy.min_score:
+            continue
+        state = states.get((descriptor.name, direction))
+        current = descriptor.current_value(current_config)
+        target = _propose_value(
+            descriptor=descriptor,
+            current=current,
+            direction=direction,
+            state=state,
+            policy=policy,
+        )
+        if target is None or target == current:
+            continue
+        risk = _direction_risk(descriptor, direction, evidence_weights)
+        score = max(0.0, evidence - risk)
+        candidates.append(
+            MechanismCandidate(
+                action_id=(
+                    f"coordinate_line_search:{descriptor.search_geometry}:"
+                    f"{descriptor.name}:{direction}:{_stable_token(current)}->{_stable_token(target)}"
+                ),
+                knob=descriptor.name,
+                mechanism=mechanism,
+                operator="coordinate_line_search",
+                direction=direction,
+                patch={descriptor.name: target},
+                score=round(score, 4),
+                score_factors={
+                    "mechanism_evidence": round(evidence, 4),
+                    "direction_risk": round(risk, 4),
+                },
+                evidence_refs=(mechanism,),
+            )
+        )
+    candidates.sort(key=lambda item: (item.score, item.action_id), reverse=True)
+    return tuple(candidates)
+
+
+def _choose_direction(
+    descriptor: KnobDescriptor,
+    evidence_weights: Mapping[str, float],
+) -> tuple[str | None, str | None, float]:
+    best_direction: str | None = None
+    best_mechanism: str | None = None
+    best_weight = 0.0
+    for direction, mechanisms in descriptor.directional_effects.items():
+        for mechanism in mechanisms:
+            weight = float(evidence_weights.get(mechanism, 0.0))
+            if weight > best_weight:
+                best_direction = direction
+                best_mechanism = mechanism
+                best_weight = weight
+    return best_direction, best_mechanism, best_weight
+
+
+def _direction_risk(
+    descriptor: KnobDescriptor,
+    direction: str,
+    evidence_weights: Mapping[str, float],
+) -> float:
+    risks = descriptor.risk_effects.get(direction, ())
+    if not risks:
+        return 0.0
+    return min(0.5, 0.2 * max(float(evidence_weights.get(item, 0.0)) for item in risks))
+
+
+def _propose_value(
+    *,
+    descriptor: KnobDescriptor,
+    current: Any,
+    direction: str,
+    state: CoordinateOperatorState | None,
+    policy: CoordinateSearchPolicy,
+) -> Any | None:
+    if descriptor.search_geometry == "toggle":
+        if not isinstance(current, bool):
+            current = bool(current)
+        return not current
+    if descriptor.search_geometry == "bounded_fraction":
+        value = _as_float(current)
+        if value is None:
+            return None
+        radius = (
+            state.trust_radius
+            if state is not None and state.trust_radius is not None
+            else policy.initial_fraction_step
+        )
+        if direction == "decrease":
+            target = value - radius
+        else:
+            target = value + radius
+        return _canonicalize_value(descriptor, target)
+    if descriptor.search_geometry == "linear":
+        value = _as_float(current)
+        if value is None:
+            return None
+        radius = (
+            state.trust_radius
+            if state is not None and state.trust_radius is not None
+            else 1.0
+        )
+        return _canonicalize_value(
+            descriptor,
+            value - radius if direction == "decrease" else value + radius,
+        )
+    if descriptor.search_geometry == "positive_capacity":
+        value = _as_float(current)
+        if value is None or value <= 0:
+            min_value = descriptor.constraints.min_value
+            return _canonicalize_value(descriptor, min_value if min_value is not None else 1)
+        radius = (
+            state.trust_radius
+            if state is not None and state.trust_radius is not None
+            else policy.initial_relative_step
+        )
+        factor = max(1.0 + radius, 1.01)
+        target = value / factor if direction == "decrease" else value * factor
+        return _canonicalize_value(descriptor, target)
+    raise ValueError(f"unsupported search geometry {descriptor.search_geometry!r}")
+
+
+def _canonicalize_value(descriptor: KnobDescriptor, value: float | int) -> Any:
+    target = float(value)
+    if descriptor.constraints.min_value is not None:
+        target = max(target, float(descriptor.constraints.min_value))
+    if descriptor.constraints.max_value is not None:
+        target = min(target, float(descriptor.constraints.max_value))
+    if descriptor.constraints.integer or descriptor.value_type == "int":
+        integer_target = int(math.ceil(target))
+        multiple_of = descriptor.constraints.multiple_of
+        if multiple_of is not None and multiple_of > 1:
+            integer_target = int(math.ceil(integer_target / multiple_of) * multiple_of)
+        if descriptor.constraints.min_value is not None:
+            integer_target = max(integer_target, int(descriptor.constraints.min_value))
+        if descriptor.constraints.max_value is not None:
+            integer_target = min(integer_target, int(descriptor.constraints.max_value))
+        return integer_target
+    return round(target, 6)
+
+
+def _as_float(value: Any) -> float | None:
+    if isinstance(value, bool):
+        return None
+    if isinstance(value, (int, float)):
+        return float(value)
+    if isinstance(value, str) and value.strip():
+        try:
+            return float(value.strip())
+        except ValueError:
+            return None
+    return None
+
+
+def _stable_token(value: Any) -> str:
+    return repr(value)

src/aituner/spec.py

@@ -732,6 +732,7 @@ class LLMPolicySpec:
     system_prompt: str
     max_history_trials: int
     use_harness: bool = True
+    harness_candidate_policy: str = "advisory"
 
     @classmethod
     def from_dict(cls, data: Mapping[str, Any] | None) -> "LLMPolicySpec":
@@ -743,6 +744,13 @@ class LLMPolicySpec:
             if payload.get("endpoint")
             else None
         )
+        harness_candidate_policy = str(
+            payload.get("harness_candidate_policy") or "advisory"
+        ).strip()
+        if harness_candidate_policy not in {"advisory", "strict"}:
+            raise SpecError(
+                "llm.harness_candidate_policy must be one of: advisory, strict."
+            )
         return cls(
             endpoint=endpoint,
             system_prompt=str(payload.get("system_prompt") or "").strip(),
@@ -754,6 +762,7 @@ class LLMPolicySpec:
                 if payload.get("use_harness") is not None
                 else True
             ),
+            harness_candidate_policy=harness_candidate_policy,
         )
 
 

src/aituner/store.py

@@ -27,7 +27,15 @@ class StudyStore:
 
     def init_study(self, *, spec_path: Path, study: StudySpec) -> Path:
         root = self.study_root(study.study_id)
-        for rel in ("prompts", "proposals", "trials", "results", "harness"):
+        for rel in (
+            "prompts",
+            "proposals",
+            "proposal_attributions",
+            "trials",
+            "results",
+            "harness",
+            "candidate_family_gaps",
+        ):
             (root / rel).mkdir(parents=True, exist_ok=True)
         (root / "study_spec.source").write_text(str(spec_path.resolve()) + "\n", encoding="utf-8")
         self.write_json(root / "study_spec.snapshot.json", to_jsonable(study))
@@ -80,6 +88,26 @@ class StudyStore:
         self.write_json(path, payload)
         return path
 
+    def write_proposal_attribution(
+        self,
+        study_id: str,
+        proposal_name: str,
+        payload: dict[str, Any],
+    ) -> Path:
+        path = self.study_root(study_id) / "proposal_attributions" / f"{proposal_name}.json"
+        self.write_json(path, payload)
+        return path
+
+    def write_candidate_family_gap(
+        self,
+        study_id: str,
+        trial_id: str,
+        payload: dict[str, Any],
+    ) -> Path:
+        path = self.study_root(study_id) / "candidate_family_gaps" / f"{trial_id}.json"
+        self.write_json(path, payload)
+        return path
+
     def materialize_trial(
         self,
         *,