Replace trajectory audit with isolated prefix scoring

This commit is contained in:
2026-08-07 00:47:31 +08:00
parent f1a090e8c4
commit c6c583dcee
18 changed files with 914 additions and 469 deletions
+147 -101
View File
@@ -1,114 +1,160 @@
"""Tests for local trajectory-audit policy and scoring."""
"""Tests for the two-call boundary and prefix-quality policy."""
from __future__ import annotations
import json
import pytest
from swe_data_processing.audit import compute_quality_score, validate_audit
from swe_data_processing.audit import (
compute_prefix_quality,
materialize_prefix,
validate_boundary,
validate_prefix_quality,
)
from swe_data_processing.policy import PolicyViolation
from swe_data_processing.workflow import prepare_audit_payload
def _audit_result() -> dict:
"""Return one internally consistent audit result."""
return {
"evaluation_mode": "PROCESS_SALVAGE",
"recommended_use": "PROCESS_PREFIX_CANDIDATE",
"truncation": {
"first_bad_assistant_turn": 3,
"truncate_before_turn": 3,
"acceptable_start_turn": 3,
"acceptable_end_turn": 3,
"prefix_usable": True,
},
"behavior_issues": [
{
"assistant_turn": 3,
"tool_result_turn": 4,
"kind": "ERROR",
"severity": "MAJOR",
}
],
"issue_counts": {
"errors": 1,
"inefficiencies": 0,
"critical": 0,
"major": 1,
"minor": 0,
},
"quality_dimensions": {
"planning": 4,
"tool_selection": 4,
"observation_use": 3,
"efficiency": 4,
"verification_discipline": 3,
"claim_calibration": 3,
},
}
from swe_data_processing.workflow import (
prepare_boundary_payload,
prepare_prefix_quality_payload,
)
def _record() -> dict:
return {
"trajectory": [
{"role": "user", "content": "issue"},
{"role": "tool", "content": "context"},
{"role": "assistant", "content": "bad call"},
{"role": "tool", "content": "failed"},
]
}
def test_valid_audit_and_score() -> None:
"""A consistent audit receives a deterministic bounded score."""
result = _audit_result()
validate_audit(_record(), result)
score = compute_quality_score(result)
assert score["educational_quality_score"] == 65.0
assert score["quality_tier"] == "LOW"
def test_first_bad_turn_must_be_assistant() -> None:
"""The truncation boundary cannot point at a tool observation."""
result = _audit_result()
result["truncation"]["first_bad_assistant_turn"] = 4
result["truncation"]["truncate_before_turn"] = 4
with pytest.raises(PolicyViolation, match="assistant turn"):
validate_audit(_record(), result)
def test_issue_counts_are_recomputed() -> None:
"""GLM cannot under-report the number of issues it listed."""
result = _audit_result()
result["issue_counts"]["errors"] = 0
with pytest.raises(PolicyViolation, match="issue_counts"):
validate_audit(_record(), result)
def test_process_salvage_cannot_become_full_trajectory_candidate() -> None:
"""Outcome routing cannot be overridden by the model recommendation."""
result = _audit_result()
result["recommended_use"] = "FULL_TRAJECTORY_CANDIDATE"
with pytest.raises(PolicyViolation, match="full-trajectory"):
validate_audit(_record(), result)
def test_audit_payload_removes_reference_solution_signals() -> None:
"""The causal audit cannot see reference patch text or derived metadata."""
record = {
"trajectory_id": "sample-1",
"resolved": 0,
"trajectory": [{"role": "user", "content": "Fix the issue"}],
"metadata": {
"model_patch": {"patch": "--- a/model.py\n+++ b/model.py\n"},
"reference_patch": {"patch": "--- a/secret.py\n+++ b/secret.py\n"},
},
"tools": [],
"trajectory": [
{"role": "system", "content": "system"},
{"role": "user", "content": "Fix the bug."},
{"role": "assistant", "content": "I will inspect the code."},
{"role": "tool", "content": "relevant.py"},
{"role": "assistant", "content": "I will apply the harmful patch."},
{"role": "tool", "content": "tests failed"},
],
}
payload = prepare_audit_payload(record)
assert "reference_patch" not in payload
assert not any("reference" in key for key in payload["static_signals"])
def _boundary() -> dict:
return {
"sample_id": "sample-1",
"decision": "TRUNCATE",
"candidate_block_id": "block-001",
"truncate_before_turn": 5,
"prefix_safe_before_boundary": True,
"category": "PERSISTENT_WRONG_IMPLEMENTATION",
"severity": "MAJOR",
"state_effect": "UNRECOVERED",
"evidence": [{"turn_id": 5, "quote": "apply the harmful patch"}],
"reason": "The patch fails and is not repaired.",
}
def _blocks() -> list[dict]:
return [{"block_id": "block-001", "start_turn": 1, "end_turn": 6}]
def _quality() -> dict:
return {
"sample_id": "sample-1",
"prefix_valid": True,
"unrecovered_major_or_critical": False,
"behavior_issues": [],
"dimensions": {
"planning": 14,
"investigation": 15,
"tool_use_and_observation": 14,
"progress": 12,
"clarity_and_efficiency": 10,
},
"evidence": [],
"reason": "Useful investigation.",
}
def test_valid_boundary_materializes_exact_prefix() -> None:
validate_boundary(_record(), _blocks(), _boundary())
prefix = materialize_prefix(_record(), 5)
assert prefix == _record()["trajectory"][:4]
def test_boundary_must_be_an_assistant_turn() -> None:
result = _boundary()
result["truncate_before_turn"] = 4
with pytest.raises(PolicyViolation, match="assistant turn"):
validate_boundary(_record(), _blocks(), result)
def test_boundary_evidence_must_quote_boundary_turn() -> None:
result = _boundary()
result["evidence"] = [{"turn_id": 6, "quote": "tests failed"}]
with pytest.raises(PolicyViolation, match="excluded assistant turn"):
validate_boundary(_record(), _blocks(), result)
def test_boundary_quote_must_be_grounded() -> None:
result = _boundary()
result["evidence"][0]["quote"] = "invented evidence"
with pytest.raises(PolicyViolation, match="not present"):
validate_boundary(_record(), _blocks(), result)
def test_keep_full_requires_safe_full_trajectory() -> None:
result = _boundary()
result.update(
decision="KEEP_FULL",
candidate_block_id=None,
truncate_before_turn=None,
prefix_safe_before_boundary=True,
category="NONE",
severity="NONE",
state_effect="NONE",
evidence=[],
)
validate_boundary(_record(), _blocks(), result)
result["prefix_safe_before_boundary"] = False
with pytest.raises(PolicyViolation, match="safe full trajectory"):
validate_boundary(_record(), _blocks(), result)
def test_prefix_quality_cannot_reference_suffix() -> None:
prefix = materialize_prefix(_record(), 5)
result = _quality()
result["prefix_valid"] = False
result["unrecovered_major_or_critical"] = True
result["evidence"] = [{"turn_id": 5, "quote": "harmful patch"}]
with pytest.raises(PolicyViolation, match="outside the prefix"):
validate_prefix_quality("sample-1", prefix, result)
def test_quality_score_and_tier_are_computed_locally() -> None:
score = compute_prefix_quality(_quality())
assert score["educational_quality_score"] == 65
assert score["quality_tier"] == "MEDIUM"
def test_boundary_payload_hides_outcome_and_patch_metadata() -> None:
record = _record()
record["resolved"] = -1
record["metadata"] = {
"model_patch": {"patch": "MODEL_PATCH_SECRET"},
"reference_patch": {"patch": "REFERENCE_PATCH_SECRET"},
}
serialized = json.dumps(prepare_boundary_payload(record), ensure_ascii=False)
assert "resolved" not in serialized
assert "MODEL_PATCH_SECRET" not in serialized
assert "REFERENCE_PATCH_SECRET" not in serialized
def test_prefix_payload_is_identical_when_only_suffix_and_labels_change() -> None:
first = _record()
second = _record()
second["resolved"] = -1
second["trajectory"][4]["content"] = "DIFFERENT SUFFIX"
second["trajectory"][5]["content"] = "DIFFERENT TOOL RESULT"
second["metadata"] = {"model_patch": {"patch": "DIFFERENT PATCH"}}
first_prefix = materialize_prefix(first, 5)
second_prefix = materialize_prefix(second, 5)
assert prepare_prefix_quality_payload(
first, first_prefix
) == prepare_prefix_quality_payload(second, second_prefix)
+156
View File
@@ -0,0 +1,156 @@
"""End-to-end tests for call isolation in the audit workflow."""
from __future__ import annotations
import json
from swe_data_processing.client import GLMResponse
from swe_data_processing.config import Settings
from swe_data_processing.workflow import audit_trajectory
class FakeClient:
"""Return deterministic responses while recording every API payload."""
def __init__(self, responses: list[dict]) -> None:
self.settings = Settings(api_key="test-secret")
self.responses = iter(responses)
self.calls: list[dict] = []
def invoke_json(self, *, system_prompt: str, payload: dict, schema: dict) -> GLMResponse:
self.calls.append(
{"system_prompt": system_prompt, "payload": payload, "schema": schema}
)
return GLMResponse(
data=next(self.responses),
request_id=f"request-{len(self.calls)}",
usage={"total_tokens": 10},
compatibility_fallback_used=False,
)
def _record() -> dict:
return {
"trajectory_id": "sample-1",
"resolved": 0,
"trajectory": [
{"role": "system", "content": "system"},
{"role": "user", "content": "Fix the bug."},
{"role": "assistant", "content": "Inspect relevant.py"},
{"role": "tool", "content": "relevant code"},
{"role": "assistant", "content": "BAD_SUFFIX_SENTINEL patch"},
{"role": "tool", "content": "BAD_SUFFIX_SENTINEL failed"},
],
}
def test_workflow_calls_boundary_then_scores_only_materialized_prefix() -> None:
client = FakeClient(
[
{
"sample_id": "sample-1",
"decision": "TRUNCATE",
"candidate_block_id": "block-001",
"truncate_before_turn": 5,
"prefix_safe_before_boundary": True,
"category": "PERSISTENT_WRONG_IMPLEMENTATION",
"severity": "MAJOR",
"state_effect": "UNRECOVERED",
"evidence": [{"turn_id": 5, "quote": "BAD_SUFFIX_SENTINEL patch"}],
"reason": "The patch is not repaired.",
},
{
"sample_id": "sample-1",
"prefix_valid": True,
"unrecovered_major_or_critical": False,
"behavior_issues": [],
"dimensions": {
"planning": 15,
"investigation": 15,
"tool_use_and_observation": 14,
"progress": 12,
"clarity_and_efficiency": 10,
},
"evidence": [],
"reason": "The prefix is useful.",
},
]
)
result = audit_trajectory(_record(), client) # type: ignore[arg-type]
assert len(client.calls) == 2
quality_payload = json.dumps(client.calls[1]["payload"], ensure_ascii=False)
assert "BAD_SUFFIX_SENTINEL" not in quality_payload
assert "truncate_before_turn" not in quality_payload
assert result["prefix"]["retained_turn_count"] == 4
assert result["quality"]["local_score"]["quality_tier"] == "MEDIUM"
assert result["recommended_use"] == "PROCESS_PREFIX_CANDIDATE"
def test_hold_boundary_skips_quality_call() -> None:
client = FakeClient(
[
{
"sample_id": "sample-1",
"decision": "HOLD",
"candidate_block_id": None,
"truncate_before_turn": None,
"prefix_safe_before_boundary": False,
"category": "NONE",
"severity": "NONE",
"state_effect": "UNCLEAR",
"evidence": [],
"reason": "No clear unrepaired defect.",
}
]
)
result = audit_trajectory(_record(), client) # type: ignore[arg-type]
assert len(client.calls) == 1
assert result["recommended_use"] == "HOLD"
assert result["quality"] is None
def test_keep_full_process_trajectory_is_scored() -> None:
client = FakeClient(
[
{
"sample_id": "sample-1",
"decision": "KEEP_FULL",
"candidate_block_id": None,
"truncate_before_turn": None,
"prefix_safe_before_boundary": True,
"category": "NONE",
"severity": "NONE",
"state_effect": "NONE",
"evidence": [],
"reason": "No unrepaired severe problem is visible.",
},
{
"sample_id": "sample-1",
"prefix_valid": True,
"unrecovered_major_or_critical": False,
"behavior_issues": [
{
"assistant_turn": 3,
"kind": "INEFFICIENCY",
"severity": "MINOR",
"reason": "The inspection was somewhat broad.",
}
],
"dimensions": {
"planning": 15,
"investigation": 15,
"tool_use_and_observation": 14,
"progress": 12,
"clarity_and_efficiency": 10,
},
"evidence": [],
"reason": "Useful despite minor inefficiency.",
},
]
)
result = audit_trajectory(_record(), client) # type: ignore[arg-type]
assert len(client.calls) == 2
assert result["prefix"]["retained_turn_count"] == 6
assert result["quality"]["local_score"]["issue_counts"]["inefficiencies"] == 1
assert result["recommended_use"] == "PROCESS_PREFIX_CANDIDATE"
+36 -1
View File
@@ -1,6 +1,11 @@
"""Tests for prompt-only trajectory compaction."""
from swe_data_processing.evidence import compact_text, compact_trajectory
from swe_data_processing.evidence import (
BOUNDARY_BLOCK_TURNS,
build_trajectory_blocks,
compact_text,
compact_trajectory,
)
def test_compact_text_preserves_short_values() -> None:
@@ -36,3 +41,33 @@ def test_compact_trajectory_prioritizes_test_observations() -> None:
compacted, metadata = compact_trajectory(trajectory, signals)
assert compacted[2]["content"] == long_content
assert 3 in metadata["important_turn_ids"]
def test_boundary_blocks_preserve_absolute_turns_without_overlap() -> None:
trajectory = [
{"turn_id": turn, "role": "assistant", "content": f"turn {turn}"}
for turn in range(1, BOUNDARY_BLOCK_TURNS + 3)
]
blocks, metadata = build_trajectory_blocks(trajectory, {})
assert len(blocks) == 2
assert blocks[0]["start_turn"] == 1
assert blocks[0]["end_turn"] == BOUNDARY_BLOCK_TURNS
assert blocks[1]["start_turn"] == BOUNDARY_BLOCK_TURNS + 1
assert blocks[1]["end_turn"] == BOUNDARY_BLOCK_TURNS + 2
turn_ids = [
message["turn_id"] for block in blocks for message in block["messages"]
]
assert turn_ids == list(range(1, BOUNDARY_BLOCK_TURNS + 3))
assert metadata["block_count"] == 2
def test_boundary_block_keeps_immediate_tool_result_with_assistant() -> None:
trajectory = [
{"turn_id": turn, "role": "user", "content": f"turn {turn}"}
for turn in range(1, BOUNDARY_BLOCK_TURNS + 2)
]
trajectory[BOUNDARY_BLOCK_TURNS - 1]["role"] = "assistant"
trajectory[BOUNDARY_BLOCK_TURNS]["role"] = "tool"
blocks, _ = build_trajectory_blocks(trajectory, {})
assert blocks[0]["end_turn"] == BOUNDARY_BLOCK_TURNS + 1
assert len(blocks) == 1