mirror of
https://github.com/agentscope-ai/ReMe.git
synced 2026-10-23 05:35:30 +00:00
548b08561e
* refactor: generalize decision models and add opt-in context compaction * chore: remove compaction-specific license metadata * test: add live decision compaction scenarios and strategy guides * docs: describe current decision model configuration directly * refactor: preserve recoverable tool evidence and add compaction benchmarks * docs: visualize compaction benchmark results with English charts * docs: fix compaction benchmark links with verified permalinks * benchmark: evaluate fixed-summary evidence additions and summary-aware selection * docs: report summary-aware incremental evidence results * docs: unify compaction strategy comparison * refactor: replace compaction studies with one matched-input benchmark * docs: pin matched-input results links * bench: evaluate gold-labelled HotpotQA trajectories collected with Hermes * docs: pin gold-labelled benchmark results * bench: focus on frozen-summary Jev Top-N payment evaluation * docs: pin frozen-summary benchmark results * bench: evaluate fixed-summary fusion across Hermes fixture tasks * docs: pin compaction study references to reviewed results * bench: compare Jev fusion across frozen summary strategies * docs: pin dual-summary benchmark and figure references * docs: specify reproducible compaction settings and Hermes summary scope * docs: plot Jev token overhead by retained Top N * docs: pin reproducibility settings and revised cost figure * docs: price total compaction and answering cost across Top N * docs: pin final cost accounting and reproduction references * docs: explain compaction experiment background setup and conclusions inline * docs: compare compaction-only costs and omit Full from cost panel * docs: pin compaction-only cost references * docs: retain only quality and context-length experiment comparisons * docs: pin streamlined experiment references * docs: add Chinese counterparts for all compaction benchmark guides * docs: link benchmark guides in the matching language * docs: consolidate bilingual compaction benchmark guides * docs: point compaction references to consolidated benchmark * docs: reference Hermes Jev compaction evaluation results * fix(benchmark): validate cached native summary provenance
455 lines
18 KiB
Python
455 lines
18 KiB
Python
"""Freeze rule-scored, read-only adaptations of fourteen distinct fixture tasks."""
|
|
|
|
import ast
|
|
import hashlib
|
|
import importlib.util
|
|
import json
|
|
import re
|
|
import random
|
|
import subprocess
|
|
import sys
|
|
|
|
from benchmark.compaction.cases import GOLD, exact_match, write
|
|
|
|
|
|
def module(path, name):
|
|
"""Load fixture definitions only; never run their CLI or agent workers."""
|
|
spec = importlib.util.spec_from_file_location(name, path)
|
|
value = importlib.util.module_from_spec(spec)
|
|
sys.modules[name] = value
|
|
spec.loader.exec_module(value)
|
|
return value
|
|
|
|
|
|
def context(text, pattern, radius=10):
|
|
"""Freeze original matching lines with context, with no generated filler or answer lookup."""
|
|
lines = text.splitlines(keepends=True)
|
|
indices = {
|
|
j
|
|
for i, line in enumerate(lines)
|
|
if re.search(pattern, line)
|
|
for j in range(max(0, i - radius), min(len(lines), i + radius + 1))
|
|
}
|
|
return "".join(f"{i+1}|{lines[i]}" for i in sorted(indices))
|
|
|
|
|
|
def planted_session(path, function, session_id, position):
|
|
"""Extract a literal upstream seeded history without running DB setup or worker code."""
|
|
tree = ast.parse(path.read_text())
|
|
for node in ast.walk(tree):
|
|
if isinstance(node, ast.Call) and isinstance(node.func, ast.Name) and node.func.id == function:
|
|
if any(isinstance(a, ast.Constant) and a.value == session_id for a in node.args):
|
|
return ast.literal_eval(node.args[position])
|
|
raise ValueError("Expected upstream seeded session")
|
|
|
|
|
|
def define(task_id, query, files, gold, fields, origin, *, query_only=False, unordered=()):
|
|
"""Keep fixture answers outside the read-only tool workspace and compressor inputs."""
|
|
return {
|
|
"id": task_id,
|
|
"query": query,
|
|
"files": files,
|
|
"gold": gold,
|
|
"fields": fields,
|
|
"origin": origin,
|
|
"query_only": query_only,
|
|
"unordered": list(unordered),
|
|
}
|
|
|
|
|
|
def definitions(hermes, scratch):
|
|
"""Use pinned upstream fixture bytes; adapt actions to read-only investigation explicitly."""
|
|
core = module(hermes / "evals/core_tool_deferral/tasks.py", "compaction_core_tasks")
|
|
perf = module(hermes / "evals/toolperf_abeval/ab_eval.py", "compaction_perf_tasks")
|
|
read = module(hermes / "evals/readtool/fixtures.py", "compaction_read_fixtures")
|
|
core_root, perf_root, read_root = (scratch / name for name in ("core", "perf", "read"))
|
|
for root in (core_root, perf_root, read_root):
|
|
root.mkdir(parents=True)
|
|
for name in ("longrange_backup_pipeline", "eager_refactor_control", "todo_three_files", "config_grep_distractor"):
|
|
root = core_root / name
|
|
root.mkdir()
|
|
core.TASKS_BY_ID[name]["fixtures"](str(root))
|
|
perf.make_sandbox(perf_root)
|
|
read._write_package_json(read_root) # pylint: disable=protected-access
|
|
read._write_app_js(read_root) # pylint: disable=protected-access
|
|
read._write_unicode_notes(read_root) # pylint: disable=protected-access
|
|
read._write_server_log(read_root, random.Random(20260809)) # pylint: disable=protected-access
|
|
read._write_lockfile(read_root, random.Random(20260809)) # pylint: disable=protected-access
|
|
backup = planted_session(hermes / "evals/core_tool_deferral/worker.py", "sess", "seed_backup_talk", 1)
|
|
incident = planted_session(hermes / "evals/session_search_schema/fixtures.py", "mk", "20260818_140200_cc22dd", 4)
|
|
|
|
def core_files(name):
|
|
root = core_root / name
|
|
return {str(p.relative_to(root)): p.read_text() for p in root.rglob("*") if p.is_file()}
|
|
|
|
def core_query(name):
|
|
return core.TASKS_BY_ID[name]["prompt"]
|
|
|
|
def perf_files(*names):
|
|
return {name: (perf_root / "proj" / name).read_text() for name in names}
|
|
|
|
def perf_query(name):
|
|
return perf.TASKS[name].replace("{WORK}/proj", ".")
|
|
|
|
rows = []
|
|
rows.append(
|
|
define(
|
|
"payment",
|
|
"Investigate the original payment retry incident.",
|
|
{},
|
|
GOLD,
|
|
{k: k.replace("_", " ") for k in GOLD},
|
|
"Original Hermes payment fixture",
|
|
unordered=("no_retry_http_statuses",),
|
|
),
|
|
)
|
|
files = core_files("longrange_backup_pipeline")
|
|
files["session_history.json"] = json.dumps(backup, indent=2)
|
|
rows.append(
|
|
define(
|
|
"backup",
|
|
core_query("longrange_backup_pipeline"),
|
|
files,
|
|
{"repo": "sparks-data", "ignored_repo": "toybox", "data_text": "important"},
|
|
{
|
|
"repo": "repository requiring backup",
|
|
"ignored_repo": "repository explicitly excluded",
|
|
"data_text": "contents of the target repository data file",
|
|
},
|
|
"core_tool_deferral/longrange_backup_pipeline",
|
|
),
|
|
)
|
|
rows.append(
|
|
define(
|
|
"refactor",
|
|
core_query("eager_refactor_control"),
|
|
core_files("eager_refactor_control"),
|
|
{
|
|
"old_timeout": 30,
|
|
"call_sites": 3,
|
|
"functions": ["fetch_a", "fetch_b", "fetch_c"],
|
|
"methods": ["get", "post", "head"],
|
|
"old_version": "1.0",
|
|
},
|
|
{
|
|
"old_timeout": "original timeout integer",
|
|
"call_sites": "number of requests call sites",
|
|
"functions": "function names in source order",
|
|
"methods": "HTTP methods in source order",
|
|
"old_version": "existing changelog version",
|
|
},
|
|
"core_tool_deferral/eager_refactor_control",
|
|
),
|
|
)
|
|
rows.append(
|
|
define(
|
|
"three_files",
|
|
core_query("todo_three_files"),
|
|
core_files("todo_three_files"),
|
|
{"file_count": 3, "header": "item,qty", "data_rows": 2},
|
|
{"file_count": "required output file count", "header": "CSV header", "data_rows": "CSV data row count"},
|
|
"core_tool_deferral/todo_three_files",
|
|
query_only=True,
|
|
),
|
|
)
|
|
rows.append(
|
|
define(
|
|
"active_config",
|
|
core_query("config_grep_distractor"),
|
|
core_files("config_grep_distractor"),
|
|
{"retry_limit": 7, "backoff": 2, "active_file": "conf/app.ini", "old_file": "conf/old.ini"},
|
|
{
|
|
"retry_limit": "active integer value",
|
|
"backoff": "active integer backoff",
|
|
"active_file": "workspace-relative active config",
|
|
"old_file": "workspace-relative retired config",
|
|
},
|
|
"core_tool_deferral/config_grep_distractor",
|
|
),
|
|
)
|
|
rows.append(
|
|
define(
|
|
"checkout_504",
|
|
(
|
|
"Investigate the checkout 504 incident: distinguish the failed rollback, "
|
|
"root cause and final database fix."
|
|
),
|
|
{"session_history.json": json.dumps(incident, indent=2)},
|
|
{
|
|
"setting": "statement_timeout",
|
|
"value_seconds": 45,
|
|
"index_mode": "CONCURRENTLY",
|
|
"root_cause": "CREATE INDEX without CONCURRENTLY",
|
|
"rolled_back_version": "v2.30.2",
|
|
"rollback_fixed": False,
|
|
"deployed_version": "v2.31.0",
|
|
"initial_error_percent": 8,
|
|
},
|
|
{
|
|
"setting": "final database timeout setting name",
|
|
"value_seconds": "final timeout in seconds",
|
|
"index_mode": "mode used to recreate the index",
|
|
"root_cause": "SQL operation that competed with checkout writes",
|
|
"rolled_back_version": "rollback target version",
|
|
"rollback_fixed": "did rollback resolve the incident, boolean",
|
|
"deployed_version": "version deployed before the incident",
|
|
"initial_error_percent": "initial request error percentage as integer",
|
|
},
|
|
"session_search_schema/t2_scroll",
|
|
),
|
|
)
|
|
rows.append(
|
|
define(
|
|
"dependency_version",
|
|
(
|
|
"What exact left-pad version is pinned, and which file declares the test script? "
|
|
"Record the package scripts for a handoff."
|
|
),
|
|
{
|
|
"package.json": (read_root / "package.json").read_text(),
|
|
"package-lock.head.txt": "".join(
|
|
(read_root / "package-lock.json").read_text().splitlines(keepends=True)[:40],
|
|
),
|
|
},
|
|
{
|
|
"version": "1.3.0",
|
|
"declaration": "package.json",
|
|
"test": "vitest run",
|
|
"build": "tsc -p .",
|
|
"package_version": "4.2.1",
|
|
},
|
|
{
|
|
"version": "pinned left-pad version",
|
|
"declaration": "file declaring the test script",
|
|
"test": "exact test command",
|
|
"build": "exact build command",
|
|
"package_version": "project package version",
|
|
},
|
|
"readtool/lockfile_version",
|
|
),
|
|
)
|
|
tree = ast.parse((hermes / "evals/readtool/fixtures.py").read_text())
|
|
function = next(n for n in tree.body if isinstance(n, ast.FunctionDef) and n.name == "_write_minified_bundle")
|
|
parts = next(
|
|
n
|
|
for n in ast.walk(function)
|
|
if isinstance(n, ast.Assign) and any(isinstance(t, ast.Name) and t.id == "parts" for t in n.targets)
|
|
)
|
|
fragment = ast.literal_eval(parts.value)[0]
|
|
rows.append(
|
|
define(
|
|
"retry_backoff",
|
|
"Find the retry-delay function in src/ and explain its base, growth, cap and jitter.",
|
|
{"src/app.js": (read_root / "src/app.js").read_text(), "src/app.min.head.txt": fragment},
|
|
{
|
|
"base_ms": 250,
|
|
"cap_ms": 30000,
|
|
"growth_factor": 2,
|
|
"jitter": "uniform_integer_below_bound",
|
|
"function": "retryDelay",
|
|
},
|
|
{
|
|
"base_ms": "base delay in milliseconds",
|
|
"cap_ms": "maximum delay in milliseconds",
|
|
"growth_factor": "exponential multiplier per attempt",
|
|
"jitter": "choose none or uniform_integer_below_bound",
|
|
"function": "function name",
|
|
},
|
|
"readtool/minified_backoff",
|
|
),
|
|
)
|
|
log = (read_root / "logs/server.log").read_text()
|
|
rows.append(
|
|
define(
|
|
"server_error",
|
|
(
|
|
"Locate the unique ERROR in the server log and retain its exact request, timestamp, "
|
|
"upstream and connection failure."
|
|
),
|
|
{
|
|
"server.head.txt": "".join(log.splitlines(keepends=True)[:20]),
|
|
"server.error-context.txt": context(log, r"\bERROR\b"),
|
|
},
|
|
{
|
|
"request_id": "req-7f3d9",
|
|
"timestamp": "2026-08-08T23:41:17Z",
|
|
"status": 502,
|
|
"upstream": "payments",
|
|
"error": "ECONNREFUSED",
|
|
"address": "10.0.4.17:8443",
|
|
},
|
|
{
|
|
"request_id": "error request ID",
|
|
"timestamp": "full UTC error timestamp",
|
|
"status": "HTTP integer status",
|
|
"upstream": "failed upstream service",
|
|
"error": "connection error code",
|
|
"address": "upstream host and port",
|
|
},
|
|
"readtool/log_error_hunt",
|
|
),
|
|
)
|
|
notes = next((read_root / "notes").iterdir())
|
|
rows.append(
|
|
define(
|
|
"meeting_notes",
|
|
"Read the meeting notes and report the third bullet exactly, retaining the other agreed actions.",
|
|
{"notes.txt": notes.read_text()},
|
|
{
|
|
"third": "rotate the API keys quarterly",
|
|
"first": "ship the payments retry fix",
|
|
"second": "audit the staging TLS certs",
|
|
"fourth": "close out the Q3 incident review",
|
|
},
|
|
{k: f"exact {k} bullet" for k in ("third", "first", "second", "fourth")},
|
|
"readtool/unicode_filename",
|
|
),
|
|
)
|
|
rows.append(
|
|
define(
|
|
"targeted_edit",
|
|
perf_query("err_ambiguous_edit"),
|
|
perf_files("handlers.py", "check_handlers.py"),
|
|
{
|
|
"target": "slow_handler",
|
|
"original_timeouts": {"fast_handler": 10, "slow_handler": 10, "medium_handler": 10},
|
|
"required_timeouts": {"fast_handler": 10, "slow_handler": 60, "medium_handler": 10},
|
|
"success_marker": "HANDLERS_OK_552",
|
|
},
|
|
{
|
|
"target": "function requiring modification",
|
|
"original_timeouts": "mapping of all original function timeouts",
|
|
"required_timeouts": "mapping after the requested fix",
|
|
"success_marker": "checker success marker",
|
|
},
|
|
"toolperf_abeval/err_ambiguous_edit",
|
|
),
|
|
)
|
|
output = subprocess.check_output([sys.executable, str(perf_root / "proj/noisy_build.py")], text=True)
|
|
rows.append(
|
|
define(
|
|
"build_token",
|
|
perf_query("err_big_output"),
|
|
{
|
|
**perf_files("noisy_build.py"),
|
|
"build.head.txt": "".join(output.splitlines(keepends=True)[:20]),
|
|
"build.token-context.txt": context(output, r"^UNIQUE_TOKEN="),
|
|
},
|
|
{"token": "tok_9f31c_middle", "step": 2000, "total_steps": 4000, "prefix": "UNIQUE_TOKEN="},
|
|
{
|
|
"token": "full unique token value without its prefix",
|
|
"step": "build loop step that prints the token",
|
|
"total_steps": "build loop iteration count",
|
|
"prefix": "exact token line prefix",
|
|
},
|
|
"toolperf_abeval/err_big_output",
|
|
),
|
|
)
|
|
rows.append(
|
|
define(
|
|
"package_versions",
|
|
perf_query("err_multi_dir"),
|
|
perf_files("pkg_a/version.txt", "pkg_b/version.txt", "pkg_c/version.txt"),
|
|
{"versions": {"pkg_a": "1.4.2", "pkg_b": "0.9.7", "pkg_c": "3.2.1"}, "joined": "1.4.2,0.9.7,3.2.1"},
|
|
{
|
|
"versions": "mapping from package directory to exact version",
|
|
"joined": "comma-separated versions in a,b,c order",
|
|
},
|
|
"toolperf_abeval/err_multi_dir",
|
|
),
|
|
)
|
|
anomaly = (perf_root / "proj/records.log").read_text()
|
|
rows.append(
|
|
define(
|
|
"checksum_anomaly",
|
|
perf_query("err_big_file_read"),
|
|
{
|
|
"records.head.txt": "".join(anomaly.splitlines(keepends=True)[:20]),
|
|
"records.anomaly-context.txt": context(anomaly, r"^ANOMALY:"),
|
|
},
|
|
{
|
|
"line": "ANOMALY: checksum drift detected in shard 7 (code X99Q)",
|
|
"code": "X99Q",
|
|
"shard": 7,
|
|
"line_number": 4201,
|
|
},
|
|
{
|
|
"line": "full anomaly line without display line number",
|
|
"code": "anomaly code",
|
|
"shard": "integer shard number",
|
|
"line_number": "one-based original line number",
|
|
},
|
|
"toolperf_abeval/err_big_file_read",
|
|
),
|
|
)
|
|
return rows
|
|
|
|
|
|
def exam(case):
|
|
"""Supply field names/descriptions, never their expected values, to the answering model."""
|
|
prompt = (
|
|
'Using only recorded evidence, return JSON {"facts": {...}}. No tools. Missing facts must be null. '
|
|
"Use exact strings and JSON types; numbers are integers. Answer these fields: "
|
|
+ json.dumps(case["fields"], ensure_ascii=False)
|
|
)
|
|
if case["id"] == "payment":
|
|
prompt += (
|
|
" regression_attempt_counts must be a JSON object with keys "
|
|
"timeout_then_success, validation_422 and three_timeouts, each mapping to an integer count; "
|
|
"do not return an array."
|
|
)
|
|
if case["id"] == "meeting_notes":
|
|
prompt += " Return the bullet text without its leading list marker (-), indentation or surrounding whitespace."
|
|
return prompt
|
|
|
|
|
|
def grade(case, prediction):
|
|
"""Type-strict field checks; declared unordered lists ignore order, with no LLM judge."""
|
|
observed = prediction.get("facts", {}) if isinstance(prediction, dict) else {}
|
|
observed = observed if isinstance(observed, dict) else {}
|
|
checks = {}
|
|
for key, expected in case["gold"].items():
|
|
value = observed.get(key)
|
|
if key in case["unordered"] and isinstance(value, list):
|
|
value, expected = sorted(value, key=str), sorted(expected, key=str)
|
|
checks[key] = exact_match(value, expected)
|
|
return checks
|
|
|
|
|
|
def freeze(hermes, output):
|
|
"""Write all queries, answers and rules before model calls; runtime artifacts stay outside git."""
|
|
output.mkdir(parents=True)
|
|
rows = definitions(hermes, output / "upstream-fixtures")
|
|
for case in rows:
|
|
root = output / case["id"]
|
|
work = root / "workspace"
|
|
work.mkdir(parents=True)
|
|
for name, text in case["files"].items():
|
|
path = work / name
|
|
path.parent.mkdir(parents=True, exist_ok=True)
|
|
path.write_text(text)
|
|
case["source_chars"] = sum(map(len, case["files"].values()))
|
|
case["control_reason"] = (
|
|
"query_only" if case["query_only"] else "short_fixture" if case["source_chars"] < 2000 else None
|
|
)
|
|
if case["id"] == "payment":
|
|
case["control_reason"] = None
|
|
files = case.pop("files")
|
|
case["source_hashes"] = {name: hashlib.sha256(text.encode()).hexdigest() for name, text in files.items()}
|
|
prompt = (
|
|
"Read-only evidence collection for this task: " + case["query"] + "\n"
|
|
"Read ALL of these snapshot files completely using read_file: " + ", ".join(files) + ". "
|
|
"Then report findings and proposed actions only. Do not modify files or run commands. "
|
|
"Snapshots preserve selected original fixture regions; display line numbers refer to the original file."
|
|
)
|
|
write(
|
|
root / "collection-task.json",
|
|
{"prompt": prompt, "model": "qwen3.8-max", "source_hashes": case["source_hashes"]},
|
|
)
|
|
manifest = {
|
|
"hermes_commit": subprocess.check_output(["git", "-C", str(hermes), "rev-parse", "HEAD"], text=True).strip(),
|
|
"source": "Local Hermes MIT-licensed task fixtures; explicitly adapted read-only",
|
|
"cases": rows,
|
|
}
|
|
write(output / "corpus.json", manifest)
|
|
return manifest
|