把 Claude Code 的 subagent 路由到 Haiku 5.5:路由表、兩個檔案與測試工具

重點摘要

• 除非有檔案另外指定,Claude Code 的 subagent 不會用 Haiku 5.5。內建的 Explore agent 和每個自訂 subagent 都繼承主模型,單獨設定 subagent 模型變數,Explore 不會有任何改變。
• 兩個檔案就能解決:一個專案內的 Explore.md agent 檔(Haiku 5.5,effort low)只處理探索者,以及一個帶有 CLAUDE_CODE_SUBAGENT_MODEL_FORCE 的 settings.json env 區塊,把每個 subagent 都推到 Haiku。
• 我們在一個真實儲存庫上的矩陣共 182 次執行:探索、測試、lint、commit、refactor、審查和總結,在 Haiku 5.5 上全部被隱藏測試或固定規則接受,低與中等 effort 各 70 次中的 70 次。
• 七個任務都交給低 effort 的 Haiku 5.5。複雜的 agentic coding 則留給 Sonnet 5.5 或 Opus 5.5,這也是 Anthropic 自己的建議。
• 真正的方案用量表幾乎沒動:70 次低 effort Haiku 執行,五小時視窗從 21% 到 21%,182 次執行的每週視窗都是 67%。/usage 明細是用本地權重排序模型,不是計費。
• 請固定使用完整的模型 ID。haiku 別名在 Bedrock、Vertex 和 Foundry 上是 Haiku 4.5。

資料來源怎麼說

Haiku 5.5 在 100k token 以內的 prompt 定價為每百萬輸入 token $0.10,超過則是 $0.50,輸出是 $0.50 和 $2.50。Haiku 4.5 是 $1.00 和 $5.00,Sonnet 5.5 是 $2.00 和 $10.00 s1。定價頁面列出 Opus 5.5 為每百萬 token $4 和 $20,並註明 Haiku 5.5 與其他 1M context 模型不同,是依 prompt 長度計價 s20。標題上的 90% 指的是前一代 Haiku 的請求中 prompt 不到 100k token 的比例,不是降價 s1。

Anthropic 把 Haiku 5.5 定位為與 Opus 5.5 和 Sonnet 5.5 並列的 subagent,並表示複雜的 agentic coding 仍以 Sonnet 5.5 和 Opus 5.5 為較佳選擇,Haiku 5.5 用於範圍明確的工作 s1。在 Terminal-Bench 4.0 上,發布文章給出 Haiku 5.5 為 39.2%,Sonnet 5.5 為 70.6% s1。

預設沒有任何東西會送到 Haiku。從 v2.1.198 開始,內建的 Explore agent 不再預設使用 Haiku,而是繼承主模型 s24。文件記載的 subagent 模型解析順序是:每次呼叫的參數、定義的 frontmatter、CLAUDE_CODE_SUBAGENT_MODEL,然後是主對話的模型 s2。單獨使用 CLAUDE_CODE_SUBAGENT_MODEL 不會改變內建的 Explore 和 Plan subagent s2。使用者或專案中名為 Explore 的 subagent 會覆蓋內建版本,文件也建議定義一個使用 Haiku 模型的版本 s2。CLAUDE_CODE_SUBAGENT_MODEL_FORCE=1 會把同一個模型套用到每個 subagent,從 v2.1.257 開始 s2 s24。

成本文件建議簡單的 subagent 任務使用 model: haiku,並說明 subagent 的請求仍然使用同一份用量 s3。每週的計數器是所有模型共用一個,加上包含 Fable 的方案另有一個 Fable 專用的 s22,其他模型也從同樣的額度中扣除 s23。

在 Claude Code 中,Haiku 5.5、Opus 5.5、Sonnet 5.5 和 Fable 的思考都無法關閉:alwaysThinkingEnabled 設為 false 和 MAX_THINKING_TOKENS=0 都沒有作用。effort 從 low 到 max,Haiku 5.5 預設為 medium s21。haiku 別名在 Anthropic API 上解析為 Haiku 5.5,在 Platform on AWS、Bedrock、Vertex 和 Foundry 上解析為 Haiku 4.5 s21。

一位實踐者的 Pro 方案配置(主 session 用中等 effort 的 Opus 5.5、一個 Sonnet 5.5 implementer、一個唯讀的 Haiku 5.5 scoper、一個低 effort 的 Haiku 5.5 shipper)回報十個 session 共 13 個 PR,每個約佔五小時視窗的 6%,單一 PR session 約佔每週計數器的 1% s4。他自己的提醒:省下來的部分來自主 context 保持很小,而不是來自比較便宜的模型,因為把 subagent 的 token 按 Opus 價格計算,也只多出 5% s4。

兩個檔案

兩個檔案,用其中一個或兩個都用。專案裡的 agent 檔 .claude/agents/Explore.md 名為 Explore,所以它會取代內建的探索者。完整的模型 ID、effort low、只有讀取和搜尋工具。

Explore.md

---
name: Explore
description: Read-only codebase explorer. Use it to find where something is defined or called and to summarize what it found, with file paths and function names.
model: claude-haiku-5-5
effort: low
tools: Read, Glob, Grep, Bash
---

You explore a codebase and report back. Search with Glob and Grep, read only the files you need, and never edit anything. Answer with file paths and function names, then stop.

Explore.md on GitHub

settings 檔 .claude/settings.json 裡放的是 env 區塊:subagent 模型,以及讓它套用到每個 subagent 的 force 旗標。

settings.json

{
  "env": {
    "CLAUDE_CODE_SUBAGENT_MODEL": "claude-haiku-5-5",
    "CLAUDE_CODE_SUBAGENT_MODEL_FORCE": "1"
  }
}

settings.json on GitHub

誰該用哪一個:

• 想讓每個 subagent 都便宜,就用 env 區塊。FORCE 會把每個 agent 都拉到 Haiku,包括你刻意指定 Opus 的那些。
• 只想讓探索者移動,就用 Explore 檔。其他 subagent 保留各自的模型。
• 設定 CLAUDE_CODE_SUBAGENT_MODEL 而不加 FORCE,對 Explore 沒有任何作用。我們做了兩次 headless 執行,主 session 用 Fable,「use the Explore agent to find where the query cache is cleared」:沒有任何設定時,工具結果寫的是 Opus 5.5;只把變數設成 Haiku 5.5、其他什麼都不改時,仍然是 Opus 5.5。用了 Explore 檔,或用了這兩個環境變數,它讀到的就是 Haiku 5.5。

檢查方式:/tasks 會顯示每個 subagent 執行時用的模型和 effort(v2.1.243 以後 s24),headless 執行的 Agent 工具結果也帶有 resolvedModel。請相信那一行,而不是檔案。

別名陷阱:請寫 claude-haiku-5-5,不要寫 haiku。這個別名只在 Anthropic API 上是 Haiku 5.5;在 Bedrock、Vertex 和 Foundry 上它仍然代表 Haiku 4.5 s21。

一份較早的公開回報說,subagent 的 frontmatter 模型被無聲地忽略 s25,較晚的一份則統計在 2.1.277 到 2.1.290 版上,1,371 個 subagent 中有 1,149 個跑在父層的 Opus 模型上 s10。在 Claude Code 2.1.293 上,我們 182 次執行每一次都用了設定的模型(結果表中 model_ok 為 True)。還是要檢查。

路由表

在 tinydb 的 18d73a1 提交上做七個日常任務,226 個測試,headless claude -p,每個任務一個確定性的接受或拒絕檢查。每個儲存格是通過的次數、每次執行的平均牌價、平均牆上秒數。Haiku 儲存格每個任務 10 次執行,Sonnet 和 Opus 儲存格每個任務 3 次執行。

「refactor」任務就是那個小功能:在 tinydb.operations 加入 push 和 pull 更新操作,由一個隱藏的測試檔評分。它在低 effort 的 Haiku 上花 $0.0052,在 Opus 上花 $0.1675,耗時 17.1 s 對 30.3 s。

留在 Sonnet 或 Opus 的:複雜的 agentic coding,這是 Anthropic 自己的話 s1。這七個是範圍明確的任務,每個不到一分鐘,在一個小專案上。

測試工具

產生這張表的基準測試。請在一個普通的終端機裡執行,期間不要有其他東西使用這個帳號,因為方案用量表是共用的。tinydb 的 checkout、隱藏測試和參考 patch 沒有附上:請把它指向你自己的儲存庫,並寫你自己的檢查。

執行器與用量表:

• README.md:這個工具是什麼,以及哪些東西沒有附上。

  README.md

# routing bench

The benchmark harness behind the routing table: run.sh runs one cell headless and reads the real meters from the rate_limit_event, matrix.sh runs cells sequentially, check.py decides accept or reject per task, analyze.py writes the results table. tasks/ holds the seven prompts, inject/ the planted bugs. The tinydb checkout (commit 18d73a1), the hidden tests and the reference patches are not included: bring your own repo and checks.

README.md on GitHub

run.sh

#!/usr/bin/env bash
# One run: fresh tinydb work copy + task injection, headless claude -p, extract tokens/meter, check.
# Usage: run.sh <config> <task> <rep>
#   config: a key of configs.json (haiku-med | haiku-low | sonnet | opus)
#   task:   a key of tasks.json   (explore | tests | lint | commit | refactor | review | summary)
set -uo pipefail
CFG="$1"; TASK="$2"; REP="${3:-1}"
HERE="$(cd "$(dirname "$0")" && pwd)"
. "$HERE/env.sh"
PY="$HERE/.venv/bin/python"
MAX_TURNS="${BENCH_MAX_TURNS:-40}"
NAME="${TASK}-${CFG}-r${REP}"
OUT="$HERE/runs/$NAME"; W="$HERE/work/$NAME"
rm -rf "$OUT"; mkdir -p "$OUT"
"$HERE/prep.sh" "$TASK" "$W" > "$OUT/prep.txt" 2>&1 || { echo "$NAME: prep failed"; cat "$OUT/prep.txt"; exit 2; }
( cd "$W" && git diff HEAD > "$OUT/pre.diff" )

# Config args (model pinned by full id, optional --effort)
CARGS=()
while IFS= read -r a; do CARGS+=("$a"); done < <("$PY" -c "
import json; [print(a) for a in json.load(open('$HERE/configs.json'))['$CFG']['args']]")
[ ${#CARGS[@]} -gt 0 ] || { echo "bad config $CFG" >&2; exit 2; }

# Fixed allow-list for every cell, including Bash(ruff:*) for the lint task.
TOOLS="Read,Edit,Write,MultiEdit,Glob,Grep,Skill,TodoWrite,Bash(uv:*),Bash(python:*),Bash(python3:*),Bash(pytest:*),Bash(ruff:*),Bash(git status:*),Bash(git diff:*),Bash(git log:*),Bash(ls:*),Bash(cat:*),Bash(mkdir:*),Bash(mktemp:*),Bash(head:*),Bash(tail:*),Bash(grep:*),Bash(wc:*)"

cd "$W"
START=$(date +%s)
claude -p "$(cat "$HERE/tasks/$TASK.md")" "${CARGS[@]}" \
  --output-format stream-json --verbose --max-turns "$MAX_TURNS" \
  --permission-mode acceptEdits --allowedTools "$TOOLS" \
  --setting-sources project --strict-mcp-config \
  > "$OUT/stream.jsonl" 2> "$OUT/stderr.txt"
echo "$?" > "$OUT/exit_code.txt"
END=$(date +%s)
echo "$((END-START))" > "$OUT/wall_s.txt"

# After-meter: one cheap Haiku probe (its own stream is kept for audit).
"$HERE/probe.sh" "$OUT/probe.jsonl" > "$OUT/after.json" 2>/dev/null

# Diff of the agent's work (tracked + untracked) vs the post-injection state
# (index left untouched: the commit task's staged changes stay staged for the check)
git diff HEAD -- . ':(exclude).coverage' > "$OUT/post.diff"
git diff HEAD --numstat -- . ':(exclude).coverage' > "$OUT/numstat.txt"
git ls-files --others --exclude-standard | while IFS= read -r f; do
  git diff --no-index -- /dev/null "$f" >> "$OUT/post.diff"
  echo "$(wc -l < "$f" | tr -d ' ')	0	$f" >> "$OUT/numstat.txt"
done

"$PY" "$HERE/extract.py" "$OUT" "$CFG" "$TASK" "$REP" > "$OUT/result.json"
"$PY" "$HERE/check.py" "$TASK" "$W" "$OUT/result.json" > "$OUT/check.txt"; echo "$?" >> "$OUT/check.txt"
"$PY" "$HERE/extract.py" "$OUT" "$CFG" "$TASK" "$REP" --score

run.sh on GitHub

matrix.sh

#!/usr/bin/env bash
# Run an ordered list of "<config> <task> <rep>" lines SEQUENTIALLY (the plan meter is shared:
# never run two cells at once). Blank lines and #comments are skipped. Appends to matrix.log.
# Usage: matrix.sh [matrix-file]   (default: matrix.txt)
#   SKIP_DONE=1 matrix.sh ...      skip cells whose runs/<task>-<config>-r<rep>/score.json exists (resume)
set -uo pipefail
HERE="$(cd "$(dirname "$0")" && pwd)"; cd "$HERE"
LIST="${1:-matrix.txt}"
# one matrix at a time: the meter is shared
mkdir "$HERE/.matrix.lock" 2>/dev/null || { echo "another matrix.sh is running (remove .matrix.lock if stale)" >&2; exit 1; }
trap 'rmdir "$HERE/.matrix.lock"' EXIT
echo "=== $(date '+%F %T') start $LIST" >> matrix.log
grep -vE '^\s*(#|$)' "$LIST" | while read -r CFG TASK REP; do
  if [ "${SKIP_DONE:-0}" = 1 ] && [ -f "runs/${TASK}-${CFG}-r${REP}/score.json" ]; then
    echo "$(date '+%F %T') skip ${TASK}-${CFG}-r${REP}" >> matrix.log; continue
  fi
  line=$(./run.sh "$CFG" "$TASK" "$REP" < /dev/null 2>&1 | tail -1)
  echo "$(date '+%F %T') $line" | tee -a matrix.log
done
echo "=== $(date '+%F %T') done $LIST" >> matrix.log

matrix.sh on GitHub

gen_matrix.py

#!/usr/bin/env python3
"""Write the ordered matrix file.

gen_matrix.py [--reps 3] [--passes 2] [--configs haiku-low,haiku-med,sonnet,opus] [--out matrix.txt]

Order: configs run as contiguous BLOCKS (all tasks of one rep set), cheap configs first; tasks are
rotated inside each block so no task always runs first. With --passes 2 the second pass runs the
configs in reverse order (ABBA), which interleaves configs over time without breaking the
contiguous segments that analyze.py needs to beat the 1% meter resolution.
"""
import argparse, json, os

HERE = os.path.dirname(os.path.abspath(__file__))
ap = argparse.ArgumentParser()
ap.add_argument("--reps", type=int, default=3, help="reps per config x task per pass")
ap.add_argument("--passes", type=int, default=2)
ap.add_argument("--configs", default="haiku-low,haiku-med,sonnet,opus")
ap.add_argument("--start-rep", type=int, default=1, help="first rep number (use 2 to keep the r1 smoke runs)")
ap.add_argument("--out", default=os.path.join(HERE, "matrix.txt"))
a = ap.parse_args()
tasks = list(json.load(open(os.path.join(HERE, "tasks.json"))))
cfgs = a.configs.split(",")
lines, rep = [], a.start_rep
for p in range(a.passes):
    order = cfgs if p % 2 == 0 else list(reversed(cfgs))
    lines.append(f"# pass {p + 1}: {' -> '.join(order)}")
    for c in order:
        lines.append(f"# block {c}")
        for r in range(a.reps):
            k = rep + r
            rot = (k - 1) % len(tasks)
            for t in tasks[rot:] + tasks[:rot]:
                lines.append(f"{c} {t} {k}")
    rep += a.reps
open(a.out, "w").write("\n".join(lines) + "\n")
n = sum(1 for l in lines if not l.startswith("#"))
print(f"{a.out}: {n} runs ({len(cfgs)} configs x {len(tasks)} tasks x {a.reps} reps x {a.passes} passes)")

gen_matrix.py on GitHub

prep.sh

#!/usr/bin/env bash
# Build a fresh work copy for one task: upstream tinydb, baseline commit, task injection.
# Usage: prep.sh <task> <workdir>
set -euo pipefail
HERE="$(cd "$(dirname "$0")" && pwd)"
TASK="$1"; W="$2"
read -r INJ MODE < <("$HERE/.venv/bin/python" -c "
import json,sys; t=json.load(open('$HERE/tasks.json'))['$TASK']; print(t['inject'] or '-', t['mode'] or '-')")
rm -rf "$W"; mkdir -p "$(dirname "$W")"
cp -R "$HERE/upstream" "$W"
cd "$W"
/usr/bin/find . -name __pycache__ -type d -prune -exec rm -rf {} +
rm -f .coverage
git update-index -q --refresh || true
G() { git -c user.email=dev@example.com -c user.name=dev "$@"; }
# Injections that belong to the baseline are folded into the top upstream commit
# (amend, same message/author/date), so `git log` shows no extra "bug" commit.
if [ "$MODE" = "commit" ]; then
  git apply "$HERE/$INJ"
  git add -A
  G commit -q --amend --no-edit --no-verify
fi
case "$MODE" in
  stage)    git apply --index "$HERE/$INJ" ;;
  worktree) git apply "$HERE/$INJ" ;;
esac

prep.sh on GitHub

env.sh

# Sourced by run.sh and probe.sh.
# Auth: an isolated CLAUDE_CONFIG_DIR is not logged in
# (`claude auth status` -> loggedIn false), so runs use the user's default config dir:
# CLAUDE_CONFIG_DIR is deliberately left unset.
unset CLAUDE_CONFIG_DIR
# Fresh work copies at the same path must not inherit memory written by an earlier rep.
export CLAUDE_CODE_DISABLE_AUTO_MEMORY=1
# The bench venv (pytest, ruff, mypy) comes first, so `python -m pytest` and `ruff` just work.
export PATH="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/.venv/bin:$PATH"

env.sh on GitHub

probe.sh

#!/usr/bin/env bash
# Cheapest possible call: one Haiku turn answering "ok". Prints the current plan
# meter read from its rate_limit_event as one JSON line. The probe itself costs a
# few hundred tokens of Haiku (well under the 1% meter resolution).
# Usage: probe.sh [raw-stream-out-file]
set -uo pipefail
HERE="$(cd "$(dirname "$0")" && pwd)"
[ -f "$HERE/env.sh" ] && . "$HERE/env.sh"
RAW="${1:-$(mktemp -t hrb-probe)}"; case "$RAW" in /*) ;; *) RAW="$PWD/$RAW";; esac
cd "$(mktemp -d -t hrb-probe-cwd)"
claude --model claude-haiku-5-5 -p "ok" --max-turns 1 --output-format stream-json --verbose \
  --setting-sources project --strict-mcp-config > "$RAW" 2>/dev/null
"$HERE/.venv/bin/python" "$HERE/meter.py" "$RAW"

probe.sh on GitHub

meter.py

#!/usr/bin/env python3
"""Read a stream-json file and print the plan meter carried by its rate_limit_event lines.

Output (one JSON line): {"ts", "five_hour", "five_hour_resets_at", "seven_day",
"seven_day_resets_at", "n_events", "raw_first", "raw_last"}: utilizations are the
values of the FIRST event (the meter as the run began). `--last` uses the last event.
"""
import json, sys, time

def events(path):
    out = []
    for line in open(path, errors="replace"):
        line = line.strip()
        if not line.startswith("{"):
            continue
        try:
            o = json.loads(line)
        except Exception:
            continue
        if o.get("type") == "rate_limit_event":
            out.append(o)
    return out

def windows(ev):
    info = ev.get("rate_limit_info") or {}
    uw = info.get("unifiedWindows") or {}
    def w(name):
        x = uw.get(name) or {}
        return x.get("utilization"), x.get("resetsAt")
    fh, fhr = w("five_hour")
    sd, sdr = w("seven_day")
    return {"five_hour": fh, "five_hour_resets_at": fhr, "seven_day": sd, "seven_day_resets_at": sdr}

def meter(path, which="first"):
    evs = events(path)
    if not evs:
        return {"ts": int(time.time()), "n_events": 0, "five_hour": None, "seven_day": None}
    ev = evs[0] if which == "first" else evs[-1]
    d = {"ts": int(time.time()), "n_events": len(evs)}
    d.update(windows(ev))
    d["raw_first"] = evs[0].get("rate_limit_info")
    d["raw_last"] = evs[-1].get("rate_limit_info")
    return d

if __name__ == "__main__":
    which = "last" if "--last" in sys.argv else "first"
    path = [a for a in sys.argv[1:] if not a.startswith("--")][0]
    print(json.dumps(meter(path, which)))

meter.py on GitHub

extract.py

#!/usr/bin/env python3
"""Extract one run's numbers from runs/<name>/stream.jsonl.

extract.py <outdir> <config> <task> <rep>          -> prints the stream's `result` line (result.json)
extract.py <outdir> <config> <task> <rep> --score  -> writes score.json, prints a one-line summary
"""
import json, os, sys

HERE = os.path.dirname(os.path.abspath(__file__))
sys.path.insert(0, HERE)
from meter import meter  # noqa: E402

out, cfg, task, rep = sys.argv[1:5]
score_mode = "--score" in sys.argv
stream = os.path.join(out, "stream.jsonl")

lines = []
for raw in open(stream, errors="replace") if os.path.exists(stream) else []:
    raw = raw.strip()
    if raw.startswith("{"):
        try:
            lines.append(json.loads(raw))
        except Exception:
            pass
result = next((o for o in reversed(lines) if o.get("type") == "result"), None)
init = next((o for o in lines if o.get("type") == "system" and o.get("subtype") == "init"), {})

if not score_mode:
    print(json.dumps(result or {"type": "result", "result": "", "missing": True}))
    sys.exit(0)

def rd(name, default=None):
    p = os.path.join(out, name)
    try:
        return open(p).read().strip()
    except Exception:
        return default

def jl(name):
    try:
        return json.loads(rd(name) or "null")
    except Exception:
        return None

cfgs = json.load(open(os.path.join(HERE, "configs.json")))
before = meter(stream, "first") if os.path.exists(stream) else None
after = jl("after.json")
r = result or {}
usage = r.get("usage") or {}
tok = {k: usage.get(k) or 0 for k in ("input_tokens", "cache_read_input_tokens", "cache_creation_input_tokens", "output_tokens")}
mu = r.get("modelUsage") or {}
assistant_models = sorted({(o.get("message") or {}).get("model") for o in lines
                           if o.get("type") == "assistant" and (o.get("message") or {}).get("model") not in (None, "<synthetic>")})
check_txt = (rd("check.txt", "") or "").split("\n")
verdict_line = check_txt[0] if check_txt else ""
numstat = [l.split("\t") for l in (rd("numstat.txt", "") or "").split("\n") if l.strip()]
added = sum(int(a) for a, d, f in numstat if a.isdigit())
deleted = sum(int(d) for a, d, f in numstat if d.isdigit())
changed_by_agent = (rd("pre.diff", "") or "") != (rd("post.diff", "") or "")

def strip_raw(m):
    if not m:
        return m
    return {k: v for k, v in m.items() if not k.startswith("raw_")}

s = {
    "run": os.path.basename(out), "config": cfg, "task": task, "rep": int(rep),
    "expected_model": cfgs[cfg]["model"], "config_args": cfgs[cfg]["args"],
    "init_model": init.get("model"), "assistant_models": assistant_models,
    "model_usage_keys": sorted(mu.keys()),
    "model_ok": init.get("model") == cfgs[cfg]["model"] and set(mu.keys()) <= {cfgs[cfg]["model"]} and bool(mu),
    "claude_code_version": init.get("claude_code_version"),
    "meter_before": strip_raw(before), "meter_after": strip_raw(after),
    "n_rate_limit_events": (before or {}).get("n_events", 0),
    "has_result_line": result is not None,
    "subtype": r.get("subtype"), "is_error": r.get("is_error"), "stop_reason": r.get("stop_reason"),
    "num_turns": r.get("num_turns"), "duration_ms": r.get("duration_ms"), "duration_api_ms": r.get("duration_api_ms"),
    "total_cost_usd": r.get("total_cost_usd"), "usage": usage, "tokens": tok, "modelUsage": mu,
    "wall_s": int(rd("wall_s.txt", "0") or 0), "exit_code": rd("exit_code.txt"),
    "final_text": (r.get("result") or "")[-2000:],
    "diff": {"files": len(numstat), "added": added, "deleted": deleted, "changed_by_agent": changed_by_agent},
    "check": {"verdict": verdict_line.split(" ")[0] if verdict_line else None, "reason": verdict_line[5:] if verdict_line else None},
}
s["accepted"] = s["check"]["verdict"] == "PASS"
json.dump(s, open(os.path.join(out, "score.json"), "w"), indent=2)
mb, ma = s["meter_before"] or {}, s["meter_after"] or {}
print(f"{s['run']}: {s['check']['verdict']} turns={s['num_turns']} cost=${(s['total_cost_usd'] or 0):.3f} "
      f"in={tok['input_tokens']} cr={tok['cache_read_input_tokens']} cc={tok['cache_creation_input_tokens']} out={tok['output_tokens']} "
      f"wall={s['wall_s']}s 5h {mb.get('five_hour')}->{ma.get('five_hour')} 7d {mb.get('seven_day')}->{ma.get('seven_day')} "
      f"model_ok={s['model_ok']} | {s['check']['reason']}")

extract.py on GitHub

check.py

#!/usr/bin/env python3
"""Deterministic accept/reject check for one run.

Usage: check.py <task> <workdir> <result.json>
  result.json = the `result` line of the run's stream (only its "result" text is used).
Prints `PASS <reason>` or `FAIL <reason>`; exit 0 on PASS, 1 on FAIL.
"""
import json, os, re, subprocess, sys

HERE = os.path.dirname(os.path.abspath(__file__))
PY = os.path.join(HERE, ".venv", "bin", "python")
RUFF = os.path.join(HERE, ".venv", "bin", "ruff")


def final_text(path):
    try:
        r = json.load(open(path))
    except Exception:
        return ""
    return r.get("result") or "" if isinstance(r, dict) else ""


def sh(args, cwd, env=None):
    p = subprocess.run(args, cwd=cwd, capture_output=True, text=True, env=env)
    return p.returncode, p.stdout + p.stderr


def suite(wd):
    rc, out = sh([PY, "-m", "pytest", "-q", "-p", "no:cacheprovider", "-o", "addopts=", "tests"], wd)
    m = re.search(r"(\d+) passed", out)
    f = re.search(r"(\d+) failed", out)
    e = re.search(r"(\d+) error", out)
    return rc == 0, f"suite {m.group(1) if m else 0} passed, {f.group(1) if f else 0} failed, {e.group(1) if e else 0} errors"


def git_diff(wd, *paths):
    # tracked changes vs the baseline commit + untracked files under paths
    _, d = sh(["git", "diff", "HEAD", "--", *paths], wd)
    _, u = sh(["git", "ls-files", "--others", "--exclude-standard", "--", *paths], wd)
    return d.strip(), u.strip()


def words(s):
    return re.findall(r"[A-Za-z0-9_']+", s)


def strip_fences(s):
    lines = s.strip().split("\n")
    if lines and lines[0].strip().startswith("```"):
        lines = lines[1:]
    if lines and lines[-1].strip().startswith("```"):
        lines = lines[:-1]
    return "\n".join(lines).strip()


def c_explore(wd, txt):
    t = txt.lower()
    miss = []
    if "table.py" not in t:
        miss.append("table.py")
    if "clear_cache" not in t and "_query_cache" not in t:
        miss.append("clear_cache/_query_cache")
    names = ["insert_multiple", "update_multiple", "insert", "update", "upsert", "remove", "truncate"]
    found = {n for n in names if re.search(r"(?<![a-z_])" + n + r"(?![a-z_])", t)}
    if len(found) < 3:
        miss.append(f"only {len(found)} mutating methods {sorted(found)}")
    return (not miss), ("missing " + ", ".join(miss)) if miss else f"table.py + cache method + {len(found)} methods {sorted(found)}"


def c_tests(wd, txt):
    ok, s = suite(wd)
    d, u = git_diff(wd, "tests")
    if d or u:
        return False, f"tests/ modified; {s}"
    return ok, s + "; tests/ untouched"


def c_lint(wd, txt):
    rc, out = sh([RUFF, "check", "tinydb", "--output-format", "concise", "--no-cache"], wd)
    cfg_d, _ = git_diff(wd, "ruff.toml", "pyproject.toml")
    d, _ = git_diff(wd, "tinydb")
    noqa = [l for l in d.split("\n") if l.startswith("+") and "noqa" in l.lower()]
    ok, s = suite(wd)
    why = []
    if rc != 0:
        found = [l for l in out.split("\n") if l.startswith("Found ")]
        why.append("ruff: " + (found[0] if found else out.strip().split("\n")[-1]))
    if cfg_d:
        why.append("lint config changed")
    if noqa:
        why.append(f"{len(noqa)} noqa added")
    if not ok:
        why.append(s)
    return (not why), ("; ".join(why) if why else f"ruff clean; {s}")


DIFF_LINE = re.compile(r"^(diff --git |index [0-9a-f]{6,}\.\.|@@ |\+\+\+ |--- a/|--- /dev/null|[+-] {3,}\S|[+-](def|class|import|from|return) )")


def c_commit(wd, txt):
    msg = strip_fences(txt)
    if not msg:
        return False, "empty answer"
    first = msg.split("\n")[0].strip()
    why = []
    if len(first) > 72:
        why.append(f"first line {len(first)} chars")
    if "push" not in first.lower():
        why.append("no 'push' in first line")
    if "pull" not in first.lower():
        why.append("no 'pull' in first line")
    dl = [l for l in msg.split("\n") if DIFF_LINE.match(l)]
    if dl:
        why.append(f"{len(dl)} diff lines")
    return (not why), ("; ".join(why) if why else f"first line {len(first)} chars: {first!r}")


def c_refactor(wd, txt):
    env = dict(os.environ, TINYDB_TREE=wd)
    rc, out = sh([PY, "-m", "pytest", "-q", "-c", os.path.join(HERE, "hidden", "pytest.ini"),
                  "--rootdir", os.path.join(HERE, "hidden"), os.path.join(HERE, "hidden", "test_T1.py")], wd, env)
    m = re.search(r"(\d+) passed", out)
    hp = int(m.group(1)) if m else 0
    ok, s = suite(wd)
    return (hp == 5 and ok), f"hidden {hp}/5; {s}"


REVIEW_PATTERNS = [
    r"limit\s*=?=\s*0\b",
    r"limit\s+(of\s+)?(0|zero)\b",
    r"\b(0|zero)\s+limit",
    r"zero[- ]limit",
    r"limit.{0,150}\b(falsy|falsey|truthy|truthiness)",
    r"\b(falsy|falsey|truthy|truthiness)\b.{0,150}limit",
    r"if limit:.{0,150}\b(0|zero)\b",
    r"\b(0|zero)\b.{0,150}if limit:",
]


def c_review(wd, txt):
    t = txt.lower().replace("`", "")
    for p in REVIEW_PATTERNS:
        m = re.search(p, t, re.S)
        if m:
            return True, f"matched {p!r}: {m.group(0)[:80]!r}"
    return False, "planted limit=0 defect not mentioned"


def c_summary(wd, txt):
    n = len(words(txt))
    t = txt.lower()
    mods = [m for m in ["database", "table", "queries", "storages", "middlewares", "operations"] if m in t]
    why = []
    if n > 170:
        why.append(f"{n} words > 170")
    if len(mods) < 4:
        why.append(f"only {len(mods)} modules {mods}")
    return (not why), ("; ".join(why) if why else f"{n} words, modules {mods}")


CHECKS = {"explore": c_explore, "tests": c_tests, "lint": c_lint, "commit": c_commit,
          "refactor": c_refactor, "review": c_review, "summary": c_summary}

if __name__ == "__main__":
    task, wd, res = sys.argv[1], os.path.abspath(sys.argv[2]), sys.argv[3]
    ok, why = CHECKS[task](wd, final_text(res))
    print(("PASS " if ok else "FAIL ") + why)
    sys.exit(0 if ok else 1)

check.py on GitHub

analyze.py

#!/usr/bin/env python3
"""Aggregate runs/*/score.json into results.json and results.md.

Per config x task: accept rate, mean tokens, mean cost, mean turns, mean wall.
Per config: measured plan-meter deltas (five_hour, seven_day, in percentage points), computed two ways:
  - per_run_sum: sum over the config's runs of (after - before). Quantized at 1% per run, so
    runs far below 1% mostly read 0: a lower-bound-ish, very noisy number.
  - segments:    runs sorted by start time are cut into maximal contiguous segments of the same
    config; each segment contributes (after of its last run - before of its first run). This
    telescopes the quantization: one +-1 pt error per segment instead of per run. PREFERRED.
  Segments/runs whose window resetsAt changed between before and after are excluded for that window.
Plus the /usage-style local heuristic: weighted = cached*1 + uncached*10 + cache_create*12.5 + output*50,
times the model tier (haiku 1 / sonnet 3 / opus 5). The probe's own Haiku tokens after each run are
counted as overhead in the heuristic (they also move the meter).
Usage: analyze.py [--runs-dir runs] [--out-prefix results]
"""
import glob, json, os, statistics, sys

HERE = os.path.dirname(os.path.abspath(__file__))
RUNS = os.path.join(HERE, sys.argv[sys.argv.index("--runs-dir") + 1]) if "--runs-dir" in sys.argv else os.path.join(HERE, "runs")
OUTP = sys.argv[sys.argv.index("--out-prefix") + 1] if "--out-prefix" in sys.argv else "results"
CFGS = json.load(open(os.path.join(HERE, "configs.json")))
TASKS = list(json.load(open(os.path.join(HERE, "tasks.json"))).keys())
W = {"cache_read_input_tokens": 1, "input_tokens": 10, "cache_creation_input_tokens": 12.5, "output_tokens": 50}
TIER = {c: v["tier"] for c, v in CFGS.items()}


def weighted(tok, tier):
    raw = sum((tok.get(k) or 0) * w for k, w in W.items())
    return raw, raw * tier


MU = {"cacheReadInputTokens": "cache_read_input_tokens", "inputTokens": "input_tokens",
      "cacheCreationInputTokens": "cache_creation_input_tokens", "outputTokens": "output_tokens"}


def model_tier(name, fallback):
    n = (name or "").lower()
    return 5 if "opus" in n else 3 if "sonnet" in n else 1 if "haiku" in n else fallback


def heuristic_run(s):
    """Tiered heuristic per model actually used (modelUsage), so helper calls on another
    model are weighted with their own tier; falls back to `usage` x config tier."""
    mu = s.get("modelUsage") or {}
    if not mu:
        return weighted(s["tokens"], TIER[s["config"]])[1]
    return sum(weighted({MU[k]: v.get(k) or 0 for k in MU}, model_tier(m, TIER[s["config"]]))[1] for m, v in mu.items())


def probe_tokens(run_dir):
    p = os.path.join(run_dir, "probe.jsonl")
    if not os.path.exists(p):
        return {}
    for line in reversed(open(p, errors="replace").read().strip().split("\n")):
        try:
            o = json.loads(line)
        except Exception:
            continue
        if o.get("type") == "result":
            u = o.get("usage") or {}
            return {k: u.get(k) or 0 for k in W}
    return {}


def mean(xs):
    xs = [x for x in xs if x is not None]
    return statistics.mean(xs) if xs else None


def window_delta(b, a, w):
    if not b or not a or b.get(w) is None or a.get(w) is None:
        return None, "missing"
    if b.get(w + "_resets_at") != a.get(w + "_resets_at"):
        return None, "reset"
    return round((a[w] - b[w]) * 100, 2), "ok"


scores = []
for p in sorted(glob.glob(os.path.join(RUNS, "*", "score.json"))):
    s = json.load(open(p))
    if s.get("config") not in CFGS:
        continue
    s["_dir"] = os.path.dirname(p)
    s["_start"] = (s.get("meter_before") or {}).get("ts") or os.path.getmtime(os.path.join(s["_dir"], "stream.jsonl"))
    s["_probe_tok"] = probe_tokens(s["_dir"])
    scores.append(s)
# meter_before.ts is written at extraction time; order by stream file creation instead
for s in scores:
    st = os.stat(os.path.join(s["_dir"], "stream.jsonl"))
    s["_start"] = getattr(st, "st_birthtime", st.st_mtime)
scores.sort(key=lambda s: s["_start"])

cells, per_cfg = {}, {}
for s in scores:
    cells.setdefault((s["config"], s["task"]), []).append(s)
    per_cfg.setdefault(s["config"], []).append(s)

cell_rows = []
for (c, t), ss in sorted(cells.items(), key=lambda kv: (list(CFGS).index(kv[0][0]), TASKS.index(kv[0][1]) if kv[0][1] in TASKS else 99)):
    row = {"config": c, "task": t, "n": len(ss),
           "accept_rate": sum(1 for s in ss if s.get("accepted")) / len(ss),
           "mean_turns": mean([s.get("num_turns") for s in ss]),
           "mean_cost_usd": mean([s.get("total_cost_usd") for s in ss]),
           "mean_wall_s": mean([s.get("wall_s") for s in ss]),
           "mean_tokens": {k: mean([s["tokens"].get(k) for s in ss]) for k in W},
           "mean_weighted_heuristic": mean([heuristic_run(s) for s in ss]),
           "model_ok_all": all(s.get("model_ok") for s in ss)}
    cell_rows.append(row)

# contiguous segments in global start order
segments, cur = [], None
for s in scores:
    if cur and cur["config"] == s["config"]:
        cur["runs"].append(s)
    else:
        cur = {"config": s["config"], "runs": [s]}
        segments.append(cur)

cfg_rows = []
for c, ss in per_cfg.items():
    tok_sum = {k: sum(s["tokens"].get(k) or 0 for s in ss) for k in W}
    probe_sum = {k: sum(s["_probe_tok"].get(k, 0) for s in ss) for k in W}
    raw_w, _ = weighted(tok_sum, TIER[c])
    heur = sum(heuristic_run(s) for s in ss)
    probe_raw, probe_heur = weighted(probe_sum, 1)
    row = {"config": c, "runs": len(ss), "accept_rate": sum(1 for s in ss if s.get("accepted")) / len(ss),
           "tokens_sum": tok_sum, "probe_tokens_sum": probe_sum,
           "cost_sum_usd": round(sum(s.get("total_cost_usd") or 0 for s in ss), 4),
           "weighted_raw_M": raw_w / 1e6, "heuristic_M": (heur + probe_heur) / 1e6}
    for w in ("five_hour", "seven_day"):
        per_run, excl = 0.0, 0
        for s in ss:
            d, why = window_delta(s.get("meter_before"), s.get("meter_after"), w)
            if d is None:
                excl += 1
            else:
                per_run += d
        seg_sum, seg_n, seg_excl = 0.0, 0, 0
        for g in segments:
            if g["config"] != c:
                continue
            d, why = window_delta(g["runs"][0].get("meter_before"), g["runs"][-1].get("meter_after"), w)
            if d is None:
                seg_excl += 1
            else:
                seg_sum += d; seg_n += 1
        row[w] = {"per_run_sum_pts": round(per_run, 2), "per_run_excluded": excl,
                  "segments_sum_pts": round(seg_sum, 2), "segments": seg_n, "segments_excluded": seg_excl,
                  "quantization_error_pts": f"+-{seg_n}",
                  "pts_per_M_heuristic": round(seg_sum / row["heuristic_M"], 4) if row["heuristic_M"] else None,
                  "pts_per_M_weighted_raw": round(seg_sum / row["weighted_raw_M"], 4) if row["weighted_raw_M"] else None}
    cfg_rows.append(row)
cfg_rows.sort(key=lambda r: list(CFGS).index(r["config"]))

out = {"generated_from": len(scores), "cells": cell_rows, "configs": cfg_rows,
       "segments": [{"config": g["config"], "runs": [s["run"] for s in g["runs"]],
                     "before": g["runs"][0].get("meter_before"), "after": g["runs"][-1].get("meter_after")} for g in segments],
       "heuristic_weights": {"tokens": W, "tier": TIER}}
json.dump(out, open(os.path.join(HERE, OUTP + ".json"), "w"), indent=2, default=str)

f = lambda x, d=0: "-" if x is None else (f"{x:,.{d}f}")
md = ["# Results", "", f"{len(scores)} runs. Meter deltas in percentage points of the plan window (1-pt resolution).", "",
      "## Per config x task", "",
      "| config | task | n | accept | turns | input | cache read | cache create | output | cost $ | wall s | heuristic (M) | model ok |",
      "|---|---|---|---|---|---|---|---|---|---|---|---|---|"]
for r in cell_rows:
    t = r["mean_tokens"]
    md.append(f"| {r['config']} | {r['task']} | {r['n']} | {r['accept_rate']:.0%} | {f(r['mean_turns'],1)} | {f(t['input_tokens'])} | "
              f"{f(t['cache_read_input_tokens'])} | {f(t['cache_creation_input_tokens'])} | {f(t['output_tokens'])} | "
              f"{f(r['mean_cost_usd'],4)} | {f(r['mean_wall_s'],1)} | {f(r['mean_weighted_heuristic']/1e6,2)} | {r['model_ok_all']} |")
md += ["", "## Per config: measured meter vs local heuristic", "",
       "| config | runs | accept | cost $ | heuristic (M units) | 5h pts (segments) | 5h pts (per-run sum) | 7d pts (segments) | segments | 5h pts / M heuristic | 7d pts / M heuristic |",
       "|---|---|---|---|---|---|---|---|---|---|---|"]
for r in cfg_rows:
    fh, sd = r["five_hour"], r["seven_day"]
    md.append(f"| {r['config']} | {r['runs']} | {r['accept_rate']:.0%} | {r['cost_sum_usd']} | {r['heuristic_M']:.2f} | "
              f"{fh['segments_sum_pts']} (excl {fh['segments_excluded']}) | {fh['per_run_sum_pts']} | {sd['segments_sum_pts']} (excl {sd['segments_excluded']}) | "
              f"{fh['segments']} | {fh['pts_per_M_heuristic']} | {sd['pts_per_M_heuristic']} |")
md += ["", "If the /usage heuristic matched the real meter, `pts / M heuristic` would be the same for every config.",
       "Each segment carries up to +-1 pt of quantization error; trust a config's number only when its segment sum is several points.", ""]
open(os.path.join(HERE, OUTP + ".md"), "w").write("\n".join(md))
print("\n".join(md))

analyze.py on GitHub

設定:

• configs.json:四個工人,附完整的模型 ID,低 effort 區塊使用 --effort low。

  configs.json

{
  "haiku-med": {"args": ["--model", "claude-haiku-5-5"], "model": "claude-haiku-5-5", "tier": 1, "note": "default effort"},
  "haiku-low": {"args": ["--model", "claude-haiku-5-5", "--effort", "low"], "model": "claude-haiku-5-5", "tier": 1},
  "sonnet":    {"args": ["--model", "claude-sonnet-5-5"], "model": "claude-sonnet-5-5", "tier": 3, "note": "default effort"},
  "opus":      {"args": ["--model", "claude-opus-5-5"], "model": "claude-opus-5-5", "tier": 5, "note": "default effort"}
}

configs.json on GitHub

tasks.json

{
  "explore":  {"inject": null,                     "mode": null,       "kind": "answer"},
  "tests":    {"inject": "inject/tests.patch",     "mode": "commit",   "kind": "code"},
  "lint":     {"inject": "inject/lint.patch",      "mode": "commit",   "kind": "code"},
  "commit":   {"inject": "reference/T1.patch",     "mode": "stage",    "kind": "answer"},
  "refactor": {"inject": null,                     "mode": null,       "kind": "code"},
  "review":   {"inject": "inject/review.patch",    "mode": "worktree", "kind": "answer"},
  "summary":  {"inject": null,                     "mode": null,       "kind": "answer"}
}

tasks.json on GitHub

ruff.toml

# Pinned lint config for the `lint` task: a small explicit rule set.
# Upstream tinydb @ 18d73a1 is clean under it (the two per-file ignores cover
# pre-existing F401s: the __version__ re-export and middlewares' Optional).
[lint]
select = ["F401", "F541", "F841", "E722"]

[lint.per-file-ignores]
"tinydb/__init__.py" = ["F401"]
"tinydb/middlewares.py" = ["F401"]

ruff.toml on GitHub

預先植入的變更:

• inject/tests.patch:翻轉 Query.__ge__ 裡的一個比較,讓一個測試失敗。

  inject/tests.patch

diff --git a/tinydb/queries.py b/tinydb/queries.py
index cdab9fb..db00a2a 100644
--- a/tinydb/queries.py
+++ b/tinydb/queries.py
@@ -322,7 +322,7 @@ class Query(QueryInstance):
         :param rhs: The value to compare against
         """
         return self._generate_test(
-            lambda value: value >= rhs,
+            lambda value: value > rhs,
             ('>=', self._path, rhs)
         )
 

inject/tests.patch on GitHub

inject/lint.patch

diff --git a/ruff.toml b/ruff.toml
new file mode 100644
--- /dev/null
+++ b/ruff.toml
@@ -0,0 +1,6 @@
+[lint]
+select = ["F401", "F541", "F841", "E722"]
+
+[lint.per-file-ignores]
+"tinydb/__init__.py" = ["F401"]
+"tinydb/middlewares.py" = ["F401"]
diff --git a/tinydb/operations.py b/tinydb/operations.py
index 7101a23..f8541fe 100644
--- a/tinydb/operations.py
+++ b/tinydb/operations.py
@@ -10,6 +10,7 @@ This would delete the ``foo`` field from all documents where ``foo`` equals 2.
 
 
 from collections.abc import Callable, MutableMapping
+import sys
 from typing import Any, Union
 
 
@@ -18,7 +19,7 @@ def delete(field: str) -> Callable[[MutableMapping], None]:
     Delete a given field from the document.
     """
     def transform(doc: MutableMapping):
-        del doc[field]
+        removed = doc.pop(field)
 
     return transform
 
diff --git a/tinydb/queries.py b/tinydb/queries.py
index cdab9fb..489a2be 100644
--- a/tinydb/queries.py
+++ b/tinydb/queries.py
@@ -227,7 +227,7 @@ class Query(QueryInstance):
         :return: A :class:`~tinydb.queries.QueryInstance` object
         """
         if not self._path and not allow_empty_path:
-            raise ValueError('Query has no path')
+            raise ValueError(f'Query has no path')
 
         def runner(value):
             try:
diff --git a/tinydb/table.py b/tinydb/table.py
index f4027bf..eb8058c 100644
--- a/tinydb/table.py
+++ b/tinydb/table.py
@@ -818,7 +818,7 @@ class Table:
 
         try:
             raw_table = tables[self.name]
-        except KeyError:
+        except:
             # The table does not exist yet, so it is empty
             raw_table = {}
 
diff --git a/tinydb/utils.py b/tinydb/utils.py
index 43cad4e..07114d5 100644
--- a/tinydb/utils.py
+++ b/tinydb/utils.py
@@ -2,6 +2,7 @@
 Utility functions.
 """
 
+import os
 from collections import OrderedDict, abc
 from collections.abc import Iterator
 from typing import TypeVar, Generic, Union, Optional, TYPE_CHECKING, cast

inject/lint.patch on GitHub

inject/review.patch

diff --git a/tinydb/table.py b/tinydb/table.py
index f4027bf..4e06ba1 100644
--- a/tinydb/table.py
+++ b/tinydb/table.py
@@ -244,10 +244,21 @@ class Table:
 
         return list(iter(self))
 
-    def search(self, cond: QueryLike) -> list[Document]:
+    def search(
+        self,
+        cond: QueryLike,
+        *,
+        sort_by: Optional[str] = None,
+        reverse: bool = False,
+        limit: Optional[int] = None,
+    ) -> list[Document]:
         """
         Search for all documents matching a 'where' cond.
 
+        Results can optionally be sorted by a field (``sort_by``, descending
+        with ``reverse=True``; documents without the field always come last)
+        and truncated to the first ``limit`` results after sorting.
+
         Note: a repeated search with the same ``cond`` is served from an
         internal cache. The returned list is a fresh copy, but its
         documents are the same objects held by the cache -- treat them as
@@ -255,8 +266,34 @@ class Table:
         what a later identical search returns.
 
         :param cond: the condition to check against
+        :param sort_by: optional field name to sort the results by
+        :param reverse: sort in descending order
+        :param limit: optional maximum number of results
         :returns: list of matching documents
         """
+        if limit is not None and limit < 0:
+            raise ValueError('limit must not be negative')
+
+        # The cache always holds the plain, unsorted, untruncated result;
+        # _search returns a fresh list we are free to reorder/slice
+        docs = self._search(cond)
+
+        if sort_by is not None:
+            field = sort_by
+            present = [doc for doc in docs if field in doc]
+            missing = [doc for doc in docs if field not in doc]
+            present.sort(key=lambda doc: doc[field], reverse=reverse)
+            docs = present + missing
+
+        if limit:
+            docs = docs[:limit]
+
+        return docs
+
+    def _search(self, cond: QueryLike) -> list[Document]:
+        """
+        Plain search backed by the query cache. Returns a fresh list.
+        """
 
         # First, we check the query cache to see if it has results for this
         # query

inject/review.patch on GitHub

prompt 與標準答案:

• tasks/explore.md:查詢快取在哪裡失效,以及哪些公開方法會觸發它。

  tasks/explore.md

Where does TinyDB invalidate its query cache, and which public methods trigger it? Give file paths and function names.

tasks/explore.md on GitHub

tasks/tests.md

pytest fails on this repo. Find the bug in the library code and fix it. Do not change the tests.

tasks/tests.md on GitHub

tasks/lint.md

ruff reports issues in tinydb/ (run `ruff check tinydb`). Fix them all without changing behaviour.

tasks/lint.md on GitHub

tasks/commit.md

Write the commit message for the staged changes. Output only the message.

tasks/commit.md on GitHub

tasks/refactor.md

I keep writing little lambdas to append things to list fields, so can you add two update operations to `tinydb.operations`, next to `increment`, `delete` and friends? `push(field, value)` should append `value` to the list stored in `field`, keeping the existing order, and `pull(field, value)` should remove every occurrence of `value` from that list, not just the first one. If a document doesn't have the field yet, `push` should create it as a one-element list, while `pull` should just leave that document alone without raising. If the field exists but isn't a list, `push` has to raise a `TypeError` instead of doing something weird with it. They should be used exactly like the existing operations, e.g. `db.update(push('tags', 'python'), User.name == 'john')`.

tasks/refactor.md on GitHub

tasks/review.md

Review the uncommitted changes for bugs and edge cases. List findings only.

tasks/review.md on GitHub

tasks/summary.md

Summarize how TinyDB is organised for a new contributor in at most 150 words: the main modules and what each owns.

tasks/summary.md on GitHub

tasks/explore.truth.md

# explore: ground truth (tinydb @ 18d73a1)

- The query cache is `Table._query_cache`, an `LRUCache` (tinydb/utils.py) created in
  `Table.__init__` (tinydb/table.py, `query_cache_class = LRUCache`, capacity
  `default_query_cache_capacity = 10`). It is filled in `Table.search`.
- Invalidation happens in one place: `Table._update_table()` (tinydb/table.py) ends with
  `self.clear_cache()`, and `Table.clear_cache()` does `self._query_cache.clear()`.
- Every public write goes through `_update_table`, so these trigger it:
  `insert`, `insert_multiple`, `update` (all three branches: callable/fields, by doc_ids, by cond),
  `update_multiple`, `upsert` (via `update` or `insert`), `remove` (by cond or doc_ids), `truncate`.
  `Table.__init__(persist_empty=True)` also calls it. `clear_cache()` itself is public.
  `TinyDB` (tinydb/database.py) forwards these via `__getattr__` to the default table;
  `drop_table`/`drop_tables` do not clear a cache, they forget the `Table` instances (`self._tables`).

## Check rule (check.py explore)
PASS iff the final answer
1. contains `table.py`, AND
2. contains `clear_cache` or `_query_cache`, AND
3. names at least 3 distinct methods among
   insert, insert_multiple, update, update_multiple, upsert, remove, truncate (word match, case-insensitive).

tasks/explore.truth.md on GitHub

tasks/review.truth.md

# review: planted defect and matching rule

The uncommitted change is the reference T4 patch (`Table.search(cond, *, sort_by, reverse, limit)`)
with one defect: the truncation guard is `if limit:` instead of `if limit is not None:`, so
`search(cond, limit=0)` returns ALL matching documents instead of `[]` (0 is falsy).
Everything else in the change is correct (missing-field docs last in both directions,
negative limit -> ValueError, cache keeps the plain result).

## Check rule (check.py review)
PASS iff the final answer (case-insensitive) matches at least one of:
- `limit\s*=?=\s*0` (e.g. "limit=0", "limit == 0")
- `limit\s+(of\s+)?(0|zero)\b` (e.g. "limit of 0", "limit zero")
- `\b(0|zero)\s+limit` / `zero[- ]limit`
- `limit` within 150 characters of `falsy|falsey|truthy|truthiness` (either order)
- `if limit:` together with `0` or `zero` within 150 characters
Decoy answers (generic review, or only the sort order) must FAIL.

tasks/review.truth.md on GitHub

週一要做的事

• 執行 Claude Code 2.1.257 或更新版本,才有 force 旗標;並使用 2.1.243 或更新版本,/tasks 才會顯示每個 subagent 的模型。
• 決定你要哪個檔案:只處理探索者就用 Explore 檔,要處理每個 subagent 就用 env 區塊。
• 把 Explore.md 存成 .claude/agents/Explore.md,或把 env 區塊合併進 .claude/settings.json。
• 使用完整 ID claude-haiku-5-5,不要用 haiku 別名,在 Bedrock、Vertex 或 Foundry 上尤其如此。
• 開一個 session,要求透過 Explore agent 搜尋程式碼,然後打開 /tasks,讀它實際用的模型和 effort。
• 任何做複雜 agentic coding 的 subagent 都留在 Sonnet 5.5 或 Opus 5.5,如果你是刻意指定了這樣的 agent,就不要設定 FORCE。
• 在相信我們的表之前,先用工具在你自己的儲存庫上重跑你自己的七個任務。
• 把 /usage 讀成「哪個 skill 或 agent 在吃我的本地紀錄」,而不是額度預測。

量測結果

方案用量表,從每次 headless 執行的 rate_limit_event 讀出,解析度一個百分點。每個區塊是連續的,期間沒有任何其他東西動到這個帳號。182 次執行中,每一次的每週視窗都讀到 67%。

矩陣摘要:182 次執行,整個矩陣的牌價約 $4.09,五小時視窗兩個百分點,每週零個百分點。每個區塊最多帶有一個百分點的四捨五入誤差,所以 Sonnet 的一個百分點和 Opus 的一個百分點無法區分。在這個用量表上,任何一個模型的有範圍任務都是看不見的。關於三個模型每輪相對成本的支援頁面,沒有給出倍率 s9。

與本地明細的對照,依設定:

/usage 明細是根據你機器上的本地紀錄計算的 s3。它的公式是從客戶端執行檔讀出來的,為模型層級乘以紀錄權重。模型層級:Fable 10、Opus 5、Haiku 1、其他 3。紀錄權重:快取 token 1、未快取輸入 10、快取建立 12.5、輸出 50。這些是客戶端的本地歸因權重,不是計費,也不能證明伺服器如何計算你的額度。落差很明顯:Haiku 中等區塊得 29.48,Opus 區塊得 27.30,所以面板把 Haiku 區塊排在 Opus 區塊前面,而真正的用量表讀到的是零對一個百分點。

一個帳號一個月的紀錄把 token 放在哪裡:2,631 次 subagent 執行,42 次用 Haiku 4.5,subagent 佔全部 token 的 48.1%,Haiku 4.5 佔加權成本的 0.27%,不論模型是什麼,subagent 啟動 prompt 的中位數都是 47,117 token。

effort 在同一個被接受的功能(refactor)上改變了食量:Haiku 中等讀了 232,985 個快取讀取 token,共 13.7 輪;Haiku 低讀了 139,801 個,共 7.6 輪;Opus 讀了 87,612 個,共 8.3 輪。

延伸閱讀

• 100k 的價格懸崖:prompt 超過 100,000 token 之後,較高的價格適用於整個請求,而不是只適用於超出的部分 s8。快取 token 是否計入那 100k,是該作者的解讀,不是引用的規則。它影響 API 金鑰的經濟帳,不影響訂閱方案的用量表。定價頁面:s20。
• Tokenizer:同樣的文字在 Haiku 5.5 上比 Haiku 4.5 多算約 30% 的 token,而且 API 上預設開啟 adaptive thinking,以 effort 作為槓桿 s12。
• effort 與每個任務的 token:一次獨立的測試量到 max effort 下每個 Intelligence Index 任務約 162k 輸出 token,high effort 下約 55k,得分 38 s7。
• 一套完整的實踐者配置,附上他的數字,以及他自己的提醒:省下來的部分來自很小的主 context:s4。
• 公開的 issue #100082,在某些版本上 subagent 的 frontmatter 模型被忽略:s10。
• 公開的 issue #100154,subagent 的 transcript 低估 output_tokens,同一個任務是 461 對 15,575,伺服器端的計費不受影響 s11。由於 /usage 把本地紀錄的輸出乘以 50,這個低估會傳到面板上。
• 這裡沒有測試的:把 Haiku 當主模型(資料來源把 Haiku 5.5 定位為 subagent)、透過 gateway 跨供應商混用模型(不屬於 Claude Code 的設定)、1M context 的 prompt,以及 Max 方案附帶的 API 額度(屬於 Claude Platform,不是 Claude Code 額度)。

常見問題

設定 CLAUDE_CODE_SUBAGENT_MODEL 就能讓 Explore 改用 Haiku 嗎?

不行。單獨使用時,它不會改變內建的 Explore 和 Plan subagent s2。請加上 Explore agent 檔,或 force 旗標。

FORCE 會弄壞我的 Opus subagent 嗎?

它會把同一個模型套用到每個 subagent,所以會:你刻意指定 Opus 的 agent 也會跑在 Haiku 上。如果只想讓探索者便宜,請用 Explore 檔。

Haiku 5.5 夠不夠勝任 subagent 的工作?

對這七個範圍明確、在一個小儲存庫上的任務,低 effort 被接受 70 次中的 70 次,中等 effort 也是 70 次中的 70 次。Anthropic 自己仍把複雜的 agentic coding 留給 Sonnet 5.5 和 Opus 5.5 s1,Terminal-Bench 4.0 的差距是 39.2% 對 70.6%。

這樣切換能還給我多少方案額度?

對一個有範圍的任務來說,在任何模型上都不到用量表的一個百分點:整個 182 次執行的矩陣讓五小時視窗動了兩個百分點,每週視窗動了零。一週的額度真正花在哪裡,是主 context 和每個 subagent 帶著的啟動 prompt。

我可以把思考關掉來省更多嗎?

在 Claude Code 中,這些模型不行 s21。剩下的旋鈕是 effort。