simulation-validator

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Simulation Validator

模拟验证器

Goal

目标

Provide a three-stage validation protocol: pre-flight checks, runtime monitoring, and post-flight validation for materials simulations.

为材料模拟提供三阶段验证流程：起飞前检查、运行时监控和起飞后验证。

Requirements

要求

Python 3.10+
No external dependencies (uses Python standard library only)
Works on Linux, macOS, and Windows

Python 3.10+
无外部依赖（仅使用Python标准库）
支持Linux、macOS和Windows

Inputs to Gather

需要收集的输入

Before running validation scripts, collect from the user:

Input	Description	Example
Config file	Simulation configuration (JSON/YAML)	`simulation.json`
Log file	Runtime output log	`simulation.log`
Metrics file	Post-run metrics (JSON)	`results.json`
Required params	Parameters that must exist	`dt,dx,kappa`
Valid ranges	Parameter bounds	`dt:1e-6:1e-2`

在运行验证脚本前，向用户收集以下信息：

输入	描述	示例
配置文件	模拟配置（JSON/YAML）	`simulation.json`
日志文件	运行时输出日志	`simulation.log`
指标文件	运行后指标（JSON）	`results.json`
必填参数	必须存在的参数	`dt,dx,kappa`
有效范围	参数边界	`dt:1e-6:1e-2`

Decision Guidance

决策指南

When to Run Each Stage

各阶段运行时机

Is simulation about to start?
├── YES → Run Stage 1: preflight_checker.py
│         └── BLOCK status? → Fix issues, do NOT run simulation
│         └── WARN status? → Review warnings, document if accepted
│         └── PASS status? → Proceed to run simulation
│
Is simulation running?
├── YES → Run Stage 2: runtime_monitor.py (periodically)
│         └── Alerts? → Consider stopping, check parameters
│
Has simulation finished?
├── YES → Run Stage 3: result_validator.py
│         └── Failed checks? → Do NOT use results
│                            → Run failure_diagnoser.py
│         └── All passed? → Results are valid

模拟即将启动？
├── 是 → 运行阶段1：preflight_checker.py
│         └── BLOCK状态？ → 修复问题，**不要**启动模拟
│         └── WARN状态？ → 查看警告，记录已接受的风险
│         └── PASS状态？ → 继续启动模拟
│
模拟正在运行？
├── 是 → 定期运行阶段2：runtime_monitor.py
│         └── 出现警报？ → 考虑停止模拟，检查参数
│
模拟已完成？
├── 是 → 运行阶段3：result_validator.py
│         └── 检查未通过？ → **不要**使用结果
│                            → 运行failure_diagnoser.py
│         └── 全部通过？ → 结果有效

Choosing Validation Thresholds

选择验证阈值

Metric	Conservative	Standard	Relaxed
Mass tolerance	1e-6	1e-3	1e-2
Residual growth	2x	10x	100x
dt reduction	10x	100x	1000x

指标	保守型	标准型	宽松型
质量容差	1e-6	1e-3	1e-2
残差增长	2x	10x	100x
dt 缩减	10x	100x	1000x

Script Outputs (JSON Fields)

脚本输出（JSON字段）

Script	Output Fields
`scripts/preflight_checker.py`	`report.status` , `report.blockers` , `report.warnings`
`scripts/runtime_monitor.py`	`alerts` , `residual_stats` , `dt_stats` (alerts include NaN/Inf/overflow detection, residual growth, and dt collapse)
`scripts/result_validator.py`	`checks` , `confidence_score` , `failed_checks` , `status` ( `PASS` / `FAIL` / `INSUFFICIENT_DATA` ); `confidence_score` is `null` when no check ran
`scripts/failure_diagnoser.py`	`probable_causes` , `recommended_fixes`

脚本	输出字段
`scripts/preflight_checker.py`	`report.status` , `report.blockers` , `report.warnings`
`scripts/runtime_monitor.py`	`alerts` , `residual_stats` , `dt_stats` （警报包含NaN/Inf/溢出检测、残差增长和dt崩溃）
`scripts/result_validator.py`	`checks` , `confidence_score` , `failed_checks` , `status` （ `PASS` / `FAIL` / `INSUFFICIENT_DATA` ）；未运行任何检查时 `confidence_score` 为 `null`
`scripts/failure_diagnoser.py`	`probable_causes` , `recommended_fixes`

Three-Stage Validation Protocol

三阶段验证流程

Stage 1: Pre-flight (Before Simulation)

阶段1：起飞前（模拟启动前）

Run

scripts/preflight_checker.py --config simulation.json

BLOCK status: Stop immediately, fix all blocker issues
WARN status: Review warnings, document accepted risks
PASS status: Proceed to simulation

Note:
preflight_checker.py
validates required keys, numeric ranges, output-directory access, and disk space. It does not evaluate numerical stability (CFL / diffusion-Fourier). For explicit stability gating use
skills/core-numerical/numerical-stability/scripts/cfl_checker.py
.

bash

python3 scripts/preflight_checker.py \
    --config simulation.json \
    --required dt,dx,kappa \
    --ranges "dt:1e-6:1e-2,dx:1e-4:1e-1" \
    --min-free-gb 1.0 \
    --json

运行

scripts/preflight_checker.py --config simulation.json

BLOCK状态：立即停止，修复所有阻塞问题
WARN状态：查看警告，记录已接受的风险
PASS状态：继续启动模拟

注意：
preflight_checker.py
会验证必填键、数值范围、输出目录权限和磁盘空间。它不评估数值稳定性（CFL / 扩散-傅里叶）。如需显式稳定性校验，请使用
skills/core-numerical/numerical-stability/scripts/cfl_checker.py
。

bash

python3 scripts/preflight_checker.py \
    --config simulation.json \
    --required dt,dx,kappa \
    --ranges "dt:1e-6:1e-2,dx:1e-4:1e-1" \
    --min-free-gb 1.0 \
    --json

Stage 2: Runtime (During Simulation)

阶段2：运行时（模拟进行中）

Run

scripts/runtime_monitor.py --log simulation.log

periodically

Configure alert thresholds based on problem type
Stop simulation if critical alerts appear

bash

python3 scripts/runtime_monitor.py \
    --log simulation.log \
    --residual-growth 10.0 \
    --dt-drop 100.0 \
    --json

定期运行

scripts/runtime_monitor.py --log simulation.log

根据问题类型配置警报阈值
出现严重警报时停止模拟

bash

python3 scripts/runtime_monitor.py \
    --log simulation.log \
    --residual-growth 10.0 \
    --dt-drop 100.0 \
    --json

Stage 3: Post-flight (After Simulation)

阶段3：起飞后（模拟完成后）

Run

scripts/result_validator.py --metrics results.json

All checks PASS: Results are valid for analysis
Any check FAIL: Do NOT use results, diagnose failure

bash

python3 scripts/result_validator.py \
    --metrics results.json \
    --bound-min 0.0 \
    --bound-max 1.0 \
    --mass-tol 1e-3 \
    --json

For variational / gradient-flow models (Allen-Cahn, Cahn-Hilliard), add

--variational

to enforce a strict monotone non-increasing energy check.

运行

scripts/result_validator.py --metrics results.json

全部检查通过：结果可用于分析
任意检查失败：不要使用结果，诊断故障原因

bash

python3 scripts/result_validator.py \
    --metrics results.json \
    --bound-min 0.0 \
    --bound-max 1.0 \
    --mass-tol 1e-3 \
    --json

对于变分/梯度流模型（Allen-Cahn、Cahn-Hilliard），添加

--variational

参数以强制严格的单调非递增能量检查。

Failure Diagnosis

故障诊断

When validation fails:

bash

python3 scripts/failure_diagnoser.py --log simulation.log --json

验证失败时：

bash

python3 scripts/failure_diagnoser.py --log simulation.log --json

Conversational Workflow Example

对话工作流示例

User: My phase field simulation crashed after 1000 steps. Can you help me figure out why?

Agent workflow:

First, check the log for obvious errors:

bash

python3 scripts/failure_diagnoser.py --log simulation.log --json

If diagnosis suggests numerical blow-up, check runtime stats:

bash

python3 scripts/runtime_monitor.py --log simulation.log --json

Recommend fixes based on findings:
- If residual grew rapidly → reduce time step
- If dt collapsed → check stability conditions
- If NaN detected → check initial conditions

用户：我的相场模拟在1000步后崩溃了，能帮我找出原因吗？

Agent工作流：

首先，检查日志中的明显错误：

bash

python3 scripts/failure_diagnoser.py --log simulation.log --json

如果诊断显示数值爆炸，检查运行时统计数据：
bash
```
python3 scripts/runtime_monitor.py --log simulation.log --json
```
根据结果推荐修复方案：
- 残差快速增长 → 减小时间步长
- dt崩溃 → 检查稳定性条件
- 检测到NaN → 检查初始条件

Error Handling

错误处理

Error	Cause	Resolution
`Config not found`	File path invalid	Verify config path exists
`Non-numeric value`	Parameter is not a number	Fix config file format
`out of range`	Parameter outside bounds	Adjust parameter or bounds
`Output directory not writable`	Permission issue	Check directory permissions
`Insufficient disk space at <path>`	Disk nearly full on the output volume	Free up space or reduce output
`Invalid parameter name`	`--required` name has disallowed characters	Use only letters, digits, `_` , `.` , `-`
`range max ... must be greater than min`	Inverted/degenerate `--ranges` or bounds	Ensure max > min
`must be a finite positive number`	`nan` / `inf` /negative threshold supplied	Pass a finite positive value
`Log file too large`	Log exceeds the 500 MB parse cap	Truncate or pre-filter the log

错误	原因	解决方法
`Config not found`	文件路径无效	验证配置文件路径是否存在
`Non-numeric value`	参数不是数值类型	修复配置文件格式
`out of range`	参数超出边界	调整参数或边界范围
`Output directory not writable`	权限问题	检查目录权限
`Insufficient disk space at <path>`	输出卷磁盘空间不足	释放空间或减少输出内容
`Invalid parameter name`	`--required` 参数名称包含非法字符	仅使用字母、数字、 `_` 、 `.` 、 `-`
`range max ... must be greater than min`	`--ranges` 或边界范围颠倒/无效	确保最大值大于最小值
`must be a finite positive number`	提供了 `nan` / `inf` /负数阈值	传入有限的正数
`Log file too large`	日志文件超过500MB解析上限	截断或预过滤日志

Interpretation Guidance

解读指南

Status Meanings

状态含义

Status	Meaning	Action
PASS	All checks passed	Proceed with confidence
WARN	Non-critical issues found	Review and document
BLOCK	Critical issues found	Must fix before proceeding

状态	含义	操作
PASS	所有检查通过	放心继续
WARN	发现非关键问题	查看并记录
BLOCK	发现关键问题	必须修复后再继续

Confidence Score Interpretation

置信度分数解读

Score	Meaning
1.0	All validation checks passed → proceed with confidence
0.75+	Most checks passed, minor issues
0.5-0.75	Significant issues, review carefully
< 0.5	Major problems, do not trust results
`null` (status `INSUFFICIENT_DATA` )	No recognized metrics fields; no check ran — NOT a pass. Inspect the metrics file.

A requested bound (

--bound-min

--bound-max

) with no matching

field_min

field_max

in the metrics is reported as a failed

bounds_unverifiable

check, never a vacuous pass. For variational/gradient-flow runs, pass

--variational

(or set

"energy_variational": true

in the metrics) to enforce a strict monotone non-increasing energy check (

energy_monotone

); otherwise a weaker

energy_net_decrease

check is used, which does not detect mid-run spikes.

分数	含义
1.0	所有验证检查通过 → 放心继续
0.75+	大部分检查通过，存在轻微问题
0.5-0.75	存在显著问题，需仔细检查
< 0.5	存在重大问题，不要信任结果
`null` （状态 `INSUFFICIENT_DATA` ）	未识别到指标字段；未运行任何检查 — 不代表通过。请检查指标文件。

若指标文件中没有匹配的

field_min

field_max

，则请求的边界（

--bound-min

--bound-max

）会被报告为

bounds_unverifiable

检查失败，绝不会被视为默认通过。对于变分/梯度流运行，传入

--variational

（或在指标中设置

"energy_variational": true

）以强制严格的单调非递增能量检查（

energy_monotone

）；否则会使用较弱的

energy_net_decrease

检查，无法检测运行中途的能量峰值。

Common Failure Patterns

常见失败模式

Pattern in Log	Likely Cause	Recommended Fix
NaN, Inf, overflow	Numerical instability	Reduce dt, increase damping
max iterations, did not converge	Solver failure	Tune preconditioner, tolerances
out of memory	Memory exhaustion	Reduce mesh, enable out-of-core
dt reduced	Adaptive stepping triggered	May be okay if controlled

日志中的模式	可能原因	推荐修复方案
NaN、Inf、溢出	数值不稳定	减小dt，增加阻尼
达到最大迭代次数，未收敛	求解器失败	调整预处理器、容差
内存不足	内存耗尽	减小网格，启用核外计算
dt 减小	触发自适应步长	若处于可控范围内则无问题

Verification checklist

验证清单

Do not trust a validation verdict until each applicable item below is satisfied with the concrete artifact named. Record these in your summary to the user.

Ran

result_validator.py --json

and confirmed

results.status

PASS

(not

INSUFFICIENT_DATA

) AND

results.confidence_score == 1.0

; a

null

score or

INSUFFICIENT_DATA

means no check ran — treat as unverified, not as a pass.

Listed
```
results.checks
```
and confirmed every requested check actually appears (e.g.
```
mass_conserved
```
,
```
bounds_satisfied
```
,
```
no_nan
```
, and
```
energy_monotone
```
/
```
energy_net_decrease
```
); confirmed
```
results.failed_checks
```
is empty and contains no
```
bounds_unverifiable
```
entry (which means a requested bound had no
```
field_min
```
/
```
field_max
```
to compare against).
For variational/gradient-flow models (Allen-Cahn, Cahn-Hilliard), passed
```
--variational
```
(or set
```
"energy_variational": true
```
) so
```
energy_monotone
```
is enforced; recorded that the weaker
```
energy_net_decrease
```
was NOT relied on, since it cannot detect mid-run energy spikes.
Recorded the mass drift tolerance used (
```
--mass-tol
```
, default
```
1e-3
```
) and confirmed it matches the Conservative/Standard/Relaxed column appropriate to the run; did not silently accept the default for a tight-conservation problem.
Ran
```
runtime_monitor.py --json
```
and recorded
```
residual_stats
```
(min/max/last) and
```
dt_stats
```
; confirmed there are no
```
alerts
```
for NaN/Inf/overflow, residual growth above
```
--residual-growth
```
, or dt collapse below
```
--dt-drop
```
.
Confirmed numerical stability was gated separately via
```
core-numerical/numerical-stability/scripts/cfl_checker.py
```
(CFL/Fourier limit) —
```
preflight_checker.py
```
does NOT evaluate CFL/Fourier and a PASS preflight says nothing about temporal/spatial stability.
On any
```
FAIL
```
or alert, ran
```
failure_diagnoser.py --json
```
and recorded the
```
probable_causes
```
/
```
recommended_fixes
```
, rather than reusing the results.

在确认以下所有适用项均满足之前，不要信任验证结论。将这些内容记录到给用户的总结中。

运行
```
result_validator.py --json
```
并确认
```
results.status
```
为
```
PASS
```
（而非
```
INSUFFICIENT_DATA
```
）且
```
results.confidence_score == 1.0
```
；分数为
```
null
```
或状态为
```
INSUFFICIENT_DATA
```
意味着未运行任何检查 — 视为未验证，而非通过。
列出
```
results.checks
```
并确认所有请求的检查均已执行（如
```
mass_conserved
```
、
```
bounds_satisfied
```
、
```
no_nan
```
以及
```
energy_monotone
```
/
```
energy_net_decrease
```
）；确认
```
results.failed_checks
```
为空且不包含
```
bounds_unverifiable
```
条目（该条目表示请求的边界无对应的
```
field_min
```
/
```
field_max
```
可对比）。
对于变分/梯度流模型（Allen-Cahn、Cahn-Hilliard），已传入
```
--variational
```
（或设置
```
"energy_variational": true
```
）以强制
```
energy_monotone
```
检查；记录未依赖较弱的
```
energy_net_decrease
```
检查，因为它无法检测运行中途的能量峰值。
记录使用的质量漂移容差（
```
--mass-tol
```
，默认值
```
1e-3
```
）并确认其符合运行对应的保守型/标准型/宽松型列；对于严格守恒问题，不要默认接受默认值。
运行
```
runtime_monitor.py --json
```
并记录
```
residual_stats
```
（最小值/最大值/最后值）和
```
dt_stats
```
；确认没有关于NaN/Inf/溢出、残差增长超过
```
--residual-growth
```
或dt崩溃低于
```
--dt-drop
```
的
```
alerts
```
。
确认已通过
```
core-numerical/numerical-stability/scripts/cfl_checker.py
```
单独校验数值稳定性（CFL/Fourier极限） —
```
preflight_checker.py
```
不评估CFL/Fourier，起飞前检查通过不代表时间/空间稳定性。
出现任何
```
FAIL
```
或警报时，运行
```
failure_diagnoser.py --json
```
并记录
```
probable_causes
```
/
```
recommended_fixes
```
，不要复用旧结果。

Common pitfalls & rationalizations

常见误区与合理化借口

Tempting shortcut	Why it's wrong / what to do
"Preflight passed, so the run is numerically stable."	`preflight_checker.py` checks required keys, ranges, output-dir writability, and disk space only. It does NOT compute CFL/Fourier. Gate stability with `cfl_checker.py` separately.
" `result_validator` printed a confidence score, so results are good."	An empty or unrecognized metrics file returns `confidence_score: null` and status `INSUFFICIENT_DATA` — that is "no check ran", not a pass. Verify recognized fields are present and `status == PASS` .
"Energy ends lower than it started, so the dissipative run is fine."	The default `energy_net_decrease` only compares first vs last and misses mid-run spikes. For gradient-flow models use `--variational` to enforce the strict monotone `energy_monotone` check.
"I asked for bounds and didn't get a `bounds_satisfied: false` , so bounds hold."	If `field_min` / `field_max` are absent the validator emits `bounds_unverifiable` (a FAILED check), never a vacuous pass. Ensure the metrics file actually carries the field extrema.
"The simulation finished without crashing, so the results are trustworthy."	Run completion is not correctness. Verify mass conservation, energy behavior, physical bounds, and a clean `runtime_monitor` alert list before using results.
"dt got smaller during the run, so the solver is failing."	`runtime_monitor` dt-collapse is direction-aware (running-max vs current) and only alerts past `--dt-drop` ; a controlled adaptive ramp is expected. Check the actual `dt_stats` and whether an alert fired.
"I'll just use the default thresholds."	Defaults ( `--mass-tol 1e-3` , `--residual-growth 10` , `--dt-drop 100` ) are the Standard column; a conservation-critical problem needs the Conservative tolerances. Pick thresholds for the physics, then record them.

诱人的捷径	为何错误 / 正确做法
“起飞前检查通过了，所以运行过程数值稳定。”	`preflight_checker.py` 仅检查必填键、范围、输出目录可写性和磁盘空间。它不计算CFL/Fourier。需单独使用 `cfl_checker.py` 校验稳定性。
“ `result_validator` 输出了置信度分数，所以结果没问题。”	空的或未识别的指标文件会返回 `confidence_score: null` 和状态 `INSUFFICIENT_DATA` — 这表示“未运行任何检查”，而非通过。请确认存在已识别的字段且 `status == PASS` 。
“最终能量低于初始值，所以耗散型运行没问题。”	默认的 `energy_net_decrease` 仅比较初始和最终值，会遗漏运行中途的峰值。对于梯度流模型，请使用 `--variational` 强制严格的单调 `energy_monotone` 检查。
“我要求检查边界但没有得到 `bounds_satisfied: false` ，所以边界符合要求。”	若 `field_min` / `field_max` 不存在，验证器会输出 `bounds_unverifiable` （检查失败），绝不会默认通过。请确保指标文件包含字段极值。
“模拟正常完成没有崩溃，所以结果可信。”	运行完成不代表结果正确。在使用结果前，请验证质量守恒、能量行为、物理边界以及 `runtime_monitor` 的警报列表是否正常。
“运行过程中dt变小了，所以求解器失败了。”	`runtime_monitor` 的dt崩溃检测是方向感知的（运行最大值与当前值对比），仅在超过 `--dt-drop` 时触发警报；可控的自适应调整是正常现象。请查看实际的 `dt_stats` 以及是否触发了警报。
“我直接使用默认阈值就好。”	默认值（ `--mass-tol 1e-3` 、 `--residual-growth 10` 、 `--dt-drop 100` ）属于标准型列；对于严格守恒的问题，需要使用保守型容差。请根据物理特性选择阈值并记录。

Security

安全

Input Validation

输入验证

Config file paths are validated for existence before parsing; non-existent paths produce clear errors (exit code 2)
```
--required
```
parameter names are validated against a safe-character allowlist (
```
^[A-Za-z0-9_.-]+$
```
); names with shell metacharacters are rejected
```
--ranges
```
entries are parsed as
```
name:min:max
```
with finite numeric bounds enforced and
```
max > min
```
required
```
--min-free-gb
```
is validated as a finite positive number (negatives, zero,
```
nan
```
,
```
inf
```
rejected)
```
--residual-growth
```
and
```
--dt-drop
```
thresholds are validated as finite positive numbers
```
--bound-min
```
and
```
--bound-max
```
are validated as finite numbers (
```
nan
```
/
```
inf
```
rejected), and
```
--bound-max > --bound-min
```
is enforced;
```
--mass-tol
```
is validated as a finite positive number
Invalid input exits with code 2 and an explanatory message

解析前会验证配置文件路径是否存在；路径无效时会输出清晰错误（退出码2）
```
--required
```
参数名称会根据安全字符白名单（
```
^[A-Za-z0-9_.-]+$
```
）验证；包含shell元字符的名称会被拒绝
```
--ranges
```
条目会被解析为
```
name:min:max
```
格式，强制要求有限数值边界且
```
max > min
```
```
--min-free-gb
```
会被验证为有限正数（拒绝负数、零、
```
nan
```
、
```
inf
```
）
```
--residual-growth
```
和
```
--dt-drop
```
阈值会被验证为有限正数
```
--bound-min
```
和
```
--bound-max
```
会被验证为有限数（拒绝
```
nan
```
/
```
inf
```
），且强制要求
```
--bound-max > --bound-min
```
；
```
--mass-tol
```
会被验证为有限正数
无效输入会以退出码2和解释性消息终止程序

File Access

文件访问

```
preflight_checker.py
```
reads a single user-specified config file (JSON/YAML) and checks disk space on the volume hosting the resolved output directory
```
runtime_monitor.py
```
reads a single log file specified by
```
--log
```
; log files are size-limited (500 MB max) and rejected before parsing if larger
```
result_validator.py
```
reads a single metrics file (JSON) specified by
```
--metrics
```
```
failure_diagnoser.py
```
reads a single log file specified by
```
--log
```
; log files are size-limited (500 MB max) before parsing
No scripts write to the filesystem; all output goes to stdout

```
preflight_checker.py
```
读取用户指定的单个配置文件（JSON/YAML），并检查解析后的输出目录所在卷的磁盘空间
```
runtime_monitor.py
```
读取
```
--log
```
指定的单个日志文件；日志文件有大小限制（最大500MB），超过限制会在解析前被拒绝
```
result_validator.py
```
读取
```
--metrics
```
指定的单个指标文件（JSON）
```
failure_diagnoser.py
```
读取
```
--log
```
指定的单个日志文件；日志文件有大小限制（最大500MB），超过限制会在解析前被拒绝
所有脚本均不写入文件系统；所有输出均输出到stdout

Tool Restrictions

工具限制

Read: Used to inspect script source, references, config files, and simulation logs
Bash: Used to execute the four Python validation scripts (
```
preflight_checker.py
```
,
```
runtime_monitor.py
```
,
```
result_validator.py
```
,
```
failure_diagnoser.py
```
) with explicit argument lists
Write: Used to save validation reports; writes are scoped to the user's working directory
Grep/Glob: Used to locate log files, config files, and search references

读取：用于检查脚本源码、参考资料、配置文件和模拟日志
Bash：用于执行四个Python验证脚本（
```
preflight_checker.py
```
、
```
runtime_monitor.py
```
、
```
result_validator.py
```
、
```
failure_diagnoser.py
```
），使用显式参数列表
写入：用于保存验证报告；写入范围仅限于用户工作目录
Grep/Glob：用于定位日志文件、配置文件和搜索参考资料

Safety Measures

安全措施

No
```
eval()
```
,
```
exec()
```
, or dynamic code generation
All subprocess calls use explicit argument lists (no
```
shell=True
```
)
```
failure_diagnoser.py
```
uses hardcoded, pre-compiled diagnostic regex patterns;
```
runtime_monitor.py
```
accepts optional
```
--residual-pattern
```
/
```
--dt-pattern
```
overrides that are compiled with
```
re.compile
```
(no
```
eval
```
) and applied only to the user's own log
Diagnostic strings emitted in output are drawn from the skill's fixed cause/fix table, not interpolated from raw log content

不使用
```
eval()
```
、
```
exec()
```
或动态代码生成
所有子进程调用均使用显式参数列表（不使用
```
shell=True
```
）
```
failure_diagnoser.py
```
使用硬编码的预编译诊断正则表达式；
```
runtime_monitor.py
```
接受可选的
```
--residual-pattern
```
/
```
--dt-pattern
```
覆盖参数，这些参数会通过
```
re.compile
```
编译（不使用
```
eval
```
），仅应用于用户自己的日志
输出中的诊断信息来自技能内置的原因/修复表，不会从原始日志内容插值生成

Limitations

局限性

Not a real-time monitor: Scripts analyze logs after-the-fact
Regex-based: Log parsing depends on pattern matching; may miss unusual formats
No automatic fixes: Scripts diagnose but don't modify simulations

非实时监控：脚本仅在事后分析日志
基于正则表达式：日志解析依赖模式匹配；可能无法识别非常规格式
无自动修复：脚本仅诊断问题，不修改模拟配置

References

参考资料

```
references/validation_protocol.md
```
- Detailed checklist and criteria
```
references/log_patterns.md
```
- Common failure signatures and regex patterns

```
references/validation_protocol.md
```
- 详细清单和标准
```
references/log_patterns.md
```
- 常见失败特征和正则表达式

Version History

版本历史

v1.2.2 (2026-06-24): Added a Verification checklist (evidence-based, tied to the four scripts' JSON outputs) and a Common pitfalls & rationalizations table to harden agent interpretation of validation verdicts.
v1.2.0 (2026-06-23): Corrected diagnostic regexes (no false convergence/blow-up on healthy logs), direction-aware dt-collapse detection, NaN/Inf scan in runtime monitor, strict variational energy check, non-vacuous bounds/confidence, config-relative output-dir + correct-volume disk check, and implemented the documented input-validation/file-size safeguards
v1.1.0 (2024-12-24): Enhanced documentation, decision guidance, Windows compatibility
v1.0.0: Initial release with 4 validation scripts

v1.2.2（2026-06-24）：添加验证清单（基于证据，与四个脚本的JSON输出绑定）和常见误区与合理化借口表，强化Agent对验证结论的解读能力。
v1.2.0（2026-06-23）：修正诊断正则表达式（不会在正常日志中误判收敛/爆炸）、方向感知的dt崩溃检测、运行时监控中的NaN/Inf扫描、严格变分能量检查、非默认边界/置信度、配置相对输出目录+正确卷磁盘检查，并实现文档中记录的输入验证/文件大小防护措施
v1.1.0（2024-12-24）：增强文档、决策指南，支持Windows系统
v1.0.0：初始版本，包含4个验证脚本