LATX, docs: Add shared agent guidance and skills - #444
Draft
LaurenIsACoder wants to merge 5 commits into
Draft
Conversation
Define the supported guest scope, repository safety rules, local pre-PR test expectations, and evidence boundaries for shared agent-assisted development. Signed-off-by: Hanlu Li <heuleehanlu@gmail.com>
Add explicit repo-scoped workflows for evidence-bounded bug-fix validation and controlled performance experiments. Keep subsystem detail in progressive references and provide a read-only context manifest helper. Signed-off-by: Hanlu Li <heuleehanlu@gmail.com>
Describe the current TB and AOT translation paths, supported debug controls, dump boundaries, and first-divergence workflow while excluding stale TU-JIT assumptions. Signed-off-by: Hanlu Li <heuleehanlu@gmail.com>
LaurenIsACoder
force-pushed
the
lauren/agent-guidance-skills
branch
from
September 2, 2026 03:28
c08fa1d to
53ab81d
Compare
Extend the performance workflow from candidate validation to evidence-led bottleneck discovery and candidate formation. Keep profiler, pass, and implementation choices open while requiring a stable baseline, falsifiable hypothesis, explicit implementation authorization, and correctness gates. Signed-off-by: Hanlu Li <heuleehanlu@gmail.com>
Keep universal Fix and performance contracts in the Skill entrypoints while moving conditional mechanics behind references. Make the LATX debugging model a Sphinx-indexed source of truth, correct debug build conditions, and remove unauditable historical performance claims. Signed-off-by: Hanlu Li <heuleehanlu@gmail.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
AGENTS.mdguidance for supported scope, change safety,local test expectations, and evidence boundaries
keep universal contracts in each
SKILL.mdand load conditional referencesprogressively
current LATX translation/debugging model without stale TU-JIT assumptions
使用教程(中文)
1.
AGENTS.md如何生效在 LAT 仓库目录中启动新的 Codex 任务时,Codex 会自动读取仓库根目录的
AGENTS.md,不需要手工调用。它提供项目范围、修改安全、测试要求和证据边界等公共规则。
如果刚刚拉取或修改了
AGENTS.md,请重新启动 Codex 任务,使新的指令链生效。2. 查看和调用项目 Skill
在 Codex CLI 或 IDE 中可以输入
/skills,或者输入$查看可用 Skill。本 PR 的两个 Skill 禁止隐式调用,必须在请求中显式写出 Skill 名称:
3. 修复或诊断 Bug
遇到 crash、hang、错误结果、兼容性回归、间歇性故障或测试失败时使用:
Skill 会先区分 diagnosis、implementation 和 existing-candidate validation。只要求
诊断或验证时,不授权编辑 repository、source、test 或 tracked documentation 文件;
temporary instrumentation 也需要编辑授权。没有授权时停在证据结论和下一步计划。
主
SKILL.md固定所有 Fix 都不能省略的合同:可信 RED、相关身份和实际路径、历史意图与旧不变量、first divergence、owning layer、probe 不是 GREEN、原始复现终态、
项目测试门禁和诚实结论。具体方法按场景渐进加载:
这些 references 是按需工具箱,不是每个 Bug 都要机械执行的统一命令清单。
4. 进行性能优化
只有性能问题、尚未确定瓶颈或 candidate 时使用:
已经有具体优化 candidate 时使用:
该 Skill 固定的是必要动作和证据门禁:可信 baseline、瓶颈归因、可证伪假设、实现
授权、正确性、实际路径、隔离测量和诚实决策。它不会写死 profiler、PMU 事件、
优化 pass 或实现方式;Agent 可以根据当前证据选择或设计最能区分假设的方法。
5. 中文对话
Skill 正文使用英文,开发者仍可完全使用中文描述任务并要求中文回答。显式
$skill-name决定调用哪个 Skill,提问语言不会改变调用结果。6. 可选:记录 Fix 复现身份
复杂 Fix 可以使用辅助脚本记录 Git、host、binary、runtime、开关和复现身份。脚本默认
只读采集并向 stdout 输出;显式指定
--output时才写入清单文件及其必要父目录:.agents/skills/lat-fix-validation/scripts/capture_fix_context.py \ --repo . \ --binary /path/to/candidate-binary \ --switch LATX_AOT=0 \ --workload workload-name \ --redact-paths \ --output fix-context.json即使使用了
--redact-paths,对外分享前仍应人工检查命令、分支名和手工输入内容。7. 权限边界
这些文件只提供工作流和约束,不会自动授权修改代码、push、创建或修改 PR、发布
release、重写公开历史或修改目标机。此类操作仍需任务中的明确授权。
Validation
git diff --checkscan
capture_fix_context.pyJSON, redaction, invalid-input, executable-mode, andread-only smoke checks
English-Skill/Chinese-prompt check
attribution, hypothesis, authorization, candidate, correctness, and paired
measurement without prescribing a profiler or implementation
cross-boundary intermittent callbacks, and compile-only candidate validation
and TB/AOT translation entry points
Validation boundary
The complete local
lat-pr-fastsuite was not rerun for this documentation-onlyfollow-up because an approved local LoongArch environment was unavailable. The
previous head passed CI, but those results do not validate this diff. This Draft
must remain unready for merge until the new head completes its own required CI;
this is an explicit exception to the repository's normal local pre-PR gate.
Notes
$lat-fix-validationor$lat-performance-experimentinvocation