@elvis1513/auto-coding-skill 4.2.1 → 4.2.3
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +74 -12
- package/cli/assets/agents/reviewer.toml +3 -3
- package/cli/assets/managed-install.json +1 -1
- package/cli/assets/skill/SKILL.md +14 -16
- package/cli/assets/skill/data/contracts/orchestration-v1.schema.json +22 -0
- package/cli/assets/skill/data/policies/workflow-migrations-v1.json +2 -2
- package/cli/assets/skill/data/templates/ENGINEERING.md +3 -2
- package/cli/assets/skill/data/templates/bridges/AGENTS.md +12 -7
- package/cli/assets/skill/scripts/ap.py +1972 -124
- package/cli/assets/skill/scripts/install_integrity.py +1 -0
- package/cli/assets/skill/scripts/scaffold_templates.py +0 -1
- package/cli/tests/ap_concurrency_test.py +340 -2
- package/cli/tests/ap_profiles_test.py +773 -0
- package/cli/tests/index.test.js +177 -20
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -9,7 +9,15 @@ The Skill is a selectable guardrail, not a command sequence that must run for
|
|
|
9
9
|
every task. The model skips machinery whose expected benefit does not exceed its
|
|
10
10
|
cost; read-only work and obvious small clean-checkout changes normally stay direct.
|
|
11
11
|
|
|
12
|
-
Version 4.2.
|
|
12
|
+
Version 4.2.3 restores an explicit opt-in strict size-warning policy without
|
|
13
|
+
changing the default, makes semicolon-terminated Java/Kotlin imports visible to
|
|
14
|
+
project layer rules, and hardens function-range detection. Version 4.2.2 preserves
|
|
15
|
+
project-owned risk and structure policy during upgrades, restores explicit full
|
|
16
|
+
and final changed-scope structure enforcement, makes Reviewer assignments
|
|
17
|
+
deadline-bound and directly executable, fixes task merge status semantics, and
|
|
18
|
+
updates Jenkins/target diagnostics for the current
|
|
19
|
+
`access.*` schema while retaining legacy fallback. Version 4.2.1 makes
|
|
20
|
+
dirty/concurrent classification fail closed, bounds focused
|
|
13
21
|
review latency, provides a complete Reviewer result template, preserves the
|
|
14
22
|
caller's runtime environment for routed commands, keeps non-authoritative Agent
|
|
15
23
|
history out of structure findings, and distinguishes UI paths and mechanical
|
|
@@ -51,8 +59,9 @@ AGENTS.md (fully managed canonical repository contract)
|
|
|
51
59
|
|
|
52
60
|
`autocoding init` also installs the exact shared documentation tree under
|
|
53
61
|
`docs/{architecture,bugs,deployment,design,interfaces,project,reviews,testing}`.
|
|
54
|
-
Managed templates are replaced;
|
|
55
|
-
interface, DD, review, or
|
|
62
|
+
Managed templates are replaced; the scaffolded project structure standard,
|
|
63
|
+
mutable project docs, and valid architecture, ADR, interface, DD, review, or
|
|
64
|
+
deploy-record documents are preserved; unrelated
|
|
56
65
|
directories are archived under `.agents/archive/`. Re-running init is the complete upgrade operation;
|
|
57
66
|
`sync` and project-local `upgrade` are compatibility commands, not required steps.
|
|
58
67
|
|
|
@@ -131,10 +140,8 @@ Dirty or parallel work receives an isolated task branch/worktree:
|
|
|
131
140
|
python3 docs/tools/autopipeline/ap.py task-start T0002 \
|
|
132
141
|
--owned-path backend --review-required
|
|
133
142
|
# implement in the printed worktree
|
|
134
|
-
python3 docs/tools/autopipeline/ap.py
|
|
135
|
-
|
|
136
|
-
--verdict approved --diff-fingerprint "$CURRENT_DIFF_FINGERPRINT" \
|
|
137
|
-
--reviewer "$REVIEWER_ID"
|
|
143
|
+
python3 docs/tools/autopipeline/ap.py review-run T0002 \
|
|
144
|
+
--reviewer "$REVIEWER_ID" --json
|
|
138
145
|
python3 docs/tools/autopipeline/ap.py commit-push T0002 \
|
|
139
146
|
--msg "T0002: bounded change"
|
|
140
147
|
python3 docs/tools/autopipeline/ap.py task-integrate T0002
|
|
@@ -202,7 +209,13 @@ diagnostics outside normal closure.
|
|
|
202
209
|
|
|
203
210
|
Registered tasks call `commit-push` directly because it performs or strictly
|
|
204
211
|
reuses that final gate. Run `light-gate` manually only for unregistered normal Git
|
|
205
|
-
closure or when explicitly requesting a fresh diagnostic pass.
|
|
212
|
+
closure or when explicitly requesting a fresh diagnostic pass. When project
|
|
213
|
+
`structure.enabled` is true, the same final gate also runs the changed-scope
|
|
214
|
+
structure check; `structure.enforcement: blocking` makes new violations fail.
|
|
215
|
+
File/function size thresholds remain warnings by default. They are promoted to
|
|
216
|
+
blocking findings only when a project sets both `structure.enforcement: blocking`
|
|
217
|
+
and `structure.block_warnings: true`; the template default is `false`, so existing
|
|
218
|
+
project behavior does not change merely by upgrading.
|
|
206
219
|
|
|
207
220
|
The recommended final closure defaults are 120 seconds per command and 180
|
|
208
221
|
seconds total. Projects may raise them for measured affected-scope checks or set
|
|
@@ -224,12 +237,25 @@ never triggers a broader fallback.
|
|
|
224
237
|
gateway, or production-configuration boundaries use 300-second deep review.
|
|
225
238
|
Fixing Reviewer JSON formatting reuses the same analysis and never starts
|
|
226
239
|
another substantive review.
|
|
240
|
+
- `review-assignment` writes the validated assignment under Git-local state with
|
|
241
|
+
the exact fingerprint, HEAD, scope revision, owning fixer, review depth, and
|
|
242
|
+
90/300-second deadline. Reissuing the same live assignment is idempotent;
|
|
243
|
+
expired or completed attempts cannot be silently renewed, and late results are
|
|
244
|
+
rejected by `task-review`.
|
|
245
|
+
- `review-run` is the default executable path: it creates/reuses that assignment,
|
|
246
|
+
starts a separate `codex exec` session in read-only mode, removes the parent
|
|
247
|
+
lifecycle identity, and supervises the full process group against the original
|
|
248
|
+
remaining deadline. Timeout performs TERM then KILL, records a Git-local blocked
|
|
249
|
+
receipt, and cannot be converted into approval. Plain `review-assignment` remains
|
|
250
|
+
available only when another host can enforce the deadline itself; it does not
|
|
251
|
+
stop an in-app subagent.
|
|
227
252
|
- DD/ADR is created only for lasting cross-module, API, data, security,
|
|
228
253
|
deployment, or key user-flow decisions.
|
|
229
254
|
- Historical debt does not block product work unless the current change worsens it.
|
|
230
255
|
|
|
231
|
-
Before returning a Reviewer result,
|
|
232
|
-
the
|
|
256
|
+
Before returning a Reviewer result, use the absolute assignment path printed by
|
|
257
|
+
`review-assignment` to generate the complete 16-field skeleton, then fill its
|
|
258
|
+
summary, evidence, findings, and risks:
|
|
233
259
|
|
|
234
260
|
```bash
|
|
235
261
|
python3 docs/tools/autopipeline/ap.py agent-result-template \
|
|
@@ -259,8 +285,44 @@ autocoding status --projects /path/a,/path/b
|
|
|
259
285
|
|
|
260
286
|
Init replaces the managed Skill, root `AGENTS.md`, managed agents, ENGINEERING
|
|
261
287
|
schema/body, runtime launcher, and documentation framework. It preserves explicit
|
|
262
|
-
model overrides
|
|
263
|
-
|
|
288
|
+
model overrides, complete project `risk.rules`, supported project/access/
|
|
289
|
+
concurrency/route/structure values, and an existing project-owned structure
|
|
290
|
+
standard byte-for-byte. Removed content is archived outside active docs.
|
|
291
|
+
|
|
292
|
+
## What changed in 4.2.3
|
|
293
|
+
|
|
294
|
+
- Added the explicit `structure.block_warnings` policy with a default of `false`.
|
|
295
|
+
File/function size threshold findings become blocking only when the project also
|
|
296
|
+
sets `structure.enforcement: blocking`; advisory and default configurations keep
|
|
297
|
+
their existing warning-only behavior.
|
|
298
|
+
- Recognized semicolon-terminated Java and Kotlin imports during structure checks,
|
|
299
|
+
so project-configured forbidden-import layer rules can enforce JVM boundaries.
|
|
300
|
+
- Hardened function-range detection for Go receivers, Python suites, brace bodies,
|
|
301
|
+
and block/expression arrow functions. Scans are threshold-bounded, honor the
|
|
302
|
+
final Gate deadline, and ignore braces in comments and string literals.
|
|
303
|
+
|
|
304
|
+
## What changed in 4.2.2
|
|
305
|
+
|
|
306
|
+
- Classified root and nested `package.json` files as `release_or_tooling` high-risk
|
|
307
|
+
changes requiring review, and added upgrade regression coverage that preserves
|
|
308
|
+
complete project `risk.rules` instead of deleting partially overlapping rules.
|
|
309
|
+
- Honored explicit `structure-check --scope full`, included tracked and unignored
|
|
310
|
+
untracked files, and restored the enabled structure check inside the final
|
|
311
|
+
changed-scope gate. Init now preserves supported strict structure settings and
|
|
312
|
+
treats `docs/architecture/structure-standard.md` as scaffold-once project policy.
|
|
313
|
+
- Added `review-run` with a validated Git-local assignment, fixed 90/300-second
|
|
314
|
+
process-group supervision, one attempt per fingerprint, Reviewer identity/HEAD/
|
|
315
|
+
scope binding, safe result normalization, and late-result rejection. The child
|
|
316
|
+
runs as a separate read-only Codex process without the lifecycle-owner identity;
|
|
317
|
+
the documented template command uses the complete
|
|
318
|
+
`python3 docs/tools/autopipeline/ap.py ...` invocation.
|
|
319
|
+
- Added `has_task_commits` and prevented a no-commit task from reporting
|
|
320
|
+
`merged_into_target=true` merely because its baseline equals the target tip.
|
|
321
|
+
- Updated `verify-jenkins`, `verify-jenkins-build`, `verify-target`, and target
|
|
322
|
+
health checks to prefer `access.jenkins.<component>` and
|
|
323
|
+
`access.project.<component>`, fail before network activity on missing or
|
|
324
|
+
ambiguous endpoints, isolate Jenkins crumbs by URL and username, and preserve
|
|
325
|
+
legacy `jenkins.*` / `target_env.*` compatibility.
|
|
264
326
|
|
|
265
327
|
## What changed in 4.2.1
|
|
266
328
|
|
|
@@ -8,7 +8,7 @@ developer_instructions = """
|
|
|
8
8
|
|
|
9
9
|
工作要求:
|
|
10
10
|
1. 只审查主代理给定的 task_id、base_sha、diff_base、diff_head、diff_fingerprint 和 owning_fixer;确认 diff 稳定后再开始。
|
|
11
|
-
2. 若主代理指定 focused review,只对给定的稳定 diff 和相关 evidence
|
|
11
|
+
2. 若主代理指定 focused review,只对给定的稳定 diff 和相关 evidence 做一次实质分析,不扩展为全库扫描。运行器会在 90 秒截止点终止整个 Reviewer 进程组;若你在终止前已发现无法继续,则返回 `status=blocked`、`verdict=blocked`。
|
|
12
12
|
3. 跨模块、并行 writer,以及 API、鉴权、数据库、支付、文件传输、网关、生产配置边界使用 deep review,预算 300 秒;仍然只审查主代理交付的范围。
|
|
13
13
|
4. 优先检查:正确性、安全性、边界条件、异常路径、并发风险、事务一致性、缓存一致性、兼容性。
|
|
14
14
|
5. 结构/优化 review 仅在已有 baseline/backlog 时读取;可选文档缺失不构成 blocker,不重复报告 accepted debt。
|
|
@@ -24,7 +24,7 @@ developer_instructions = """
|
|
|
24
24
|
11. 发现测试不足时,指出应补哪些测试或验证路径。
|
|
25
25
|
12. 实质结论必须是 approved、changes-requested 或 blocked;changes-requested 只返回 owning_fixer,修改后必须绑定新的 diff fingerprint。代码、配置或行为语义变化需要重新审查;仅链接、归档索引、状态措辞等机械文档修正,可由同一 reviewer 只做 targeted recheck,不必重跑完整审计。
|
|
26
26
|
13. 不修改代码,不提交、不推送、不集成、不清理分支;审查不扩展本地门禁。
|
|
27
|
-
14.
|
|
27
|
+
14. 使用 `review-run` 在提示和 `AUTOCODING_REVIEW_ASSIGNMENT` 环境变量中传入的 assignment JSON;在其中的 `deadline_at` 前完成实质审查。输出前运行 `python3 docs/tools/autopipeline/ap.py agent-result-template --file <assignment.json> --verdict <approved|changes-requested|blocked>`,从已验证 assignment 生成包含全部 16 个必填字段的骨架,然后填入本次分析的 summary、evidence、findings 和 risks。最终只返回该 JSON 对象,不要 Markdown 或代码围栏。最小完整形状为:
|
|
28
28
|
{
|
|
29
29
|
"contract_version": 1,
|
|
30
30
|
"node_id": "<assignment.node_id>",
|
|
@@ -33,7 +33,7 @@ developer_instructions = """
|
|
|
33
33
|
"base_sha": "<assignment.base_sha>",
|
|
34
34
|
"status": "completed",
|
|
35
35
|
"summary": "<review summary>",
|
|
36
|
-
"depends_on": [],
|
|
36
|
+
"depends_on": ["<assignment.owning_fixer>"],
|
|
37
37
|
"owned_paths": [],
|
|
38
38
|
"changed_paths": [],
|
|
39
39
|
"diff_fingerprint": "<assignment.diff_fingerprint>",
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"schema_version":1,"skill_version":"4.2.
|
|
1
|
+
{"schema_version":1,"skill_version":"4.2.3","manifest_path":".agents/managed-install.json","entries":[{"path":".agents/agents/browser-debugger.toml","source":"agents/browser-debugger.toml","ownership":"normalized-agent","sha256":"40727952944917eb0b573bb96dca2906c27bc794737f3b6b392b56df7b4208aa","executable":false,"scope":"shared","version":"4.2.3"},{"path":".agents/agents/docs-researcher.toml","source":"agents/docs-researcher.toml","ownership":"normalized-agent","sha256":"aa1fed6a6a1cde282fc152c7a88b8e097a6c53bcf447d35978607d594e3cb3e4","executable":false,"scope":"shared","version":"4.2.3"},{"path":".agents/agents/explorer.toml","source":"agents/explorer.toml","ownership":"normalized-agent","sha256":"4cd89888acf7c0c04fbbcd0b9a0f346c6efed42fb723ec2037af9331a84a1cac","executable":false,"scope":"shared","version":"4.2.3"},{"path":".agents/agents/fixer.toml","source":"agents/fixer.toml","ownership":"normalized-agent","sha256":"7bc00a45b9d1bcc90b8b0f06d773556eba1d52effff664472c3cb81073f6abfb","executable":false,"scope":"shared","version":"4.2.3"},{"path":".agents/agents/reviewer.toml","source":"agents/reviewer.toml","ownership":"normalized-agent","sha256":"d68c472fab6aef7679330798d753b3c495515545522b6f0a54cabccc0f523c39","executable":false,"scope":"shared","version":"4.2.3"},{"path":".agents/skills/auto-coding-skill/SKILL.md","source":"skill/SKILL.md","ownership":"exact","sha256":"f4c5a340bf3387700385959848dbfa2cc4d90d1312f330d11b0cedc307426eb5","executable":false,"scope":"shared","version":"4.2.3"},{"path":".agents/skills/auto-coding-skill/data/contracts/orchestration-v1.schema.json","source":"skill/data/contracts/orchestration-v1.schema.json","ownership":"exact","sha256":"0e8d5ebb06b47414be1218a1fc93cdbba94a7300fc7ba1c0e12d9c1ca60aeb43","executable":false,"scope":"shared","version":"4.2.3"},{"path":".agents/skills/auto-coding-skill/data/policies/workflow-migrations-v1.json","source":"skill/data/policies/workflow-migrations-v1.json","ownership":"exact","sha256":"179eba27cc728127a715ec5f73d7220ff814b46b1e98a918cfa015fc0c212fdb","executable":false,"scope":"shared","version":"4.2.3"},{"path":".agents/skills/auto-coding-skill/data/templates/ENGINEERING.md","source":"skill/data/templates/ENGINEERING.md","ownership":"exact","sha256":"748f68b2199d85599a0a68f04da76db7ad7828878e625f53e23afcf1c72131ad","executable":false,"scope":"shared","version":"4.2.3"},{"path":".agents/skills/auto-coding-skill/data/templates/bridges/AGENTS.md","source":"skill/data/templates/bridges/AGENTS.md","ownership":"exact","sha256":"ec64f06faaff3a1a8b754f914acb1143b68c1830981f91dfb58795d4898fffc5","executable":false,"scope":"shared","version":"4.2.3"},{"path":".agents/skills/auto-coding-skill/data/templates/tools/ap.py","source":"skill/data/templates/tools/ap.py","ownership":"exact","sha256":"c352fbf2cbcb9692a34fd952d8541b1cbe6d475c6e11e64500a1f6b5283a00be","executable":false,"scope":"shared","version":"4.2.3"},{"path":".agents/skills/auto-coding-skill/requirements.txt","source":"skill/requirements.txt","ownership":"exact","sha256":"0969da99a0bc2a1b71ed50584560f4588a37567ac63af3ddbaf3c4617ca5621a","executable":false,"scope":"shared","version":"4.2.3"},{"path":".agents/skills/auto-coding-skill/scripts/ap.py","source":"skill/scripts/ap.py","ownership":"exact","sha256":"35dd6d32e783aba9ac811a9eb0dd8d4219ee71c15e3600845b11c2e9433f0251","executable":false,"scope":"shared","version":"4.2.3"},{"path":".agents/skills/auto-coding-skill/scripts/core.py","source":"skill/scripts/core.py","ownership":"exact","sha256":"640c37e8b274d90d6b7765d4243e054360d5a5a85b3150fbfe6449527c1cd28f","executable":true,"scope":"shared","version":"4.2.3"},{"path":".agents/skills/auto-coding-skill/scripts/http_checks.py","source":"skill/scripts/http_checks.py","ownership":"exact","sha256":"5620e187a0129f135621425a84b3a4e8f31137263c7e549a36a801fc36ff54ea","executable":false,"scope":"shared","version":"4.2.3"},{"path":".agents/skills/auto-coding-skill/scripts/install_integrity.py","source":"skill/scripts/install_integrity.py","ownership":"exact","sha256":"a9ca7bd67893bbd2d7b35ece30a40457f0cbcb9ae01580cfc5daca2cd96fd676","executable":false,"scope":"shared","version":"4.2.3"},{"path":".agents/skills/auto-coding-skill/scripts/scaffold_templates.py","source":"skill/scripts/scaffold_templates.py","ownership":"exact","sha256":"6f0ee92eff2d5db9627a64b332738c9c917a93cc559d5bbacf771c5966215821","executable":false,"scope":"shared","version":"4.2.3"},{"path":"AGENTS.md","source":"skill/data/templates/bridges/AGENTS.md","ownership":"exact","sha256":"ec64f06faaff3a1a8b754f914acb1143b68c1830981f91dfb58795d4898fffc5","executable":false,"scope":"project","version":"4.2.3"},{"path":"docs/ENGINEERING.md","source":"skill/data/templates/ENGINEERING.md#managed-workflow","ownership":"managed-workflow","sha256":"6fcab61ec631c0fdc8056a3ec23834a1aaca016c4065a198dc209d0da695e795","executable":false,"scope":"project","version":"4.2.3"},{"path":"docs/architecture/adr/_TEMPLATE-ADR.md","source":"generated:scaffold_templates:docs/architecture/adr/_TEMPLATE-ADR.md","ownership":"exact","sha256":"88c89065ae0f8555412dbe096c05342152efc7becae8d8981e6442cdfee8e672","executable":false,"scope":"project","version":"4.2.3"},{"path":"docs/deployment/deploy-records/_TEMPLATE-DEPLOY-RECORD.md","source":"generated:scaffold_templates:docs/deployment/deploy-records/_TEMPLATE-DEPLOY-RECORD.md","ownership":"exact","sha256":"f2c17c0febc322b0ad50fb9d6f7e64e6c0cfb15c8a3e445a99da40f0a0dd1901","executable":false,"scope":"project","version":"4.2.3"},{"path":"docs/design/_TEMPLATE-DD.md","source":"generated:scaffold_templates:docs/design/_TEMPLATE-DD.md","ownership":"exact","sha256":"6ca022d127bfff68521f466b60bace4f1206baf0913daa855b9f751e74198db3","executable":false,"scope":"project","version":"4.2.3"},{"path":"docs/reviews/_TEMPLATE-REVIEW.md","source":"generated:scaffold_templates:docs/reviews/_TEMPLATE-REVIEW.md","ownership":"exact","sha256":"134f0d1bd3c7a317ef3cf4c2aea9f0539f3d53dccd5bcdabf6915b3629ef8802","executable":false,"scope":"project","version":"4.2.3"},{"path":"docs/tools/autopipeline/ap.py","source":"skill/data/templates/tools/ap.py","ownership":"exact","sha256":"c352fbf2cbcb9692a34fd952d8541b1cbe6d475c6e11e64500a1f6b5283a00be","executable":false,"scope":"project","version":"4.2.3"}],"managed_namespaces":[{"path":".agents/skills/auto-coding-skill","scope":"shared"},{"path":"docs/tools/autopipeline","scope":"project"}],"preserved":[".agents/archive/**",".agents/agents/* (except paths listed in entries)","docs/project/**","docs/architecture/structure-standard.md","docs/architecture/adr/[0-9]*.md","docs/design/*.md","docs/interfaces/*.md","docs/deployment/deploy-records/*.md","docs/reviews/*.md"]}
|
|
@@ -33,18 +33,15 @@ value exceeds coordination cost, and keep `forbidden` off absent user override.
|
|
|
33
33
|
`dirty_paths`, and `active_writer`, and reclassify if state changes before writing.
|
|
34
34
|
Same-owner claims conflict unless continuing the exact ID; `change_nature` never bypasses a rule or review.
|
|
35
35
|
|
|
36
|
-
Use the registered lifecycle only when classification requires isolation or
|
|
37
|
-
fingerprinted review, or when the user explicitly requests it:
|
|
36
|
+
Use the registered lifecycle only when classification requires isolation/fingerprinted review or the user explicitly requests it:
|
|
38
37
|
|
|
39
38
|
```bash
|
|
40
39
|
python3 docs/tools/autopipeline/ap.py task-start T0001 \
|
|
41
40
|
--owned-path src [--isolated] [--review-required] [--continue-direct --direct-claim <ID>]
|
|
42
41
|
# Before the first commit, expand an active task instead of restarting it:
|
|
43
42
|
python3 docs/tools/autopipeline/ap.py task-scope-add T0001 --owned-path config/new-scope
|
|
44
|
-
#
|
|
45
|
-
python3 docs/tools/autopipeline/ap.py
|
|
46
|
-
python3 docs/tools/autopipeline/ap.py task-review T0001 \
|
|
47
|
-
--verdict approved --diff-fingerprint <CURRENT_DIFF_FINGERPRINT> --reviewer <REVIEWER_ID>
|
|
43
|
+
# Run a read-only Reviewer under its fixed deadline and record the bound result:
|
|
44
|
+
python3 docs/tools/autopipeline/ap.py review-run T0001 --reviewer <REVIEWER_ID> --json
|
|
48
45
|
python3 docs/tools/autopipeline/ap.py commit-push T0001 --msg "T0001: summary"
|
|
49
46
|
# Isolated tasks only:
|
|
50
47
|
python3 docs/tools/autopipeline/ap.py task-integrate T0001
|
|
@@ -55,11 +52,13 @@ Each parallel writer uses a task ID, worktree, lease, dependency SHAs, and disti
|
|
|
55
52
|
with `agent-contract-check`; parallel fixers require reclassification with
|
|
56
53
|
`--writers >1`.
|
|
57
54
|
|
|
58
|
-
Use
|
|
59
|
-
|
|
60
|
-
|
|
61
|
-
|
|
62
|
-
|
|
55
|
+
Use `reviewer` at `xhigh`: focused gets 90 seconds; parallel/cross-module or sensitive
|
|
56
|
+
boundaries get 300. `review-run` creates the assignment, launches a separate read-only
|
|
57
|
+
Codex process without the lifecycle-owner identity, terminates its process group at the
|
|
58
|
+
deadline, and records only an exact HEAD/scope/fingerprint match. Timeout is `blocked`.
|
|
59
|
+
`review-assignment` alone requires another deadline-capable host and cannot stop an
|
|
60
|
+
in-app subagent. `agent-result-template` supplies all 16 fields; `review-run` safely
|
|
61
|
+
normalizes presentation fields from the same analysis.
|
|
63
62
|
|
|
64
63
|
## Close with the bounded routed gate
|
|
65
64
|
|
|
@@ -75,11 +74,10 @@ an exact Git-local PASS only while content, base, scope, routes, commands, and
|
|
|
75
74
|
lease match. Matching manual passes are reusable; changed state is not.
|
|
76
75
|
|
|
77
76
|
Every changed code/config path must map to a real project command. The runtime
|
|
78
|
-
de-duplicates commands and enforces
|
|
79
|
-
|
|
80
|
-
|
|
81
|
-
|
|
82
|
-
the caller's PATH in non-login Bash; declare activation in the configured command.
|
|
77
|
+
de-duplicates commands and enforces 120-second command and 180-second total
|
|
78
|
+
budgets; measured routes may override them. Timeouts narrow, never expand, scope.
|
|
79
|
+
Focused test/fix/retest remains allowed; commands inherit PATH in non-login Bash.
|
|
80
|
+
Size warnings block only with `structure.enforcement: blocking` and `structure.block_warnings: true` (default `false`).
|
|
83
81
|
|
|
84
82
|
Run full regression, Docker, Jenkins, deployment, browser/device writes, or target
|
|
85
83
|
acceptance only as an explicit diagnostic. A requested just-pushed failure
|
|
@@ -124,6 +124,28 @@
|
|
|
124
124
|
"owning_fixer": {
|
|
125
125
|
"type": "string",
|
|
126
126
|
"minLength": 1
|
|
127
|
+
},
|
|
128
|
+
"review_depth": {
|
|
129
|
+
"enum": [
|
|
130
|
+
"focused",
|
|
131
|
+
"deep"
|
|
132
|
+
]
|
|
133
|
+
},
|
|
134
|
+
"timeout_seconds": {
|
|
135
|
+
"type": "integer",
|
|
136
|
+
"minimum": 1
|
|
137
|
+
},
|
|
138
|
+
"issued_at": {
|
|
139
|
+
"type": "string",
|
|
140
|
+
"minLength": 1
|
|
141
|
+
},
|
|
142
|
+
"deadline_at": {
|
|
143
|
+
"type": "string",
|
|
144
|
+
"minLength": 1
|
|
145
|
+
},
|
|
146
|
+
"scope_revision": {
|
|
147
|
+
"type": "integer",
|
|
148
|
+
"minimum": 1
|
|
127
149
|
}
|
|
128
150
|
},
|
|
129
151
|
"allOf": [
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
---
|
|
2
2
|
workflow:
|
|
3
|
-
skill_version: "4.2.
|
|
3
|
+
skill_version: "4.2.3"
|
|
4
4
|
mode: "dev"
|
|
5
5
|
profile: "auto"
|
|
6
6
|
completion: "push"
|
|
@@ -63,6 +63,7 @@ risk:
|
|
|
63
63
|
structure:
|
|
64
64
|
enabled: true
|
|
65
65
|
enforcement: "advisory"
|
|
66
|
+
block_warnings: false
|
|
66
67
|
architecture_standard: "project-defined"
|
|
67
68
|
accepted_debt_paths: []
|
|
68
69
|
layer_rules:
|
|
@@ -82,7 +83,7 @@ docs:
|
|
|
82
83
|
api_change_log: "docs/interfaces/api-change-log.md"
|
|
83
84
|
---
|
|
84
85
|
# Engineering Configuration and Project Facts
|
|
85
|
-
<!-- auto-coding-skill:managed-workflow:start version=4.2.
|
|
86
|
+
<!-- auto-coding-skill:managed-workflow:start version=4.2.3 -->
|
|
86
87
|
Root `AGENTS.md` is the single shared behavioral protocol. The installed
|
|
87
88
|
`SKILL.md` contains invocation guidance. This file is the exact-schema source for
|
|
88
89
|
project workflow configuration and access values that neither file can infer.
|
|
@@ -1,4 +1,4 @@
|
|
|
1
|
-
<!-- auto-coding-skill:managed-agents:start version=4.2.
|
|
1
|
+
<!-- auto-coding-skill:managed-agents:start version=4.2.3 -->
|
|
2
2
|
# Shared Engineering Protocol
|
|
3
3
|
|
|
4
4
|
This file is fully managed by `auto-coding-skill`. Keep project-specific facts,
|
|
@@ -82,8 +82,13 @@ failure may continue in the same conversation/task without a second lifecycle.
|
|
|
82
82
|
- Keep `reviewer` at `xhigh`: focused is one 90-second analysis; deep gets 300
|
|
83
83
|
seconds for parallel/cross-module or sensitive boundaries. Timeout is `blocked`
|
|
84
84
|
and is not sent to `task-review`.
|
|
85
|
-
-
|
|
86
|
-
|
|
85
|
+
- Run `python3 docs/tools/autopipeline/ap.py review-run <TASK> --reviewer <ID> --json`.
|
|
86
|
+
It launches a separate read-only Codex process without the lifecycle-owner identity,
|
|
87
|
+
stops its process group at the fixed deadline, and records only the assigned HEAD,
|
|
88
|
+
scope, identity, and fingerprint. `review-assignment` alone requires a different
|
|
89
|
+
deadline-capable host and cannot stop an in-app subagent.
|
|
90
|
+
- `agent-result-template` supplies all 16 fields; contract checking aggregates errors,
|
|
91
|
+
and `review-run` safely normalizes presentation fields from the same analysis.
|
|
87
92
|
- Review blocks only defects introduced or worsened in the promised scope.
|
|
88
93
|
Adjacent existing issues are non-blocking follow-ups.
|
|
89
94
|
- Semantic changes invalidate approval. Mechanical documentation-only corrections
|
|
@@ -106,10 +111,10 @@ failure may continue in the same conversation/task without a second lifecycle.
|
|
|
106
111
|
`light-gate` first. A strict Git-local PASS receipt may be reused only while the
|
|
107
112
|
content/index, base, scope, route/command plan, and writer lease still match.
|
|
108
113
|
Unregistered clean serial work runs `light-gate` before normal Git closure.
|
|
109
|
-
-
|
|
110
|
-
|
|
111
|
-
|
|
112
|
-
|
|
114
|
+
- Final gate budgets are 120 seconds per command and 180 total; projects may raise
|
|
115
|
+
measured budgets or set smaller route timeouts. Timeouts narrow, never expand,
|
|
116
|
+
scope. Size warnings block only with `structure.enforcement: blocking` and
|
|
117
|
+
`structure.block_warnings: true` (default `false`).
|
|
113
118
|
- Do not proactively install dependencies. Only after the selected route fails
|
|
114
119
|
because a repository-locked dependency is absent may it be restored once and
|
|
115
120
|
only that route retried.
|