@elvis1513/auto-coding-skill 3.0.1 → 3.0.3
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 +25 -2
- package/cli/assets/agents/fixer.toml +3 -3
- package/cli/assets/skill/SKILL.md +35 -22
- package/cli/assets/skill/data/contracts/orchestration-v1.schema.json +18 -2
- package/cli/assets/skill/data/policies/workflow-migrations-v1.json +371 -0
- package/cli/assets/skill/data/templates/ENGINEERING.md +27 -13
- package/cli/assets/skill/data/templates/bridges/AGENTS.md +5 -1
- package/cli/assets/skill/scripts/ap.py +403 -19
- package/cli/src/index.js +390 -39
- package/cli/tests/ap_concurrency_test.py +73 -7
- package/cli/tests/ap_profiles_test.py +100 -2
- package/cli/tests/index.test.js +102 -12
- package/package.json +1 -1
|
@@ -39,7 +39,7 @@ access:
|
|
|
39
39
|
password: ""
|
|
40
40
|
|
|
41
41
|
concurrency:
|
|
42
|
-
isolation: "
|
|
42
|
+
isolation: "adaptive"
|
|
43
43
|
base_ref: ""
|
|
44
44
|
target_branch: ""
|
|
45
45
|
branch_prefix: "codex/"
|
|
@@ -121,7 +121,7 @@ docs:
|
|
|
121
121
|
|
|
122
122
|
# Engineering Workflow
|
|
123
123
|
|
|
124
|
-
<!-- auto-coding-skill:managed-workflow:start version=3.0.
|
|
124
|
+
<!-- auto-coding-skill:managed-workflow:start version=3.0.3 -->
|
|
125
125
|
|
|
126
126
|
This file is the single project workflow configuration. Keep it in Git. Its YAML
|
|
127
127
|
frontmatter and content outside these versioned markers are manually maintained;
|
|
@@ -162,8 +162,8 @@ Required for normal development:
|
|
|
162
162
|
initialization incomplete and block `doctor`; keep each value as an inline
|
|
163
163
|
YAML string, quoting values that resemble numbers, dates, booleans, or YAML
|
|
164
164
|
collections
|
|
165
|
-
- `concurrency.isolation`:
|
|
166
|
-
|
|
165
|
+
- `concurrency.isolation`: use `adaptive`; a clean serial task works directly on
|
|
166
|
+
the current branch, while dirty or parallel write work uses isolated worktrees
|
|
167
167
|
- `concurrency.base_ref` and `target_branch`: leave blank to derive the current
|
|
168
168
|
upstream, or set them explicitly for a fixed integration branch
|
|
169
169
|
- `concurrency.branch_prefix` and `worktree_root`
|
|
@@ -179,10 +179,21 @@ callable explicitly with `ap.py run <name>` but never replace the automatic
|
|
|
179
179
|
changed gate. `quick_test` remains the only fallback when `gate_changed` is
|
|
180
180
|
absent. Run `doctor` for exact missing-field diagnostics.
|
|
181
181
|
|
|
182
|
+
If the actual changed gate fails only because a dependency already declared in
|
|
183
|
+
the repository lockfile is not installed in the working checkout, restore that
|
|
184
|
+
locked dependency locally (for example with `npm ci`) and rerun the same changed
|
|
185
|
+
gate once. Do not install dependencies or restart a standard/full diagnostic
|
|
186
|
+
that was invoked outside the normal development gate, and never promote this
|
|
187
|
+
recovery into a full-gate run.
|
|
188
|
+
|
|
182
189
|
## Concurrent write tasks
|
|
183
190
|
|
|
184
|
-
|
|
185
|
-
the
|
|
191
|
+
For one serial write task, inspect the current checkout first. If it is clean,
|
|
192
|
+
develop directly on the current branch, run the changed gate once, commit, and
|
|
193
|
+
push without creating a temporary branch. If it already contains changes, or if
|
|
194
|
+
multiple writers will run concurrently, preserve the checkout and use one
|
|
195
|
+
registered task branch/worktree per writer. Never share one worktree between
|
|
196
|
+
writers. Clean temporary worktrees and merged task branches after integration.
|
|
186
197
|
|
|
187
198
|
```bash
|
|
188
199
|
python3 docs/tools/autopipeline/ap.py task-start <TASK_ID> \
|
|
@@ -261,9 +272,10 @@ work concurrently.
|
|
|
261
272
|
it is not post-push acceptance.
|
|
262
273
|
2. The main agent merges discovery evidence and decides the design, dependency
|
|
263
274
|
graph, and non-overlapping path ownership.
|
|
264
|
-
3. Assign each independent write unit to exactly one `fixer
|
|
265
|
-
|
|
266
|
-
|
|
275
|
+
3. Assign each independent write unit to exactly one `fixer`. A single serial
|
|
276
|
+
fixer may use a clean current branch; dirty checkouts and parallel fixers each
|
|
277
|
+
require a registered task branch/worktree. Never run two writers in one worktree.
|
|
278
|
+
Do not let the main agent edit a fixer-owned worktree concurrently.
|
|
267
279
|
4. Parallelize fixer units only when they are dependency-free and their owned
|
|
268
280
|
paths do not overlap. Complete implementation → review → gate/integration for
|
|
269
281
|
the current dependency wave, then start the next wave only after its
|
|
@@ -285,7 +297,8 @@ work concurrently.
|
|
|
285
297
|
`classify` emits a machine-readable `agent_plan` with this stage and ownership
|
|
286
298
|
contract. Micro tasks remain main-agent-only unless useful independent work
|
|
287
299
|
clearly exceeds delegation overhead. If the client cannot run subagents, execute
|
|
288
|
-
the same stages sequentially
|
|
300
|
+
the same stages sequentially and check for a clean current branch before creating
|
|
301
|
+
any temporary worktree.
|
|
289
302
|
|
|
290
303
|
## Default workflow
|
|
291
304
|
|
|
@@ -295,7 +308,7 @@ Development:
|
|
|
295
308
|
2. Analyze and decompose the request; run or reason through `classify --scope auto`.
|
|
296
309
|
3. Fan out independent discovery roles, then fan their results back into one main-agent design.
|
|
297
310
|
4. Record the smallest useful design note; create DD/ADR only when indicated.
|
|
298
|
-
5.
|
|
311
|
+
5. Use the clean current branch for one serial writer; only dirty or parallel work starts registered worktrees with explicit owned paths, dependency SHAs, and writer leases.
|
|
299
312
|
6. Review stable diffs, record their fingerprints with `task-review`, and return findings to their owning fixers until approved.
|
|
300
313
|
7. Hand the writer lease to the main agent. The main agent runs `commit-push` for each write task; it enforces ownership,
|
|
301
314
|
dependency, lease, and current-review gates, executes the one changed-scope fast gate, records
|
|
@@ -362,8 +375,9 @@ python3 docs/tools/autopipeline/ap.py docs-ledger-check
|
|
|
362
375
|
python3 docs/tools/autopipeline/ap.py gate-profile
|
|
363
376
|
```
|
|
364
377
|
|
|
365
|
-
`light-gate` is available for an explicit gate-diagnostic task. Do not
|
|
366
|
-
|
|
378
|
+
`light-gate` is available for an explicit gate-diagnostic task. Do not add it to
|
|
379
|
+
normal closure. Run exactly one configured changed gate directly on a clean
|
|
380
|
+
serial branch or through `commit-push` for isolated work.
|
|
367
381
|
|
|
368
382
|
The launcher under `docs/tools/autopipeline` delegates to the single runtime in
|
|
369
383
|
`.agents/skills/auto-coding-skill/scripts`; do not duplicate that runtime.
|
|
@@ -1,12 +1,16 @@
|
|
|
1
|
+
<!-- auto-coding-skill:managed-agents:start version=3.0.3 -->
|
|
2
|
+
|
|
1
3
|
Follow `docs/ENGINEERING.md` strictly. Source of truth: `docs/ENGINEERING.md`.
|
|
2
4
|
At task start, use `ap.py classify --scope auto` when changed-file impact is not obvious.
|
|
3
5
|
Before code changes, read the configured structure standard and place new code in the correct layer; do not add new responsibilities to already-large files.
|
|
4
6
|
Obey `structure.layer_rules` import boundaries unless a DD/ADR explicitly records the exception.
|
|
5
7
|
Before optimization reviews, read the project health baseline and optimization backlog, and report only new, worsened, unrecorded P0/P1, or upgraded-priority items.
|
|
6
8
|
Route work through already available MCP servers, installed skills, plugins, and app connectors when they provide current docs, design context, browser evidence, GitHub/CI state, security review, or artifact rendering.
|
|
7
|
-
Use the `.agents/agents` role model when available. The main agent decomposes and fans out independent explorer/docs_researcher/browser_debugger work, fans evidence into one design,
|
|
9
|
+
Use the `.agents/agents` role model when available. The main agent decomposes and fans out independent explorer/docs_researcher/browser_debugger work, then fans evidence into one design. For one serial writer, use the current branch when its checkout is clean; create registered task branches/worktrees only when that checkout is already dirty or multiple writers run concurrently. Give every writer explicit non-overlapping paths, route stable diffs through reviewer, then let the main agent run the one fast gate, commit, integrate, push, and clean temporary branches. Never run two writers in one worktree; start dependent write work only after its prerequisite is integrated.
|
|
8
10
|
Use exactly one fast changed-scope local gate before pushing. Keep advisory structure, docs-ledger, full regression, Docker, API, Jenkins, and target checks outside the default development gate.
|
|
9
11
|
Keep active docs ledgers small: `taskbook.md`, `closure-log.md`, and top-level `docs/design/T*.md` must be physically archived when over budget. Use `docs-ledger-archive --plan` before `--write`; `archive-index.md` is only navigation.
|
|
10
12
|
Keep `docs/tasks/evidence.jsonl` and closure Markdown aligned with actual executed checks.
|
|
11
13
|
Treat target-branch push as coding completion. Do not wait for, poll, diagnose, or fix Jenkins/build/deploy results unless the user starts a separate diagnostic task; the project owner performs acceptance.
|
|
12
14
|
Use the direct URL, username, and password values configured under `access.*` in `docs/ENGINEERING.md`; do not invent credentials.
|
|
15
|
+
|
|
16
|
+
<!-- auto-coding-skill:managed-agents:end -->
|