@elvis1513/auto-coding-skill 4.1.3 → 4.1.6
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 +30 -3
- package/cli/assets/skill/SKILL.md +10 -12
- package/cli/assets/skill/data/contracts/orchestration-v1.schema.json +4 -0
- package/cli/assets/skill/data/policies/workflow-migrations-v1.json +2 -2
- package/cli/assets/skill/data/templates/ENGINEERING.md +2 -2
- package/cli/assets/skill/data/templates/bridges/AGENTS.md +6 -5
- package/cli/assets/skill/requirements.txt +1 -2
- package/cli/assets/skill/scripts/ap.py +447 -39
- package/cli/assets/skill/scripts/core.py +35 -18
- package/cli/src/index.js +23 -1
- package/cli/tests/ap_concurrency_test.py +59 -1
- package/cli/tests/ap_profiles_test.py +105 -8
- package/cli/tests/index.test.js +40 -12
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -9,8 +9,12 @@ 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 4.1.
|
|
13
|
-
|
|
12
|
+
Version 4.1.6 makes the Python runtime check, release verification, and tag
|
|
13
|
+
publication environment reproducible while removing the unnecessary `requests`
|
|
14
|
+
dependency. Version 4.1.4
|
|
15
|
+
made direct continuation provably pre-write, closed self-review and
|
|
16
|
+
risk-classification gaps, validated Agent contracts, and made tag publication
|
|
17
|
+
idempotent. Version 4.1.3 closed classification bypasses. Version 4.1.2 made mechanisms required,
|
|
14
18
|
model-selectable when beneficial, or forbidden for the current task. Version
|
|
15
19
|
4.1.1 consolidated the 4.x delivery-first workflow into one canonical
|
|
16
20
|
repository contract. Version 4.0 replaced the 3.x governance-first defaults with progressive
|
|
@@ -22,9 +26,9 @@ affected-scope checks are enabled only when concurrency or risk justifies them.
|
|
|
22
26
|
|
|
23
27
|
```bash
|
|
24
28
|
npm install -g @elvis1513/auto-coding-skill
|
|
29
|
+
python3 -m pip install PyYAML==6.0.3
|
|
25
30
|
autocoding init
|
|
26
31
|
autocoding sync --projects .
|
|
27
|
-
pip install pyyaml requests
|
|
28
32
|
```
|
|
29
33
|
|
|
30
34
|
The project install contains:
|
|
@@ -209,6 +213,29 @@ project-specific facts outside the managed ENGINEERING block. Root `AGENTS.md` i
|
|
|
209
213
|
replaced as a whole; its previous content is archived under
|
|
210
214
|
`docs/archive/workflow/` as historical, non-authoritative context.
|
|
211
215
|
|
|
216
|
+
## What changed in 4.1.6
|
|
217
|
+
|
|
218
|
+
- Made tag publication reproducible with explicit Node 24, Python 3.12, and pinned
|
|
219
|
+
PyYAML setup before package verification.
|
|
220
|
+
- Made `autocoding init` fail before writes with one interpreter-specific recovery
|
|
221
|
+
command when its Python runtime cannot import PyYAML.
|
|
222
|
+
- Removed the `requests` runtime dependency by using Python's standard HTTP library.
|
|
223
|
+
- Made concurrency tests self-contained instead of borrowing local thread and Git
|
|
224
|
+
identity configuration.
|
|
225
|
+
|
|
226
|
+
## What changed in 4.1.4
|
|
227
|
+
|
|
228
|
+
- Added clean pre-write direct claims so broad paths cannot adopt unknown existing
|
|
229
|
+
dirt after development starts.
|
|
230
|
+
- Prevented the current writer lease holder from approving its own diff and added
|
|
231
|
+
executable assignment/result contract validation.
|
|
232
|
+
- Escalated high-confidence database, authorization, settlement, gateway, and
|
|
233
|
+
production intents while keeping ordinary UI work lightweight.
|
|
234
|
+
- Made mechanism plans dependency-closed: parallel fixers require reclassification
|
|
235
|
+
with multiple writers and therefore require isolated worktrees.
|
|
236
|
+
- Published from matching `v*` tags with idempotent npm registry checks and a final
|
|
237
|
+
registry verification.
|
|
238
|
+
|
|
212
239
|
## What changed in 4.1.3
|
|
213
240
|
|
|
214
241
|
- Made explicit task kinds fail closed: `none` is internal-only and terminal
|
|
@@ -13,33 +13,31 @@ Do not reconstruct or duplicate those rules from historical task documents.
|
|
|
13
13
|
|
|
14
14
|
Normal delivery is:
|
|
15
15
|
|
|
16
|
-
`analysis → decomposition → necessary design → development →
|
|
17
|
-
changed-scope gate → commit/push`.
|
|
16
|
+
`analysis → decomposition → necessary design → development → bounded gate → commit/push`.
|
|
18
17
|
|
|
19
18
|
## Select the minimum mechanism set
|
|
20
19
|
|
|
21
|
-
Read-only questions need no workflow command.
|
|
22
|
-
|
|
23
|
-
impact, risk, or concurrency is unclear, run:
|
|
20
|
+
Read-only questions need no workflow command. Clean serial edits and terminal
|
|
21
|
+
maintenance may follow `AGENTS.md` directly. When impact or concurrency is unclear, run:
|
|
24
22
|
|
|
25
23
|
```bash
|
|
26
24
|
python3 docs/tools/autopipeline/ap.py classify --scope auto \
|
|
27
25
|
--planned-path <PATH> --intent "<intent>" [--writers <N>] \
|
|
28
|
-
[--task-kind read_only|change|terminal_maintenance]
|
|
26
|
+
[--task-kind read_only|change|terminal_maintenance] [--claim-direct]
|
|
29
27
|
```
|
|
30
28
|
|
|
31
29
|
Run `mechanism_plan.required`. The model may select
|
|
32
30
|
`optional_when_beneficial` only when expected value exceeds coordination cost.
|
|
33
31
|
Do not run `forbidden` mechanisms unless the user explicitly overrides the plan.
|
|
34
|
-
Reclassify
|
|
35
|
-
|
|
32
|
+
Reclassify before changing writer count. For uncertain direct work, create
|
|
33
|
+
`--claim-direct` while clean; continuation requires its ID and exact paths.
|
|
36
34
|
|
|
37
35
|
Use the registered lifecycle only when classification requires isolation or
|
|
38
36
|
fingerprinted review, or when the user explicitly requests it:
|
|
39
37
|
|
|
40
38
|
```bash
|
|
41
39
|
python3 docs/tools/autopipeline/ap.py task-start T0001 \
|
|
42
|
-
--owned-path src [--isolated] [--review-required] [--continue-direct
|
|
40
|
+
--owned-path src [--isolated] [--review-required] [--continue-direct --direct-claim <ID>]
|
|
43
41
|
# For review-required work, obtain the current fingerprint and approve it:
|
|
44
42
|
python3 docs/tools/autopipeline/ap.py task-status T0001 --json
|
|
45
43
|
python3 docs/tools/autopipeline/ap.py task-review T0001 \
|
|
@@ -49,9 +47,9 @@ python3 docs/tools/autopipeline/ap.py commit-push T0001 --msg "T0001: summary"
|
|
|
49
47
|
python3 docs/tools/autopipeline/ap.py task-integrate T0001
|
|
50
48
|
```
|
|
51
49
|
|
|
52
|
-
Each parallel writer uses a
|
|
53
|
-
|
|
54
|
-
|
|
50
|
+
Each parallel writer uses a task ID, worktree, lease, dependency SHAs, and distinct
|
|
51
|
+
`owned_paths`. Main integrates, gates, pushes, and cleans. Validate delegated JSON
|
|
52
|
+
with `agent-contract-check`; parallel fixers require reclassification with `--writers >1`.
|
|
55
53
|
|
|
56
54
|
## Close with the bounded routed gate
|
|
57
55
|
|
|
@@ -459,6 +459,7 @@
|
|
|
459
459
|
"intent_provided",
|
|
460
460
|
"intent_categories",
|
|
461
461
|
"intent_risk_candidates",
|
|
462
|
+
"high_confidence_intent_categories",
|
|
462
463
|
"task_kind",
|
|
463
464
|
"profile",
|
|
464
465
|
"categories",
|
|
@@ -492,6 +493,9 @@
|
|
|
492
493
|
"intent_risk_candidates": {
|
|
493
494
|
"$ref": "#/$defs/stringArray"
|
|
494
495
|
},
|
|
496
|
+
"high_confidence_intent_categories": {
|
|
497
|
+
"$ref": "#/$defs/stringArray"
|
|
498
|
+
},
|
|
495
499
|
"task_kind": {
|
|
496
500
|
"enum": ["none", "read_only", "change", "terminal_maintenance"]
|
|
497
501
|
},
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
---
|
|
2
2
|
workflow:
|
|
3
|
-
skill_version: "4.1.
|
|
3
|
+
skill_version: "4.1.6"
|
|
4
4
|
mode: "dev"
|
|
5
5
|
profile: "auto"
|
|
6
6
|
completion: "push"
|
|
@@ -94,7 +94,7 @@ docs:
|
|
|
94
94
|
|
|
95
95
|
# Engineering Configuration and Project Facts
|
|
96
96
|
|
|
97
|
-
<!-- auto-coding-skill:managed-workflow:start version=4.1.
|
|
97
|
+
<!-- auto-coding-skill:managed-workflow:start version=4.1.6 -->
|
|
98
98
|
|
|
99
99
|
Root `AGENTS.md` is the single shared behavioral protocol. The installed
|
|
100
100
|
`SKILL.md` contains invocation guidance. This file is the single source for the
|
|
@@ -1,4 +1,4 @@
|
|
|
1
|
-
<!-- auto-coding-skill:managed-agents:start version=4.1.
|
|
1
|
+
<!-- auto-coding-skill:managed-agents:start version=4.1.6 -->
|
|
2
2
|
# Shared Engineering Protocol
|
|
3
3
|
|
|
4
4
|
This file is fully managed by `auto-coding-skill`. Keep project-specific facts,
|
|
@@ -51,8 +51,8 @@ failure may continue in the same conversation/task without a second lifecycle.
|
|
|
51
51
|
|
|
52
52
|
## Git and parallel work
|
|
53
53
|
|
|
54
|
-
- One writer in a clean checkout works directly
|
|
55
|
-
|
|
54
|
+
- One writer in a clean checkout works directly. If review may be needed, create a
|
|
55
|
+
claim before the first write; continuation requires that claim and exact paths.
|
|
56
56
|
- Existing unrelated changes, another writer, or configured mandatory isolation
|
|
57
57
|
requires a registered task branch/worktree.
|
|
58
58
|
- Every delegated fixer or parallel writer owns a task ID/worktree, writer lease,
|
|
@@ -60,8 +60,7 @@ failure may continue in the same conversation/task without a second lifecycle.
|
|
|
60
60
|
- Never let multiple writing agents share a checkout. Never restore, reset, stash,
|
|
61
61
|
clean, overwrite, or commit unknown changes.
|
|
62
62
|
- No diff means no commit, push, or temporary branch.
|
|
63
|
-
-
|
|
64
|
-
merged temporary worktrees and branches.
|
|
63
|
+
- Main integrates in dependency order and removes only clean, merged temporary state.
|
|
65
64
|
- Do not sync or upgrade while any registered task is active.
|
|
66
65
|
|
|
67
66
|
## Design, agents, and review
|
|
@@ -73,6 +72,8 @@ failure may continue in the same conversation/task without a second lifecycle.
|
|
|
73
72
|
or key user-flow decisions.
|
|
74
73
|
- Use read-only explorer/docs/browser agents only for independent questions.
|
|
75
74
|
- Use parallel fixers only for bounded, dependency-free, non-overlapping units.
|
|
75
|
+
- Reclassify before parallel fixers; single-writer plans grant no implicit writes.
|
|
76
|
+
- Validate delegated assignment/result JSON with `agent-contract-check` before use.
|
|
76
77
|
- Require fingerprinted review only for path/rule-confirmed high-risk,
|
|
77
78
|
contract-crossing, parallel, or configured work; intent words are candidates only.
|
|
78
79
|
- Review blocks only defects introduced or worsened in the promised scope.
|
|
@@ -1,2 +1 @@
|
|
|
1
|
-
|
|
2
|
-
requests>=2.31.0
|
|
1
|
+
PyYAML==6.0.3
|