@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 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 4.1.3 closes classification bypasses and keeps current-task changes direct
13
- without weakening dirty-workspace isolation. Version 4.1.2 made mechanisms required,
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 → one bounded final
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. Obvious clean serial edits and
22
- terminal ledger maintenance may follow root `AGENTS.md` directly. When task kind,
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 only after material change. For already-direct work, add `--continue-direct`
35
- with every task path and reuse it on `task-start` if needed; unknown dirt isolates.
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] [--force-lifecycle]
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 distinct task ID, registered worktree, writer lease,
53
- dependency SHAs, and non-overlapping `owned_paths`. The main agent alone runs the
54
- final gate, integrates, pushes, and cleans safely merged temporary branches.
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
  },
@@ -1,8 +1,8 @@
1
1
  {
2
2
  "schema_version": 1,
3
3
  "managed_versions": {
4
- "agents": "4.1.3",
5
- "engineering": "4.1.3"
4
+ "agents": "4.1.6",
5
+ "engineering": "4.1.6"
6
6
  },
7
7
  "known_official_agents_sha256": [
8
8
  "ebaaadab60327b3a4852948443d7191a4d48cb00bf4910038ab78c9149089373"
@@ -1,6 +1,6 @@
1
1
  ---
2
2
  workflow:
3
- skill_version: "4.1.3"
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=4.1.3 -->
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=4.1.3 -->
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 without a lifecycle. On
55
- reclassification, `--continue-direct` requires every dirty path to be declared.
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
- - The main agent integrates in dependency order and removes only clean, safely
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
- pyyaml>=6.0
2
- requests>=2.31.0
1
+ PyYAML==6.0.3