ai-engineering-loop 1.0.14 → 1.0.16

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.
Files changed (46) hide show
  1. package/.agents/workflows/ai-engineering-loop.md +2 -2
  2. package/.claude/commands/ai-engineering-loop.md +1 -1
  3. package/.claude/skills/ai-engineering-loop/SKILL.md +4 -3
  4. package/.gemini/skills/ai-engineering-loop/SKILL.md +4 -3
  5. package/.grok/commands/ai-engineering-loop.md +1 -1
  6. package/.grok/skills/ai-engineering-loop/SKILL.md +4 -4
  7. package/README.md +16 -10
  8. package/adapters/README.md +27 -0
  9. package/adapters/dot/README.md +8 -8
  10. package/adapters/dot/coreview.md +3 -2
  11. package/adapters/dot/gitlab.md +3 -3
  12. package/adapters/dot/mattermost.md +59 -71
  13. package/adapters/dot/multi-branch.md +3 -2
  14. package/adapters/dot/skills/dot-dev-workflow/SKILL.md +2 -2
  15. package/adapters/dot/skills/task-impact-inquiry/SKILL.md +155 -0
  16. package/adapters/generate-adapter/SKILL.md +123 -0
  17. package/adapters/github/README.md +28 -0
  18. package/adapters/github/pull-request.md +23 -0
  19. package/adapters/gitlab/README.md +28 -0
  20. package/adapters/gitlab/merge-request.md +26 -0
  21. package/adapters/standard/README.md +44 -0
  22. package/bin/ai-engineering-loop.js +31 -3
  23. package/core/grill-policy.md +14 -10
  24. package/core/repo-config-schema.md +1 -1
  25. package/examples/backend-api/payment-idempotency/README.md +3 -3
  26. package/examples/dot/status-display/README.md +23 -0
  27. package/examples/dot/status-display/delivery-report.md +41 -0
  28. package/examples/dot/status-display/goal-contract.md +46 -0
  29. package/examples/dot/status-display/judge-verdict.md +44 -0
  30. package/examples/dot/status-display/review-findings.md +63 -0
  31. package/examples/initialization/README.md +2 -2
  32. package/examples/initialization/discovery-trace.md +1 -1
  33. package/examples/mobile-app/offline-sync-queue/README.md +3 -3
  34. package/lib/generate-adapter.js +118 -0
  35. package/lib/sync-hosts.js +7 -1
  36. package/package.json +1 -1
  37. package/templates/repo-config/adapter.md +1 -1
  38. package/tests/generate-adapter.test.js +80 -0
  39. package/tests/no-company-leak.test.js +82 -0
  40. package/tests/skill-host-compat.test.js +45 -7
  41. package/tests/sync-hosts.test.js +33 -1
  42. package/examples/dot/attendance-confirmation/README.md +0 -22
  43. package/examples/dot/attendance-confirmation/delivery-report.md +0 -51
  44. package/examples/dot/attendance-confirmation/goal-contract.md +0 -39
  45. package/examples/dot/attendance-confirmation/judge-verdict.md +0 -43
  46. package/examples/dot/attendance-confirmation/review-findings.md +0 -57
@@ -0,0 +1,155 @@
1
+ ---
2
+ name: task-impact-inquiry
3
+ description: Map business blast radius before code. Use for impact, side effects, sibling data, approval, queues, or when a new developer must learn the current flow. Triggers: cek impactnya, blast radius, analisa pengaruh, brainstorming impact. Not a substitute for ai-engineering-loop.
4
+ ---
5
+
6
+ # Task Impact Inquiry
7
+
8
+ Map the **current business flow** and the **blast radius** of a change before any production edit.
9
+
10
+ This skill fills AI Engineering Loop Stage 1 grill. It is not a parallel engineering OS.
11
+
12
+ If Stage 1 grill already produced this matrix and the user confirmed it, stop. Do not interview again. On commit-bound work, continue in `ai-engineering-loop` (freeze the Goal Contract, then Maker). Do not start `dot-dev-workflow` Phases 1-6.
13
+
14
+ ## Hard gate
15
+
16
+ Do not create a branch or edit production code until:
17
+
18
+ 1. The current lifecycle is drawn from evidence (not guessed).
19
+ 2. The impact matrix is on screen.
20
+ 3. The user has answered the probing questions (or waived them).
21
+
22
+ Green unit tests later are not proof that siblings, approvals, or downstream jobs survived. A 100% passing suite can still reset approved history or fire the wrong downstream job.
23
+
24
+ ## When to use
25
+
26
+ - "cek impactnya", "blast radius", "analisa pengaruh", "brainstorming impact"
27
+ - Bug, edge case, or business-logic change
28
+ - Shared service, status transition, calculation, validation, authorization, schema
29
+ - The user is new to the domain and does not know the flow
30
+
31
+ Impact-only (no implementation): run this skill and stop after the report.
32
+
33
+ Commit-bound work: run this inside AEL Stage 1, then freeze. Do not run it a second time after grill.
34
+
35
+ ## Host notes
36
+
37
+ Claude Code / Kiro: no mermaid, no LaTeX, no extra tool keys. ASCII diagrams only.
38
+
39
+ Grok: do not spawn children for this skill. Stay in the parent.
40
+
41
+ Look up facts (files, enums, jobs). Grill only **decisions**.
42
+
43
+ ## Steps
44
+
45
+ ### 1. Look up (do not ask)
46
+
47
+ Read in this order. Skip a source if it is missing. Do not invent statuses.
48
+
49
+ 1. `.ai-engineering-loop/glossary.md`
50
+ 2. Existing FSD if present (`docs/fsd/`, `specs-book/fsd/`, especially `impact-matrix.md`). Read only. Do not generate an FSD.
51
+ 3. Status enums, services, validators, listeners, BullMQ / cron / queue processors
52
+ 4. Matching FE pages, routes, and permission guards when both FE and BE are in the workspace
53
+
54
+ Cite the path for each claim. If FE or BE is missing, say so.
55
+
56
+ ### 2. New-dev briefing + lifecycle picture
57
+
58
+ Explain the current flow in plain language for someone new to the app: who acts, what status changes, when a period locks.
59
+
60
+ Then draw the lifecycle in ASCII. Do not ask the user what the code already shows.
61
+
62
+ ```text
63
+ Author submit -> DRAFT
64
+ Author send -> NEED_APPROVAL
65
+ Reviewer approve -> APPROVED
66
+ period lock -> CONFIRMED --> billing / aggregate job
67
+ ```
68
+
69
+ If the flow cannot be determined from the repo, say what is missing.
70
+
71
+ ### 3. Four-pillar scan
72
+
73
+ **State and conditions.** Does the rule apply the same in normal vs special cases (rush vs standard, holiday, locked vs open period)? What happens in DRAFT, SUBMITTED, NEED_APPROVAL, APPROVED, REJECTED, CONFIRMED, UNCONFIRMED?
74
+
75
+ **Sibling / historical isolation.** If entity A in parent P changes, do B and C in the same parent, period, or cart change? Can already-approved history reset?
76
+
77
+ **Actor and approval.** Who creates, who may edit, who must re-approve? When is an existing approval void, and when must it be kept?
78
+
79
+ **Downstream.** BullMQ, cron, listeners, billing, dashboard totals.
80
+
81
+ ### 4. Where it hits (hit map + blast picture)
82
+
83
+ List the surfaces a naive edit would touch. Empty rows mean you have not finished looking.
84
+
85
+ ```text
86
+ Surface Path / job Naive risk
87
+ FE page <route or page> <what the user would see>
88
+ BE service <service / status write> <what the row would become>
89
+ Sibling rows <same parent / period / cart> isolate | also-update
90
+ Approval <who, void vs keep> <approval lost or kept>
91
+ Queue / billing <job name> rerun | skip
92
+ ```
93
+
94
+ Then the blast-radius picture (ASCII only):
95
+
96
+ ```text
97
+ edit(A in period P)
98
+ |- sibling B in P : isolate | also-update
99
+ |- approval on A : void | keep
100
+ |- billing / queue : rerun | skip
101
+ ```
102
+
103
+ ### 5. Impact matrix (failure table)
104
+
105
+ | Scenario | Current logic (cite path) | Side effect if we ship naive | Proposed treatment |
106
+ |---|---|---|---|
107
+ | Happy path | | | |
108
+ | Empty / omitted field | | | |
109
+ | Boundary (min/max, locked vs open) | | | |
110
+ | Sibling in the same parent | | | |
111
+ | Error / denied / unauthorized | | | |
112
+
113
+ A matrix with only the sunny path is not done.
114
+
115
+ ### 6. Probing questions
116
+
117
+ Ask 2-3 decisions. Number them. Give a recommended answer. Wait.
118
+
119
+ ```text
120
+ Q1 - <title>: <choices>
121
+ Recommended: <your answer>
122
+ ```
123
+
124
+ Typical decisions: void vs keep approval; isolate vs also-update siblings; rerun vs skip the downstream job.
125
+
126
+ ### 7. Contract rows
127
+
128
+ Each accepted matrix row becomes a numbered AC in the Goal Contract **file** (failure table). Name the seam or artifact.
129
+
130
+ If this session is AEL: freeze after those ACs are in the file. Chat `setuju` is not freeze.
131
+
132
+ If this session is impact-only: print the report and stop. Do not implement.
133
+
134
+ ## Output
135
+
136
+ ```text
137
+ Task impact inquiry
138
+ Briefing: <plain-language current flow>
139
+ Lifecycle: <ASCII>
140
+ Hit map: <surfaces + paths>
141
+ Blast radius: <ASCII>
142
+ Matrix: <table>
143
+ Questions: Q1..Qn with Recommended
144
+ Proposed AC: AC-1..N (happy, empty/omit, boundary, sibling, error)
145
+ Next: freeze Goal Contract | stop (impact-only)
146
+ ```
147
+
148
+ ## Forbidden
149
+
150
+ - Implementing, branching, or "small fix while we discuss"
151
+ - Second interview after AEL grill already captured the matrix
152
+ - Mermaid or LaTeX
153
+ - Claiming isolation because unit tests passed
154
+ - Inventing business rules the repo and the user did not supply
155
+ - Generating an FSD or starting `dot-dev-workflow` as a second loop
@@ -0,0 +1,123 @@
1
+ ---
2
+ name: generate-adapter
3
+ description: Grill then write a Stage 8 delivery adapter for this repo. Use when the user says generate-adapter, buat adapter, or each team needs its own forge. Not a substitute for ai-engineering-loop.
4
+ ---
5
+
6
+ # Generate Adapter
7
+
8
+ Write **this repo's** Stage 8 delivery adapter. Every team has different tools. Do not copy DOT, and do not invent Slack/Jira/bots the user did not name.
9
+
10
+ This skill is not the engineering OS. After the adapter file exists, commit-bound work still runs `ai-engineering-loop`. Stage 8 reads the file this skill writes.
11
+
12
+ ## Hard gate
13
+
14
+ Do not edit production code. Do not create a feature branch for the product.
15
+
16
+ Do not write `.ai-engineering-loop/adapter.md` until:
17
+
18
+ 1. Look-up is done (remote, CI, existing adapter).
19
+ 2. Q1–Q5 are on screen with a recommended answer.
20
+ 3. The user has answered or waived.
21
+
22
+ ## When to use
23
+
24
+ - `generate-adapter`, `buat adapter`, `adapter sendiri`
25
+ - `.ai-engineering-loop/adapter.md` missing, `adapter_type` unknown, or Stage 8 would have to guess
26
+ - The user wants GitHub / GitLab / standard / custom delivery
27
+
28
+ If Stage 1 grill for a **product task** is already running, do not start this skill as a second interview. Finish that Goal Contract first.
29
+
30
+ ## Host notes
31
+
32
+ Claude Code / Kiro: no mermaid, no LaTeX, no extra tool keys.
33
+
34
+ Grok: do not spawn children. Stay in the parent.
35
+
36
+ Look up facts. Grill only **decisions**.
37
+
38
+ ## Steps
39
+
40
+ ### 1. Look up
41
+
42
+ Read, in order. Skip if missing.
43
+
44
+ 1. `git remote -v` and `.git/config`
45
+ 2. `.github/workflows/`, `.gitlab-ci.yml`
46
+ 3. `.ai-engineering-loop/adapter.md`
47
+ 4. Shipped specs: `adapters/standard/`, `adapters/github/`, `adapters/gitlab/`, `adapters/dot/` (in the ai-engineering-loop package)
48
+
49
+ Or run `npx ai-engineering-loop generate-adapter` and use its detected block.
50
+
51
+ Cite the remote host. Do not ask what git already shows.
52
+
53
+ Recommended type:
54
+
55
+ - `github.com` → `github`
56
+ - GitLab host that is not a named company adapter → `gitlab`
57
+ - no remote / unknown → `standard`
58
+ - user said they need the DOT pipeline → `dot` (load `adapters/dot/`, do not invent extra tools)
59
+
60
+ ### 2. Grill (wait)
61
+
62
+ Ask all five in one round. Number them. Give Recommended. Wait.
63
+
64
+ ```text
65
+ Q1 - Forge: github | gitlab | standard (git only) | custom
66
+ Recommended: <from look-up>
67
+
68
+ Q2 - Open the change with: gh | glab | human copies the URL
69
+ Recommended: <binary that exists, else human>
70
+
71
+ Q3 - Extra environment branches after the default: none | list them
72
+ Recommended: none
73
+
74
+ Q4 - Notify after the PR/MR: none | name the tool you already use
75
+ Recommended: none
76
+
77
+ Q5 - Issue tracker: github | gitlab | none | name it
78
+ Recommended: same as forge, or none
79
+ ```
80
+
81
+ If the user picks **custom**, they must name the tools. Do not fill Linear/Slack/Bitbucket unless they said so.
82
+
83
+ ### 3. Write
84
+
85
+ Write `.ai-engineering-loop/adapter.md` (create `.ai-engineering-loop/` if needed).
86
+
87
+ - `adapter_type`: `standard` | `github` | `gitlab` | `dot` | `custom`
88
+ - `spec`: shipped folder (`adapters/github/`) or `.ai-engineering-loop/adapter/delivery.md` for custom
89
+ - remote, default branch, ci_provider from look-up
90
+ - extra branches and notify only if the user named them
91
+ - no tokens, no webhooks with secrets, no coworker handles, no internal ticket URLs
92
+
93
+ If `custom`, also write `.ai-engineering-loop/adapter/delivery.md` from their answers, following the same hard gate as `adapters/standard/` (Judge PASS first, no silent installs).
94
+
95
+ Headless alternative the user can run:
96
+
97
+ ```bash
98
+ npx ai-engineering-loop generate-adapter --type github
99
+ ```
100
+
101
+ `--type` skips this interview. Do not pass `--type` yourself unless they waived the grill.
102
+
103
+ ### 4. Stop
104
+
105
+ Print the path written and the type. Do not start Maker. Do not open a PR.
106
+
107
+ ## Output
108
+
109
+ ```text
110
+ Generate adapter
111
+ Detected: <remote> <ci>
112
+ Questions: Q1..Q5 with Recommended
113
+ Wrote: .ai-engineering-loop/adapter.md (type=<type>)
114
+ Next: /ai-engineering-loop for product work. Stage 8 uses this file.
115
+ ```
116
+
117
+ ## Forbidden
118
+
119
+ - Copying `adapters/dot/` onto a non-DOT repo
120
+ - Inventing company chat, review bots, or extra branches
121
+ - Mermaid or LaTeX
122
+ - Putting secrets or private ticket URLs in adapter.md
123
+ - Running the 8-stage product loop inside this skill
@@ -0,0 +1,28 @@
1
+ # GitHub delivery adapter
2
+
3
+ Stage 8 after Judge `PASS` on GitHub-hosted repos.
4
+
5
+ This is not the engineering OS. Do not run Maker. Do not skip Devil's Advocate or Judge.
6
+
7
+ Requires `gh` authenticated to the current remote. If `gh` is missing, fall back to [`../standard/`](../standard/) and print the compare URL.
8
+
9
+ ## Steps
10
+
11
+ 1. Re-run `.ai-engineering-loop/verification.md` if the log is stale.
12
+ 2. Commit the surgical diff. Push the topic branch. Never push the default branch.
13
+
14
+ ```bash
15
+ git push -u origin HEAD
16
+ ```
17
+
18
+ 3. Optional issue if none is linked (branch name, `Fixes #n`, or `gh issue list`):
19
+
20
+ ```bash
21
+ gh issue create --title "<summary>" --body "<Goal Contract path and AC list>"
22
+ ```
23
+
24
+ 4. Open the pull request. Follow [`pull-request.md`](pull-request.md).
25
+
26
+ 5. Extra branches, review bots, and chat are **off** unless `.ai-engineering-loop/adapter.md` names them. Do not invent Actions secrets or Slack webhooks.
27
+
28
+ 6. Stop. The human merges on GitHub.
@@ -0,0 +1,23 @@
1
+ # GitHub pull request
2
+
3
+ ```bash
4
+ gh pr create \
5
+ --title "<type>(<scope>): <summary>" \
6
+ --body "$(cat <<'EOF'
7
+ ## Goal Contract
8
+ `.ai-engineering-loop/tasks/goal-contract.md` (or the path this repo uses)
9
+
10
+ ## What changed
11
+ - <root cause or behaviour>
12
+ - <edge cases>
13
+ - <tests added>
14
+
15
+ ## Verification
16
+ Commands from `.ai-engineering-loop/verification.md` (exit 0).
17
+ EOF
18
+ )"
19
+ ```
20
+
21
+ Link an issue with `Fixes #n` in the body when an issue exists.
22
+
23
+ Do not paste raw diffs, tokens, or local machine paths.
@@ -0,0 +1,28 @@
1
+ # GitLab delivery adapter
2
+
3
+ Stage 8 after Judge `PASS` on GitLab.com or self-hosted GitLab.
4
+
5
+ This is the **generic** GitLab adapter. It is not the DOT adapter. Do not load `adapters/dot/`. No extra environment cherry-picks unless `.ai-engineering-loop/adapter.md` lists those branches.
6
+
7
+ Requires `glab` authenticated to the current remote. If `glab` is missing, fall back to [`../standard/`](../standard/) and print the branch name.
8
+
9
+ ## Steps
10
+
11
+ 1. Re-run `.ai-engineering-loop/verification.md` if the log is stale.
12
+ 2. Commit the surgical diff. Push the topic branch. Never push the default branch.
13
+
14
+ ```bash
15
+ git push -u origin HEAD
16
+ ```
17
+
18
+ 3. Optional issue if none is linked:
19
+
20
+ ```bash
21
+ glab issue create --title "<summary>" --description "<Goal Contract path and AC list>" --yes
22
+ ```
23
+
24
+ 4. Open the merge request. Follow [`merge-request.md`](merge-request.md).
25
+
26
+ 5. Extra environments and chat notifications stay off unless `adapter.md` lists them.
27
+
28
+ 6. Stop. The human merges on GitLab.
@@ -0,0 +1,26 @@
1
+ # GitLab merge request
2
+
3
+ ```bash
4
+ glab mr create \
5
+ --source-branch <branch-name> \
6
+ --target-branch <default-branch> \
7
+ --title "<type>(<scope>): <summary>" \
8
+ --description "$(cat <<'EOF'
9
+ ## Goal Contract
10
+ `.ai-engineering-loop/tasks/goal-contract.md` (or the path this repo uses)
11
+
12
+ ## What changed
13
+ - <root cause or behaviour>
14
+ - <edge cases>
15
+ - <tests added>
16
+
17
+ ## Verification
18
+ Commands from `.ai-engineering-loop/verification.md` (exit 0).
19
+ EOF
20
+ )" \
21
+ --yes
22
+ ```
23
+
24
+ Link the issue URL in the description when an issue exists.
25
+
26
+ Do not paste raw diffs, tokens, or local machine paths.
@@ -0,0 +1,44 @@
1
+ # Standard delivery adapter
2
+
3
+ General Stage 8 for any git project. No GitHub, GitLab, Slack, or company bot is required.
4
+
5
+ Use this when the remote is unknown, the human merges by hand, or you have not generated a forge-specific adapter yet.
6
+
7
+ ## Hard gate
8
+
9
+ Do not commit, push, or open a change request until Judge `PASS`.
10
+
11
+ If `.ai-engineering-loop/adapter.md` names a more specific type (`github`, `gitlab`, `dot`), follow that spec instead.
12
+
13
+ ## Steps
14
+
15
+ 1. Read `.ai-engineering-loop/verification.md`. Re-run those commands if the last log is stale. Keep exit codes.
16
+ 2. Commit only the surgical diff for this Goal Contract.
17
+
18
+ ```bash
19
+ git status
20
+ git diff
21
+ git add <modified-files>
22
+ git commit -m "<type>(<scope>): <summary>"
23
+ ```
24
+
25
+ 3. Push the topic branch. Do not push to `main` / `master` / the default branch.
26
+
27
+ ```bash
28
+ git push -u origin HEAD
29
+ ```
30
+
31
+ 4. Open a change request **with the tool that already exists**, or stop and give the human the compare URL:
32
+ - `gh pr create` if GitHub and `gh` works
33
+ - `glab mr create` if GitLab and `glab` works
34
+ - otherwise print `git remote -v` and the branch name; the human opens the PR/MR
35
+ 5. Do not cherry-pick to extra environments unless `adapter.md` lists those branches.
36
+ 6. Do not send chat notifications unless `adapter.md` names a channel and a tool. Never invent a webhook or token.
37
+ 7. Stop. Merge is a human action unless the user already said to merge.
38
+
39
+ ## Best practice
40
+
41
+ - One branch, one change request, default branch only.
42
+ - Link the Goal Contract path in the PR/MR body (not the whole chat).
43
+ - No secrets, no internal hostnames, no coworker handles in the description.
44
+ - If the forge CLI is missing, do not install it silently. Tell the user.
@@ -20,8 +20,14 @@ const {
20
20
  planHostSync,
21
21
  formatHostSyncReport
22
22
  } = require('../lib/sync-hosts.js');
23
+ const {
24
+ detectAdapterHints,
25
+ writeShippedAdapter,
26
+ formatGenerateAdapterReport,
27
+ parseTypeArg
28
+ } = require('../lib/generate-adapter.js');
23
29
 
24
- const VERSION = '1.0.14';
30
+ const VERSION = '1.0.16';
25
31
  const CWD = process.cwd();
26
32
  const CONTEXT_DIR = path.join(CWD, '.ai-engineering-loop');
27
33
 
@@ -275,7 +281,7 @@ function generateContextFiles(rootDir, discovery, trigger = 'init', impact = 'IN
275
281
 
276
282
  // 0. metadata.json (Baseline)
277
283
  const metadataJson = {
278
- contextVersion: '1.0.14',
284
+ contextVersion: '1.0.16',
279
285
  generatedAt: new Date().toISOString(),
280
286
  repositoryRevision: currentRevision,
281
287
  projectProfile: discovery.profile,
@@ -365,7 +371,7 @@ ${discovery.scripts.e2e ? `- **e2e**: \`${discovery.scripts.e2e}\`` : ''}
365
371
  const adapterMd = `# Project Delivery Adapter Configuration
366
372
 
367
373
  ## Delivery Pipeline
368
- - **adapter_type**: "${discovery.adapter.type}" # dot | github | gitlab | standard
374
+ - **adapter_type**: "${discovery.adapter.type}" # standard | github | gitlab | dot | custom
369
375
  ${discovery.adapter.repoSlug ? `- **remote_repository**: "${discovery.adapter.repoSlug}"` : ''}
370
376
  - **default_target_branch**: "${discovery.adapter.defaultBranch}"
371
377
  - **ci_provider**: "${discovery.adapter.ciProvider}"
@@ -654,6 +660,23 @@ function handleSyncHosts() {
654
660
  console.log(formatHostSyncReport(results, { version: VERSION, dryRun }));
655
661
  }
656
662
 
663
+ function handleGenerateAdapter() {
664
+ log.info('AI Engineering Loop — Generate delivery adapter (generate-adapter)');
665
+ const hints = detectAdapterHints(CWD);
666
+ const type = parseTypeArg(process.argv);
667
+ if (!type) {
668
+ console.log(formatGenerateAdapterReport(hints, { version: VERSION }));
669
+ return;
670
+ }
671
+ try {
672
+ const wrote = writeShippedAdapter(CWD, { type, hints });
673
+ console.log(formatGenerateAdapterReport(hints, { version: VERSION, wrote }));
674
+ } catch (err) {
675
+ log.error(err.message);
676
+ process.exit(1);
677
+ }
678
+ }
679
+
657
680
  function detectGrokHost() {
658
681
  try {
659
682
  const { detectGrokRuntime } = require('../lib/orchestration.js');
@@ -746,6 +769,8 @@ Commands:
746
769
  sync-hosts Copy package skills/agents/commands into ~/.claude ~/.grok ~/.gemini ~/.agents
747
770
  (only hosts that already exist; DOT skills only if already installed)
748
771
  --dry-run print the plan without writing
772
+ generate-adapter Print detected forge and grill protocol for Stage 8
773
+ --type standard|github|gitlab|dot write .ai-engineering-loop/adapter.md (skip grill)
749
774
 
750
775
  Options:
751
776
  -h, --help Show this help menu
@@ -776,6 +801,9 @@ switch (command) {
776
801
  case 'sync-hosts':
777
802
  handleSyncHosts();
778
803
  break;
804
+ case 'generate-adapter':
805
+ handleGenerateAdapter();
806
+ break;
779
807
  case '-v':
780
808
  case '--version':
781
809
  console.log(`ai-engineering-loop v${VERSION}`);
@@ -45,22 +45,26 @@ Before Maker starts:
45
45
 
46
46
  If a decision was agreed in chat and is missing from the file, the contract is not frozen. Do not start Maker.
47
47
 
48
- ## DOT adapter (`adapter_type: dot`)
48
+ ## Business blast radius
49
49
 
50
- On DOT repositories, grill is **one** session that includes the four-pillar blast radius from Antigravity skill `task-impact-inquiry` (`~/.gemini/config/skills/task-impact-inquiry/SKILL.md`). Do not run that skill as a second interview after grill.
50
+ Green unit tests are not proof that sibling rows, approvals, or downstream jobs survived.
51
51
 
52
- The four pillars must appear in the grill (and then in the Goal Contract) whenever the change can touch:
52
+ When the change can touch state, siblings, actors/approvals, or downstream work, grill **must** include blast radius — even if AC look obvious or the user said "just do it". Typo, lint, and version-bump skips still apply.
53
53
 
54
- 1. State and condition permutations (status, overtime vs normal hours, locked vs open periods)
55
- 2. Sibling / historical isolation (other entities in the same parent, period, or cart)
56
- 3. Actor and approval authority (who edits, when an existing approval is void vs kept)
57
- 4. Downstream jobs and queues (BullMQ, cron, payroll/aggregates)
54
+ On `adapter_type: dot`, this is mandatory. On other adapters, skip only when the change cannot touch those four (copy, CSS, comment).
58
55
 
59
- **Do not skip grill** for those four cases, even if AC look obvious or the user said "just do it". Typo, lint, and version-bump skips still apply.
56
+ Canonical skill: `adapters/dot/skills/task-impact-inquiry/SKILL.md`. Host copies via `sync-hosts`: `~/.claude/skills/task-impact-inquiry/`, `~/.grok/skills/task-impact-inquiry/`, `~/.gemini/config/skills/task-impact-inquiry/`. Load that skill if present. If it is missing, still run this section. Do not claim the skill ran.
60
57
 
61
- If the skill file is missing on this host, still ask the four pillars from this section. Do not claim the Gemini skill ran.
58
+ If Stage 1 grill already produced the matrix and the user confirmed it, do not run a second interview.
62
59
 
63
- Present the impact matrix and 2–3 probing questions in the same grill round as other Stage 1 decisions. Recommended answers required. After the frontier is empty, freeze the Goal Contract once.
60
+ In the same grill round:
61
+
62
+ 1. Look up the current flow. Draw an ASCII lifecycle (actor → status → lock). Do not ask look-up facts.
63
+ 2. Scan four pillars: state/conditions; sibling/historical isolation; actor and approval (void vs keep); downstream jobs and queues.
64
+ 3. ASCII blast-radius picture. No mermaid.
65
+ 4. Impact matrix (happy, empty/omit, boundary, sibling, error). Sunny-path-only is not done.
66
+ 5. 2–3 probing questions with recommended answers. Wait.
67
+ 6. Each accepted row becomes a numbered AC in the Goal Contract **file** (failure table).
64
68
 
65
69
  ## Design tree
66
70
 
@@ -64,7 +64,7 @@ Maintains lightweight state for instant drift detection:
64
64
  - `e2e`: (Optional) End-to-end / browser test command.
65
65
 
66
66
  ### 6. `adapter.md` — Delivery Pipeline Configuration
67
- - `adapter_type`: Configured adapter (`dot`, `github`, `gitlab`, `standard`).
67
+ - `adapter_type`: Configured adapter (`standard`, `github`, `gitlab`, `dot`, `custom`). Shipped specs live in `adapters/<type>/`. Generate with `npx ai-engineering-loop generate-adapter` (grill) or `--type`.
68
68
  - `remote_repository`: Git remote repository slug.
69
69
  - `default_target_branch`: Base target branch.
70
70
  - `ci_provider`: Detected CI engine (GitHub Actions, GitLab CI).
@@ -22,12 +22,12 @@ Task: Implement atomic idempotency key validation and SELECT FOR UPDATE row lock
22
22
 
23
23
  ## 3. Walkthrough Artifacts
24
24
 
25
- 1. **[Goal Contract (`goal-contract.md`)](file:///Users/egagofur/Development/work/ai-engineering-loop/examples/backend-api/payment-idempotency/goal-contract.md)**:
25
+ 1. **[Goal Contract (`goal-contract.md`)](./goal-contract.md)**:
26
26
  - AC-1: Idempotency-Key header mandatory on POST `/api/v1/payments/charge`.
27
27
  - AC-2: Atomic reservation using PostgreSQL `INSERT ... ON CONFLICT DO NOTHING`.
28
28
  - AC-3: Concurrent requests for same user wallet serialized with `SELECT ... FOR UPDATE`.
29
- 2. **[Adversarial Review Findings (`review-findings.md`)](file:///Users/egagofur/Development/work/ai-engineering-loop/examples/backend-api/payment-idempotency/review-findings.md)**:
29
+ 2. **[Adversarial Review Findings (`review-findings.md`)](./review-findings.md)**:
30
30
  - Devil's Advocate activates `backend-api` rules (concurrency, database atomicity).
31
31
  - Flags missing rollback on external gateway timeout (`ERR-001`).
32
- 3. **[Judge Verdict (`judge-verdict.md`)](file:///Users/egagofur/Development/work/ai-engineering-loop/examples/backend-api/payment-idempotency/judge-verdict.md)**:
32
+ 3. **[Judge Verdict (`judge-verdict.md`)](./judge-verdict.md)**:
33
33
  - Evaluates parallel test execution (`go test -race ./...`), verifies concurrency safety, and issues `PASS` verdict.
@@ -0,0 +1,23 @@
1
+ # Reference Example: Request Display Status Fix
2
+
3
+ ## 1. Context & Scenario
4
+
5
+ This walkthrough shows how a status-display bug moves through the **AI Engineering Loop** and the **DOT Delivery Adapter**. Names, URLs, and schema below are **fictional**. Do not copy real client tickets, GitLab links, or field names into this package.
6
+
7
+ ### The Problem
8
+
9
+ On an employee portal, request cards on the list and pagination endpoints showed `"PENDING"` after every line item was already approved or rejected. Non-standard-window records were also scored with the standard-day rule.
10
+
11
+ ---
12
+
13
+ ## 2. Walkthrough Stages & Artifacts
14
+
15
+ 1. **[Stage 1: Goal Contract (`goal-contract.md`)](./goal-contract.md)**:
16
+ - Objective, acceptance criteria (standard window, holiday, non-standard window, null values), and verification plan.
17
+ 2. **[Stage 2: Adversarial Review & Triage (`review-findings.md`)](./review-findings.md)**:
18
+ - Devil's Advocate flags a null-safety bug (`COR-001`) and an invalid nitpick (`MAINT-001`).
19
+ - Maker triage and surgical fix.
20
+ 3. **[Stage 3: Judge Evaluation & Verdict (`judge-verdict.md`)](./judge-verdict.md)**:
21
+ - Audit of tests, typecheck, finding resolutions, and `PASS`.
22
+ 4. **[Stage 4: DOT Delivery Pipeline (`delivery-report.md`)](./delivery-report.md)**:
23
+ - Fictional issue, base MR, cherry-picks to `staging` and `develop`, Coreview triage, Mattermost notice.
@@ -0,0 +1,41 @@
1
+ # DOT Delivery Report: Request Display Status Fix
2
+
3
+ Fictional sample. Replace host, group, repo, issue, and MR ids from `glab` output. Never paste real client URLs into this package.
4
+
5
+ ## 1. Summary of Delivery Actions
6
+
7
+ 1. **GitLab Issue Created**: [Issue #42 - [BE] [Requests] Fix display status](https://gitlab.example.com/example-org/work-portal/-/issues/42).
8
+ 2. **Primary MR Created**: [MR !10 targeting `main`](https://gitlab.example.com/example-org/work-portal/-/merge_requests/10).
9
+ 3. **Multi-Branch Cherry-Pick**:
10
+ - [MR !11 targeting `staging`](https://gitlab.example.com/example-org/work-portal/-/merge_requests/11).
11
+ - [MR !12 targeting `develop`](https://gitlab.example.com/example-org/work-portal/-/merge_requests/12).
12
+ 4. **Coreview Bot Triage**:
13
+ - Comments fetched on MR !12. Zero blocking comments.
14
+ 5. **Mattermost Notification**:
15
+ - Resolved repository `example-org/work-portal` to channel `"team-work-portal"`.
16
+ - Dispatched via MCP `mattermost_send_message` with `from: "AI Agent"`.
17
+
18
+ ---
19
+
20
+ ## 2. GitLab Links
21
+
22
+ | Artifact | Branch | Link |
23
+ |---|---|---|
24
+ | **GitLab Issue** | — | [Issue #42](https://gitlab.example.com/example-org/work-portal/-/issues/42) |
25
+ | **Merge Request DEV** | `develop` | [MR !12](https://gitlab.example.com/example-org/work-portal/-/merge_requests/12) |
26
+ | **Merge Request STAGING** | `staging` | [MR !11](https://gitlab.example.com/example-org/work-portal/-/merge_requests/11) |
27
+ | **Merge Request MAIN** | `main` | [MR !10](https://gitlab.example.com/example-org/work-portal/-/merge_requests/10) |
28
+
29
+ ---
30
+
31
+ ## 3. Dispatched Mattermost Notification
32
+
33
+ ```text
34
+ [MR DEV] https://gitlab.example.com/example-org/work-portal/-/merge_requests/12
35
+ Changes log
36
+ - Include standard-window and rush-note fields when loading request list pages.
37
+ - Resolve display status from all line items, including holiday and null collections.
38
+ - Add unit tests for standard, holiday, non-standard-window, and null line-item cases.
39
+
40
+ cc: @owner
41
+ ```