@williambeto/ai-workflow 2.7.1 → 2.8.1
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/CHANGELOG.md +69 -0
- package/README.md +3 -2
- package/bin/ai-workflow.js +1203 -301
- package/bin/ai-workflow.js.map +1 -1
- package/{chunk-W4RTQWVQ.js → chunk-4FI5ODAM.js} +879 -759
- package/chunk-AINIR25D.js +120 -0
- package/chunk-AY33SA5W.js +46 -0
- package/{evidence-validator-76ZQQYDU.js → chunk-FNT7DN3N.js} +22 -2
- package/{chunk-XW747GIG.js → chunk-H7GIKXFO.js} +339 -14
- package/{chunk-BDZPUAEX.js → chunk-LD7EHAU2.js} +352 -39
- package/chunk-YOBY5C72.js +76 -0
- package/core/index.d.ts +51 -1
- package/core/index.js +5 -3
- package/dist-assets/agents/atlas.md +25 -6
- package/dist-assets/commands/atlas.md +7 -2
- package/dist-assets/docs/QUICKSTART.md +10 -1
- package/dist-assets/docs/cli-reference.md +47 -2
- package/dist-assets/docs/compatibility/provider-usage.md +16 -1
- package/dist-assets/docs/compatibility/runtime-matrix.md +13 -2
- package/dist-assets/docs/policies/06-FINAL_EVIDENCE_CONTRACT.md +11 -1
- package/dist-assets/docs/policies/SKILLS_COMMON_GOVERNANCE.md +16 -0
- package/dist-assets/schemas/README.md +4 -0
- package/dist-assets/schemas/approval-receipt.schema.json +35 -0
- package/dist-assets/schemas/evidence.schema.json +93 -1
- package/evidence-validator-HS3NTWAB.js +8 -0
- package/package.json +17 -2
- package/skill-4MEGJ3DO.js +211 -0
- package/skill-frontmatter-linter-FMJADOK4.js +14 -0
- package/{validate-A46WUBVZ.js → validate-F3ZH63LI.js} +3 -3
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,74 @@
|
|
|
1
1
|
## [unreleased]
|
|
2
2
|
|
|
3
|
+
## [2.8.1] - 2026-07-14
|
|
4
|
+
|
|
5
|
+
### 🐛 Bug Fixes
|
|
6
|
+
|
|
7
|
+
- Route natural workspace mutations to Astra instead of stopping after a
|
|
8
|
+
specialist prints code
|
|
9
|
+
- Keep Phoenix limited to bounded remediation of observed findings
|
|
10
|
+
- Require execution-scoped repository changes and proportional validation for
|
|
11
|
+
successful workspace delivery
|
|
12
|
+
- Preserve explicit read-only, preview, already-satisfied, clarification, and
|
|
13
|
+
non-delivery outcomes without manufacturing changes
|
|
14
|
+
- Prevent natural phrases such as `next step` from being interpreted as a
|
|
15
|
+
Next.js stack request
|
|
16
|
+
- Propagate observed OpenCode commands to the evidence ledger and derive test
|
|
17
|
+
actions from the delivered diff
|
|
18
|
+
- Prevent duplicate finalization and require exactly one observed Astra
|
|
19
|
+
delegation in the OpenCode fallback path
|
|
20
|
+
- Route mixed inspection-and-change requests to Astra whenever the request has
|
|
21
|
+
write intent
|
|
22
|
+
- Allow read-only Git, `sed`, and `awk` inspection while continuing to block
|
|
23
|
+
mutations, and exclude ignored build artifacts from delivery deltas
|
|
24
|
+
- Keep validation proportional for documentation, simple code, backend scripts,
|
|
25
|
+
and React applications while retaining blocking build requirements for UI
|
|
26
|
+
|
|
27
|
+
### 🧪 Testing
|
|
28
|
+
|
|
29
|
+
- Cover routing ownership, delivery outcomes, answer-only confinement, project
|
|
30
|
+
context compatibility, execution delta attribution, and generated OpenCode
|
|
31
|
+
permissions through reusable invariants
|
|
32
|
+
- Keep pre-existing dirty work from satisfying delivery or test-action evidence
|
|
33
|
+
- Validate the corrected workflow with a real GPT-5.6 Sol OpenCode delivery and
|
|
34
|
+
record GPT-5.3 Codex Spark medium as experimental after observed incomplete
|
|
35
|
+
delivery was correctly blocked
|
|
36
|
+
|
|
37
|
+
### 📚 Documentation
|
|
38
|
+
|
|
39
|
+
- Align Atlas, quickstart, ownership, runtime-flow, evidence, and skill
|
|
40
|
+
governance documentation with the natural-request delivery contract
|
|
41
|
+
- Document the distinction between CLI-enforced gates and model-qualified
|
|
42
|
+
direct Atlas sessions
|
|
43
|
+
|
|
44
|
+
## [2.8.0] - 2026-07-14
|
|
45
|
+
|
|
46
|
+
### 🚀 Features
|
|
47
|
+
|
|
48
|
+
- Add governed skill scaffolding, frontmatter linting, and contract tests
|
|
49
|
+
- Introduce executable DEEP SDD checkpoints with hash-bound approval receipts
|
|
50
|
+
- Add Orion technical-plan validation and Astra file-scope enforcement
|
|
51
|
+
- Confirm high-risk OpenCode actor identity through machine-readable runtime evidence
|
|
52
|
+
|
|
53
|
+
### 🐛 Bug Fixes
|
|
54
|
+
|
|
55
|
+
- Preserve low- and medium-risk OpenCode graceful degradation behavior
|
|
56
|
+
- Resolve packaged evidence schemas from the installed package root
|
|
57
|
+
- Prevent metadata sentinels from being treated as Astra file mutations
|
|
58
|
+
|
|
59
|
+
### 🧪 Testing
|
|
60
|
+
|
|
61
|
+
- Cover external, missing, incompatible, duplicate, and concurrent workflow ledgers
|
|
62
|
+
- Add real OpenCode consumer smoke coverage and actor-confirmation adapter tests
|
|
63
|
+
- Enforce Node 20 consumer compatibility and Node 22 contributor validation
|
|
64
|
+
|
|
65
|
+
### ⚙️ Miscellaneous Tasks
|
|
66
|
+
|
|
67
|
+
- Add sequential release verification across build, tests, validation, packaging, and runtime smoke
|
|
68
|
+
- Align CI quality gates with the supported Node toolchain
|
|
69
|
+
|
|
70
|
+
## [2.7.1] - 2026-07-07
|
|
71
|
+
|
|
3
72
|
### 🚀 Features
|
|
4
73
|
|
|
5
74
|
- *(adapters)* Harden Codex adapter with robust system boundaries
|
package/README.md
CHANGED
|
@@ -148,6 +148,7 @@ Agents are installed as prompts in your `.ai-workflow/agents/` directory. You ca
|
|
|
148
148
|
| `npx aw collect-evidence` | Collect and compile delivery evidence to `EVIDENCE.json` |
|
|
149
149
|
| `npx aw doctor` | Diagnose installation health |
|
|
150
150
|
| `npx aw clean` | Remove all AIWK configuration from the project |
|
|
151
|
+
| `npx aw skill create <name>` | Scaffold a workspace-local skill with valid frontmatter |
|
|
151
152
|
|
|
152
153
|
---
|
|
153
154
|
|
|
@@ -200,7 +201,7 @@ Everything is plain text — readable, auditable, and version-controlled.
|
|
|
200
201
|
Beyond the 6 core agents, AIWK ships 25 domain skills that agents activate as context lenses when the request profile warrants it. You can also author your own:
|
|
201
202
|
|
|
202
203
|
```
|
|
203
|
-
.
|
|
204
|
+
.agents/skills/
|
|
204
205
|
├── architecture/
|
|
205
206
|
├── backend-development/
|
|
206
207
|
├── cyber-security/ # activated by Sage on audit tasks
|
|
@@ -246,7 +247,7 @@ Run the full validation suite before submitting a pull request:
|
|
|
246
247
|
npm run validate
|
|
247
248
|
```
|
|
248
249
|
|
|
249
|
-
All
|
|
250
|
+
All 23 quality gates must pass.
|
|
250
251
|
|
|
251
252
|
---
|
|
252
253
|
|