@mmerterden/multi-agent-pipeline 20.12.0 → 20.13.0
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 +36 -0
- package/README.md +1 -1
- package/README.tr.md +1 -1
- package/docs/facts.json +1 -1
- package/install/_common.mjs +1 -1
- package/install/_plugin-skills.mjs +13 -9
- package/install/catalog-history.json +1 -1
- package/install/codex.mjs +12 -12
- package/manifest.json +59 -53
- package/package.json +1 -1
- package/pipeline/commands/multi-agent/SKILL.md +1 -0
- package/pipeline/commands/multi-agent/analysis/SKILL.md +7 -3
- package/pipeline/commands/multi-agent/analysis-jira/SKILL.md +57 -7
- package/pipeline/commands/multi-agent/analysis-resolve/SKILL.md +2 -2
- package/pipeline/commands/multi-agent/autopilot/SKILL.md +6 -0
- package/pipeline/commands/multi-agent/autopilot-off/SKILL.md +1 -0
- package/pipeline/commands/multi-agent/doctor/SKILL.md +6 -0
- package/pipeline/commands/multi-agent/feedback/SKILL.md +2 -2
- package/pipeline/commands/multi-agent/forget/SKILL.md +1 -0
- package/pipeline/commands/multi-agent/garbage-collect/SKILL.md +1 -0
- package/pipeline/commands/multi-agent/kill/SKILL.md +1 -0
- package/pipeline/commands/multi-agent/prune-logs/SKILL.md +1 -0
- package/pipeline/commands/multi-agent/prune-prompts/SKILL.md +1 -0
- package/pipeline/commands/multi-agent/review/SKILL.md +5 -0
- package/pipeline/commands/multi-agent/review-analysis/SKILL.md +7 -2
- package/pipeline/lib/analysis-jira-write.sh +81 -27
- package/pipeline/lib/analysis-quality.mjs +261 -0
- package/pipeline/lib/analysis-sections.mjs +105 -0
- package/pipeline/lib/jira-epic-link.sh +54 -0
- package/pipeline/multi-agent-refs/analysis/locked.md +4 -4
- package/pipeline/multi-agent-refs/analysis/redesign.md +3 -1
- package/pipeline/multi-agent-refs/analysis/render.md +20 -21
- package/pipeline/multi-agent-refs/analysis/resolve.md +1 -1
- package/pipeline/multi-agent-refs/analysis/review.md +16 -3
- package/pipeline/multi-agent-refs/analysis/synthesis.md +10 -2
- package/pipeline/multi-agent-refs/analysis-template-corporate.md +44 -9
- package/pipeline/multi-agent-refs/analysis-template.md +21 -14
- package/pipeline/multi-agent-refs/cross-cli-contract.md +4 -0
- package/pipeline/multi-agent-refs/features/analysis-jira.md +69 -19
- package/pipeline/schemas/analysis-spec.schema.json +22 -0
- package/pipeline/schemas/prefs.schema.json +22 -1
- package/pipeline/scripts/analysis-story-body.mjs +210 -0
- package/pipeline/scripts/analysis-story-tree.mjs +73 -12
- package/pipeline/scripts/analysis-tickets-writeback.mjs +101 -0
- package/pipeline/scripts/build-references.mjs +14 -1
- package/pipeline/scripts/confluence-readback.mjs +148 -0
- package/pipeline/scripts/jira-wiki-escape.mjs +40 -0
- package/pipeline/scripts/validate-analysis-doc.mjs +120 -70
- package/pipeline/skills/.skill-manifest.json +8 -8
- package/pipeline/skills/shared/core/multi-agent-analysis/SKILL.md +6 -1
- package/pipeline/skills/shared/core/multi-agent-analysis-jira/SKILL.md +56 -6
- package/pipeline/skills/shared/core/multi-agent-autopilot/SKILL.md +6 -0
- package/pipeline/skills/shared/core/multi-agent-doctor/SKILL.md +6 -0
- package/pipeline/skills/shared/core/multi-agent-review/SKILL.md +5 -0
- package/pipeline/skills/shared/core/multi-agent-review-analysis/SKILL.md +5 -0
- package/pipeline/skills/shared/core/multi-agent-setup/SKILL.md +1 -0
|
@@ -20,6 +20,12 @@ same way - late, mid-run, after the pickers had been answered. A missing script
|
|
|
20
20
|
fails at the call. Malformed preferences fail after Phase 0 has asked five
|
|
21
21
|
questions. A token in a remote URL does not fail at all; it leaks.
|
|
22
22
|
|
|
23
|
+
## Gotchas
|
|
24
|
+
|
|
25
|
+
- Exit 4 means the layout did not resolve and nothing was checked. It is not a pass.
|
|
26
|
+
- Without `--probe` no credential is sent anywhere, so a revoked token still reads as mapped.
|
|
27
|
+
- `usage-report` SKIP means nothing has been sent from this machine yet, not that reporting works.
|
|
28
|
+
|
|
23
29
|
## Run it
|
|
24
30
|
|
|
25
31
|
```bash
|
|
@@ -13,6 +13,11 @@ metadata:
|
|
|
13
13
|
|
|
14
14
|
Skip Phase 0-3 and review a diff only. Input shapes: a PR (`#N`, `repo#N`, GitHub/Bitbucket-Server PR URL), a branch name, or empty.
|
|
15
15
|
|
|
16
|
+
## Gotchas
|
|
17
|
+
|
|
18
|
+
- The counterpart-repo comparison needs exactly one resolved candidate. With several, an unattended run skips it silently, so an autopilot review can have no cross-platform section.
|
|
19
|
+
- The counterpart's stack comes from marker files, never from the repo name.
|
|
20
|
+
|
|
16
21
|
## Steps
|
|
17
22
|
|
|
18
23
|
1. **Resolve the input** (`{kind, provider}`):
|
|
@@ -13,6 +13,11 @@ metadata:
|
|
|
13
13
|
|
|
14
14
|
`multi-agent-review` judges a diff. This judges the document that diff was supposed to come from, before the code exists. No worktree, no branch, no commit, and the reviewed document is never edited in place.
|
|
15
15
|
|
|
16
|
+
## Gotchas
|
|
17
|
+
|
|
18
|
+
- Validator ERRORs are Blockers and WARNs are Important, unless the document states why the warned-about item is acceptable.
|
|
19
|
+
- Every rubric class is printed, with `none` when empty. A class missing from the verdict did not run; it is not a clean result.
|
|
20
|
+
|
|
16
21
|
## Flow
|
|
17
22
|
|
|
18
23
|
Read `$HOME/.copilot/multi-agent-refs/analysis/review.md` and execute it:
|
|
@@ -1,6 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: multi-agent-setup
|
|
3
3
|
description: "First-run setup wizard: keychain token discovery, Git Identity onboarding, and pipeline preparation. Use when the pipeline is being set up for the first time, or tokens and git identity need onboarding."
|
|
4
|
+
argument-hint: "[jira-keys | hosts | accounts] - optional; no argument runs the whole onboarding"
|
|
4
5
|
user-invocable: true
|
|
5
6
|
metadata:
|
|
6
7
|
language: en
|