@mmerterden/multi-agent-pipeline 19.1.4 → 20.0.0
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 +94 -0
- package/README.md +19 -36
- package/README.tr.md +18 -35
- package/docs/adr/0002-instruction-driven-flag.md +6 -5
- package/docs/adr/0005-lazy-phase-docs.md +2 -2
- package/docs/adr/0008-installer-modularization-and-secret-leak-defense.md +1 -0
- package/docs/adr/0009-claude-stack-skills-plugin-only.md +1 -1
- package/docs/adr/0010-own-code-graph.md +5 -4
- package/docs/adr/0012-macos-only.md +2 -2
- package/docs/adr/0013-lsp-code-intelligence.md +2 -2
- package/docs/adr/0014-six-phase-consolidation.md +9 -9
- package/docs/adr/0015-one-pipeline-no-depth-answer.md +83 -0
- package/docs/adr/0016-the-run-shape-is-asked-not-typed.md +69 -0
- package/docs/adr/README.md +18 -16
- package/docs/architecture.md +2 -2
- package/docs/ecosystem.md +5 -5
- package/docs/facts.json +3 -6
- package/docs/features.md +4 -5
- package/docs/token-budget-history.md +1 -1
- package/install/_common.mjs +9 -1
- package/install/templates/copilot-instructions.md +7 -16
- package/manifest.json +111 -114
- package/package.json +1 -1
- package/pipeline/commands/multi-agent/SKILL.md +6 -8
- package/pipeline/commands/multi-agent/analysis/SKILL.md +2 -0
- package/pipeline/commands/multi-agent/analysis-jira/SKILL.md +2 -0
- package/pipeline/commands/multi-agent/analysis-resolve/SKILL.md +2 -0
- package/pipeline/commands/multi-agent/autopilot/SKILL.md +2 -0
- package/pipeline/commands/multi-agent/autopilot-on/SKILL.md +2 -0
- package/pipeline/commands/multi-agent/autopilot-status/SKILL.md +1 -1
- package/pipeline/commands/multi-agent/build-optimize/SKILL.md +2 -0
- package/pipeline/commands/multi-agent/channels/SKILL.md +1 -1
- package/pipeline/commands/multi-agent/create-jira/SKILL.md +2 -0
- package/pipeline/commands/multi-agent/design-check/SKILL.md +1 -1
- package/pipeline/commands/multi-agent/forget/SKILL.md +2 -0
- package/pipeline/commands/multi-agent/garbage-collect/SKILL.md +4 -2
- package/pipeline/commands/multi-agent/help/SKILL.md +21 -27
- package/pipeline/commands/multi-agent/ios-coding-standard/SKILL.md +5 -4
- package/pipeline/commands/multi-agent/issue/SKILL.md +2 -0
- package/pipeline/commands/multi-agent/jira/SKILL.md +2 -0
- package/pipeline/commands/multi-agent/language/SKILL.md +2 -0
- package/pipeline/commands/multi-agent/prune-logs/SKILL.md +2 -0
- package/pipeline/commands/multi-agent/purge/SKILL.md +2 -0
- package/pipeline/commands/multi-agent/resume/SKILL.md +177 -48
- package/pipeline/commands/multi-agent/save/SKILL.md +2 -0
- package/pipeline/commands/multi-agent/stack/SKILL.md +2 -0
- package/pipeline/commands/multi-agent/sync/SKILL.md +6 -7
- package/pipeline/commands/multi-agent/test-screenshots/SKILL.md +2 -0
- package/pipeline/commands/multi-agent/uninstall/SKILL.md +2 -0
- package/pipeline/lib/repo-hygiene.sh +1 -1
- package/pipeline/multi-agent-refs/analysis/render.md +1 -1
- package/pipeline/multi-agent-refs/analysis/resolve.md +1 -1
- package/pipeline/multi-agent-refs/analysis/synthesis.md +1 -1
- package/pipeline/multi-agent-refs/analysis-template.md +1 -1
- package/pipeline/multi-agent-refs/component-dispatch.md +0 -8
- package/pipeline/multi-agent-refs/cross-cli-contract.md +10 -11
- package/pipeline/multi-agent-refs/features/external-context-injection.md +2 -0
- package/pipeline/multi-agent-refs/features/review-delta.md +1 -1
- package/pipeline/multi-agent-refs/features/review-multi-repo.md +3 -3
- package/pipeline/multi-agent-refs/features/skill-conformance.md +1 -1
- package/pipeline/multi-agent-refs/features/visual-evidence.md +2 -1
- package/pipeline/multi-agent-refs/features/worktree-finalize.md +1 -1
- package/pipeline/multi-agent-refs/generate-issue.md +2 -0
- package/pipeline/multi-agent-refs/issue-jira-triad.md +2 -0
- package/pipeline/multi-agent-refs/keychain.md +2 -0
- package/pipeline/multi-agent-refs/knowledge.md +0 -7
- package/pipeline/multi-agent-refs/outside-the-pipeline.md +1 -1
- package/pipeline/multi-agent-refs/payload-contracts.md +1 -1
- package/pipeline/multi-agent-refs/phases/modes.md +32 -108
- package/pipeline/multi-agent-refs/phases/operations.md +2 -0
- package/pipeline/multi-agent-refs/phases/phase-0-init.md +23 -42
- package/pipeline/multi-agent-refs/phases/phase-1-plan.md +7 -18
- package/pipeline/multi-agent-refs/phases/phase-2-dev.md +13 -44
- package/pipeline/multi-agent-refs/phases/phase-3-review.md +19 -22
- package/pipeline/multi-agent-refs/phases/phase-4-commit.md +6 -6
- package/pipeline/multi-agent-refs/phases/phase-5-report.md +2 -2
- package/pipeline/multi-agent-refs/phases.md +9 -11
- package/pipeline/multi-agent-refs/progress-contract.md +1 -1
- package/pipeline/multi-agent-refs/readiness-review.md +2 -0
- package/pipeline/multi-agent-refs/rules.md +1 -1
- package/pipeline/multi-agent-refs/tracker-contract.md +9 -40
- package/pipeline/multi-agent-refs/wiki-capture.md +3 -2
- package/pipeline/preferences-template.json +2 -2
- package/pipeline/rules/figma-pipeline.md +1 -1
- package/pipeline/schemas/agent-state.schema.json +5 -10
- package/pipeline/schemas/migrations/prefs-2.7.0-to-2.8.0.mjs +33 -0
- package/pipeline/schemas/phases.json +3 -24
- package/pipeline/schemas/prefs.schema.json +5 -5
- package/pipeline/scripts/cost-table.json +1 -1
- package/pipeline/scripts/gc-refs.sh +1 -1
- package/pipeline/scripts/gen-mode-dispatch.mjs +11 -41
- package/pipeline/scripts/migrate-prefs.mjs +18 -17
- package/pipeline/scripts/phase-tracker.sh +2 -2
- package/pipeline/scripts/phase0-exit-gate.mjs +1 -1
- package/pipeline/scripts/plan-coverage-gate.mjs +3 -3
- package/pipeline/scripts/run-aggregator.mjs +1 -1
- package/pipeline/scripts/usage-report.mjs +0 -2
- package/pipeline/scripts/worktree-finalize.sh +2 -2
- package/pipeline/skills/.skill-manifest.json +8 -20
- package/pipeline/skills/.skills-index.json +6 -39
- package/pipeline/skills/shared/README.md +5 -8
- package/pipeline/skills/shared/core/multi-agent/SKILL.md +8 -11
- package/pipeline/skills/shared/core/multi-agent-autopilot-status/SKILL.md +1 -1
- package/pipeline/skills/shared/core/multi-agent-help/SKILL.md +13 -16
- package/pipeline/skills/shared/core/multi-agent-ios-coding-standard/SKILL.md +2 -3
- package/pipeline/skills/shared/core/multi-agent-resume/SKILL.md +51 -15
- package/pipeline/skills/shared/core/multi-agent-sync/SKILL.md +6 -6
- package/pipeline/skills/skills-index.md +3 -6
- package/pipeline/commands/multi-agent/local/SKILL.md +0 -132
- package/pipeline/commands/multi-agent/local-autopilot/SKILL.md +0 -142
- package/pipeline/commands/multi-agent/resume-local/SKILL.md +0 -114
- package/pipeline/skills/shared/core/multi-agent-local/SKILL.md +0 -41
- package/pipeline/skills/shared/core/multi-agent-local-autopilot/SKILL.md +0 -55
- package/pipeline/skills/shared/core/multi-agent-resume-local/SKILL.md +0 -51
|
@@ -1,55 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
name: multi-agent-local-autopilot
|
|
3
|
-
language: en
|
|
4
|
-
description: "Full pipeline + local + autopilot - no worktree, no confirmations, all 6 phases run end-to-end on the current branch. Use when the full pipeline should run on the current branch with no worktree and no prompts."
|
|
5
|
-
user-invocable: true
|
|
6
|
-
argument-hint: '"task" - issue URL, Jira ID, free-text, or #id (for resume)'
|
|
7
|
-
---
|
|
8
|
-
|
|
9
|
-
# multi-agent-local-autopilot - Full Pipeline, Local Branch, Autonomous
|
|
10
|
-
|
|
11
|
-
**Input**: $ARGUMENTS
|
|
12
|
-
|
|
13
|
-
Runs the full 6-phase pipeline **without creating a worktree** + **skipping all confirmations**. The `autopilot + local` combination. Byte-identical behavior to `/multi-agent:local-autopilot` (Claude Code colon-form).
|
|
14
|
-
|
|
15
|
-
## Matrix (which one should I use?)
|
|
16
|
-
|
|
17
|
-
| Command | Pipeline | Worktree | Confirmation |
|
|
18
|
-
|---|---|---|---|
|
|
19
|
-
| `multi-agent "task"` | Full 6 phases | ✅ | ✅ (interactive) |
|
|
20
|
-
| `multi-agent-autopilot "task"` | Full 6 phases | ✅ | ❌ |
|
|
21
|
-
| `multi-agent-local "task"` | Full 6 phases | ❌ | ✅ |
|
|
22
|
-
| **`multi-agent-local-autopilot "task"`** | **Full 6 phases** | **❌** | **❌** |
|
|
23
|
-
|
|
24
|
-
Depth is a separate axis, asked at Phase 0 Step 7.5 rather than encoded in the command name: Full runs every phase above, Short runs Dev → Review → Test → Commit → Report. The two autopilot rows never ask and always run Full.
|
|
25
|
-
|
|
26
|
-
## What changes
|
|
27
|
-
|
|
28
|
-
- The Phase 0 Step 6 worktree step is skipped (local contract)
|
|
29
|
-
- The Phase 2 Plan Approval Gate is skipped (autopilot contract) - `state.autopilot === true`
|
|
30
|
-
- The Phase 3 test prompt is skipped, Phase 4 commit/PR does not wait for confirmation
|
|
31
|
-
- **v7.0.0+**: The Phase 2 safety classifier (`classify-plan-safety.mjs`) always runs; if the score is ≥ 50 it asks for a single manual confirmation even in autopilot (`prefs.global.autopilotSafetyGate`, default on)
|
|
32
|
-
|
|
33
|
-
## What is NEVER skipped
|
|
34
|
-
|
|
35
|
-
- 🔴 Review blocking → Automatic fix + rebuild (max 3 retries)
|
|
36
|
-
- 💥 Build fail → Automatic fix + rebuild (max 3 retries, then pause)
|
|
37
|
-
- 🛡️ Safety classifier pause → manual confirmation when a high-risk plan is detected
|
|
38
|
-
- ⚠️ Kill/Purge → Always asks for confirmation (destructive)
|
|
39
|
-
|
|
40
|
-
## Examples
|
|
41
|
-
|
|
42
|
-
```bash
|
|
43
|
-
multi-agent-local-autopilot "PROJ-12345"
|
|
44
|
-
multi-agent-local-autopilot https://github.com/org/repo/issues/316
|
|
45
|
-
multi-agent-local-autopilot "LoginView dark mode fix"
|
|
46
|
-
multi-agent-local-autopilot "#3"
|
|
47
|
-
```
|
|
48
|
-
|
|
49
|
-
## Delegation
|
|
50
|
-
|
|
51
|
-
The orchestrator skill (`multi-agent/SKILL.md`) takes the `--local` + `"autopilot": true` state flags together. Contract: `refs/phases/phase-0-init.md` Step 6 (local branch) + `refs/phases/phase-1-plan.md` Step 5 (gate skip) + Step 5c (safety classifier, v7.0.0+).
|
|
52
|
-
|
|
53
|
-
## Required: outward-facing payload contracts
|
|
54
|
-
|
|
55
|
-
Before writing anything outward-facing - PR body, Jira comment, Confluence page, closing report - load `$HOME/.claude/multi-agent-refs/payload-contracts.md`. It names the canonical section set for each payload, the markup dialect per surface (PR body is Markdown, Jira is wiki markup - mixing them is a defect), and the token/duration numbers the closing report must carry. Improvising a payload shape from memory is the most common failure of the short modes.
|
|
@@ -1,51 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
name: multi-agent-resume-local
|
|
3
|
-
language: en
|
|
4
|
-
description: "Continue already-done LOCAL work through the pipeline tail: Review (with its build gate) → Commit/PR → Report (technical analysis + Jira test-scenario comment). No dev phase. Use when local work is already done and only review, build, commit and reporting remain."
|
|
5
|
-
user-invocable: true
|
|
6
|
-
---
|
|
7
|
-
|
|
8
|
-
# multi-agent resume-local - Take Existing Branch Work Through the Pipeline Tail
|
|
9
|
-
|
|
10
|
-
You already wrote (and maybe hand-tested) the change on the current branch, or committed it outside the pipeline entirely. `ship` picks up from there and runs the **pipeline tail** over that existing work in one command, without re-developing. (As of v14.0.0 a Short run reviews its own output, so this is for work with no pipeline run behind it.)
|
|
11
|
-
|
|
12
|
-
## Pipeline
|
|
13
|
-
|
|
14
|
-
```
|
|
15
|
-
Phase 0: Init → project/branch detect, resolve base + diff (work already done), Jira id, state (NO worktree)
|
|
16
|
-
Phase 3: Review → the Verify gate first (stack-aware build + existing tests; SUCCESS required), then
|
|
17
|
-
parallel review (Fable + Opus + Sonnet) + Fable triage
|
|
18
|
-
Phase 4: Commit → commit remaining changes + push + open PR if none exists
|
|
19
|
-
Phase 5: Report → technical analysis + Jira comment with test scenarios (channels: Jira / PR / Confluence / Wiki)
|
|
20
|
-
```
|
|
21
|
-
|
|
22
|
-
Phases 1-2 (Plan / Dev) are skipped by design - the branch's local diff IS the Phase 2 output. The build that Dev's exit gate would have run happens inside Review instead, because there is no Dev run to inherit a log from.
|
|
23
|
-
|
|
24
|
-
## When to use it
|
|
25
|
-
|
|
26
|
-
- After a `:local` run answered Short (which skips Review + Test) to run the full quality tail on the same branch.
|
|
27
|
-
- After hand-coding / hand-testing a change, to get review + build/test + PR + Jira write-up without re-running dev.
|
|
28
|
-
|
|
29
|
-
## When NOT to use it
|
|
30
|
-
|
|
31
|
-
- Change not written yet → `multi-agent` / `multi-agent:local`.
|
|
32
|
-
- Only the review → `multi-agent:review`; only report/channels → `multi-agent:channels`; only device UI test → `multi-agent:test` / `multi-agent:manual-test`.
|
|
33
|
-
|
|
34
|
-
## Input
|
|
35
|
-
|
|
36
|
-
```bash
|
|
37
|
-
multi-agent resume-local # current branch vs base; Jira id from branch name
|
|
38
|
-
multi-agent resume-local PROJ-12345 # explicit Jira id for the Phase 5 comment
|
|
39
|
-
multi-agent resume-local --base develop # override base branch for the diff
|
|
40
|
-
multi-agent resume-local autopilot # no gate prompts: auto-fix, auto-PR, auto-comment
|
|
41
|
-
```
|
|
42
|
-
|
|
43
|
-
## Notes
|
|
44
|
-
|
|
45
|
-
- Build+Test is the automated success gate (not the interactive device user-test - that is `multi-agent:manual-test`). If the repo has no tests, it reports "no tests present" - never fabricates results.
|
|
46
|
-
- Commit/PR follows house rules: conventional message, `Ref: #N` (never Closes/Fixes), NO AI/bot attribution. PR opened only if one does not already exist.
|
|
47
|
-
- Full phase contract lives in the Claude Code command `commands/multi-agent/ship/SKILL.md`; this skill is the Copilot-CLI counterpart.
|
|
48
|
-
|
|
49
|
-
## Required: outward-facing payload contracts
|
|
50
|
-
|
|
51
|
-
Before writing anything outward-facing - PR body, Jira comment, Confluence page, closing report - load `$HOME/.claude/multi-agent-refs/payload-contracts.md`. It names the canonical section set for each payload, the markup dialect per surface (PR body is Markdown, Jira is wiki markup - mixing them is a defect), and the token/duration numbers the closing report must carry. Improvising a payload shape from memory is the most common failure of the short modes.
|